From 9c785ea4c33001a88e801233bf3a7da505792c36 Mon Sep 17 00:00:00 2001 From: Christoph Helma Date: Tue, 15 Dec 2015 17:28:31 +0100 Subject: activity comparison of datasets --- loael-dataset-comparison.rb | 113 -- loael-dataset-comparison.svg | 796 -------- loael-variability.rb | 89 - loael_variance.svg | 1067 +++++------ original/Korrektur.txt | 6 + original/LOAEL-Duplicates-mg.csv | 218 +++ original/LOAEL-Duplicates-mmol.csv | 218 +++ original/LOAEL.zip | Bin 0 -> 923157 bytes original/LOAEL2.xls | Bin 0 -> 752128 bytes original/LOAEL_log_mg.csv | 566 ++++++ original/LOAEL_log_mg_corrected_smiles.csv | 568 ++++++ original/LOAEL_log_mmol.csv | 563 ++++++ original/LOAEL_log_mmol_corrected_smiles.csv | 568 ++++++ original/LOAEL_mg.csv | 566 ++++++ original/LOAEL_mg_corrected_smiles.csv | 568 ++++++ original/NOAEL-LOAEL_dv.xlsx | Bin 0 -> 331117 bytes original/NOAEL-LOAEL_elena_email_20150306.xlsx | Bin 0 -> 245908 bytes original/box.png | Bin 0 -> 4481 bytes original/deviation_analysis.R | 30 + original/gr_m_var.png | Bin 0 -> 11258 bytes original/loael_in_drei_formaten.R | Bin 0 -> 64105 bytes original/loael_in_drei_formaten_corrected_smiles.R | Bin 0 -> 75533 bytes original/qq.png | Bin 0 -> 14729 bytes original/qq_resid.png | Bin 0 -> 9438 bytes paper/SMARTS_InteLigand.txt | 983 ++++++++++ paper/functional-groups.csv | 307 +++ paper/functional-groups.rb | 31 + paper/functional-groups.txt | 307 +++ paper/functional-groups.yaml | 309 ++++ paper/loael-dataset-comparison-all-compounds.pdf | Bin 0 -> 67739 bytes paper/loael-dataset-comparison-all-compounds.svg | 1953 +++++++++++++++++++ .../loael-dataset-comparison-common-compounds.pdf | Bin 0 -> 71753 bytes .../loael-dataset-comparison-common-compounds.svg | 1954 ++++++++++++++++++++ paper/loael-dataset-comparison.rb | 73 + paper/loael-dataset-correlation.pdf | Bin 0 -> 23237 bytes paper/loael-dataset-correlation.svg | 387 ++++ paper/loael-variability.rb | 61 + paper/loael.html | 384 ++++ paper/loael.pdf | 205 ++ paper/loael.rst | 31 +- regression/LOAEL_mg_corrected_smiles.csv | 568 ++++++ regression/LOAEL_mg_corrected_smiles_mmol.csv | 568 ++++++ regression/NOAEL-LOAEL_dv.xlsx | Bin 331117 -> 0 bytes regression/NOAEL-LOAEL_elena_email_20150306.xlsx | Bin 245908 -> 0 bytes 44 files changed, 12532 insertions(+), 1525 deletions(-) delete mode 100644 loael-dataset-comparison.rb delete mode 100644 loael-dataset-comparison.svg delete mode 100644 loael-variability.rb create mode 100755 original/Korrektur.txt create mode 100755 original/LOAEL-Duplicates-mg.csv create mode 100755 original/LOAEL-Duplicates-mmol.csv create mode 100644 original/LOAEL.zip create mode 100755 original/LOAEL2.xls create mode 100755 original/LOAEL_log_mg.csv create mode 100755 original/LOAEL_log_mg_corrected_smiles.csv create mode 100755 original/LOAEL_log_mmol.csv create mode 100755 original/LOAEL_log_mmol_corrected_smiles.csv create mode 100755 original/LOAEL_mg.csv create mode 100755 original/LOAEL_mg_corrected_smiles.csv create mode 100644 original/NOAEL-LOAEL_dv.xlsx create mode 100644 original/NOAEL-LOAEL_elena_email_20150306.xlsx create mode 100755 original/box.png create mode 100755 original/deviation_analysis.R create mode 100755 original/gr_m_var.png create mode 100755 original/loael_in_drei_formaten.R create mode 100755 original/loael_in_drei_formaten_corrected_smiles.R create mode 100755 original/qq.png create mode 100755 original/qq_resid.png create mode 100644 paper/SMARTS_InteLigand.txt create mode 100644 paper/functional-groups.csv create mode 100644 paper/functional-groups.rb create mode 100644 paper/functional-groups.txt create mode 100644 paper/functional-groups.yaml create mode 100644 paper/loael-dataset-comparison-all-compounds.pdf create mode 100644 paper/loael-dataset-comparison-all-compounds.svg create mode 100644 paper/loael-dataset-comparison-common-compounds.pdf create mode 100644 paper/loael-dataset-comparison-common-compounds.svg create mode 100644 paper/loael-dataset-comparison.rb create mode 100644 paper/loael-dataset-correlation.pdf create mode 100644 paper/loael-dataset-correlation.svg create mode 100644 paper/loael-variability.rb create mode 100644 paper/loael.html create mode 100644 paper/loael.pdf create mode 100644 regression/LOAEL_mg_corrected_smiles.csv create mode 100644 regression/LOAEL_mg_corrected_smiles_mmol.csv delete mode 100644 regression/NOAEL-LOAEL_dv.xlsx delete mode 100644 regression/NOAEL-LOAEL_elena_email_20150306.xlsx diff --git a/loael-dataset-comparison.rb b/loael-dataset-comparison.rb deleted file mode 100644 index ad708d3..0000000 --- a/loael-dataset-comparison.rb +++ /dev/null @@ -1,113 +0,0 @@ -require_relative '../lazar/lib/lazar' -include OpenTox -#$mongo.database.drop -#$gridfs = $mongo.database.fs # recreate GridFS indexes -# compare duplicates within datasets -old = Dataset.from_csv_file File.join(File.dirname(__FILE__),"regression","LOAEL_mmol_corrected_smiles.csv") -new = Dataset.from_csv_file File.join(File.dirname(__FILE__),"regression","swissRat_chron_LOAEL.csv") - -combined_compounds = old.compound_ids & new.compound_ids - -compound_vector = [] -value_vector = [] -dataset_vector = [] - -combined_compounds.each do |cid| - c = Compound.find cid - old.values(c,old.features.first).each do |v| - compound_vector << c.smiles - value_vector << -Math.log(v) - dataset_vector << old.name - end - new.values(c,new.features.first).each do |v| - compound_vector << c.smiles - value_vector << -Math.log(v) - dataset_vector << new.name - end -end - -R.assign "smi", compound_vector -R.assign "values", value_vector -R.assign "dataset", dataset_vector -R.eval "df <- data.frame(factor(smi),values,factor(dataset))" -R.eval "img <- ggplot(df, aes(smi,values,ymin = min(values), ymax=max(values),color=dataset))" -R.eval "img <- img + scale_x_discrete(breaks=NULL) + geom_point() + coord_flip() + ylab('-log(LOAEL)') + xlab('Compound')" -R.eval "ggsave(file='/home/ch/opentox/lazar-nestec-data/loael-dataset-comparison.svg', plot=img)" - -=begin - -vars = [] - -[old, new].each do |dataset| - vars << [] - #vars[dataset.name] = [] - p dataset.name - p dataset.compounds.size - p dataset.duplicates(dataset.features.first).size - dataset.duplicates.each do |cid,values| - R.assign "values", values - var = R.eval("var(-log(values))").to_f - vars.last << var - #smi = Compound.find(cid).smiles - smi = cid.to_s - values.each do |val| - compound_vector << smi - value_vector << - Math.log(val) - dataset_vector << dataset.name - end - #vars << { :var => var, :values => values, :smiles => smi } - end - #vars.sort!{|a,b| a[:var] <=> b[:var]} - #vars.each do |dup| - #dup[:values].each do |v| - #compound_vector << dup[:smiles] - #value_vector << v - #end - #end -end -#p vars -# TODO statistical test for variances -R.assign "vars1", vars[0] -R.assign "vars2", vars[1] -print "p-value: #{R.eval("t.test(vars1,vars2)$p.value").to_f}" - -R.assign "smi", compound_vector -R.assign "values", value_vector -R.assign "dataset", dataset_vector -R.eval "df <- data.frame(factor(smi),values,factor(dataset))" -R.eval "img <- ggplot(df, aes(smi,values,ymin = min(values), ymax=max(values),color=dataset))" -R.eval "img <- img + scale_x_discrete(breaks=NULL) + geom_point() + coord_flip()"# + xlab('-log(LOAEL)'), ylab('Compound')" -R.eval "ggsave(file='/home/ch/opentox/lazar-nestec-data/loael_variance.svg', plot=img)" -#R.eval "print(img)" -#R.eval "write.csv(df,'/home/ch/opentox/lazar-nestec-data/loael.csv')" -#`inkview /home/ch/opentox/lazar-nestec-data/loael_variance.svg` -#R.eval "ggsave(file='test.svg', plot=img)" -# compare datasets -# compare combined datasets -file = File.join(File.dirname(__FILE__),"regression","LOAEL-rat-combined.csv") -d = Dataset.from_csv_file file -replicates = [] -compounds = d.compound_ids.uniq -sds = [] -compounds.each do |cid| - compound_idxs = d.compound_ids.each_index.select{|i| d.compound_ids[i] == cid} - if compound_idxs.size > 1 - vals = compound_idxs.collect{|i| d.data_entries[i].first } - R.assign "values", vals - #sd = R.eval("sd(-log(values))").to_f - sd = R.eval("var(values)").to_f - sds << { :sd => sd, :values => vals, :smiles => Compound.find(cid).smiles } - #replicates << compound_idxs.collect{|i| d.data_entries[i].first } - #replicates[Compound.find(cid).smiles] = compound_idxs.collect{|i| d.data_entries[i].first } - end -end -p sds.sort{|a,b| a[:sd] <=> b[:sd]} -#R.assign "replicates", replicates -#R.assign "compounds", compounds.collect{|id| Compound.find id } -#R.eval "df = data.frame(compounds,replicates)" -#library(ggplot2) -#qplot(compounds, replicates, data=df, geom="boxplot") -#p replicates.to_json -#p replicates.size -# http://www.unc.edu/courses/2008spring/psyc/270/001/variance.html -=end diff --git a/loael-dataset-comparison.svg b/loael-dataset-comparison.svg deleted file mode 100644 index 665c236..0000000 --- a/loael-dataset-comparison.svg +++ /dev/null @@ -1,796 +0,0 @@ - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - diff --git a/loael-variability.rb b/loael-variability.rb deleted file mode 100644 index 99e6c34..0000000 --- a/loael-variability.rb +++ /dev/null @@ -1,89 +0,0 @@ -require_relative '../lazar/lib/lazar' -include OpenTox -#$mongo.database.drop -#$gridfs = $mongo.database.fs # recreate GridFS indexes -# compare duplicates within datasets -old = Dataset.from_csv_file File.join(File.dirname(__FILE__),"regression","LOAEL_mmol_corrected_smiles.csv") -new = Dataset.from_csv_file File.join(File.dirname(__FILE__),"regression","swissRat_chron_LOAEL.csv") -combined = Dataset.from_csv_file File.join(File.dirname(__FILE__),"regression","LOAEL-rat-combined.csv") - -compound_vector = [] -value_vector = [] -dataset_vector = [] - -vars = [] - -[old, new].each do |dataset| - vars << [] - #vars[dataset.name] = [] - p dataset.name - p dataset.compounds.size - p dataset.duplicates(dataset.features.first).size - dataset.duplicates.each do |cid,values| - R.assign "values", values - var = R.eval("var(-log(values))").to_f - vars.last << var - #smi = Compound.find(cid).smiles - smi = cid.to_s - values.each do |val| - compound_vector << smi - value_vector << - Math.log(val) - dataset_vector << dataset.name - end - #vars << { :var => var, :values => values, :smiles => smi } - end - #vars.sort!{|a,b| a[:var] <=> b[:var]} - #vars.each do |dup| - #dup[:values].each do |v| - #compound_vector << dup[:smiles] - #value_vector << v - #end - #end -end -#p vars -# TODO statistical test for variances -R.assign "vars1", vars[0] -R.assign "vars2", vars[1] -print "p-value: #{R.eval("t.test(vars1,vars2)$p.value").to_f}" - -R.assign "smi", compound_vector -R.assign "values", value_vector -R.assign "dataset", dataset_vector -R.eval "df <- data.frame(factor(smi),values,factor(dataset))" -R.eval "img <- ggplot(df, aes(smi,values,ymin = min(values), ymax=max(values),color=dataset))" -R.eval "img <- img + scale_x_discrete(breaks=NULL) + geom_point() + coord_flip()"# + xlab('-log(LOAEL)'), ylab('Compound')" -R.eval "ggsave(file='/home/ch/opentox/lazar-nestec-data/loael_variance.svg', plot=img)" -#R.eval "print(img)" -#R.eval "write.csv(df,'/home/ch/opentox/lazar-nestec-data/loael.csv')" -#`inkview /home/ch/opentox/lazar-nestec-data/loael_variance.svg` -#R.eval "ggsave(file='test.svg', plot=img)" -=begin -# compare datasets -# compare combined datasets -file = File.join(File.dirname(__FILE__),"regression","LOAEL-rat-combined.csv") -d = Dataset.from_csv_file file -replicates = [] -compounds = d.compound_ids.uniq -sds = [] -compounds.each do |cid| - compound_idxs = d.compound_ids.each_index.select{|i| d.compound_ids[i] == cid} - if compound_idxs.size > 1 - vals = compound_idxs.collect{|i| d.data_entries[i].first } - R.assign "values", vals - #sd = R.eval("sd(-log(values))").to_f - sd = R.eval("var(values)").to_f - sds << { :sd => sd, :values => vals, :smiles => Compound.find(cid).smiles } - #replicates << compound_idxs.collect{|i| d.data_entries[i].first } - #replicates[Compound.find(cid).smiles] = compound_idxs.collect{|i| d.data_entries[i].first } - end -end -p sds.sort{|a,b| a[:sd] <=> b[:sd]} -#R.assign "replicates", replicates -#R.assign "compounds", compounds.collect{|id| Compound.find id } -#R.eval "df = data.frame(compounds,replicates)" -#library(ggplot2) -#qplot(compounds, replicates, data=df, geom="boxplot") -#p replicates.to_json -#p replicates.size -# http://www.unc.edu/courses/2008spring/psyc/270/001/variance.html -=end diff --git a/loael_variance.svg b/loael_variance.svg index 8dd54db..657f50f 100644 --- a/loael_variance.svg +++ b/loael_variance.svg @@ -9,66 +9,72 @@ - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + + + + + + + @@ -124,37 +130,37 @@ - + - + - + - + - + - + - + - + - + - + - + @@ -162,537 +168,550 @@ - + - + - + - + - + - + - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - + - + - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + - + - + + + + + + + + + - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - + - - + + - - - - - - + + + + + + - + - - - - - - - + + + + + + + - - - - + + + + - - - - - - - - - - - - - - - - - - - - - - - - - - - + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + - - - - - - - - - - - - - - - - - - - - + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/original/Korrektur.txt b/original/Korrektur.txt new file mode 100755 index 0000000..39c0274 --- /dev/null +++ b/original/Korrektur.txt @@ -0,0 +1,6 @@ +ROW,ID,SMILES,MOLWT,COMMENT +1,5,C1=C(C(=CC(=C1NN=C3C2=C(C=C([S]([O-])(=O)=O)C=C2)C=CC3=O)OC)[S]([O-])(=O)=O)C.[Na+].[Na+],496.42,"SMILES could not be read by obabel" +36,194,C1=C(C(=CC=C1OC2=CC=C(C=C2Cl)C(F)(F)F)[N+](=O)[O-])C(=O)[O-].[Na+],383.64,"SMILES could not be read by obabel" +65,299,C(C1C2C(C(O)C(O1)OC8C(OC(OC7C(OC(OC6C(OC(OC5C(C(C(OC4C(C(C(OC3C(C(C(O2)OC3CO)O)O)OC4CO)O)O)OC5CO)O)O)C(C6O)O)CO)C(C7O)O)CO)C(C8O)O)CO)O)O,1134.99,"SMILES was truncated" +138,549,O=[S](NC1CCCCC1)(=O)[O-].[Na+],201.22,"SMILES could not be read by obabel" +398,997,[C@@]14([C@@H]5OCC1=CC=C[C@@H]([C@H](O[C@H]2C[C@@H]([C@H]([C@@H](O2)C)O[C@H]3C[C@@H]([C@H]([C@@H](O3)C)O)OC)OC)C(=CC[C@@H]6C[C@H](OC([C@@H]4C=C([C@H]5O)C)=O)C[C@]7(O6)O[C@@H]([C@H](C=C7)C)[C@H](CC)C)C)C)O,873.0884,"SMILES was truncated" diff --git a/original/LOAEL-Duplicates-mg.csv b/original/LOAEL-Duplicates-mg.csv new file mode 100755 index 0000000..940c92f --- /dev/null +++ b/original/LOAEL-Duplicates-mg.csv @@ -0,0 +1,218 @@ +GID,SMILES,MG +1,Clc1cc(Cl)ccc1C2(Cn3ncnc3)OC(CCC)CO2,1.3979400087 +1,Clc1cc(Cl)ccc1C2(Cn3ncnc3)OC(CCC)CO2,1.982271233 +2,n(c(nc(n1)NCC)NCC)c1Cl,0.6989700043 +2,n(c(nc(n1)NCC)NCC)c1Cl,0.7242758696 +3,CC1(C(C1C(=O)OC(C#N)C2=CC(=C(C=C2)F)OC3=CC=CC=C3)C=C(Cl)Cl)C,1.096910013 +3,CC1(C(C1C(=O)OC(C#N)C2=CC(=C(C=C2)F)OC3=CC=CC=C3)C=C(Cl)Cl)C,0.8750612634 +3,CC1(C(C1C(=O)OC(C#N)C2=CC(=C(C=C2)F)OC3=CC=CC=C3)C=C(Cl)Cl)C,0.7781512504 +3,CC1(C(C1C(=O)OC(C#N)C2=CC(=C(C=C2)F)OC3=CC=CC=C3)C=C(Cl)Cl)C,1.079181246 +4,S=P(OC)(OC)SCN1N=Nc2ccccc2C1(=O),-0.4436974992 +4,S=P(OC)(OC)SCN1N=Nc2ccccc2C1(=O),0.3521825181 +4,S=P(OC)(OC)SCN1N=Nc2ccccc2C1(=O),0.411619706 +5,OC(=O)CNCP(O)(O)=O,3 +5,OC(=O)CNCP(O)(O)=O,2.4771212547 +6,CN(=CC=C1C(C=C2)=CC=N2C)C=C1,0.5740312677 +6,CN(=CC=C1C(C=C2)=CC=N2C)C=C1,0.4065401804 +7,O=C(N(SC(Cl)(Cl)Cl)C(=O)c1cccc2)c12,2.6989700043 +7,O=C(N(SC(Cl)(Cl)Cl)C(=O)c1cccc2)c12,1.6020599913 +7,O=C(N(SC(Cl)(Cl)Cl)C(=O)c1cccc2)c12,1.6989700043 +8,CCCCOCCOCCOCC1=CC2=C(C=C1CCC)OCO2,2.3979400087 +8,CCCCOCCOCCOCC1=CC2=C(C=C1CCC)OCO2,2 +9,C(=CC=C1)(C2=C1)NC(=N2)C(=CS3)N=C3,0.3010299957 +9,C(=CC=C1)(C2=C1)NC(=N2)C(=CS3)N=C3,1.6020599913 +9,C(=CC=C1)(C2=C1)NC(=N2)C(=CS3)N=C3,1.4771212547 +10,O=C(N(C)C)Nc(ccc(c1Cl)Cl)c1,0.7781512504 +10,O=C(N(C)C)Nc(ccc(c1Cl)Cl)c1,0.7958800173 +11,CC1(C(C1(C)C)C(=O)OC(C#N)C2=CC(=CC=C2)OC3=CC=CC=C3)C,1.2889196057 +11,CC1(C(C1(C)C)C(=O)OC(C#N)C2=CC(=CC=C2)OC3=CC=CC=C3)C,1.3979400087 +12,CCC(=C1C(=O)CC(CC1=O)CC(C)SCC)NOCC=CCl,2 +12,CCC(=C1C(=O)CC(CC1=O)CC(C)SCC)NOCC=CCl,1.9344984512 +13,ClC4=C(Cl)C5(Cl)C3C1CC(C2OC12)C3C4(Cl)C5(Cl)Cl,-1.3010299957 +13,C1C2C3C(C1C4C2O4)C5(C(=C(C3(C5(Cl)Cl)Cl)Cl)Cl)Cl,-0.903089987 +13,ClC4=C(Cl)C5(Cl)C3C1CC(C2OC12)C3C4(Cl)C5(Cl)Cl,-1 +13,C1C2C3C(C1C4C2O4)C5(C(=C(C3(C5(Cl)Cl)Cl)Cl)Cl)Cl,-0.6020599913 +14,COP(=O)(NC(=O)(C))SC,1.5440680444 +14,COP(=O)(NC(=O)(C))SC,0.3979400087 +15,ClC(Cl)=CC1C(C)(C)C1C(=O)OC(C(#N))c2cccc(Oc3ccccc3)c2,1.8750612634 +15,ClC(Cl)=CC1C(C)(C)C1C(=O)OC(C(#N))c2cccc(Oc3ccccc3)c2,1.6989700043 +16,CCOP(=S)(OCC)Oc1ccc(cc1)N(=O)=O,0.5440680444 +16,CCOP(=S)(OCC)Oc1ccc(cc1)N(=O)=O,-0.3767507096 +17,CC(C)OC(=O)NC1=CC(=CC=C1)Cl,2.6989700043 +17,CC(C)OC(=O)NC1=CC(=CC=C1)Cl,3 +18,CCOC(=O)CC(SP(=S)(OC)OC)C(=O)OCC,1.6989700043 +18,CCOC(=O)CC(SP(=S)(OC)OC)C(=O)OCC,2.5563025008 +19,CC(C)(C)c2ccc(OC1CCCCC1OS(=O)OCC#C)cc2,2 +19,CC(C)(C)c2ccc(OC1CCCCC1OS(=O)OCC#C)cc2,1.278753601 +20,OC(c1ccc(Cl)cc1)(c2ccc(Cl)cc2)C(Cl)(Cl)Cl,1.3010299957 +20,OC(c1ccc(Cl)cc1)(c2ccc(Cl)cc2)C(Cl)(Cl)Cl,0.3979400087 +21,CC1=CC=CC=C1OCC2=CC=CC=C2C(=NOC)C(=O)OC,2.5740312677 +21,CC1=CC=CC=C1OCC2=CC=CC=C2C(=NOC)C(=O)OC,2.5682017241 +22,Clc1cc(Cl)cc(Cl)c1OCCN(CCC)C(=O)n2cncc2,0.8750612634 +22,Clc1cc(Cl)cc(Cl)c1OCCN(CCC)C(=O)n2cncc2,0.7075701761 +23,N(c(cccc1)c1)c(cccc2)c2,1.4913616938 +23,N(c(cccc1)c1)c(cccc2)c2,1.3979400087 +24,CC(C)(C)C(C(N1C=NC=N1)OC2=CC=C(C=C2)Cl)O,1.3979400087 +24,CC(C)(C)C(C(N1C=NC=N1)OC2=CC=C(C=C2)Cl)O,2.0211892991 +25,CCOP(=O)(NC(C)C)Oc1ccc(SC)c(C)c1,0.1760912591 +25,CCOP(=O)(NC(C)C)Oc1ccc(SC)c(C)c1,0.2304489214 +26,CNC(=O)ON=C(C)SC,1 +26,CNC(=O)ON=C(C)SC,1.3010299957 +27,CCOP(=S)(OCC)SCSC(C)(C)C,-1.3010299957 +27,CCOP(=S)(OCC)SCSC(C)(C)C,0.3010299957 +27,CCOP(=S)(OCC)SCSC(C)(C)C,-1.2218487496 +28,C(C=C1)(=N(C=C1)CC2)C(N2=C3)=CC=C3,-0.2365720064 +28,C(C=C1)(=N(C=C1)CC2)C(N2=C3)=CC=C3,-0.2441251443 +29,COP(=S)(OC)SCN2C(=O)c1ccccc1C2(=O),1.3010299957 +29,COP(=S)(OC)SCN2C(=O)c1ccccc1C2(=O),0.9542425094 +30,CN1C=C(c2ccccc2)C(=O)C(c3cc(C(F)(F)F)ccc3)=C1,1.3979400087 +30,CN1C=C(c2ccccc2)C(=O)C(c3cc(C(F)(F)F)ccc3)=C1,1.511883361 +31,NC(CCCC1)C1,1.7671558661 +31,NC(CCCC1)C1,1.7781512504 +32,ClC(=CC=C1N)C=C1,0.7781512504 +32,C1=CC(=CC=C1N)Cl,1.096910013 +33,O=N(=O)C(C(=C1N(=O)=O)N(C(C)C)C(C)C)=CC(=C1)S(=O)(=O)N,1.5665553309 +33,O=N(=O)C(C(=C1N(=O)=O)N(C(C)C)C(C)C)=CC(=C1)S(=O)(=O)N,1.6532125138 +34,c1c(C(F)(F)F)cccc1N2C(=O)C(Cl)=C(NC)C=N2,1.2730012721 +34,c1c(C(F)(F)F)cccc1N2C(=O)C(Cl)=C(NC)C=N2,1.7096938697 +35,c(cccc1)(c1)CC,2.6106601631 +35,c(cccc1)(c1)CC,2.463892989 +36,c1cc(Cl)ccc1C(C(#N))(CCCC)Cn2ncnc2,0.9929950984 +36,CCCCC(CN1C=NC=N1)(C#N)C2=CC=C(C=C2)Cl,0.9912260757 +37,CC1C=CC=C2COC3C2(C(C=C(C3O)C)C(=O)OC4CC(CC=C(C1OC5CC(C(C(O5)C)OC6CC(C(C(O6)C)NC(=O)C)OC)OC)C)OC7(C4)C=CC(C(O7)C(C)C)C)O,0 +37,CC1C=CC=C2COC3C2(C(C=C(C3O)C)C(=O)OC4CC(CC=C(C1OC5CC(C(C(O5)C)OC6CC(C(C(O6)C)NC(=O)C)OC)OC)C)OC7(C4)C=CC(C(O7)C(C)C)C)O,0.3979400087 +38,CCOP(=S)(OCC)SCCSCC,-1 +38,CCOP(=S)(OCC)SCCSCC,-1.3979400087 +38,CCOP(=S)(OCC)SCCSCC,-0.6575773192 +39,CC(C)OC1=CC=CC(=C1)NC(=O)C2=CC=CC=C2C(F)(F)F,2.6989700043 +39,C(F)(F)(F)c1ccccc1C(=O)Nc2cccc(OC(C)C)c2,1.9395192526 +40,S=P(OC)(OC)SCN1C(=O)SC(OC)=N1,0.3010299957 +40,S=P(OC)(OC)SCN1C(=O)SC(OC)=N1,-0.096910013 +40,S=P(OC)(OC)SCN1C(=O)SC(OC)=N1,0.096910013 +40,S=P(OC)(OC)SCN1C(=O)SC(OC)=N1,0.2041199827 +41,O=C(N(OC)C)Nc(ccc(c1Cl)Cl)c1,0.7958800173 +41,O=C(N(OC)C)Nc(ccc(c1Cl)Cl)c1,0.3979400087 +42,C1=CC(=C(C(=C1)F)C(=O)NC(=O)NC2=CC(=C(C(=C2F)Cl)F)Cl)F,1.414973348 +42,C1=CC(=C(C(=C1)F)C(=O)NC(=O)NC2=CC(=C(C(=C2F)Cl)F)Cl)F,1.3979400087 +43,S=P(OCC)(OCC)Oc1ccc2C(C)=C(Cl)C(=O)Oc2c1,-0.096910013 +43,S=P(OCC)(OCC)Oc1ccc2C(C)=C(Cl)C(=O)Oc2c1,0.2304489214 +44,Clc1ccccc1c2nnc(c3ccccc3Cl)nn2,1.3010299957 +44,C1=CC=C(C(=C1)C2=NN=C(N=N2)C3=CC=CC=C3Cl)Cl,1.2380461031 +45,CC1=C(C(=O)CC1OC(=O)C2C(C2(C)C)C=C(C)C)CC=C,1.8750612634 +45,CC1=C(C(=O)CC1OC(=O)C2C(C2(C)C)C=C(C)C)CC=C,1.3891660844 +45,CC1=C(C(=O)CC1OC(=O)C2C(C2(C)C)C=C(C)C)CC=C,1.1398790864 +46,C1=C(C=C(C(=C1Cl)N)Cl)[N+](=O)[O-],2.1760912591 +46,C1=C(C=C(C(=C1Cl)N)Cl)[N+](=O)[O-],2.3802112417 +47,CCOP(=S)(OCC)OC1=NC(=C(C=C1Cl)Cl)Cl,1 +47,CCOP(=S)(OCC)OC1=NC(=C(C=C1Cl)Cl)Cl,0 +48,FC(F)(F)C(=CC(N(=O)=O)=C1N(C(C)C)C(C)C)C=C1N(=O)=O,1.6020599913 +48,FC(F)(F)C(=CC(N(=O)=O)=C1N(C(C)C)C(C)C)C=C1N(=O)=O,3 +49,CCSC(=O)N1CCCCCC1,1.1705550585 +49,CCSC(=O)N1CCCCCC1,0.3010299957 +50,ClC1C=CC2C1C3(Cl)C(=C(Cl)C2(Cl)C3(Cl)Cl)Cl,-0.6020599913 +50,C1=CC(C2C1C3(C(=C(C2(C3(Cl)Cl)Cl)Cl)Cl)Cl)Cl,-0.4202164034 +51,CC1=CC(=C(C=C1)N=CN(C)C=NC2=C(C=C(C=C2)C)C)C,1.0086001718 +51,CN(C=Nc1ccc(C)cc1C)C=Nc2ccc(C)cc2C,1 +52,c(cccc1)(c1)C=C,1.3222192947 +52,c(cccc1)(c1)C=C,2.45484486 +52,c(cccc1)(c1)C=C,2.6020599913 +53,ClC1CC2C(C1Cl)C3(Cl)C(=C(Cl)C2(Cl)C3(Cl)Cl)Cl,-0.5686362358 +53,ClC1CC2C(C1Cl)C3(Cl)C(=C(Cl)C2(Cl)C3(Cl)Cl)Cl,-0.3010299957 +53,ClC1CC2C(C1Cl)C3(Cl)C(=C(Cl)C2(Cl)C3(Cl)Cl)Cl,0.7781512504 +53,ClC1CC2C(C1Cl)C3(Cl)C(=C(Cl)C2(Cl)C3(Cl)Cl)Cl,-0.6020599913 +54,OCCO,2.3979400087 +54,C(CO)O,2.6020599913 +54,C(CO)O,3.3010299957 +54,C(CO)O,2.9637878273 +54,OCCO,3 +55,CCOP(=S)(OCC)OC1=NC(=NC(=C1)C)C(C)C,0.1760912591 +55,CCOP(=S)(OCC)OC1=NC(=NC(=C1)C)C(C)C,0.7634279936 +56,C1(=C(C(=C(C(=C1Cl)Cl)Cl)Cl)Cl)[N+](=O)[O-],2.096910013 +56,C1(=C(C(=C(C(=C1Cl)Cl)Cl)Cl)Cl)[N+](=O)[O-],2.1461280357 +57,COC(=O)c1c(Cl)c(Cl)c(C(=O)OC)c(Cl)c1Cl,2.6989700043 +57,COC(=O)c1c(Cl)c(Cl)c(C(=O)OC)c(Cl)c1Cl,1 +58,O=C(NC(=O)c(c(F)ccc1)c1F)Nc(ccc(c2)Cl)c2,0.903089987 +58,O=C(NC(=O)c(c(F)ccc1)c1F)Nc(ccc(c2)Cl)c2,0.8920946027 +58,O=C(NC(=O)c(c(F)ccc1)c1F)Nc(ccc(c2)Cl)c2,0.84509804 +59,O1C(=O)C(O)=C(O)C1C(O)CO,3.4844422076 +59,OCC(O)C1C(O)=C(O)C(=O)O1,3.1914510145 +60,O=C(O)C(Cl)(Cl)C,1.449786847 +60,CC(C(=O)O)(Cl)Cl,1.6989700043 +61,CCCCCCCCc1cc(N(=O)(=O))c(OC(=O)C=CC)c(c1)N(=O)(=O),1.6989700043 +61,CCCCCCCCc1cc(N(=O)(=O))c(OC(=O)C=CC)c(c1)N(=O)(=O),1.806179974 +62,COP(=O)(N)SC,-0.0457574906 +62,COP(N)(=O)SC,-1 +62,COP(N)(=O)SC,-0.5376020021 +63,C1=CC(=CC=C1C(C#N)C2=C(C=CC(=C2Cl)N3C(=O)NC(=O)C=N3)Cl)Cl,1.1760912591 +63,C1=CC(=CC=C1C(C#N)C2=C(C=CC(=C2Cl)N3C(=O)NC(=O)C=N3)Cl)Cl,1.361727836 +64,CCc1cccc(CC)c1N(COC)C(=O)CCl,1.1760912591 +64,CCc1cccc(CC)c1N(COC)C(=O)CCl,1.1461280357 +65,O=P(O)(O)CCCl,2.1760912591 +65,O=P(O)(O)CCCl,2.6493348587 +65,O=P(O)(O)CCCl,1.079181246 +66,C1=CC=C2C(=C1)C(=O)C3=C(C2=O)SC(=C(S3)C#N)C#N,1 +66,C1=CC=C2C(=C1)C(=O)C3=C(C2=O)SC(=C(S3)C#N)C#N,0.7781512504 +67,ClC(Cl)C(Cl)(Cl)SN2C(=O)C1CC=CCC1C2(=O),1.079181246 +67,ClC(Cl)C(Cl)(Cl)SN2C(=O)C1CC=CCC1C2(=O),1.1760912591 +68,CCN(CC)C(=O)C(Cl)=C(C)OP(=O)(OC)OC,1.0899051114 +68,CCN(CC)C(=O)C(Cl)=C(C)OP(=O)(OC)OC,0.1760912591 +69,S=P(OCC)(Sc1ccccc1)CC,0.198657087 +69,CCOP(=S)(CC)SC1=CC=CC=C1,0.6989700043 +70,C1=CC=C(C=C1)C(CCC2=CC=C(C=C2)Cl)(CN3C=NC=N3)C#N,1.6020599913 +70,C1=CC=C(C=C1)C(CCC2=CC=C(C=C2)Cl)(CN3C=NC=N3)C#N,1.4771212547 +71,N(C(=S)SSC(N(C)C)=S)(C)C,1.1760912591 +71,N(C(=S)SSC(N(C)C)=S)(C)C,1.0606978404 +71,N(C(=S)SSC(N(C)C)=S)(C)C,0.7379873263 +71,N(C(=S)SSC(N(C)C)=S)(C)C,1.079181246 +72,CCN(CC)c1nc(C)cc(OP(=S)(OC)OC)n1,0.3979400087 +72,CCN(CC)c1nc(C)cc(OP(=S)(OC)OC)n1,1.1398790864 +73,COP(=S)(OC)Oc1ccc(SC)c(C)c1,0.5740312677 +73,COP(=S)(OC)Oc1ccc(SC)c(C)c1,-0.1426675036 +73,COP(=S)(OC)Oc1ccc(SC)c(C)c1,-0.3467874862 +74,O=P(OC)(OC)OC=C(Cl)Cl,0.361727836 +74,COP(=O)(OC)OC=C(Cl)Cl,0.3324384599 +75,CCC(=O)Nc1ccc(Cl)c(Cl)c1,1.3010299957 +75,CCC(=O)Nc1ccc(Cl)c(Cl)c1,1.8808135923 +76,C1CNC(=S)N1,-0.638272164 +76,N(C(=S)NC1)C1,-0.6020599913 +76,N(C(=S)NC1)C1,0.096910013 +77,CCOC1=C(C=CC(=C1)OC2=C(C=C(C=C2)C(F)(F)F)Cl)[N+](=O)[O-],1.6020599913 +77,Clc1cc(C(F)(F)F)ccc1Oc2cc(OCC)c(N(=O)(=O))cc2,1 +78,C1CN(CCN1CCCC(=O)C2=CC=C(C=C2)F)C3=CC=CC=N3,2.0606978404 +78,C1CN(CCN1CCCC(=O)C2=CC=C(C=C2)F)C3=CC=CC=N3,1.4771212547 +79,C1=NNC(=N1)N,0.3979400087 +79,C1=NNC(=N1)N,0.6989700043 +80,ClC2C1OC1C3C2C4(Cl)C(=C(Cl)C3(Cl)C4(Cl)Cl)Cl,-0.6989700043 +80,ClC2C1OC1C3C2C4(Cl)C(=C(Cl)C3(Cl)C4(Cl)Cl)Cl,-1.6020599913 +81,COP(=O)(OC)OC(=CCl)c1cc(Cl)c(Cl)cc1Cl,2 +81,COP(=O)(OC)OC(=CCl)c1cc(Cl)c(Cl)cc1Cl,1.6989700043 +82,O=C(NC)CSP(OC)(OC)=S,-0.6020599913 +82,O=C(NC)CSP(OC)(OC)=S,0.6989700043 +83,CC(C)(C)C(=O)C(Oc1ccc(Cl)cc1)n2cncn2,1.3979400087 +83,CC(C)(C)C(=O)C(N1C=NC=N1)OC2=CC=C(C=C2)Cl,2.0569048513 +84,c(ccc(c1)Cl)(c1)C(c(ccc(c2)Cl)c2)C(Cl)(Cl)Cl,1.5051499783 +84,C1=CC(=CC=C1C(C2=CC=C(C=C2)Cl)C(Cl)(Cl)Cl)Cl,-0.6020599913 +85,CC1=C(N=C(N=C1OC(=O)N(C)C)N(C)C)C,1.096910013 +85,CC1=C(N=C(N=C1OC(=O)N(C)C)N(C)C)C,1.0899051114 +86,c(cccc1)(c1)C(C)C,2.6646419756 +86,c(cccc1)(c1)C(C)C,2.5198279938 +87,CCCN(CCC)C(=O)SCC,0.9542425094 +87,CCCN(CCC)C(=O)SCC,1.3979400087 +88,c1ccc2nc(NC(=O)OC)n(C(=O)NCCCC)c2c1,2.0606978404 +88,CCCCNC(=O)N1C2=CC=CC=C2N=C1NC(=O)OC,2.3979400087 +89,ClCCl,1.6989700043 +89,ClCCl,1.7208205818 +90,O=C(N(S(=O)(=O)Nc1cccc2)C(C)C)c12,1.6020599913 +90,O=C(N(S(=O)(=O)Nc1cccc2)C(C)C)c12,1.5440680444 +91,CC1=C(C=CC=C1COC(=O)C2C(C2(C)C)C=C(C(F)(F)F)Cl)C3=CC=CC=C3,0.6989700043 +91,c1ccccc1c2c(C)c(COC(=O)C3C(C)(C)C3C=C(Cl)C(F)(F)F)ccc2,0.6989700043 +91,c1ccccc1c2c(C)c(COC(=O)C3C(C)(C)C3C=C(Cl)C(F)(F)F)ccc2,0.903089987 +92,C(C(C(C(C1Cl)Cl)Cl)Cl)(C1Cl)Cl,0.6989700043 +92,C(C(C(C(C1Cl)Cl)Cl)Cl)(C1Cl)Cl,0.6627578317 +92,C1(C(C(C(C(C1Cl)Cl)Cl)Cl)Cl)Cl,0.6720978579 +92,C(C(C(C(C1Cl)Cl)Cl)Cl)(C1Cl)Cl,0.903089987 +92,C(C(C(C(C1Cl)Cl)Cl)Cl)(C1Cl)Cl,0.6020599913 +93,O=C(Oc(c(c(ccc1)cc2)c1)c2)NC,1.1931245984 +93,O=C(Oc(c(c(ccc1)cc2)c1)c2)NC,1.7781512504 +94,c1cc(Cl)cc(Cl)c1C(OCC=C)Cn2cncc2,1.6020599913 +94,c1cc(Cl)cc(Cl)c1C(OCC=C)Cn2cncc2,1.1760912591 diff --git a/original/LOAEL-Duplicates-mmol.csv b/original/LOAEL-Duplicates-mmol.csv new file mode 100755 index 0000000..93bf8de --- /dev/null +++ b/original/LOAEL-Duplicates-mmol.csv @@ -0,0 +1,218 @@ +GID,SMILES,MMOL +1,Clc1cc(Cl)ccc1C2(Cn3ncnc3)OC(CCC)CO2,4.1363658605 +1,Clc1cc(Cl)ccc1C2(Cn3ncnc3)OC(CCC)CO2,3.5520346362 +2,n(c(nc(n1)NCC)NCC)c1Cl,4.6056426085 +2,n(c(nc(n1)NCC)NCC)c1Cl,4.5803367432 +3,CC1(C(C1C(=O)OC(C#N)C2=CC(=C(C=C2)F)OC3=CC=CC=C3)C=C(Cl)Cl)C,4.5408674395 +3,CC1(C(C1C(=O)OC(C#N)C2=CC(=C(C=C2)F)OC3=CC=CC=C3)C=C(Cl)Cl)C,4.7627161892 +3,CC1(C(C1C(=O)OC(C#N)C2=CC(=C(C=C2)F)OC3=CC=CC=C3)C=C(Cl)Cl)C,4.8596262022 +3,CC1(C(C1C(=O)OC(C#N)C2=CC(=C(C=C2)F)OC3=CC=CC=C3)C=C(Cl)Cl)C,4.5585962065 +4,S=P(OC)(OC)SCN1N=Nc2ccccc2C1(=O),5.945200886 +4,S=P(OC)(OC)SCN1N=Nc2ccccc2C1(=O),5.1493208687 +4,S=P(OC)(OC)SCN1N=Nc2ccccc2C1(=O),5.0898836808 +5,OC(=O)CNCP(O)(O)=O,2.2280744668 +5,OC(=O)CNCP(O)(O)=O,2.7509532121 +6,CN(=CC=C1C(C=C2)=CC=N2C)C=C1,4.6960719157 +6,CN(=CC=C1C(C=C2)=CC=N2C)C=C1,4.863563003 +7,O=C(N(SC(Cl)(Cl)Cl)C(=O)c1cccc2)c12,2.7731389954 +7,O=C(N(SC(Cl)(Cl)Cl)C(=O)c1cccc2)c12,3.8700490084 +7,O=C(N(SC(Cl)(Cl)Cl)C(=O)c1cccc2)c12,3.7731389954 +8,CCCCOCCOCCOCC1=CC2=C(C=C1CCC)OCO2,3.1315397529 +8,CCCCOCCOCCOCC1=CC2=C(C=C1CCC)OCO2,3.5294797615 +9,C(=CC=C1)(C2=C1)NC(=N2)C(=CS3)N=C3,5.0027008868 +9,C(=CC=C1)(C2=C1)NC(=N2)C(=CS3)N=C3,3.7016708912 +9,C(=CC=C1)(C2=C1)NC(=N2)C(=CS3)N=C3,3.8266096278 +10,O=C(N(C)C)Nc(ccc(c1Cl)Cl)c1,4.5893807758 +10,O=C(N(C)C)Nc(ccc(c1Cl)Cl)c1,4.5716520089 +11,CC1(C(C1(C)C)C(=O)OC(C#N)C2=CC(=CC=C2)OC3=CC=CC=C3)C,4.254431783 +11,CC1(C(C1(C)C)C(=O)OC(C#N)C2=CC(=CC=C2)OC3=CC=CC=C3)C,4.14541138 +12,CCC(=C1C(=O)CC(CC1=O)CC(C)SCC)NOCC=CCl,3.5561954098 +12,CCC(=C1C(=O)CC(CC1=O)CC(C)SCC)NOCC=CCl,3.6216969586 +13,ClC4=C(Cl)C5(Cl)C3C1CC(C2OC12)C3C4(Cl)C5(Cl)Cl,6.8818515947 +13,C1C2C3C(C1C4C2O4)C5(C(=C(C3(C5(Cl)Cl)Cl)Cl)Cl)Cl,6.483911586 +13,ClC4=C(Cl)C5(Cl)C3C1CC(C2OC12)C3C4(Cl)C5(Cl)Cl,6.580821599 +13,C1C2C3C(C1C4C2O4)C5(C(=C(C3(C5(Cl)Cl)Cl)Cl)Cl)Cl,6.1828815903 +14,COP(=O)(NC(=O)(C))SC,3.7187764874 +14,COP(=O)(NC(=O)(C))SC,4.8649045231 +15,ClC(Cl)=CC1C(C)(C)C1C(=O)OC(C(#N))c2cccc(Oc3ccccc3)c2,3.7443421847 +15,ClC(Cl)=CC1C(C)(C)C1C(=O)OC(C(#N))c2cccc(Oc3ccccc3)c2,3.9204334438 +16,CCOP(=S)(OCC)Oc1ccc(cc1)N(=O)=O,4.9202137268 +16,CCOP(=S)(OCC)Oc1ccc(cc1)N(=O)=O,5.8410324807 +17,CC(C)OC(=O)NC1=CC(=CC=C1)Cl,2.6307548052 +17,CC(C)OC(=O)NC1=CC(=CC=C1)Cl,2.3297248095 +18,CCOC(=O)CC(SP(=S)(OC)OC)C(=O)OCC,3.8200148515 +18,CCOC(=O)CC(SP(=S)(OC)OC)C(=O)OCC,2.9626823551 +19,CC(C)(C)c2ccc(OC1CCCCC1OS(=O)OCC#C)cc2,3.5446537482 +19,CC(C)(C)c2ccc(OC1CCCCC1OS(=O)OCC#C)cc2,4.2659001473 +20,OC(c1ccc(Cl)cc1)(c2ccc(Cl)cc2)C(Cl)(Cl)Cl,4.2677414072 +20,OC(c1ccc(Cl)cc1)(c2ccc(Cl)cc2)C(Cl)(Cl)Cl,5.1708313942 +21,CC1=CC=CC=C1OCC2=CC=CC=C2C(=NOC)C(=O)OC,2.9219953267 +21,CC1=CC=CC=C1OCC2=CC=CC=C2C(=NOC)C(=O)OC,2.9278248704 +22,Clc1cc(Cl)cc(Cl)c1OCCN(CCC)C(=O)n2cncc2,4.700894511 +22,Clc1cc(Cl)cc(Cl)c1OCCN(CCC)C(=O)n2cncc2,4.8683855983 +23,N(c(cccc1)c1)c(cccc2)c2,3.737096259 +23,N(c(cccc1)c1)c(cccc2)c2,3.8305179441 +24,CC(C)(C)C(C(N1C=NC=N1)OC2=CC=C(C=C2)Cl)O,4.0730062129 +24,CC(C)(C)C(C(N1C=NC=N1)OC2=CC=C(C=C2)Cl)O,3.4497569225 +25,CCOP(=O)(NC(C)C)Oc1ccc(SC)c(C)c1,5.3058633931 +25,CCOP(=O)(NC(C)C)Oc1ccc(SC)c(C)c1,5.2515057308 +26,CNC(=O)ON=C(C)SC,4.210077892 +26,CNC(=O)ON=C(C)SC,3.9090478964 +27,CCOP(=S)(OCC)SCSC(C)(C)C,6.7610713306 +27,CCOP(=S)(OCC)SCSC(C)(C)C,5.1590113392 +27,CCOP(=S)(OCC)SCSC(C)(C)C,6.6818900845 +28,C(C=C1)(=N(C=C1)CC2)C(N2=C3)=CC=C3,5.5019490483 +28,C(C=C1)(=N(C=C1)CC2)C(N2=C3)=CC=C3,5.5095021861 +29,COP(=S)(OC)SCN2C(=O)c1ccccc1C2(=O),4.2004688747 +29,COP(=S)(OC)SCN2C(=O)c1ccccc1C2(=O),4.5472563609 +30,CN1C=C(c2ccccc2)C(=O)C(c3cc(C(F)(F)F)ccc3)=C1,4.1196725191 +30,CN1C=C(c2ccccc2)C(=O)C(c3cc(C(F)(F)F)ccc3)=C1,4.0057291668 +31,NC(CCCC1)C1,3.2292424895 +31,NC(CCCC1)C1,3.2182471052 +32,ClC(=CC=C1N)C=C1,4.3276025478 +32,C1=CC(=CC=C1N)Cl,4.0088437852 +33,O=N(=O)C(C(=C1N(=O)=O)N(C(C)C)C(C)C)=CC(=C1)S(=O)(=O)N,3.9729717982 +33,O=N(=O)C(C(=C1N(=O)=O)N(C(C)C)C(C)C)=CC(=C1)S(=O)(=O)N,3.8863146153 +34,c1c(C(F)(F)F)cccc1N2C(=O)C(Cl)=C(NC)C=N2,4.2093971415 +34,c1c(C(F)(F)F)cccc1N2C(=O)C(Cl)=C(NC)C=N2,3.7727045439 +35,c(cccc1)(c1)CC,2.415321201 +35,c(cccc1)(c1)CC,2.5620883751 +36,c1cc(Cl)ccc1C(C(#N))(CCCC)Cn2ncnc2,4.4675649152 +36,CCCCC(CN1C=NC=N1)(C#N)C2=CC=C(C=C2)Cl,4.4693339379 +37,CC1C=CC=C2COC3C2(C(C=C(C3O)C)C(=O)OC4CC(CC=C(C1OC5CC(C(C(O5)C)OC6CC(C(C(O6)C)NC(=O)C)OC)OC)C)OC7(C4)C=CC(C(O7)C(C)C)C)O,5.9542918328 +37,CC1C=CC=C2COC3C2(C(C=C(C3O)C)C(=O)OC4CC(CC=C(C1OC5CC(C(C(O5)C)OC6CC(C(C(O6)C)NC(=O)C)OC)OC)C)OC7(C4)C=CC(C(O7)C(C)C)C)O,5.5563518242 +38,CCOP(=S)(OCC)SCCSCC,6.438390471 +38,CCOP(=S)(OCC)SCCSCC,6.8363304797 +38,CCOP(=S)(OCC)SCCSCC,6.0959677902 +39,CC(C)OC1=CC=CC(=C1)NC(=O)C2=CC=CC=C2C(F)(F)F,2.8106486626 +39,C(F)(F)(F)c1ccccc1C(=O)Nc2cccc(OC(C)C)c2,3.5700994143 +40,S=P(OC)(OC)SCN1C(=O)SC(OC)=N1,5.1794531173 +40,S=P(OC)(OC)SCN1C(=O)SC(OC)=N1,5.5773931259 +40,S=P(OC)(OC)SCN1C(=O)SC(OC)=N1,5.3835730999 +40,S=P(OC)(OC)SCN1C(=O)SC(OC)=N1,5.2763631303 +41,O=C(N(OC)C)Nc(ccc(c1Cl)Cl)c1,4.600483075 +41,O=C(N(OC)C)Nc(ccc(c1Cl)Cl)c1,4.9984230837 +42,C1=CC(=C(C(=C1)F)C(=O)NC(=O)NC2=CC(=C(C(=C2F)Cl)F)Cl)F,4.166076145 +42,C1=CC(=C(C(=C1)F)C(=O)NC(=O)NC2=CC(=C(C(=C2F)Cl)F)Cl)F,4.1831094843 +43,S=P(OCC)(OCC)Oc1ccc2C(C)=C(Cl)C(=O)Oc2c1,5.6565361117 +43,S=P(OCC)(OCC)Oc1ccc2C(C)=C(Cl)C(=O)Oc2c1,5.3291771773 +44,Clc1ccccc1c2nnc(c3ccccc3Cl)nn2,4.1806220184 +44,C1=CC=C(C(=C1)C2=NN=C(N=N2)C3=CC=CC=C3Cl)Cl,4.2436059109 +45,CC1=C(C(=O)CC1OC(=O)C2C(C2(C)C)C=C(C)C)CC=C,3.6055319264 +45,CC1=C(C(=O)CC1OC(=O)C2C(C2(C)C)C=C(C)C)CC=C,4.0914271054 +45,CC1=C(C(=O)CC1OC(=O)C2C(C2(C)C)C=C(C)C)CC=C,4.3407141034 +46,C1=C(C=C(C(=C1Cl)N)Cl)[N+](=O)[O-],3.1399087936 +46,C1=C(C=C(C(=C1Cl)N)Cl)[N+](=O)[O-],2.935788811 +47,CCOP(=S)(OCC)OC1=NC(=C(C=C1Cl)Cl)Cl,4.5447949422 +47,CCOP(=S)(OCC)OC1=NC(=C(C=C1Cl)Cl)Cl,5.5447949422 +48,FC(F)(F)C(=CC(N(=O)=O)=C1N(C(C)C)C(C)C)C=C1N(=O)=O,3.9233464254 +48,FC(F)(F)C(=CC(N(=O)=O)=C1N(C(C)C)C(C)C)C=C1N(=O)=O,2.5254064168 +49,CCSC(=O)N1CCCCCC1,4.1019882374 +49,CCSC(=O)N1CCCCCC1,4.9715133002 +50,ClC1C=CC2C1C3(Cl)C(=C(Cl)C2(Cl)C3(Cl)Cl)Cl,6.1741385728 +50,C1=CC(C2C1C3(C(=C(C2(C3(Cl)Cl)Cl)Cl)Cl)Cl)Cl,5.9922949849 +51,CC1=CC(=C(C=C1)N=CN(C)C=NC2=C(C=C(C=C2)C)C)C,4.4588688485 +51,CN(C=Nc1ccc(C)cc1C)C=Nc2ccc(C)cc2C,4.4674690203 +52,c(cccc1)(c1)C=C,3.69543631 +52,c(cccc1)(c1)C=C,2.5628107448 +52,c(cccc1)(c1)C=C,2.4155956134 +53,ClC1CC2C(C1Cl)C3(Cl)C(=C(Cl)C2(Cl)C3(Cl)Cl)Cl,6.1811855526 +53,ClC1CC2C(C1Cl)C3(Cl)C(=C(Cl)C2(Cl)C3(Cl)Cl)Cl,5.9135793124 +53,ClC1CC2C(C1Cl)C3(Cl)C(=C(Cl)C2(Cl)C3(Cl)Cl)Cl,4.8343980664 +53,ClC1CC2C(C1Cl)C3(Cl)C(=C(Cl)C2(Cl)C3(Cl)Cl)Cl,6.2146093081 +54,OCCO,2.3949266233 +54,C(CO)O,2.1908066406 +54,C(CO)O,1.4918366363 +54,C(CO)O,1.8290788046 +54,OCCO,1.7928666319 +55,CCOP(=S)(OCC)OC1=NC(=NC(=C1)C)C(C)C,5.3072756271 +55,CCOP(=S)(OCC)OC1=NC(=NC(=C1)C)C(C)C,4.7199388926 +56,C1(=C(C(=C(C(=C1Cl)Cl)Cl)Cl)Cl)[N+](=O)[O-],3.3734044639 +56,C1(=C(C(=C(C(=C1Cl)Cl)Cl)Cl)Cl)[N+](=O)[O-],3.3241864412 +57,COC(=O)c1c(Cl)c(Cl)c(C(=O)OC)c(Cl)c1Cl,2.8221212986 +57,COC(=O)c1c(Cl)c(Cl)c(C(=O)OC)c(Cl)c1Cl,4.521091303 +58,O=C(NC(=O)c(c(F)ccc1)c1F)Nc(ccc(c2)Cl)c2,4.5892278755 +58,O=C(NC(=O)c(c(F)ccc1)c1F)Nc(ccc(c2)Cl)c2,4.6002232598 +58,O=C(NC(=O)c(c(F)ccc1)c1F)Nc(ccc(c2)Cl)c2,4.6472198225 +59,O1C(=O)C(O)=C(O)C1C(O)CO,1.7613766285 +59,OCC(O)C1C(O)=C(O)C(=O)O1,2.0543678217 +60,O=C(O)C(Cl)(Cl)C,3.7054539997 +60,CC(C(=O)O)(Cl)Cl,3.4562708424 +61,CCCCCCCCc1cc(N(=O)(=O))c(OC(=O)C=CC)c(c1)N(=O)(=O),3.8625999736 +61,CCCCCCCCc1cc(N(=O)(=O))c(OC(=O)C=CC)c(c1)N(=O)(=O),3.7553900039 +62,COP(=O)(N)SC,5.1953743118 +62,COP(N)(=O)SC,6.1496168212 +62,COP(N)(=O)SC,5.6872188233 +63,C1=CC(=CC=C1C(C#N)C2=C(C=CC(=C2Cl)N3C(=O)NC(=O)C=N3)Cl)Cl,4.4341833605 +63,C1=CC(=CC=C1C(C#N)C2=C(C=CC(=C2Cl)N3C(=O)NC(=O)C=N3)Cl)Cl,4.2485467835 +64,CCc1cccc(CC)c1N(COC)C(=O)CCl,4.2548977242 +64,CCc1cccc(CC)c1N(COC)C(=O)CCl,4.2848609476 +65,O=P(O)(O)CCCl,2.9837585577 +65,O=P(O)(O)CCCl,2.510514958 +65,O=P(O)(O)CCCl,4.0806685707 +66,C1=CC=C2C(=C1)C(=O)C3=C(C2=O)SC(=C(S3)C#N)C#N,4.4717664757 +66,C1=CC=C2C(=C1)C(=O)C3=C(C2=O)SC(=C(S3)C#N)C#N,4.6936152253 +67,ClC(Cl)C(Cl)(Cl)SN2C(=O)C1CC=CCC1C2(=O),4.4637200327 +67,ClC(Cl)C(Cl)(Cl)SN2C(=O)C1CC=CCC1C2(=O),4.3668100197 +68,CCN(CC)C(=O)C(Cl)=C(C)OP(=O)(OC)OC,4.3867647072 +68,CCN(CC)C(=O)C(Cl)=C(C)OP(=O)(OC)OC,5.3005785596 +69,S=P(OCC)(Sc1ccccc1)CC,5.192858917 +69,CCOP(=S)(CC)SC1=CC=CC=C1,4.6925459996 +70,C1=CC=C(C=C1)C(CCC2=CC=C(C=C2)Cl)(CN3C=NC=N3)C#N,3.9253354045 +70,C1=CC=C(C=C1)C(CCC2=CC=C(C=C2)Cl)(CN3C=NC=N3)C#N,4.0502741412 +71,N(C(=S)SSC(N(C)C)=S)(C)C,4.2049025996 +71,N(C(=S)SSC(N(C)C)=S)(C)C,4.3202960183 +71,N(C(=S)SSC(N(C)C)=S)(C)C,4.6430065323 +71,N(C(=S)SSC(N(C)C)=S)(C)C,4.3018126126 +72,CCN(CC)c1nc(C)cc(OP(=S)(OC)OC)n1,5.0868345341 +72,CCN(CC)c1nc(C)cc(OP(=S)(OC)OC)n1,4.3448954564 +73,COP(=S)(OC)Oc1ccc(SC)c(C)c1,4.8705257263 +73,COP(=S)(OC)Oc1ccc(SC)c(C)c1,5.5872244976 +73,COP(=S)(OC)Oc1ccc(SC)c(C)c1,5.7913444803 +74,O=P(OC)(OC)OC=C(Cl)Cl,4.9826167629 +74,COP(=O)(OC)OC=C(Cl)Cl,5.011906139 +75,CCC(=O)Nc1ccc(Cl)c(Cl)c1,4.037585564 +75,CCC(=O)Nc1ccc(Cl)c(Cl)c1,3.4578019674 +76,C1CNC(=S)N1,5.6475451411 +76,N(C(=S)NC1)C1,5.6113329684 +76,N(C(=S)NC1)C1,4.9123629641 +77,CCOC1=C(C=CC(=C1)OC2=C(C=C(C=C2)C(F)(F)F)Cl)[N+](=O)[O-],3.9562889372 +77,Clc1cc(C(F)(F)F)ccc1Oc2cc(OCC)c(N(=O)(=O))cc2,4.5583489285 +78,C1CN(CCN1CCCC(=O)C2=CC=C(C=C2)F)C3=CC=CC=N3,3.4543753738 +78,C1CN(CCN1CCCC(=O)C2=CC=C(C=C2)F)C3=CC=CC=N3,4.0379519594 +79,C1=NNC(=N1)N,4.5267524877 +79,C1=NNC(=N1)N,4.2257224921 +80,ClC2C1OC1C3C2C4(Cl)C(=C(Cl)C3(Cl)C4(Cl)Cl)Cl,6.289273484 +80,ClC2C1OC1C3C2C4(Cl)C(=C(Cl)C3(Cl)C4(Cl)Cl)Cl,7.192363471 +81,COP(=O)(OC)OC(=CCl)c1cc(Cl)c(Cl)cc1Cl,3.5634357799 +81,COP(=O)(OC)OC(=CCl)c1cc(Cl)c(Cl)cc1Cl,3.8644657756 +82,O=C(NC)CSP(OC)(OC)=S,5.9623834318 +82,O=C(NC)CSP(OC)(OC)=S,4.6613534361 +83,CC(C)(C)C(=O)C(Oc1ccc(Cl)cc1)n2cncn2,4.0700360038 +83,CC(C)(C)C(=O)C(N1C=NC=N1)OC2=CC=C(C=C2)Cl,3.4110711611 +84,c(ccc(c1)Cl)(c1)C(c(ccc(c2)Cl)c2)C(Cl)(Cl)Cl,4.0444494281 +84,C1=CC(=CC=C1C(C2=CC=C(C=C2)Cl)C(Cl)(Cl)Cl)Cl,6.1516593978 +85,CC1=C(N=C(N=C1OC(=O)N(C)C)N(C)C)C,4.280188915 +85,CC1=C(N=C(N=C1OC(=O)N(C)C)N(C)C)C,4.2871938166 +86,c(cccc1)(c1)C(C)C,2.4152320688 +86,c(cccc1)(c1)C(C)C,2.5600460505 +87,CCCN(CCC)C(=O)SCC,4.3229499948 +87,CCCN(CCC)C(=O)SCC,3.8792524956 +88,c1ccc2nc(NC(=O)OC)n(C(=O)NCCCC)c2c1,3.4021757041 +88,CCCCNC(=O)N1C2=CC=CC=C2N=C1NC(=O)OC,3.0649335358 +89,ClCCl,3.2301043125 +89,ClCCl,3.2082537351 +90,O=C(N(S(=O)(=O)Nc1cccc2)C(C)C)c12,3.7786556076 +90,O=C(N(S(=O)(=O)Nc1cccc2)C(C)C)c12,3.8366475546 +91,CC1=C(C=CC=C1COC(=O)C2C(C2(C)C)C=C(C(F)(F)F)Cl)C3=CC=CC=C3,4.9272346013 +91,c1ccccc1c2c(C)c(COC(=O)C3C(C)(C)C3C=C(Cl)C(F)(F)F)ccc2,4.9272346013 +91,c1ccccc1c2c(C)c(COC(=O)C3C(C)(C)C3C=C(Cl)C(F)(F)F)ccc2,4.7231146186 +92,C(C(C(C(C1Cl)Cl)Cl)Cl)(C1Cl)Cl,4.76466896 +92,C(C(C(C(C1Cl)Cl)Cl)Cl)(C1Cl)Cl,4.8008811327 +92,C1(C(C(C(C(C1Cl)Cl)Cl)Cl)Cl)Cl,4.7915411064 +92,C(C(C(C(C1Cl)Cl)Cl)Cl)(C1Cl)Cl,4.5605489774 +92,C(C(C(C(C1Cl)Cl)Cl)Cl)(C1Cl)Cl,4.861578973 +93,O=C(Oc(c(c(ccc1)cc2)c1)c2)NC,4.1105492226 +93,O=C(Oc(c(c(ccc1)cc2)c1)c2)NC,3.5255225706 +94,c1cc(Cl)cc(Cl)c1C(OCC=C)Cn2cncc2,3.8709592363 +94,c1cc(Cl)cc(Cl)c1C(OCC=C)Cn2cncc2,4.2969279686 diff --git a/original/LOAEL.zip b/original/LOAEL.zip new file mode 100644 index 0000000..85a71c9 Binary files /dev/null and b/original/LOAEL.zip differ diff --git a/original/LOAEL2.xls b/original/LOAEL2.xls new file mode 100755 index 0000000..8e2d2d8 Binary files /dev/null and b/original/LOAEL2.xls differ diff --git a/original/LOAEL_log_mg.csv b/original/LOAEL_log_mg.csv new file mode 100755 index 0000000..958ea4e --- /dev/null +++ b/original/LOAEL_log_mg.csv @@ -0,0 +1,566 @@ +SMILES,LOAEL_log_mg_kg_bw_day +'COc1cc(c(C)cc1N=Nc2c(O)ccc3cc(ccc23)S(OH)(=O)=O)S(OH)(=O)=O',3.57275546515422 +'O1C(=O)C(O)=C(O)C1C(O)CO',3.48444220764241 +'C1(C)=C(C=CC(C)=CC=CC(C)=CC=CC=C(C)C=CC=C(C)C(=O)OC)C(C)(C)CCC1',2.69897000433602 +'c(cccc1)(c1)C(C)C',2.66464197555613 +'O=C(OCCCC)c(c(ccc1)C(=O)OCCCC)c1',2.77815125038364 +'O=C(OCC)c(c(ccc1)C(=O)OCC)c1',3.64689362416774 +'O=C(OC(OC(OC1C)C)C1)C',2.09691001300806 +'Oc(c(ccc1)C)c1C',0.778151250383644 +'Oc(ccc(c1C)C)c1',1.14612803567824 +'O=C(OCC)C=C',2.39445168082622 +'c(cccc1)(c1)CC',2.61066016308988 +'OCCO',2.39794000867204 +'c(ccc1C(=O)OCC(=O)OCC)cc1C(=O)OCC',3.39794000867204 +'O=C',1.91381385238372 +'O=C(O)C=CC(=O)O',3.03382569395331 +'OCC(O)CO',3.83777776955373 +'O=C(OC)c(ccc(O)c1)c1',3.17609125905568 +'O=C(OCCC)c(ccc(O)c1)c1',3.17609125905568 +'CC(CCC(=O)(O))C3CCC4C2CCC1CC(O)CCC1(C)C2CCC34C',2.69897000433602 +'OC(C(CCC1C)C(C)C)C1',2.77305469336426 +'O=C(O)C(=C)C',2.39445168082622 +'O=C(OC)c(c(O)ccc1)c1',2.55630250076729 +'Oc(cccc1)c1',2.53655844257153 +'O=C(OCCC)c(cc(O)c(O)c1O)c1',2.93651374247889 +'OCC(O)C1C(O)=C(O)C(=O)O1',3.19145101446490 +'c(cccc1)(c1)C=C',1.32221929473392 +'O=Cc(occ1)c1',1.77815125038364 +'NCCNc1cccc2ccccc12',1.89762709129044 +'CN(C)(C)CCCl',2.43933269383026 +'O=C(Nc(ccc(c1)C(=O)CCl)c1)C',3.19865708695442 +'c(ccc(c1)Cl)(c1)C(c(ccc(c2)Cl)c2)C(Cl)(Cl)Cl',1.50514997831991 +'CC(Oc1cc(Cl)c(Cl)cc1Cl)C(=O)(O)',0.939519252618618 +'O=N(=O)C(=CC=C1OC)C=C1N=NC(C(O)=C2C(=O)NC(=CC=C4)C=C4N(=O)=O)=C(C=C3)C(=C2)C=C3',3.32221929473392 +'O=N(=O)C(C=C1)=CC(OCCO)=C1NCCO',2.35983548233989 +'Cc1cccc(CC)c1N(C(=O)CCl)COCC',1.69897000433602 +'Clc(cc(c1)C(F)(F)F)c(c1)Oc(ccc2N(=O)(=O))cc2C(=O)OH',2.25527250510331 +'CCc1cccc(CC)c1N(COC)C(=O)CCl',1.17609125905568 +'O=C(Nc(ccc(OCC)c1N)c1)C',3.07371835034612 +'Oc(ccc(N)c1)c1',2.83632411570675 +'CC(N)CC(=CC=C1)C=C1',0.698970004336019 +'O(c(ccc(c1)C=CC)c1)C',2.53655844257153 +'COc1ccc(N)cc1',2.67577834167409 +'O=C(O)c(c(N)ccc1)c1',3.43949059038968 +'Clc2cccc(c2)c1ccccc1',0.602059991327962 +'O=C(NC(C(=O)OC)Cc(cccc1)c1)C(N)CC(=O)O',2.16731733474818 +'n1c2ccc(Cl)cc2ncc1Oc3ccc(OC(C)C(=O)OCC)cc3',0.568201724066995 +'COC(=O)NS(=O)(=O)c1ccc(N)cc1',2.25527250510331 +'S=P(OC)(OC)SCN1N=Nc2ccccc2C1(=O)',-0.443697499232713 +'CNC(=O)Oc1ccccc1OC(C)C',1.69897000433602 +'CC(C)(C)C(=O)C(Oc1ccc(Cl)cc1)n2cncn2',1.39794000867204 +'O=S(O)(=O)C(=CC=C1)C=C1CN(CC)=C(C=C2)C=CC2=C(C(C=C3)=CC=C3N(C)C)C(C=C4)=CC=C4N(CC)CC(C=C5)=CC(=C5)S(=O)(=O)O',2.85733249643127 +'c(c(cccc1)c1)(cccc2)c2',2.39794000867204 +'BrC(Cl)Cl',2.11394335230684 +'ClC(Cl)C(Cl)(Cl)SN2C(=O)C1CC=CCC1C2(=O)',1.07918124604762 +'O=C(Oc(c(c(ccc1)cc2)c1)c2)NC',1.19312459835446 +'CC1=C(SCCO1)C(=O)Nc2ccccc2',1.47712125471966 +'ClC1CC2C(C1Cl)C3(Cl)C(=C(Cl)C2(Cl)C3(Cl)Cl)Cl',-0.568636235841013 +'O=C(O)CCl',1.47712125471966 +'ClC(=CC=C1N)C=C1',0.778151250383644 +'CC(C)OC(=O)C(O)(c1ccc(Cl)cc1)c2ccc(Cl)cc2',0.954242509439325 +'n1c(OC)nc(C)nc1NC(=O)NS(=O)(=O)c2ccccc2Cl',1.39794000867204 +'OS(=O)(=O)C(C(=CC=C2)C1=C2)=CC=C1N=NC(C(O)=C3N=NC(C(C=C5)=C4C=C5)=CC=C4S(O)(=O)=O)=CC(=C3O)CO',2.8668778143375 +'S=P(OCC)(OCC)Oc1ccc2C(C)=C(Cl)C(=O)Oc2c1',-0.0969100130080564 +'CNP(=O)(OC)Oc1ccc(cc1Cl)C(C)(C)C',0.602059991327962 +'n1c(N)nc(N)nc1NC2CC2',1.17609125905568 +'COC(=O)c1c(Cl)c(Cl)c(C(=O)OC)c(Cl)c1Cl',2.69897000433602 +'O=C(O)C(Cl)(Cl)C',1.44978684698577 +'Nc1cc(N)c(O)cc1',1.39794000867204 +'FC(F)(Cl)Cl',2.17609125905568 +'ClCCl',1.69897000433602 +'O=P(OC)(OC)OC=C(Cl)Cl',0.361727836017593 +'OC(c1ccc(Cl)cc1)(c2ccc(Cl)cc2)C(Cl)(Cl)Cl',1.30102999566398 +'ClC4=C(Cl)C5(Cl)C3C1CC(C2OC12)C3C4(Cl)C5(Cl)Cl',-1.30102999566398 +'CN(=C1C(C=C2)=CC=C2)N(C)C(=C1)C(C=C3)=CC=C3',2.09691001300806 +'O=C(NC(=O)c(c(F)ccc1)c1F)Nc(ccc(c2)Cl)c2',0.903089986991944 +'CC1=C(C)S(=O)(=O)CCS1(=O)=O',1 +'O=C(NC)CSP(OC)(OC)=S',-0.602059991327962 +'COc1ccc(N)c(OC)c1',2.44090908206522 +'COP(=O)OC',2 +'CC(=C(N(=O)=O)C=C1N(=O)=O)C=C1',1.53147891704226 +'CN(C)C(=O)C(c1ccccc1)c2ccccc2',1.47712125471966 +'N(c(cccc1)c1)c(cccc2)c2',1.49136169383427 +'C(C=C1)(=N(C=C1)CC2)C(N2=C3)=CC=C3',-0.236572006437063 +'CCOP(=S)(OCC)SCCSCC',-1 +'NC(=S)NNC(N)=S',2.97634997900327 +'O=C(N(C)C)Nc(ccc(c1Cl)Cl)c1',0.778151250383644 +'O=P(O)(O)CCCl',2.17609125905568 +'O=C(OCC)C(O1)C1(c(cccc2)c2)C',2.24303804868629 +'COC(=O)NC(=NC1=C2)NC1=CC(=C2)SC(C=C3)=CC=C3',1.17609125905568 +'CN1C=C(c2ccccc2)C(=O)C(c3cc(C(F)(F)F)ccc3)=C1',1.39794000867204 +'c1cc(C(F)(F)F)cc(Cl)c1NC(C(C)C)C(=O)OC(C(#N))c2cccc(Oc3ccccc3)c2',0.397940008672038 +'S=P(OCC)(Sc1ccccc1)CC',0.198657086954423 +'n1c(C)nc(OC)nc1NC(=O)NS(=O)(=O)c2ccsc2C(=O)OC',1.39794000867204 +'C(C(C(C(C1Cl)Cl)Cl)Cl)(C1Cl)Cl',0.698970004336019 +'O=N(=O)N(CN1N(=O)=O)CN(C1)N(=O)=O',0.176091259055681 +'O=C(N=C(N(C1(=O))C)N(C)C)N1C(CCCC2)C2',1.69897000433602 +'n(c(c(ccc1)cc2)c1O)c2',2.15533603746506 +'c1cc(Cl)cc(Cl)c1C(OCC=C)Cn2cncc2',1.60205999132796 +'COc1cccc(OC)c1C(=O)Nc2onc(C(C)(CC)CC)c2',1.70500795933334 +'n1c(OC)cc(OC)nc1NC(=O)NS(=O)(=O)Cc2ccccc2C(=O)OC',2.48995847942483 +'CCOC(=O)CC(SP(=S)(OC)OC)C(=O)OCC',1.69897000433602 +'CN(C)(CCC1)CC1',2.17609125905568 +'O=P(SCCCC)(SCCCC)SCCCC',0.0969100130080564 +'COCC(=O)N(C(C)C(=O)OC)c1c(C)cccc1C',1.79588001734408 +'S=P(OC)(OC)SCN1C(=O)SC(OC)=N1',0.301029995663981 +'CNC(=O)ON=C(C)SC',1 +'COP(=S)(OC)Oc1ccc(cc1)N(=O)(=O)',-0.602059991327962 +'O=C1N(N)C(SC)=NN=C1C(C)(C)C',1.17609125905568 +'COP(=O)(OC)OC(Br)C(Cl)(Cl)Br',0.301029995663981 +'OC(C(N)C1O)C(C)OC1(C)OC(CC(C)(C(C2O)C(O)=O)OC(O)(C2)CC(O)CC(C)(O3)C3C=C4)C=CC=CC=CC=CCC(C)OC4=O',1.85733249643127 +'O=N(=O)c(ccc(c1N)C)c1',0.903089986991944 +'O=N(=O)c(c(N)ccc1N)c1',1.93951925261862 +'O=C(O)C(=C(N)C=C1N(=O)=O)C=C1',3.07371835034612 +'O=N(=O)c(c(c(ccc1)cc2)c1)c2',2.21748394421391 +'c12c(N=Nc3ccccc3)c(O)ccc1cc(S(=O)(=O)O)cc2',2.25527250510331 +'CC(C)Oc1cc(c(Cl)cc1Cl)N2N=C(OC2(=O))C(C)(C)C',0.698970004336019 +'CNC(=O)ON=C(SC)C(=O)N(C)C',0.698970004336019 +'CCOP(=S)(OCC)Oc1ccc(cc1)N(=O)=O',0.544068044350276 +'Oc(c(c(c(c1Cl)Cl)Cl)Cl)c1Cl',1 +'NC(=N)NC(=N)NCCc1ccccc1',1.86332286012046 +'COP(=S)(OC)SCN2C(=O)c1ccccc1C2(=O)',1.30102999566398 +'CCN(CC)C(=O)C(Cl)=C(C)OP(=O)(OC)OC',1.08990511143940 +'ClC3C6(Cl)C4C2C1OC1C5C2C3(Cl)C(Cl)(C45)C6(Cl)Cl',-0.154901959985743 +'O=C(OC(=O)c1cccc2)c12',3.07371835034612 +'Nc1c(Cl)c(Cl)nc(C(=O)(O))c1Cl',1.77815125038364 +'CCN(CC)c1nc(C)cc(OP(=S)(OC)OC)n1',0.397940008672038 +'Nc3ccc2cc1ccc(N)cc1nc2c3',1.67209785793572 +'CCC(=O)Nc1ccc(Cl)c(Cl)c1',1.30102999566398 +'Clc1cc(Cl)ccc1C2(Cn3ncnc3)OC(CCC)CO2',1.39794000867204 +'O=C(N)c(nccn1)c1',2.89707700320942 +'Oc1cc(O)c2C(=O)C(O)=C(c3cc(O)c(O)cc3)Oc2c1',3.30835094858673 +'CCC(O)(C)C#C',1.66275783168157 +'CC(C(NCC)=C1)=CC(C1=O2)=C(C(C2=C3)=CC(C)=C3NCC)C(=CC=C4)C(=C4)C(=O)OCC',1.07918124604762 +'O=C(NS(=O)(=O)c1cccc2)c12',3.55654370848351 +'c1cc(Cl)ccc1C2SC(=O)N(C(=O)NC3CCCCC3)C2C',2.20411998265593 +'n(c(nc(n1)NCC)NCC)c1Cl',0.698970004336019 +'HOS(=O)(=O)NC1CCCCC1',3.55654370848351 +'O=C(OCC(C1OCC(C1O)O)O)CCCCCCCCCCC',3.83777776955373 +'O(CC1O)C(C1O)C(O)COC(=O)CCCCCCCCCCCCCCCCC',3.85751341477669 +'O=S(=O)(Nc(nc(cc1C)C)n1)c(ccc(N)c2)c2',1.51851393987789 +'CCNc1nc(NC(C)(C)C)nc(SC)n1',1.17609125905568 +'Oc(c(cc(c1)C(C)(C)C)Cl)c1',2.33445375115093 +'C(C(Cl)Cl)(Cl)Cl',2.03342375548695 +'COP(=O)(OC)OC(=CCl)c1cc(Cl)c(Cl)cc1Cl',2 +'CCN(CC)C(=O)SCc1ccc(Cl)cc1',0.698970004336019 +'COC(=O)NC(=S)Nc1ccccc1NC(=S)NC(=O)OC',1.50514997831991 +'N(C(=S)SSC(N(C)C)=S)(C)C',1.17609125905568 +'c12OC(CCCC(C)CCCC(C)CCCC(C)C)(C)CCc1c(C)c(OC(=O)C)c(C)c2C',3.30102999566398 +'Cc1cc(N)ccc1NOS(O)(=O)=O',2.26481782300954 +'C(Br)(C(Br)(Br)Br)C1C(C)(C)C1C(=O)OC(C(#N))c2cccc(Oc3ccccc3)c2',0.477121254719662 +'O=C(O)COc(c(cc(c1Cl)Cl)Cl)c1',1 +'FC(F)(F)C(=CC(N(=O)=O)=C1N(C(C)C)C(C)C)C=C1N(=O)=O',1.60205999132796 +'Cc1cc(C)c(N)cc1C',1.79934054945358 +'CC(O)(C(O)C(O1)C)CC1(C)OC(C(C)O2)C(C(O)C2(C)OC(C(C)C(O)CC(=O)OC(CC)C3COC(C(OC)C4OC)OC(C)C4O)C(CC=O)CC(C)C(=O)C=CC(=C3)C)N(C)C',2.69897000433602 +'c1c(Cl)cc(Cl)cc1N2C(=O)C(C)(C=C)OC2(=O)',1.86272752831797 +'O=C(OC(CCCC(O)CCCCCc1cc(O)cc2O)C)c12',-0.698970004336019 +'COC(=O)C1(C2=CC=CC=C2C3=C1C=C(C=C3)Cl)O',2.17609125905568 +'CC(C(=O)O)OC1=CC(=CC=C1)Cl',2 +'P12P3P1P23',3.16790781000148 +'C(CO)O',2.60205999132796 +'CCCCOCC(C)OCC(C)O',2.10720996964787 +'C(CO)O',3.30102999566398 +'C(CO)O',2.96378782734556 +'[O-][As](=O)([O-])[O-]',0.795880017344075 +'[Si](CN1C=NC=N1)(C2=CC=C(C=C2)F)C3=CC=C(C=C3)F',0.361727836017593 +'N(C(=S)SSC(N(C)C)=S)(C)C',1.06069784035361 +'COP(=O)(N)SC',-0.0457574905606751 +'N(C(=S)SSC(N(C)C)=S)(C)C',0.737987326333431 +'COP(=O)(NC(=O)(C))SC',1.54406804435028 +'C1=CC=C(C=C1)NC(=O)NC2=CN=NS2',1.47712125471966 +'CCOP(=S)(NC(C)C)OC1=CC=CC=C1C(=O)OC(C)C',-0.301029995663981 +'CC(=NOC(=O)N(C)SN(C)C(=O)ON=C(C)SC)SC',1 +'CCOP(=S)(OCC)OC1=NC(=NC(=C1)C)C(C)C',0.176091259055681 +'NC(CCCC1)C1',1.76715586608218 +'CN1C=C(c2ccccc2)C(=O)C(c3cc(C(F)(F)F)ccc3)=C1',1.51188336097887 +'ClC1CC2C(C1Cl)C3(Cl)C(=C(Cl)C2(Cl)C3(Cl)Cl)Cl',-0.301029995663981 +'CCCCC(CC)COC(=O)C1=CC=CC=C1C(=O)OCC(CC)CCCC',2.30102999566398 +'OC(=O)CNCP(O)(O)=O',3 +'C1CNC(=S)N1',-0.638272163982407 +'O=C(N(OC)C)Nc(ccc(c1Cl)Cl)c1',0.795880017344075 +'C1=CC=C2C(=C1)NC(=S)S2',2.8750612633917 +'CCOP(=S)(OCC)OC1=NC(=C(C=C1Cl)Cl)Cl',1 +'c(c(c(c(c1Cl)Cl)Cl)Cl)(c1Cl)Cl',-0.537602002101044 +'COc1ccc(cc1)C(c2ccc(OC)cc2)C(Cl)(Cl)Cl',2.09691001300806 +'C1=CC(=CC=C1Cl)Cl',2.47712125471966 +'CC(C)OC(=O)NC1=CC(=CC=C1)Cl',2.69897000433602 +'COP(=O)(OC)OC=C(Cl)Cl',0.332438459915605 +'CCOP(=S)(OCC)Oc1ccc(cc1)N(=O)=O',-0.376750709602100 +'CNC(=O)N(C)c1nnc(s1)C(C)(C)C',1.60205999132796 +'CCCCOCCOCCOCC1=CC2=C(C=C1CCC)OCO2',2.39794000867204 +'CC(C(=O)O)OC1=C(C=C(C=C1)Cl)Cl',0.954242509439325 +'CC1(C(C1C(=O)OC(C#N)C2=CC(=C(C=C2)F)OC3=CC=CC=C3)C=C(Cl)Cl)C',1.09691001300806 +'C(#N)c(c(c(c(c1C(#N))Cl)Cl)Cl)c1Cl',0.602059991327962 +'O=C(OCC)C(O)(c(ccc(c1)Cl)c1)c(ccc(c2)Cl)c2',1.26481782300954 +'O=C(N(C)C)Nc(ccc(c1)Cl)c1',2.09691001300806 +'O=C(N(SC(Cl)(Cl)Cl)C(=O)C1CC=CC2)C12',2 +'CCc1cccc(C)c1N(C(C)COC)C(=O)CCl',2.17609125905568 +'C1=CC(=C(C=C1Cl)Cl)OCC(=O)O',0.698970004336019 +'CCNC1=NC(=NC(=N1)Cl)NC(C)(C)C#N',0.0969100130080564 +'C(C(C(C(C1Cl)Cl)Cl)Cl)(C1Cl)Cl',0.662757831681574 +'COP(=S)(OC)OC1=CC(=C(C=C1Cl)Cl)Cl',1.69897000433602 +'C1C2C=CC1C3C2C4(C(=C(C3(C4(Cl)Cl)Cl)Cl)Cl)Cl',-2 +'CC1(C(C1C(=O)OCC2=CC(=CC=C2)OC3=CC=CC=C3)C=C(Cl)Cl)C',1.39794000867204 +'CCN(CC)C(=O)C(C)OC1=CC=CC2=CC=CC=C21',2 +'ClC1C=CC2C1C3(Cl)C(=C(Cl)C2(Cl)C3(Cl)Cl)Cl',-0.602059991327962 +'CC(=CC(=O)NC)OP(=O)(OC)OC',-0.346787486224656 +'CC(C)C1(C)N=C(NC1(=O))c3nc2ccccc2cc3C(=O)(O)',1.30102999566398 +'CC(C)Nc1nc(Cl)nc(NC(C)C)n1',1.69897000433602 +'CC(C(=O)O)(Cl)Cl',1.69897000433602 +'CC1(C(C1C(=O)OC(C#N)C2=CC(=C(C=C2)F)OC3=CC=CC=C3)C=C(Cl)Cl)C',0.8750612633917 +'O=C(NC)CSP(OC)(OC)=S',0.698970004336019 +'C12C3(C4(C5(C3(C(C1(C5(C2(C4(Cl)Cl)Cl)Cl)Cl)(Cl)Cl)Cl)Cl)Cl)Cl',-2 +'COC(=O)C1=CC=CC=C1C(=O)OC',3.30102999566398 +'CCOP(=S)(OCC)SCSC(C)(C)C',-1.30102999566398 +'CCC(C)SP(=O)(OCC)SC(C)CC',-0.602059991327962 +'CCOP(=S)(OCC)SCSC(C)(C)C',0.301029995663981 +'C1C(C(C(=O)N1C2=CC=CC(=C2)C(F)(F)F)Cl)CCl',0.698970004336019 +'O=C(O)C(C(C(=O)O)C(O1)CC2)C12',2.06069784035361 +'O=C(Oc(c(OC(C1)(C)C)c1cc2)c2)NC',0.698970004336019 +'Oc(c(c(c(c1)Cl)Cl)Cc(c(c(cc2Cl)Cl)Cl)c2O)c1Cl',0.698970004336019 +'CC1(CON(C1=O)CC2=CC=CC=C2Cl)C',1.33243845991561 +'CCC(C)N1C(=O)C(=C(NC1=O)C)Br',1.79588001734408 +'CC1=CC(=CC(=C1N(C)C)C)OC(=O)NC',0.176091259055681 +'CNC(=O)OC1=CC=CC(=C1)N=CN(C)C',1.09691001300806 +'CC1=NN(C(=O)N1C(F)F)C2=CC(=C(C=C2Cl)Cl)NS(=O)(=O)C',1.82607480270083 +'CCOP(=S)(CC)SC1=CC=CC=C1',0.698970004336019 +'CCOP(=S)(OCC)SC(CCl)N1C(=O)C2=CC=CC=C2C1=O',0.397940008672038 +'N1CC(C)(C)CNC1=NN=C(C=Cc2ccc(C(F)(F)F)cc2)C=Cc3ccc(C(F)(F)F)cc3',0.698970004336019 +'CC1=C(C(=C(C(=C1F)F)COC(=O)C2C(C2(C)C)C=C(C(F)(F)F)Cl)F)F',0.662757831681574 +'CC1=CC(=C(C=C1)N=CN(C)C=NC2=C(C=C(C=C2)C)C)C',1.00860017176192 +'S=P(OC)(OC)SCN1C(=O)SC(OC)=N1',-0.0969100130080564 +'CC(C)N(C(C)C)C(=O)SCC(Cl)=C(Cl)Cl',1.09691001300806 +'S=P(OC)(OC)SCN1N=Nc2ccccc2C1(=O)',0.352182518111362 +'CC1=NC(=NC(=N1)OC)NC(=O)NS(=O)(=O)C2=CC=CC=C2CCC(F)(F)F',1.90254677931399 +'O=C(N(S(=O)(=O)Nc1cccc2)C(C)C)c12',1.60205999132796 +'CCN(CC)c1nc(C)cc(OP(=S)(OC)OC)n1',1.13987908640124 +'O=C(ON=CC(SC)(C)C)NC',-1 +'ClC(Cl)(Cl)CC1(OC1)c2cc(Cl)cc(Cl)c2',1.47712125471966 +'CCC1CCCC(C(C(=O)C2CC3C(C2CC(=O)O1)CCC4C3CC(C4)OC5CC(C(C(C5OC)OC)OC)C)C)OC6CCC(C(O6)C)N(C)C',1.38021124171161 +'CC(C)(C)C(=NOC(=O)NC)CSC',0.778151250383644 +'CON=C(CC1=CN=CC=C1)C2=C(C=C(C=C2)Cl)Cl',1.65321251377534 +'CC(=CC1C(C1(C)C)C(=O)OCN2C(=O)C3=C(C2=O)CCCC3)C',2.39794000867204 +'C1COC(O1)(CN2C=NC=N2)C3=C(C=C(C=C3)Cl)Cl',1 +'CCCOC(=O)C1=CN=C(C=C1)C(=O)OCCC',2.39794000867204 +'CC1=CC(=NC(=N1)NC(=O)NS(=O)(=O)C2=CC=CC=C2C(=O)OC3COC3)C',1.91907809237607 +'C1=C(C(=NC(=C1Cl)Cl)OCC(=O)O)Cl',1.55630250076729 +'CCOCN1C(=C(C(=C1C(F)(F)F)Br)C#N)C2=CC=C(C=C2)Cl',1.13353890837022 +'CC(C)CC1=C(C(=NC(=C1C(=O)SC)C(F)(F)F)C(F)F)C(=O)SC',0.559906625036112 +'CC12CC1(C(=O)N(C2=O)C3=CC(=CC(=C3)Cl)Cl)C',1.17609125905568 +'CC1=CC(=C(C=C1)C(=O)OC)C2=NC(C(=O)N2)(C)C(C)C',1.69897000433602 +'COP(=S)(OC)OC1=NC(=C(C=C1Cl)Cl)Cl',0.477121254719662 +'CC(C)CC1=C(C(=NC(=C1C(=O)OC)C(F)F)C(F)(F)F)C2=NCCS2',1.64542226934909 +'CCOC(=O)C(CC1=CC(=C(C=C1Cl)F)N2C(=O)N(C(=N2)C)C(F)F)Cl',1.07918124604762 +'CC(C)=CC3C(C(=O)OCc2coc(Cc1ccccc1)c2)C3(C)C',2.09691001300806 +'CCCSP(=S)(OCC)OC1=CC=C(C=C1)SC',1.06069784035361 +'CC1=CC(=C(C(=C1)OC(=O)NC)C)C',1.77232170672292 +'CC1=CC=CC=C1COC2CC3(CCC2(O3)C)C(C)C',2.17609125905568 +'CC1=C2C(=CC=C1)SC3=NN=CN23',1.49136169383427 +'CCC(=C1C(=O)CC(CC1=O)CC(C)SCC)NOCC=CCl',2 +'CCCN(CCC)C(=O)SCC',0.954242509439325 +'CC(C)OC(=O)C=C(C)C=CCC(C)CCCC(C)(C)OC',1.66275783168157 +'COP(=S)(OC)Oc1ccc(SC)c(C)c1',0.574031267727719 +'COC1=C(C=C(C=C1)C(=CC(=O)N2CCOCC2)C3=CC=C(C=C3)Cl)OC',1.66558099101795 +'CCSC(=O)N(CC(C)C)CC(C)C',2 +'CC(C)OP(=S)(OC(C)C)SCCNS(=O)(=O)C1=CC=CC=C1',1.17609125905568 +'CC(=CC1C(C1(C)C)C(=O)OCC2=CC(=CC=C2)OC3=CC=CC=C3)C',2.17609125905568 +'CC1=CC(=CC(=C1C)C)OC(=O)NC',1 +'CCOP(=S)(OCC)SCSC1=CC=C(C=C1)Cl',0 +'C1CN(CCN1C(C(Cl)(Cl)Cl)NC=O)C(C(Cl)(Cl)Cl)NC=O',2 +'C(=CC=C1)(C2=C1)NC(=N2)C(=CS3)N=C3',0.301029995663981 +'C1(=C(C(=C(C(=C1Cl)Cl)Cl)Cl)Cl)[N+](=O)[O-]',2.09691001300806 +'CCCC(=NOCC)C1C(=O)CC(CC1=O)CC(C)SCC',1.21906033244886 +'ClC2(Cl)C4(Cl)C1(Cl)C5(Cl)C(Cl)(Cl)C3(Cl)C1(Cl)C2(Cl)C3(Cl)C45Cl',-0.154901959985743 +'CCN(C1CCCCC1)C(=O)SCC',0.477121254719662 +'CC1=NC(=NC(=N1)OC)NC(=O)NS(=O)(=O)C2=CC=CC=C2OCCCl',2.34399906905716 +'C(C(=O)O)OC1=NC(=C(C(=C1Cl)N)Cl)F',2.69897000433602 +'CC1=C(C(=O)CC1OC(=O)C2C(C2(C)C)C=C(C)C)CC#C',1.97772360528885 +'C1C(COC1(CN2C=NC=N2)C3=C(C=C(C=C3)Cl)Cl)Br',0.811575005870593 +'C1=NNC(=N1)N',0.397940008672038 +'C1=CC(=C(C(=C1)F)C(=O)NC(=O)NC2=CC(=C(C(=C2F)Cl)F)Cl)F',1.41497334797082 +'C1=CC(=CC=C1OS(=O)(=O)C2=CC=C(C=C2)Cl)Cl',0.397940008672038 +'FC(F)(F)C(=CC(N(=O)=O)=C1N(C(C)C)C(C)C)C=C1N(=O)=O',3 +'CC1=C(C(=O)CC1OC(=O)C2C(C2(C)C)C=C(C)C)CC=C',1.8750612633917 +'C1=CC(=C(C(=C1)Cl)C#N)Cl',0.397940008672038 +'C1C(O1)COC2=CC=CC=C2C3=CC=CC=C3',2.69897000433602 +'CC1=CC=CC=C1OCC2=CC=CC=C2C(=NOC)C(=O)OC',2.57403126772772 +'O=N(=O)C(C(=C1N(=O)=O)N(C(C)C)C(C)C)=CC(=C1)S(=O)(=O)N',1.56655533088306 +'C1=CC(=C(C2=NC=C(C=C21)Cl)C(=O)O)Cl',2.87909587950007 +'CC(C)NC(=O)N1CC(=O)N(C1=O)C2=CC(=CC(=C2)Cl)Cl',1.66275783168157 +'CCCN(CCCl)C1=C(C=C(C=C1[N+](=O)[O-])C(F)(F)F)[N+](=O)[O-]',2.30621050816776 +'C1=CC=C(C=C1)C2=CC=CC=C2O',3 +'O=C(N(C)C)Nc(cccc1C(F)(F)F)c1',1.17609125905568 +'C1=CC(=NC(=C1)Cl)C(Cl)(Cl)Cl',0 +'Clc1cc(Cl)cc(Cl)c1OCCN(CCC)C(=O)n2cncc2',0.8750612633917 +'CC1=CC(=C(C=C1NC(=O)C)NS(=O)(=O)C(F)(F)F)C',1.44090908206522 +'C(=C(I)I)(I)I',1.69897000433602 +'C1=C(C=C(C(=C1Cl)N2C(=C(C(=N2)C#N)S(=O)C(F)(F)F)N)Cl)C(F)(F)F',-1.22184874961636 +'O=C(N(C)C)Nc(ccc(c1Cl)Cl)c1',0.795880017344075 +'CC1=C(C(=O)CC1OC(=O)C2C(C2(C)C)C=C(C)C)CC=C',1.38916608436453 +'CC1=CC2=C(C=C1)N=C3C(=N2)SC(=O)S3',0.8750612633917 +'CC(C)N(C(=O)CCl)c1ccccc1',1.36172783601759 +'CC(C)C1(C(=O)NC(=N1)C2=C(C=CC=N2)C(=O)O)C',2.69897000433602 +'CC1(C(C1(C)C)C(=O)OC(C#N)C2=CC(=CC=C2)OC3=CC=CC=C3)C',1.28891960566173 +'CN1CN(C(=S)SC1)C',1.47712125471966 +'ClC(Cl)=CC1C(C)(C)C1C(=O)OC(C(#N))c2cccc(Oc3ccccc3)c2',1.8750612633917 +'ClC2C1OC1C3C2C4(Cl)C(=C(Cl)C3(Cl)C4(Cl)Cl)Cl',-0.698970004336019 +'CCOC(=O)CN1C2=C(C=CC=C2Cl)SC1=O',1.09691001300806 +'CCCN(CCC)C1=C(C=C(C(=C1[N+](=O)[O-])N)C(F)(F)F)[N+](=O)[O-]',1.46834733041216 +'C1=CC=C(C=C1)C(CCC2=CC=C(C=C2)Cl)(CN3C=NC=N3)C#N',1.60205999132796 +'CC(C)(C)C(CCC1=CC=C(C=C1)Cl)(CN2C=NC=N2)O',1.20139712432045 +'CC1=C(C=CC=C1COC(=O)C2C(C2(C)C)C=C(C(F)(F)F)Cl)C3=CC=CC=C3',0.698970004336019 +'C(=CC=C1)(C2=C1)NC(=N2)C(=CS3)N=C3',1.60205999132796 +'C1=C(C=C(C(=C1Cl)N)Cl)[N+](=O)[O-]',2.17609125905568 +'CC1=C(C=C(C=C1C(=O)N)[N+](=O)[O-])[N+](=O)[O-]',0.795880017344075 +'CC(C)OC1=CC=CC(=C1)NC(=O)C2=CC=CC=C2C(F)(F)F',2.69897000433602 +'OC(c1ccc(Cl)cc1)(c2ccc(Cl)cc2)C(Cl)(Cl)Cl',0.397940008672038 +'O=P(O)(O)CCCl',2.64933485871214 +'CN(C(=O)NC1=CC=C(C=C1)Br)OC',1.09691001300806 +'CC1=CC(=CC=C1)NC(=O)OC2=CC=CC(=C2)NC(=O)OC',1.39794000867204 +'CC(C)(C)C1=NN=C(S1)N2C(CN(C2=O)C)O',1.69897000433602 +'S=P(OCC)(OCC)Oc1ccc2C(C)=C(Cl)C(=O)Oc2c1',0.230448921378274 +'COC(=O)c1ccccc1S(=O)(=O)NC(=O)N(C)c2nc(OC)nc(C)n2',1.09691001300806 +'C1=CC=C(C(=C1)NC2=NC(=NC(=N2)Cl)Cl)Cl',0.0606978403536116 +'CC1=C(C=CC(=C1)OP(=S)(OC)OC)[N+](=O)[O-]',-0.337242168318426 +'COc1c(Cl)ccc(Cl)c1C(=O)(O)',2.06069784035361 +'CC1(C(C1C(=O)OC(C#N)C2=CC(=CC=C2)OC3=CC=CC=C3)C=C(Br)Br)C',0.397940008672038 +'C1=CC=C(C(=C1)C(C2=CC=C(C=C2)F)(C3=CN=CN=C3)O)Cl',0.397940008672038 +'c1ccc2nc(NC(=O)OC)n(C(=O)NCCCC)c2c1',2.06069784035361 +'CCOC(=O)COC(=O)C1=C(C=CC(=C1)OC2=C(C=C(C=C2)C(F)(F)F)Cl)[N+](=O)[O-]',1.39794000867204 +'CC(C)(C)C(C(N1C=NC=N1)OC2=CC=C(C=C2)C3=CC=CC=C3)O',1.39794000867204 +'CCNC(=O)NC(=O)C(=NOC)C#N',1.48144262850231 +'CCOC1=C(C=CC(=C1)OC2=C(C=C(C=C2)C(F)(F)F)Cl)[N+](=O)[O-]',1.60205999132796 +'CC1=NC=C(N1CCO)[N+](=O)[O-]',2.17609125905568 +'O=C(N(SC(Cl)(Cl)Cl)C(=O)c1cccc2)c12',2.69897000433602 +'CC(C)(C)c2ccc(OC1CCCCC1OS(=O)OCC#C)cc2',2 +'CCCCC(CN1C=NC=N1)(C2=C(C=C(C=C2)Cl)Cl)O',0.672097857935718 +'CC(C)(C)C(C(=CC1=C(C=C(C=C1)Cl)Cl)N2C=NC=N2)O',1.69897000433602 +'C1=CC(C2C1C3(C(=C(C2(C3(Cl)Cl)Cl)Cl)Cl)Cl)Cl',-0.42021640338319 +'C1=CC=C2C(=C1)C(=O)C3=C(C2=O)SC(=C(S3)C#N)C#N',1 +'CC1=NN(C(=C1C=NOCC2=CC=C(C=C2)C(=O)OC(C)(C)C)OC3=CC=CC=C3)C',0.488550716500444 +'CS(=O)(=O)C1=C(C=CC(=C1)C(F)(F)F)C(=O)C2=C(ON=C2)C3CC3',1.30102999566398 +'CC1=C(N=C(N=C1OC(=O)N(C)C)N(C)C)C',1.09691001300806 +'CCN(CC)C(=O)C(Cl)=C(C)OP(=O)(OC)OC',0.176091259055681 +'C1=CC(=CC=C1C(CN)O)O',2.39794000867204 +'CC1=C(C(=CC=C1)C)N(C(=O)COC)N2CCOC2=O',1.69897000433602 +'c1c(C(F)(F)F)cccc1N2C(=O)C(Cl)=C(NC)C=N2',1.27300127206374 +'CCC(C)NC1=C(C=C(C=C1[N+](=O)[O-])C(C)(C)C)[N+](=O)[O-]',1.69897000433602 +'C1=CC(=CC=C1S(=O)(=O)C2=CC(=C(C=C2Cl)Cl)Cl)Cl',2.36172783601759 +'CCCCC1=C(NC(=NC1=O)NCC)C',1.39794000867204 +'n(c(nc(n1)NCC)NCC)c1Cl',0.724275869600789 +'FC(F)(F)C(C=C1N(=O)=O)=CC(N(=O)=O)=C1N(CC)CC(C)=C',1.09691001300806 +'C1CCC(C1)N(CC2=CC=C(C=C2)Cl)C(=O)NC3=CC=CC=C3',1.39794000867204 +'CS(=O)(=O)NC(=O)C1=C(C=CC(=C1)OC2=C(C=C(C=C2)C(F)(F)F)Cl)[N+](=O)[O-]',1.69897000433602 +'CCOC(=O)C(C)OC1=CC=C(C=C1)OC2=NC3=C(O2)C=C(C=C3)Cl',0.954242509439325 +'CCC1=C(C(=CC=C1)CC)N(CNC(=O)C)C(=O)CCl',1.79588001734408 +'NC(=N)NCCCCCCCCCCCC(OC(=O)C)',1.46239799789896 +'C1=CC(=CC(=C1)Cl)NC(=O)OCC#CCCl',2.65321251377534 +'CC(C)C(C(=O)OC(C(#N))c2cccc(Oc1ccccc1)c2)c3ccc(Cl)cc3',1.39794000867204 +'CC(C)C1=C(C=CC(=C1)C(C)(C)C2=CC(=C(C=C2)O)C(C)C)O',1.39794000867204 +'CCN(CC1=C(C=CC=C1Cl)F)C2=C(C=C(C=C2[N+](=O)[O-])C(F)(F)F)[N+](=O)[O-]',1.69897000433602 +'CCCCCCCCSC(=O)OC1=CC(=NN=C1C2=CC=CC=C2)Cl',1.82930377283102 +'CC1=C(C(=O)CC1OC(=O)C2C(C2(C)C)C=C(C)C)CC=C',1.13987908640124 +'CCCCNC(=O)N1C2=CC=CC=C2N=C1NC(=O)OC',2.39794000867204 +'CC1=C(C(=CC=C1)C)N(C(C)C(=O)OC)C(=O)CC2=CC=CC=C2',1.66275783168157 +'CC(C)C(C1=CC=C(C=C1)OC(F)F)C(=O)OC(C#N)C2=CC(=CC=C2)OC3=CC=CC=C3',0.778151250383644 +'Clc1ccccc1c2nnc(c3ccccc3Cl)nn2',1.30102999566398 +'CCOC(=O)NCCOC1=CC=C(C=C1)OC2=CC=CC=C2',1 +'CCC1=C(C(=CC=C1)CC)N(CC(=O)OCC)C(=O)CCl',1.69897000433602 +'c1(O2)c(CC2(C)C)cccc1OC(=O)N(C)SN(CCCC)CCCC',1.39794000867204 +'CCCCOC(=O)C(C)OC1=CC=C(C=C1)OC2=NC=C(C=C2)C(F)(F)F',0.477121254719662 +'COC1=CC(=C(C=C1Cl)OC)Cl',2.09691001300806 +'CCOP(=S)(OCC)OC1=NN(C(=N1)Cl)C(C)C',1.09691001300806 +'n(c(nc(n1)NC(C)C)NCC)c1Cl',1.39794000867204 +'CC(C)(C)C(C(=CC1=CC=C(C=C1)Cl)N2C=NC=N2)O',1.59560643486560 +'CCCCCCCCc1cc(N(=O)(=O))c(OC(=O)C=CC)c(c1)N(=O)(=O)',1.69897000433602 +'c1cc(OC(F)(F)F)ccc1C(O)(C(C)C)c2cncnc2',1.08278537031645 +'COP(=O)(C(C(Cl)(Cl)Cl)O)OC',1.30102999566398 +'C1=CC(=C(C=C1C(F)(F)F)Cl)OC2=CC(=C(C=C2)[N+](=O)[O-])C(=O)O',2.09691001300806 +'CCCN(CC1CC1)C2=C(C=C(C=C2[N+](=O)[O-])C(F)(F)F)[N+](=O)[O-]',0.698970004336019 +'CCOC(=O)C(C)OC(=O)C1=C(C=CC(=C1)OC2=C(C=C(C=C2)C(F)(F)F)Cl)[N+](=O)[O-]',1.69897000433602 +'CCSC(=O)N1CCCCCC1',1.17055505852121 +'CCC1=CC=C(C=C1)C(=O)NN(C(=O)C2=CC(=CC(=C2)C)C)C(C)(C)C',1.68124123737559 +'ClC(Cl)C(Cl)(Cl)SN2C(=O)C1CC=CCC1C2(=O)',1.17609125905568 +'COC(=O)C1=CC=CC=C1S(=O)(=O)NC(=O)NC2=NC(=CC(=N2)OC(F)F)OC(F)F',2.14612803567824 +'CC(C)(C)C(C(N1C=NC=N1)OC2=CC=C(C=C2)Cl)O',1.39794000867204 +'CC1=C(C=CC(=C1)Cl)OCC(=O)O',0.602059991327962 +'COC=C(C1=CC=CC=C1OC2=NC=NC(=C2)OC3=CC=CC=C3C#N)C(=O)OC',1.79413935576777 +'C1=CC=C(C(=C1)C(C2=CC=C(C=C2)Cl)(C3=CN=CN=C3)O)Cl',0.361727836017593 +'[O-]Br(=O)=O',0.785329835010767 +'OP(=O)OCC',2.60205999132796 +'COP(N)(=O)SC',-1 +'CCOP(=O)(NC(C)C)Oc1ccc(SC)c(C)c1',0.176091259055681 +'CCOP(=S)(OCC)SCCSCC',-1.39794000867204 +'CCOP(=S)(OCC)SCSP(=S)(OCC)OCC',0.301029995663981 +'O=C(OCC(CCCC)CC)CCCCC(=O)OCC(CCCC)CC',3.17609125905568 +'CN(C=Nc1ccc(C)cc1C)C=Nc2ccc(C)cc2C',1 +'O=C(N(S(=O)(=O)Nc1cccc2)C(C)C)c12',1.54406804435028 +'S=P(OC)(OC)SCN1C(=O)SC(OC)=N1',0.0969100130080564 +'C(#N)Cl',1.84509804001426 +'C(#N)Br',2.08635983067475 +'C1=CC(=CC=C1C(C2=CC=C(C=C2)Cl)C(Cl)(Cl)Cl)Cl',-0.602059991327962 +'c(cccc1)(c1)C(C)C',2.51982799377572 +'CCCN(CCC)C(=O)SCC',1.39794000867204 +'NC(CCCC1)C1',1.77815125038364 +'ClC1CC2C(C1Cl)C3(Cl)C(=C(Cl)C2(Cl)C3(Cl)Cl)Cl',0.778151250383644 +'CC(C)OC(=O)NC1=CC(=CC=C1)Cl',3 +'COC(=O)c1c(Cl)c(Cl)c(C(=O)OC)c(Cl)c1Cl',1 +'COC(=O)C1=CC=C(C=C1)C(=O)OC',2.09691001300806 +'N(C(=S)NC1)C1',-0.602059991327962 +'O=C(N(OC)C)Nc(ccc(c1Cl)Cl)c1',0.397940008672038 +'c(cccc1)(c1)C=C',2.45484486000851 +'COC(=O)c1ccccc1S(=O)(=O)NC(=O)Nc2nc(OC)nc(C)n2',2.39794000867204 +'C1=CC(=CC=C1N)Cl',1.09691001300806 +'FC(F)(F)C(Cl)=CC1C(C)(C)C1C(=O)OC(C(#N))c2cc(Oc3ccccc3)ccc2',1.09691001300806 +'C(Cl)(Br)Br',1.45484486000851 +'C=C(Cl)Cl',1.14612803567824 +'C(C=CCl)Cl',0.707570176097936 +'COP(=O)(OC)OC(=CCl)c1cc(Cl)c(Cl)cc1Cl',1.69897000433602 +'Oc(ccc(c1)C(c(ccc(O)c2)c2)(C)C)c1',1.69897000433602 +'O=C(OCc(cccc1)c1)c(c(ccc2)C(=O)OCCCC)c2',2.67209785793572 +'O=C(NCCCC1)C1',2.09691001300806 +'c(cccc1)(c1)Cl',2.07918124604762 +'C(Cl)(Cl)Cl',1.77815125038364 +'ClCCl',1.72082058177034 +'C1C2C3C(C1C4C2O4)C5(C(=C(C3(C5(Cl)Cl)Cl)Cl)Cl)Cl',-0.903089986991944 +'OCCO',3 +'O=C(C=C(CC1(C)C)C)C1',2.25285303097989 +'C(F)(Cl)(Cl)Cl',2.54282542695918 +'CCc1cccc(CC)c1N(COC)C(=O)CCl',1.14612803567824 +'c1ccccc1c2c(C)c(COC(=O)C3C(C)(C)C3C=C(Cl)C(F)(F)F)ccc2',0.698970004336019 +'n1c(Cl)cc(OC)nc1NC(=O)NS(=O)(=O)c2ccccc2C(=O)OCC',2.09691001300806 +'O=C(NC(=O)c(c(F)ccc1)c1F)Nc(ccc(c2)Cl)c2',0.89209460269048 +'c(cccc1)(c1)CC',2.46389298898591 +'O=C(N(SC(Cl)(Cl)Cl)C(=O)c1cccc2)c12',1.60205999132796 +'Clc1cc(C(F)(F)F)cnc1Oc2ccc(OC(C)C(=O)OC)cc2',0 +'C#N',1.49136169383427 +'ClC(C(OC(C=C2C(=O)OC(C)C(=O)OCC)=CC=C2N(=O)=O)=C1)=CC=C1C(F)(F)F',1.69897000433602 +'c1c(C(F)(F)F)cccc1N2C(=O)C(Cl)=C(NC)C=N2',1.70969386972779 +'O=N(=O)C(C(=C1N(=O)=O)N(C(C)C)C(C)C)=CC(=C1)S(=O)(=O)N',1.65321251377534 +'CN(=CC=C1C(C=C2)=CC=N2C)C=C1',0.574031267727719 +'C1=C(C=C(C=C1[N+](=O)[O-])[N+](=O)[O-])[N+](=O)[O-]',1.12417805547468 +'C(=C)Cl',0.113943352306837 +'C1CCC(=O)CC1',2.95904139232109 +'CC1(C(C1(C)C)C(=O)OC(C#N)C2=CC(=CC=C2)OC3=CC=CC=C3)C',1.39794000867204 +'C1=CC(=O)NNC1(=O)',2.69897000433602 +'CCSC(=O)N1CCCCCC1',0.301029995663981 +'C(C(Cl)(Cl)Cl)(O)O',2.13033376849501 +'ClC2C1OC1C3C2C4(Cl)C(=C(Cl)C3(Cl)C4(Cl)Cl)Cl',-1.60205999132796 +'Clc1cc(C(F)(F)F)ccc1Oc2cc(OCC)c(N(=O)(=O))cc2',1 +'c1cc(Cl)ccc1C(C(#N))(CCCC)Cn2ncnc2',0.992995098431341 +'CC1=C(C=C(C=C1[N+](=O)[O-])[N+](=O)[O-])[N+](=O)[O-]',0.301029995663981 +'CC(C)OC(=O)C(C1=CC=C(C=C1)Br)(C2=CC=C(C=C2)Br)O',1.41497334797082 +'C[N+](C)(C)CCCl',2.11394335230684 +'CCC(=C1C(=O)CC(CC1=O)CC(C)SCC)NOCC=CCl',1.93449845124357 +'CC1=NC(=NC(=C1)C2CC2)NC3=CC=CC=C3',1.55144999797288 +'N(c(cccc1)c1)c(cccc2)c2',1.39794000867204 +'CC1(C(=O)N(C(=O)O1)NC2=CC=CC=C2)C3=CC=C(C=C3)OC4=CC=CC=C4',1.22530928172586 +'CC1(CCCCC1)C(=O)NC2=C(C(=C(C=C2)O)Cl)Cl',2.46538285144842 +'C1=CC(=C2C(=C1)OC(O2)(F)F)C3=CNC=C3C#N',2.04139268515822 +'C(F)(F)(F)c1ccccc1C(=O)Nc2cccc(OC(C)C)c2',1.93951925261862 +'C(CCCCN=C(N)N)CCCNCCCCCCCCN=C(N)N',1.27875360095283 +'C1CN(C(=N1)N[N+](=O)[O-])CC2=CN=C(C=C2)Cl',1.23044892137827 +'COC(=O)C12CC3=C(C1=NN(CO2)C(=O)N(C4=CC=C(C=C4)OC(F)(F)F)C(=O)OC)C=CC(=C3)Cl',0.556302500767287 +'CC1=CC=CC=C1OCC2=CC=CC=C2C(=NOC)C(=O)OC',2.56820172406699 +'CC1=CC(=CC(=C1)C(=O)N(C(C)(C)C)NC(=O)C2=C(C(=CC=C2)OC)C)C',2.61384182187607 +'C1=CC(=C(C(=C1)F)C(=O)NC(=O)NC2=CC(=C(C=C2)OC(C(OC(F)(F)F)F)(F)F)Cl)F',1.55630250076729 +'CC1=CC=C(C=C1)N(SC(F)(Cl)Cl)S(=O)(=O)N(C)C',1.25527250510331 +'CC(C)(C)C1=C(C=CC(=C1)O)O',2.35218251811136 +'CC(=NOCC1=CC=CC=C1C(=NOC)C(=O)OC)C2=CC(=CC=C2)C(F)(F)F',1.77815125038364 +'COC(=O)N(C1=CC=CC=C1COC2=NN(C=C2)C3=CC=C(C=C3)Cl)OC',0.954242509439325 +'CC(C)N1C(=NC(C)(C)C)SCN(C1=O)C2=CC=CC=C2',0.939519252618618 +'C1=CC=C(C(=C1)C2=NN=C(N=N2)C3=CC=CC=C3Cl)Cl',1.23804610312880 +'CCCC(=C1C(=O)CC(CC1=O)C2CCCSC2)NOCC',1.44715803134222 +'C1CC1NC2=NC(=C(C(=N2)N)C#N)N',1.34242268082221 +'C(C=C1)(=N(C=C1)CC2)C(N2=C3)=CC=C3',-0.244125144327509 +'C1=CC=C2C(=C1)C(=O)C3=C(C2=O)SC(=C(S3)C#N)C#N',0.778151250383644 +'CCOC1=CC2=C(C=C1)NC(C=C2C)(C)C',1.07918124604762 +'C1=CC=C(C=C1)C(CCC2=CC=C(C=C2)Cl)(CN3C=NC=N3)C#N',1.47712125471966 +'CC1CN(CC(O1)C)CC(C)CC2=CC=C(C=C2)C(C)(C)C',0.230448921378274 +'C[Si](CN1C=NC=N1)(C2=CC=C(C=C2)F)C3=CC=C(C=C3)F',0.301029995663981 +'c1cc(Cl)cc(Cl)c1C(OCC=C)Cn2cncc2',1.17609125905568 +'CN(=CC=C1C(C=C2)=CC=N2C)C=C1',0.406540180433955 +'CCCCOCCOCCOCC1=CC2=C(C=C1CCC)OCO2',2 +'Clc1cc(Cl)ccc1C2(Cn3ncnc3)OC(CCC)CO2',1.98227123303957 +'C(=CC=C1)(C2=C1)NC(=N2)C(=CS3)N=C3',1.47712125471966 +'CCOC1=CC=C(C=C1)C(C)(C)COCC2=CC(=CC=C2)OC3=CC=CC=C3',1.41497334797082 +'CC(C)(C)c2ccc(OC1CCCCC1OS(=O)OCC#C)cc2',1.27875360095283 +'CC(COC1=CC=C(C=C1)OC2=CC=CC=C2)OC3=CC=CC=N3',2.14612803567824 +'CC(C)(C)C(=O)C(N1C=NC=N1)OC2=CC=C(C=C2)Cl',2.05690485133647 +'CC(C)(C)C(C(N1C=NC=N1)OC2=CC=C(C=C2)Cl)O',2.02118929906994 +'c1ccccc1c2c(C)c(COC(=O)C3C(C)(C)C3C=C(Cl)C(F)(F)F)ccc2',0.903089986991944 +'CC1(C(C1C(=O)OC(C#N)C2=CC(=C(C=C2)F)OC3=CC=CC=C3)C=C(Cl)Cl)C',0.778151250383644 +'CC1(C(C1C(=O)OC(C#N)C2=CC(=C(C=C2)F)OC3=CC=CC=C3)C=C(Cl)Cl)C',1.07918124604762 +'ClC(Cl)=CC1C(C)(C)C1C(=O)OC(C(#N))c2cccc(Oc3ccccc3)c2',1.69897000433602 +'ClC1CC2C(C1Cl)C3(Cl)C(=C(Cl)C2(Cl)C3(Cl)Cl)Cl',-0.602059991327962 +'ClC4=C(Cl)C5(Cl)C3C1CC(C2OC12)C3C4(Cl)C5(Cl)Cl',-1 +'C1C2C3C(C1C4C2O4)C5(C(=C(C3(C5(Cl)Cl)Cl)Cl)Cl)Cl',-0.602059991327962 +'C1(C(C(C(C(C1Cl)Cl)Cl)Cl)Cl)Cl',0.672097857935718 +'CCC(=O)Nc1ccc(Cl)c(Cl)c1',1.88081359228079 +'C1(=C(C(=C(C(=C1Cl)Cl)Cl)Cl)Cl)[N+](=O)[O-]',2.14612803567824 +'C1C2C(COS(=O)O1)C3(C(=C(C2(C3(Cl)Cl)Cl)Cl)Cl)Cl',0.462397997898956 +'O=C(N(SC(Cl)(Cl)Cl)C(=O)c1cccc2)c12',1.69897000433602 +'CC(C(=O)O)OC1=CC=C(C=C1)OC2=C(C=C(C=N2)C(F)(F)F)Cl',-1 +'CCCCC(CN1C=NC=N1)(C#N)C2=CC=C(C=C2)Cl',0.991226075692495 +'Clc1cc(Cl)cc(Cl)c1OCCN(CCC)C(=O)n2cncc2',0.707570176097936 +'COP(=O)(NC(=O)(C))SC',0.397940008672038 +'CCOP(=O)(OCC)OC(=CCl)C1=C(C=C(C=C1)Cl)Cl',0.176091259055681 +'CCOP(=S)(OCC)SCCSCC',-0.657577319177794 +'O=P(O)(O)CCCl',1.07918124604762 +'CCCSP(=O)(OCC)SCCC',0.431363764158987 +'CCOP(=O)(NC(C)C)Oc1ccc(SC)c(C)c1',0.230448921378274 +'COP(=S)(OC)Oc1ccc(SC)c(C)c1',-0.142667503568732 +'OC(=O)C(N)CCP(C)(=O)O',0.544068044350276 +'OC(=O)CNCP(O)(O)=O',2.47712125471966 +'CCOC(=O)CC(SP(=S)(OC)OC)C(=O)OCC',2.55630250076729 +'COP(N)(=O)SC',-0.537602002101044 +'CC(=CC(=O)OC)OP(=O)(OC)OC',-0.455931955649724 +'CCOP(=S)(OCC)SCSCC',-0.795880017344075 +'CCOP(=S)(OCC)SCSC(C)(C)C',-1.22184874961636 +'S=P(OC)(OC)SCN1N=Nc2ccccc2C1(=O)',0.41161970596323 +'CCOP(=S)(OCC)OC1=NC(=C(C=C1Cl)Cl)Cl',0 +'CCOP(=S)(OCC)OC1=NC(=NC(=C1)C)C(C)C',0.763427993562937 +'CCC1=NC(=CC(=N1)OP(=S)(OC)OC)OCC',-0.346787486224656 +'S=P(OC)(OC)SCN1C(=O)SC(OC)=N1',0.204119982655925 +'CCOP(=S)(OCC)SCN1C2=C(C=C(C=C2)Cl)OC1=O',0.301029995663981 +'COP(=S)(OC)SCN2C(=O)c1ccccc1C2(=O)',0.954242509439325 +'CCOC(=O)C1=CN2C(=CC(=N2)OP(=S)(OCC)OCC)N=C1C',0.602059991327962 +'CCOP(=S)(OCC)OC1=NN(C=N1)C2=CC=CC=C2',0.113943352306837 +'O=C(Oc(c(c(ccc1)cc2)c1)c2)NC',1.77815125038364 +'CC1=CC(=CC(=C1SC)C)OC(=O)NC',0.968482948553935 +'CNC(=O)ON=C(C)SC',1.30102999566398 +'CCCOC(=O)NCCCN(C)C',2.83250891270624 +'COC(=O)NC1=NC2=CC=CC=C2N1',1.8750612633917 +'CC1=C(N=C(N=C1OC(=O)N(C)C)N(C)C)C',1.08990511143940 +'CNC(=O)CCSCCSP(=O)(OC)OC',-0.267606240177031 +'N(C(=S)SSC(N(C)C)=S)(C)C',1.07918124604762 +'C1=NNC(=N1)N',0.698970004336019 +'CCCCCCCCc1cc(N(=O)(=O))c(OC(=O)C=CC)c(c1)N(=O)(=O)',1.80617997398389 +'C1=CC=C(C=C1)[Sn](C2=CC=CC=C2)C3=CC=CC=C3',-0.522878745280338 +'O=C(NC(=O)c(c(F)ccc1)c1F)Nc(ccc(c2)Cl)c2',0.845098040014257 +'N(C(=S)NC1)C1',0.0969100130080564 +'C1=CC(=C(C(=C1)F)C(=O)NC(=O)NC2=CC(=C(C(=C2F)Cl)F)Cl)F',1.39794000867204 +'CCCSC1=CC2=C(C=C1)N=C(N2)NC(=O)OC',1.30102999566398 +'C1CN(CCN1CCCC(=O)C2=CC=C(C=C2)F)C3=CC=CC=N3',2.06069784035361 +'CC1(C2C(C3C(C(=O)C(=C(N)O)C(=O)C3(C(=O)C2=C(C4=C(C=CC(=C41)Cl)O)O)O)N(C)C)O)O',3.7160033436348 +'CC1=CC(=C(C=C1NC(=O)C2=CC(=CC(=C2O)I)I)Cl)C(C#N)C3=CC=C(C=C3)Cl',1 +'CN1CC2CC1CN2C3=C(C=C4C(=C3)N(C=C(C4=O)C(=O)O)C5CC5)F',1.69897000433602 +'C1=CC(=CC=C1C(C#N)C2=C(C=CC(=C2Cl)N3C(=O)NC(=O)C=N3)Cl)Cl',1.17609125905568 +'CC1=NC=C(N1C)[N+](=O)[O-]',1.17609125905568 +'CCN1CCN(CC1)C2=C(C=C3C(=C2)N(C=C(C3=O)C(=O)O)C4CC4)F',1.41497334797082 +'CC1C=CC=C2COC3C2(C(C=C(C3O)C)C(=O)OC4CC(CC=C(C1OC5CC(C(C(O5)C)OC6CC(C(C(O6)C)NC(=O)C)OC)OC)C)OC7(C4)C=CC(C(O7)C(C)C)C)O',0 +'COCC(=O)NC1=C(C=CC(=C1)SC2=CC=CC=C2)NC(=NC(=O)OC)NC(=O)OC',1.60205999132796 +'CC1CCC2=C3N1C=C(C(=O)C3=CC(=C2)F)C(=O)O',2.60205999132796 +'COC(=O)NC1=NC2=C(N1)C=C(C=C2)S(=O)C3=CC=CC=C3',0.301029995663981 +'CC1(C2CC3C(C(=O)C(=C(N)O)C(=O)C3(C(=O)C2=C(C4=C1C=CC=C4O)O)O)N(C)C)O',2.17609125905568 +'C1CN(CCN1CCCC(=O)C2=CC=C(C=C2)F)C3=CC=CC=N3',1.47712125471966 +'CC(C)NCC(COC1=CC=CC2=C1C3=CC=CC=C3N2)O',0.845098040014257 +'C1=CC(=CC=C1C(C#N)C2=C(C=CC(=C2Cl)N3C(=O)NC(=O)C=N3)Cl)Cl',1.36172783601759 +'CC1C=CC=C2COC3C2(C(C=C(C3O)C)C(=O)OC4CC(CC=C(C1OC5CC(C(C(O5)C)OC6CC(C(C(O6)C)NC(=O)C)OC)OC)C)OC7(C4)C=CC(C(O7)C(C)C)C)O',0.397940008672038 +'COP(=S)(OC)Oc1ccc(SC)c(C)c1',-0.346787486224656 +'C(C(C(C(C1Cl)Cl)Cl)Cl)(C1Cl)Cl',0.903089986991944 +'C(C(C(C(C1Cl)Cl)Cl)Cl)(C1Cl)Cl',0.602059991327962 +'CC(N(C)C)CN(C(=CC=C3)C1=C3)C(=CC=C2)C(=C2)S1',1.22010808804006 +'C1=C(C=C(C(=C1Cl)N)Cl)[N+](=O)[O-]',2.38021124171161 +'c(cccc1)(c1)C=C',2.60205999132796 diff --git a/original/LOAEL_log_mg_corrected_smiles.csv b/original/LOAEL_log_mg_corrected_smiles.csv new file mode 100755 index 0000000..e7dde1f --- /dev/null +++ b/original/LOAEL_log_mg_corrected_smiles.csv @@ -0,0 +1,568 @@ +SMILES,LOAEL_log_mg_kg_bw_day +'C1=C(C(=CC(=C1NN=C3C2=C(C=C([S]([O-])(=O)=O)C=C2)C=CC3=O)OC)[S]([O-])(=O)=O)C.[Na+].[Na+]',3.57275546515422 +'O1C(=O)C(O)=C(O)C1C(O)CO',3.48444220764241 +'C1(C)=C(C=CC(C)=CC=CC(C)=CC=CC=C(C)C=CC=C(C)C(=O)OC)C(C)(C)CCC1',2.69897000433602 +'c(cccc1)(c1)C(C)C',2.66464197555613 +'O=C(OCCCC)c(c(ccc1)C(=O)OCCCC)c1',2.77815125038364 +'O=C(OCC)c(c(ccc1)C(=O)OCC)c1',3.64689362416774 +'O=C(OC(OC(OC1C)C)C1)C',2.09691001300806 +'Oc(c(ccc1)C)c1C',0.778151250383644 +'Oc(ccc(c1C)C)c1',1.14612803567824 +'O=C(OCC)C=C',2.39445168082622 +'c(cccc1)(c1)CC',2.61066016308988 +'OCCO',2.39794000867204 +'c(ccc1C(=O)OCC(=O)OCC)cc1C(=O)OCC',3.39794000867204 +'O=C',1.91381385238372 +'O=C(O)C=CC(=O)O',3.03382569395331 +'OCC(O)CO',3.83777776955373 +'O=C(OC)c(ccc(O)c1)c1',3.17609125905568 +'O=C(OCCC)c(ccc(O)c1)c1',3.17609125905568 +'CC(CCC(=O)(O))C3CCC4C2CCC1CC(O)CCC1(C)C2CCC34C',2.69897000433602 +'OC(C(CCC1C)C(C)C)C1',2.77305469336426 +'O=C(O)C(=C)C',2.39445168082622 +'O=C(OC)c(c(O)ccc1)c1',2.55630250076729 +'Oc(cccc1)c1',2.53655844257153 +'O=C(OCCC)c(cc(O)c(O)c1O)c1',2.93651374247889 +'OCC(O)C1C(O)=C(O)C(=O)O1',3.19145101446490 +'c(cccc1)(c1)C=C',1.32221929473392 +'O=Cc(occ1)c1',1.77815125038364 +'NCCNc1cccc2ccccc12',1.89762709129044 +'CN(C)(C)CCCl',2.43933269383026 +'O=C(Nc(ccc(c1)C(=O)CCl)c1)C',3.19865708695442 +'c(ccc(c1)Cl)(c1)C(c(ccc(c2)Cl)c2)C(Cl)(Cl)Cl',1.50514997831991 +'CC(Oc1cc(Cl)c(Cl)cc1Cl)C(=O)(O)',0.939519252618618 +'O=N(=O)C(=CC=C1OC)C=C1N=NC(C(O)=C2C(=O)NC(=CC=C4)C=C4N(=O)=O)=C(C=C3)C(=C2)C=C3',3.32221929473392 +'O=N(=O)C(C=C1)=CC(OCCO)=C1NCCO',2.35983548233989 +'Cc1cccc(CC)c1N(C(=O)CCl)COCC',1.69897000433602 +'C1=C(C(=CC=C1OC2=CC=C(C=C2Cl)C(F)(F)F)[N+](=O)[O-])C(=O)[O-].[Na+]',2.25527250510331 +'CCc1cccc(CC)c1N(COC)C(=O)CCl',1.17609125905568 +'O=C(Nc(ccc(OCC)c1N)c1)C',3.07371835034612 +'Oc(ccc(N)c1)c1',2.83632411570675 +'CC(N)CC(=CC=C1)C=C1',0.698970004336019 +'O(c(ccc(c1)C=CC)c1)C',2.53655844257153 +'COc1ccc(N)cc1',2.67577834167409 +'O=C(O)c(c(N)ccc1)c1',3.43949059038968 +'Clc2cccc(c2)c1ccccc1',0.602059991327962 +'O=C(NC(C(=O)OC)Cc(cccc1)c1)C(N)CC(=O)O',2.16731733474818 +'n1c2ccc(Cl)cc2ncc1Oc3ccc(OC(C)C(=O)OCC)cc3',0.568201724066995 +'COC(=O)NS(=O)(=O)c1ccc(N)cc1',2.25527250510331 +'S=P(OC)(OC)SCN1N=Nc2ccccc2C1(=O)',-0.443697499232713 +'CNC(=O)Oc1ccccc1OC(C)C',1.69897000433602 +'CC(C)(C)C(=O)C(Oc1ccc(Cl)cc1)n2cncn2',1.39794000867204 +'O=S(O)(=O)C(=CC=C1)C=C1CN(CC)=C(C=C2)C=CC2=C(C(C=C3)=CC=C3N(C)C)C(C=C4)=CC=C4N(CC)CC(C=C5)=CC(=C5)S(=O)(=O)O',2.85733249643127 +'c(c(cccc1)c1)(cccc2)c2',2.39794000867204 +'BrC(Cl)Cl',2.11394335230684 +'ClC(Cl)C(Cl)(Cl)SN2C(=O)C1CC=CCC1C2(=O)',1.07918124604762 +'O=C(Oc(c(c(ccc1)cc2)c1)c2)NC',1.19312459835446 +'CC1=C(SCCO1)C(=O)Nc2ccccc2',1.47712125471966 +'ClC1CC2C(C1Cl)C3(Cl)C(=C(Cl)C2(Cl)C3(Cl)Cl)Cl',-0.568636235841013 +'O=C(O)CCl',1.47712125471966 +'ClC(=CC=C1N)C=C1',0.778151250383644 +'CC(C)OC(=O)C(O)(c1ccc(Cl)cc1)c2ccc(Cl)cc2',0.954242509439325 +'n1c(OC)nc(C)nc1NC(=O)NS(=O)(=O)c2ccccc2Cl',1.39794000867204 +'OS(=O)(=O)C(C(=CC=C2)C1=C2)=CC=C1N=NC(C(O)=C3N=NC(C(C=C5)=C4C=C5)=CC=C4S(O)(=O)=O)=CC(=C3O)CO',2.8668778143375 +'S=P(OCC)(OCC)Oc1ccc2C(C)=C(Cl)C(=O)Oc2c1',-0.0969100130080564 +'CNP(=O)(OC)Oc1ccc(cc1Cl)C(C)(C)C',0.602059991327962 +'C(C1C2C(C(O)C(O1)OC8C(OC(OC7C(OC(OC6C(OC(OC5C(C(C(OC4C(C(C(OC3C(C(C(O2)OC3CO)O)O)OC4CO)O)O)OC5CO)O)O)C(C6O)O)CO)C(C7O)O)CO)C(C8O)O)CO)O)O',3.20411998265593 +'n1c(N)nc(N)nc1NC2CC2',1.17609125905568 +'COC(=O)c1c(Cl)c(Cl)c(C(=O)OC)c(Cl)c1Cl',2.69897000433602 +'O=C(O)C(Cl)(Cl)C',1.44978684698577 +'Nc1cc(N)c(O)cc1',1.39794000867204 +'FC(F)(Cl)Cl',2.17609125905568 +'ClCCl',1.69897000433602 +'O=P(OC)(OC)OC=C(Cl)Cl',0.361727836017593 +'OC(c1ccc(Cl)cc1)(c2ccc(Cl)cc2)C(Cl)(Cl)Cl',1.30102999566398 +'ClC4=C(Cl)C5(Cl)C3C1CC(C2OC12)C3C4(Cl)C5(Cl)Cl',-1.30102999566398 +'CN(=C1C(C=C2)=CC=C2)N(C)C(=C1)C(C=C3)=CC=C3',2.09691001300806 +'O=C(NC(=O)c(c(F)ccc1)c1F)Nc(ccc(c2)Cl)c2',0.903089986991944 +'CC1=C(C)S(=O)(=O)CCS1(=O)=O',1 +'O=C(NC)CSP(OC)(OC)=S',-0.602059991327962 +'COc1ccc(N)c(OC)c1',2.44090908206522 +'COP(=O)OC',2 +'CC(=C(N(=O)=O)C=C1N(=O)=O)C=C1',1.53147891704226 +'CN(C)C(=O)C(c1ccccc1)c2ccccc2',1.47712125471966 +'N(c(cccc1)c1)c(cccc2)c2',1.49136169383427 +'C(C=C1)(=N(C=C1)CC2)C(N2=C3)=CC=C3',-0.236572006437063 +'CCOP(=S)(OCC)SCCSCC',-1 +'NC(=S)NNC(N)=S',2.97634997900327 +'O=C(N(C)C)Nc(ccc(c1Cl)Cl)c1',0.778151250383644 +'O=P(O)(O)CCCl',2.17609125905568 +'O=C(OCC)C(O1)C1(c(cccc2)c2)C',2.24303804868629 +'COC(=O)NC(=NC1=C2)NC1=CC(=C2)SC(C=C3)=CC=C3',1.17609125905568 +'CN1C=C(c2ccccc2)C(=O)C(c3cc(C(F)(F)F)ccc3)=C1',1.39794000867204 +'c1cc(C(F)(F)F)cc(Cl)c1NC(C(C)C)C(=O)OC(C(#N))c2cccc(Oc3ccccc3)c2',0.397940008672038 +'S=P(OCC)(Sc1ccccc1)CC',0.198657086954423 +'n1c(C)nc(OC)nc1NC(=O)NS(=O)(=O)c2ccsc2C(=O)OC',1.39794000867204 +'C(C(C(C(C1Cl)Cl)Cl)Cl)(C1Cl)Cl',0.698970004336019 +'O=N(=O)N(CN1N(=O)=O)CN(C1)N(=O)=O',0.176091259055681 +'O=C(N=C(N(C1(=O))C)N(C)C)N1C(CCCC2)C2',1.69897000433602 +'n(c(c(ccc1)cc2)c1O)c2',2.15533603746506 +'c1cc(Cl)cc(Cl)c1C(OCC=C)Cn2cncc2',1.60205999132796 +'COc1cccc(OC)c1C(=O)Nc2onc(C(C)(CC)CC)c2',1.70500795933334 +'n1c(OC)cc(OC)nc1NC(=O)NS(=O)(=O)Cc2ccccc2C(=O)OC',2.48995847942483 +'CCOC(=O)CC(SP(=S)(OC)OC)C(=O)OCC',1.69897000433602 +'CN(C)(CCC1)CC1',2.17609125905568 +'O=P(SCCCC)(SCCCC)SCCCC',0.0969100130080564 +'COCC(=O)N(C(C)C(=O)OC)c1c(C)cccc1C',1.79588001734408 +'S=P(OC)(OC)SCN1C(=O)SC(OC)=N1',0.301029995663981 +'CNC(=O)ON=C(C)SC',1 +'COP(=S)(OC)Oc1ccc(cc1)N(=O)(=O)',-0.602059991327962 +'O=C1N(N)C(SC)=NN=C1C(C)(C)C',1.17609125905568 +'COP(=O)(OC)OC(Br)C(Cl)(Cl)Br',0.301029995663981 +'OC(C(N)C1O)C(C)OC1(C)OC(CC(C)(C(C2O)C(O)=O)OC(O)(C2)CC(O)CC(C)(O3)C3C=C4)C=CC=CC=CC=CCC(C)OC4=O',1.85733249643127 +'O=N(=O)c(ccc(c1N)C)c1',0.903089986991944 +'O=N(=O)c(c(N)ccc1N)c1',1.93951925261862 +'O=C(O)C(=C(N)C=C1N(=O)=O)C=C1',3.07371835034612 +'O=N(=O)c(c(c(ccc1)cc2)c1)c2',2.21748394421391 +'c12c(N=Nc3ccccc3)c(O)ccc1cc(S(=O)(=O)O)cc2',2.25527250510331 +'CC(C)Oc1cc(c(Cl)cc1Cl)N2N=C(OC2(=O))C(C)(C)C',0.698970004336019 +'CNC(=O)ON=C(SC)C(=O)N(C)C',0.698970004336019 +'CCOP(=S)(OCC)Oc1ccc(cc1)N(=O)=O',0.544068044350276 +'Oc(c(c(c(c1Cl)Cl)Cl)Cl)c1Cl',1 +'NC(=N)NC(=N)NCCc1ccccc1',1.86332286012046 +'COP(=S)(OC)SCN2C(=O)c1ccccc1C2(=O)',1.30102999566398 +'CCN(CC)C(=O)C(Cl)=C(C)OP(=O)(OC)OC',1.08990511143940 +'ClC3C6(Cl)C4C2C1OC1C5C2C3(Cl)C(Cl)(C45)C6(Cl)Cl',-0.154901959985743 +'O=C(OC(=O)c1cccc2)c12',3.07371835034612 +'Nc1c(Cl)c(Cl)nc(C(=O)(O))c1Cl',1.77815125038364 +'CCN(CC)c1nc(C)cc(OP(=S)(OC)OC)n1',0.397940008672038 +'Nc3ccc2cc1ccc(N)cc1nc2c3',1.67209785793572 +'CCC(=O)Nc1ccc(Cl)c(Cl)c1',1.30102999566398 +'Clc1cc(Cl)ccc1C2(Cn3ncnc3)OC(CCC)CO2',1.39794000867204 +'O=C(N)c(nccn1)c1',2.89707700320942 +'Oc1cc(O)c2C(=O)C(O)=C(c3cc(O)c(O)cc3)Oc2c1',3.30835094858673 +'CCC(O)(C)C#C',1.66275783168157 +'CC(C(NCC)=C1)=CC(C1=O2)=C(C(C2=C3)=CC(C)=C3NCC)C(=CC=C4)C(=C4)C(=O)OCC',1.07918124604762 +'O=C(NS(=O)(=O)c1cccc2)c12',3.55654370848351 +'c1cc(Cl)ccc1C2SC(=O)N(C(=O)NC3CCCCC3)C2C',2.20411998265593 +'n(c(nc(n1)NCC)NCC)c1Cl',0.698970004336019 +'O=[S](NC1CCCCC1)(=O)[O-].[Na+]',3.55654370848351 +'O=C(OCC(C1OCC(C1O)O)O)CCCCCCCCCCC',3.83777776955373 +'O(CC1O)C(C1O)C(O)COC(=O)CCCCCCCCCCCCCCCCC',3.85751341477669 +'O=S(=O)(Nc(nc(cc1C)C)n1)c(ccc(N)c2)c2',1.51851393987789 +'CCNc1nc(NC(C)(C)C)nc(SC)n1',1.17609125905568 +'Oc(c(cc(c1)C(C)(C)C)Cl)c1',2.33445375115093 +'C(C(Cl)Cl)(Cl)Cl',2.03342375548695 +'COP(=O)(OC)OC(=CCl)c1cc(Cl)c(Cl)cc1Cl',2 +'CCN(CC)C(=O)SCc1ccc(Cl)cc1',0.698970004336019 +'COC(=O)NC(=S)Nc1ccccc1NC(=S)NC(=O)OC',1.50514997831991 +'N(C(=S)SSC(N(C)C)=S)(C)C',1.17609125905568 +'c12OC(CCCC(C)CCCC(C)CCCC(C)C)(C)CCc1c(C)c(OC(=O)C)c(C)c2C',3.30102999566398 +'Cc1cc(N)ccc1NOS(O)(=O)=O',2.26481782300954 +'C(Br)(C(Br)(Br)Br)C1C(C)(C)C1C(=O)OC(C(#N))c2cccc(Oc3ccccc3)c2',0.477121254719662 +'O=C(O)COc(c(cc(c1Cl)Cl)Cl)c1',1 +'FC(F)(F)C(=CC(N(=O)=O)=C1N(C(C)C)C(C)C)C=C1N(=O)=O',1.60205999132796 +'Cc1cc(C)c(N)cc1C',1.79934054945358 +'CC(O)(C(O)C(O1)C)CC1(C)OC(C(C)O2)C(C(O)C2(C)OC(C(C)C(O)CC(=O)OC(CC)C3COC(C(OC)C4OC)OC(C)C4O)C(CC=O)CC(C)C(=O)C=CC(=C3)C)N(C)C',2.69897000433602 +'c1c(Cl)cc(Cl)cc1N2C(=O)C(C)(C=C)OC2(=O)',1.86272752831797 +'O=C(OC(CCCC(O)CCCCCc1cc(O)cc2O)C)c12',-0.698970004336019 +'COC(=O)C1(C2=CC=CC=C2C3=C1C=C(C=C3)Cl)O',2.17609125905568 +'CC(C(=O)O)OC1=CC(=CC=C1)Cl',2 +'P12P3P1P23',3.16790781000148 +'C(CO)O',2.60205999132796 +'CCCCOCC(C)OCC(C)O',2.10720996964787 +'C(CO)O',3.30102999566398 +'C(CO)O',2.96378782734556 +'[O-][As](=O)([O-])[O-]',0.795880017344075 +'[Si](CN1C=NC=N1)(C2=CC=C(C=C2)F)C3=CC=C(C=C3)F',0.361727836017593 +'N(C(=S)SSC(N(C)C)=S)(C)C',1.06069784035361 +'COP(=O)(N)SC',-0.0457574905606751 +'N(C(=S)SSC(N(C)C)=S)(C)C',0.737987326333431 +'COP(=O)(NC(=O)(C))SC',1.54406804435028 +'C1=CC=C(C=C1)NC(=O)NC2=CN=NS2',1.47712125471966 +'CCOP(=S)(NC(C)C)OC1=CC=CC=C1C(=O)OC(C)C',-0.301029995663981 +'CC(=NOC(=O)N(C)SN(C)C(=O)ON=C(C)SC)SC',1 +'CCOP(=S)(OCC)OC1=NC(=NC(=C1)C)C(C)C',0.176091259055681 +'NC(CCCC1)C1',1.76715586608218 +'CN1C=C(c2ccccc2)C(=O)C(c3cc(C(F)(F)F)ccc3)=C1',1.51188336097887 +'ClC1CC2C(C1Cl)C3(Cl)C(=C(Cl)C2(Cl)C3(Cl)Cl)Cl',-0.301029995663981 +'CCCCC(CC)COC(=O)C1=CC=CC=C1C(=O)OCC(CC)CCCC',2.30102999566398 +'OC(=O)CNCP(O)(O)=O',3 +'C1CNC(=S)N1',-0.638272163982407 +'O=C(N(OC)C)Nc(ccc(c1Cl)Cl)c1',0.795880017344075 +'C1=CC=C2C(=C1)NC(=S)S2',2.8750612633917 +'CCOP(=S)(OCC)OC1=NC(=C(C=C1Cl)Cl)Cl',1 +'c(c(c(c(c1Cl)Cl)Cl)Cl)(c1Cl)Cl',-0.537602002101044 +'COc1ccc(cc1)C(c2ccc(OC)cc2)C(Cl)(Cl)Cl',2.09691001300806 +'C1=CC(=CC=C1Cl)Cl',2.47712125471966 +'CC(C)OC(=O)NC1=CC(=CC=C1)Cl',2.69897000433602 +'COP(=O)(OC)OC=C(Cl)Cl',0.332438459915605 +'CCOP(=S)(OCC)Oc1ccc(cc1)N(=O)=O',-0.376750709602100 +'CNC(=O)N(C)c1nnc(s1)C(C)(C)C',1.60205999132796 +'CCCCOCCOCCOCC1=CC2=C(C=C1CCC)OCO2',2.39794000867204 +'CC(C(=O)O)OC1=C(C=C(C=C1)Cl)Cl',0.954242509439325 +'CC1(C(C1C(=O)OC(C#N)C2=CC(=C(C=C2)F)OC3=CC=CC=C3)C=C(Cl)Cl)C',1.09691001300806 +'C(#N)c(c(c(c(c1C(#N))Cl)Cl)Cl)c1Cl',0.602059991327962 +'O=C(OCC)C(O)(c(ccc(c1)Cl)c1)c(ccc(c2)Cl)c2',1.26481782300954 +'O=C(N(C)C)Nc(ccc(c1)Cl)c1',2.09691001300806 +'O=C(N(SC(Cl)(Cl)Cl)C(=O)C1CC=CC2)C12',2 +'CCc1cccc(C)c1N(C(C)COC)C(=O)CCl',2.17609125905568 +'C1=CC(=C(C=C1Cl)Cl)OCC(=O)O',0.698970004336019 +'CCNC1=NC(=NC(=N1)Cl)NC(C)(C)C#N',0.0969100130080564 +'C(C(C(C(C1Cl)Cl)Cl)Cl)(C1Cl)Cl',0.662757831681574 +'COP(=S)(OC)OC1=CC(=C(C=C1Cl)Cl)Cl',1.69897000433602 +'C1C2C=CC1C3C2C4(C(=C(C3(C4(Cl)Cl)Cl)Cl)Cl)Cl',-2 +'CC1(C(C1C(=O)OCC2=CC(=CC=C2)OC3=CC=CC=C3)C=C(Cl)Cl)C',1.39794000867204 +'CCN(CC)C(=O)C(C)OC1=CC=CC2=CC=CC=C21',2 +'ClC1C=CC2C1C3(Cl)C(=C(Cl)C2(Cl)C3(Cl)Cl)Cl',-0.602059991327962 +'CC(=CC(=O)NC)OP(=O)(OC)OC',-0.346787486224656 +'CC(C)C1(C)N=C(NC1(=O))c3nc2ccccc2cc3C(=O)(O)',1.30102999566398 +'CC(C)Nc1nc(Cl)nc(NC(C)C)n1',1.69897000433602 +'CC(C(=O)O)(Cl)Cl',1.69897000433602 +'CC1(C(C1C(=O)OC(C#N)C2=CC(=C(C=C2)F)OC3=CC=CC=C3)C=C(Cl)Cl)C',0.8750612633917 +'O=C(NC)CSP(OC)(OC)=S',0.698970004336019 +'C12C3(C4(C5(C3(C(C1(C5(C2(C4(Cl)Cl)Cl)Cl)Cl)(Cl)Cl)Cl)Cl)Cl)Cl',-2 +'COC(=O)C1=CC=CC=C1C(=O)OC',3.30102999566398 +'CCOP(=S)(OCC)SCSC(C)(C)C',-1.30102999566398 +'CCC(C)SP(=O)(OCC)SC(C)CC',-0.602059991327962 +'CCOP(=S)(OCC)SCSC(C)(C)C',0.301029995663981 +'C1C(C(C(=O)N1C2=CC=CC(=C2)C(F)(F)F)Cl)CCl',0.698970004336019 +'O=C(O)C(C(C(=O)O)C(O1)CC2)C12',2.06069784035361 +'O=C(Oc(c(OC(C1)(C)C)c1cc2)c2)NC',0.698970004336019 +'Oc(c(c(c(c1)Cl)Cl)Cc(c(c(cc2Cl)Cl)Cl)c2O)c1Cl',0.698970004336019 +'CC1(CON(C1=O)CC2=CC=CC=C2Cl)C',1.33243845991561 +'CCC(C)N1C(=O)C(=C(NC1=O)C)Br',1.79588001734408 +'CC1=CC(=CC(=C1N(C)C)C)OC(=O)NC',0.176091259055681 +'CNC(=O)OC1=CC=CC(=C1)N=CN(C)C',1.09691001300806 +'CC1=NN(C(=O)N1C(F)F)C2=CC(=C(C=C2Cl)Cl)NS(=O)(=O)C',1.82607480270083 +'CCOP(=S)(CC)SC1=CC=CC=C1',0.698970004336019 +'CCOP(=S)(OCC)SC(CCl)N1C(=O)C2=CC=CC=C2C1=O',0.397940008672038 +'N1CC(C)(C)CNC1=NN=C(C=Cc2ccc(C(F)(F)F)cc2)C=Cc3ccc(C(F)(F)F)cc3',0.698970004336019 +'CC1=C(C(=C(C(=C1F)F)COC(=O)C2C(C2(C)C)C=C(C(F)(F)F)Cl)F)F',0.662757831681574 +'CC1=CC(=C(C=C1)N=CN(C)C=NC2=C(C=C(C=C2)C)C)C',1.00860017176192 +'S=P(OC)(OC)SCN1C(=O)SC(OC)=N1',-0.0969100130080564 +'CC(C)N(C(C)C)C(=O)SCC(Cl)=C(Cl)Cl',1.09691001300806 +'S=P(OC)(OC)SCN1N=Nc2ccccc2C1(=O)',0.352182518111362 +'CC1=NC(=NC(=N1)OC)NC(=O)NS(=O)(=O)C2=CC=CC=C2CCC(F)(F)F',1.90254677931399 +'O=C(N(S(=O)(=O)Nc1cccc2)C(C)C)c12',1.60205999132796 +'CCN(CC)c1nc(C)cc(OP(=S)(OC)OC)n1',1.13987908640124 +'O=C(ON=CC(SC)(C)C)NC',-1 +'ClC(Cl)(Cl)CC1(OC1)c2cc(Cl)cc(Cl)c2',1.47712125471966 +'CCC1CCCC(C(C(=O)C2CC3C(C2CC(=O)O1)CCC4C3CC(C4)OC5CC(C(C(C5OC)OC)OC)C)C)OC6CCC(C(O6)C)N(C)C',1.38021124171161 +'CC(C)(C)C(=NOC(=O)NC)CSC',0.778151250383644 +'CON=C(CC1=CN=CC=C1)C2=C(C=C(C=C2)Cl)Cl',1.65321251377534 +'CC(=CC1C(C1(C)C)C(=O)OCN2C(=O)C3=C(C2=O)CCCC3)C',2.39794000867204 +'C1COC(O1)(CN2C=NC=N2)C3=C(C=C(C=C3)Cl)Cl',1 +'CCCOC(=O)C1=CN=C(C=C1)C(=O)OCCC',2.39794000867204 +'CC1=CC(=NC(=N1)NC(=O)NS(=O)(=O)C2=CC=CC=C2C(=O)OC3COC3)C',1.91907809237607 +'C1=C(C(=NC(=C1Cl)Cl)OCC(=O)O)Cl',1.55630250076729 +'CCOCN1C(=C(C(=C1C(F)(F)F)Br)C#N)C2=CC=C(C=C2)Cl',1.13353890837022 +'CC(C)CC1=C(C(=NC(=C1C(=O)SC)C(F)(F)F)C(F)F)C(=O)SC',0.559906625036112 +'CC12CC1(C(=O)N(C2=O)C3=CC(=CC(=C3)Cl)Cl)C',1.17609125905568 +'CC1=CC(=C(C=C1)C(=O)OC)C2=NC(C(=O)N2)(C)C(C)C',1.69897000433602 +'COP(=S)(OC)OC1=NC(=C(C=C1Cl)Cl)Cl',0.477121254719662 +'CC(C)CC1=C(C(=NC(=C1C(=O)OC)C(F)F)C(F)(F)F)C2=NCCS2',1.64542226934909 +'CCOC(=O)C(CC1=CC(=C(C=C1Cl)F)N2C(=O)N(C(=N2)C)C(F)F)Cl',1.07918124604762 +'CC(C)=CC3C(C(=O)OCc2coc(Cc1ccccc1)c2)C3(C)C',2.09691001300806 +'CCCSP(=S)(OCC)OC1=CC=C(C=C1)SC',1.06069784035361 +'CC1=CC(=C(C(=C1)OC(=O)NC)C)C',1.77232170672292 +'CC1=CC=CC=C1COC2CC3(CCC2(O3)C)C(C)C',2.17609125905568 +'CC1=C2C(=CC=C1)SC3=NN=CN23',1.49136169383427 +'CCC(=C1C(=O)CC(CC1=O)CC(C)SCC)NOCC=CCl',2 +'CCCN(CCC)C(=O)SCC',0.954242509439325 +'CC(C)OC(=O)C=C(C)C=CCC(C)CCCC(C)(C)OC',1.66275783168157 +'COP(=S)(OC)Oc1ccc(SC)c(C)c1',0.574031267727719 +'COC1=C(C=C(C=C1)C(=CC(=O)N2CCOCC2)C3=CC=C(C=C3)Cl)OC',1.66558099101795 +'CCSC(=O)N(CC(C)C)CC(C)C',2 +'CC(C)OP(=S)(OC(C)C)SCCNS(=O)(=O)C1=CC=CC=C1',1.17609125905568 +'CC(=CC1C(C1(C)C)C(=O)OCC2=CC(=CC=C2)OC3=CC=CC=C3)C',2.17609125905568 +'CC1=CC(=CC(=C1C)C)OC(=O)NC',1 +'CCOP(=S)(OCC)SCSC1=CC=C(C=C1)Cl',0 +'C1CN(CCN1C(C(Cl)(Cl)Cl)NC=O)C(C(Cl)(Cl)Cl)NC=O',2 +'C(=CC=C1)(C2=C1)NC(=N2)C(=CS3)N=C3',0.301029995663981 +'C1(=C(C(=C(C(=C1Cl)Cl)Cl)Cl)Cl)[N+](=O)[O-]',2.09691001300806 +'CCCC(=NOCC)C1C(=O)CC(CC1=O)CC(C)SCC',1.21906033244886 +'ClC2(Cl)C4(Cl)C1(Cl)C5(Cl)C(Cl)(Cl)C3(Cl)C1(Cl)C2(Cl)C3(Cl)C45Cl',-0.154901959985743 +'CCN(C1CCCCC1)C(=O)SCC',0.477121254719662 +'CC1=NC(=NC(=N1)OC)NC(=O)NS(=O)(=O)C2=CC=CC=C2OCCCl',2.34399906905716 +'C(C(=O)O)OC1=NC(=C(C(=C1Cl)N)Cl)F',2.69897000433602 +'CC1=C(C(=O)CC1OC(=O)C2C(C2(C)C)C=C(C)C)CC#C',1.97772360528885 +'C1C(COC1(CN2C=NC=N2)C3=C(C=C(C=C3)Cl)Cl)Br',0.811575005870593 +'C1=NNC(=N1)N',0.397940008672038 +'C1=CC(=C(C(=C1)F)C(=O)NC(=O)NC2=CC(=C(C(=C2F)Cl)F)Cl)F',1.41497334797082 +'C1=CC(=CC=C1OS(=O)(=O)C2=CC=C(C=C2)Cl)Cl',0.397940008672038 +'FC(F)(F)C(=CC(N(=O)=O)=C1N(C(C)C)C(C)C)C=C1N(=O)=O',3 +'CC1=C(C(=O)CC1OC(=O)C2C(C2(C)C)C=C(C)C)CC=C',1.8750612633917 +'C1=CC(=C(C(=C1)Cl)C#N)Cl',0.397940008672038 +'C1C(O1)COC2=CC=CC=C2C3=CC=CC=C3',2.69897000433602 +'CC1=CC=CC=C1OCC2=CC=CC=C2C(=NOC)C(=O)OC',2.57403126772772 +'O=N(=O)C(C(=C1N(=O)=O)N(C(C)C)C(C)C)=CC(=C1)S(=O)(=O)N',1.56655533088306 +'C1=CC(=C(C2=NC=C(C=C21)Cl)C(=O)O)Cl',2.87909587950007 +'CC(C)NC(=O)N1CC(=O)N(C1=O)C2=CC(=CC(=C2)Cl)Cl',1.66275783168157 +'CCCN(CCCl)C1=C(C=C(C=C1[N+](=O)[O-])C(F)(F)F)[N+](=O)[O-]',2.30621050816776 +'C1=CC=C(C=C1)C2=CC=CC=C2O',3 +'O=C(N(C)C)Nc(cccc1C(F)(F)F)c1',1.17609125905568 +'C1=CC(=NC(=C1)Cl)C(Cl)(Cl)Cl',0 +'Clc1cc(Cl)cc(Cl)c1OCCN(CCC)C(=O)n2cncc2',0.8750612633917 +'CC1=CC(=C(C=C1NC(=O)C)NS(=O)(=O)C(F)(F)F)C',1.44090908206522 +'C(=C(I)I)(I)I',1.69897000433602 +'C1=C(C=C(C(=C1Cl)N2C(=C(C(=N2)C#N)S(=O)C(F)(F)F)N)Cl)C(F)(F)F',-1.22184874961636 +'O=C(N(C)C)Nc(ccc(c1Cl)Cl)c1',0.795880017344075 +'CC1=C(C(=O)CC1OC(=O)C2C(C2(C)C)C=C(C)C)CC=C',1.38916608436453 +'CC1=CC2=C(C=C1)N=C3C(=N2)SC(=O)S3',0.8750612633917 +'CC(C)N(C(=O)CCl)c1ccccc1',1.36172783601759 +'CC(C)C1(C(=O)NC(=N1)C2=C(C=CC=N2)C(=O)O)C',2.69897000433602 +'CC1(C(C1(C)C)C(=O)OC(C#N)C2=CC(=CC=C2)OC3=CC=CC=C3)C',1.28891960566173 +'CN1CN(C(=S)SC1)C',1.47712125471966 +'ClC(Cl)=CC1C(C)(C)C1C(=O)OC(C(#N))c2cccc(Oc3ccccc3)c2',1.8750612633917 +'ClC2C1OC1C3C2C4(Cl)C(=C(Cl)C3(Cl)C4(Cl)Cl)Cl',-0.698970004336019 +'CCOC(=O)CN1C2=C(C=CC=C2Cl)SC1=O',1.09691001300806 +'CCCN(CCC)C1=C(C=C(C(=C1[N+](=O)[O-])N)C(F)(F)F)[N+](=O)[O-]',1.46834733041216 +'C1=CC=C(C=C1)C(CCC2=CC=C(C=C2)Cl)(CN3C=NC=N3)C#N',1.60205999132796 +'CC(C)(C)C(CCC1=CC=C(C=C1)Cl)(CN2C=NC=N2)O',1.20139712432045 +'CC1=C(C=CC=C1COC(=O)C2C(C2(C)C)C=C(C(F)(F)F)Cl)C3=CC=CC=C3',0.698970004336019 +'C(=CC=C1)(C2=C1)NC(=N2)C(=CS3)N=C3',1.60205999132796 +'C1=C(C=C(C(=C1Cl)N)Cl)[N+](=O)[O-]',2.17609125905568 +'CC1=C(C=C(C=C1C(=O)N)[N+](=O)[O-])[N+](=O)[O-]',0.795880017344075 +'CC(C)OC1=CC=CC(=C1)NC(=O)C2=CC=CC=C2C(F)(F)F',2.69897000433602 +'OC(c1ccc(Cl)cc1)(c2ccc(Cl)cc2)C(Cl)(Cl)Cl',0.397940008672038 +'O=P(O)(O)CCCl',2.64933485871214 +'CN(C(=O)NC1=CC=C(C=C1)Br)OC',1.09691001300806 +'CC1=CC(=CC=C1)NC(=O)OC2=CC=CC(=C2)NC(=O)OC',1.39794000867204 +'CC(C)(C)C1=NN=C(S1)N2C(CN(C2=O)C)O',1.69897000433602 +'S=P(OCC)(OCC)Oc1ccc2C(C)=C(Cl)C(=O)Oc2c1',0.230448921378274 +'COC(=O)c1ccccc1S(=O)(=O)NC(=O)N(C)c2nc(OC)nc(C)n2',1.09691001300806 +'C1=CC=C(C(=C1)NC2=NC(=NC(=N2)Cl)Cl)Cl',0.0606978403536116 +'CC1=C(C=CC(=C1)OP(=S)(OC)OC)[N+](=O)[O-]',-0.337242168318426 +'COc1c(Cl)ccc(Cl)c1C(=O)(O)',2.06069784035361 +'CC1(C(C1C(=O)OC(C#N)C2=CC(=CC=C2)OC3=CC=CC=C3)C=C(Br)Br)C',0.397940008672038 +'C1=CC=C(C(=C1)C(C2=CC=C(C=C2)F)(C3=CN=CN=C3)O)Cl',0.397940008672038 +'c1ccc2nc(NC(=O)OC)n(C(=O)NCCCC)c2c1',2.06069784035361 +'CCOC(=O)COC(=O)C1=C(C=CC(=C1)OC2=C(C=C(C=C2)C(F)(F)F)Cl)[N+](=O)[O-]',1.39794000867204 +'CC(C)(C)C(C(N1C=NC=N1)OC2=CC=C(C=C2)C3=CC=CC=C3)O',1.39794000867204 +'CCNC(=O)NC(=O)C(=NOC)C#N',1.48144262850231 +'CCOC1=C(C=CC(=C1)OC2=C(C=C(C=C2)C(F)(F)F)Cl)[N+](=O)[O-]',1.60205999132796 +'CC1=NC=C(N1CCO)[N+](=O)[O-]',2.17609125905568 +'O=C(N(SC(Cl)(Cl)Cl)C(=O)c1cccc2)c12',2.69897000433602 +'CC(C)(C)c2ccc(OC1CCCCC1OS(=O)OCC#C)cc2',2 +'CCCCC(CN1C=NC=N1)(C2=C(C=C(C=C2)Cl)Cl)O',0.672097857935718 +'CC(C)(C)C(C(=CC1=C(C=C(C=C1)Cl)Cl)N2C=NC=N2)O',1.69897000433602 +'C1=CC(C2C1C3(C(=C(C2(C3(Cl)Cl)Cl)Cl)Cl)Cl)Cl',-0.42021640338319 +'C1=CC=C2C(=C1)C(=O)C3=C(C2=O)SC(=C(S3)C#N)C#N',1 +'CC1=NN(C(=C1C=NOCC2=CC=C(C=C2)C(=O)OC(C)(C)C)OC3=CC=CC=C3)C',0.488550716500444 +'CS(=O)(=O)C1=C(C=CC(=C1)C(F)(F)F)C(=O)C2=C(ON=C2)C3CC3',1.30102999566398 +'CC1=C(N=C(N=C1OC(=O)N(C)C)N(C)C)C',1.09691001300806 +'CCN(CC)C(=O)C(Cl)=C(C)OP(=O)(OC)OC',0.176091259055681 +'C1=CC(=CC=C1C(CN)O)O',2.39794000867204 +'CC1=C(C(=CC=C1)C)N(C(=O)COC)N2CCOC2=O',1.69897000433602 +'c1c(C(F)(F)F)cccc1N2C(=O)C(Cl)=C(NC)C=N2',1.27300127206374 +'CCC(C)NC1=C(C=C(C=C1[N+](=O)[O-])C(C)(C)C)[N+](=O)[O-]',1.69897000433602 +'C1=CC(=CC=C1S(=O)(=O)C2=CC(=C(C=C2Cl)Cl)Cl)Cl',2.36172783601759 +'CCCCC1=C(NC(=NC1=O)NCC)C',1.39794000867204 +'n(c(nc(n1)NCC)NCC)c1Cl',0.724275869600789 +'FC(F)(F)C(C=C1N(=O)=O)=CC(N(=O)=O)=C1N(CC)CC(C)=C',1.09691001300806 +'C1CCC(C1)N(CC2=CC=C(C=C2)Cl)C(=O)NC3=CC=CC=C3',1.39794000867204 +'CS(=O)(=O)NC(=O)C1=C(C=CC(=C1)OC2=C(C=C(C=C2)C(F)(F)F)Cl)[N+](=O)[O-]',1.69897000433602 +'CCOC(=O)C(C)OC1=CC=C(C=C1)OC2=NC3=C(O2)C=C(C=C3)Cl',0.954242509439325 +'CCC1=C(C(=CC=C1)CC)N(CNC(=O)C)C(=O)CCl',1.79588001734408 +'NC(=N)NCCCCCCCCCCCC(OC(=O)C)',1.46239799789896 +'C1=CC(=CC(=C1)Cl)NC(=O)OCC#CCCl',2.65321251377534 +'CC(C)C(C(=O)OC(C(#N))c2cccc(Oc1ccccc1)c2)c3ccc(Cl)cc3',1.39794000867204 +'CC(C)C1=C(C=CC(=C1)C(C)(C)C2=CC(=C(C=C2)O)C(C)C)O',1.39794000867204 +'CCN(CC1=C(C=CC=C1Cl)F)C2=C(C=C(C=C2[N+](=O)[O-])C(F)(F)F)[N+](=O)[O-]',1.69897000433602 +'CCCCCCCCSC(=O)OC1=CC(=NN=C1C2=CC=CC=C2)Cl',1.82930377283102 +'CC1=C(C(=O)CC1OC(=O)C2C(C2(C)C)C=C(C)C)CC=C',1.13987908640124 +'CCCCNC(=O)N1C2=CC=CC=C2N=C1NC(=O)OC',2.39794000867204 +'CC1=C(C(=CC=C1)C)N(C(C)C(=O)OC)C(=O)CC2=CC=CC=C2',1.66275783168157 +'CC(C)C(C1=CC=C(C=C1)OC(F)F)C(=O)OC(C#N)C2=CC(=CC=C2)OC3=CC=CC=C3',0.778151250383644 +'Clc1ccccc1c2nnc(c3ccccc3Cl)nn2',1.30102999566398 +'CCOC(=O)NCCOC1=CC=C(C=C1)OC2=CC=CC=C2',1 +'CCC1=C(C(=CC=C1)CC)N(CC(=O)OCC)C(=O)CCl',1.69897000433602 +'c1(O2)c(CC2(C)C)cccc1OC(=O)N(C)SN(CCCC)CCCC',1.39794000867204 +'CCCCOC(=O)C(C)OC1=CC=C(C=C1)OC2=NC=C(C=C2)C(F)(F)F',0.477121254719662 +'COC1=CC(=C(C=C1Cl)OC)Cl',2.09691001300806 +'CCOP(=S)(OCC)OC1=NN(C(=N1)Cl)C(C)C',1.09691001300806 +'n(c(nc(n1)NC(C)C)NCC)c1Cl',1.39794000867204 +'CC(C)(C)C(C(=CC1=CC=C(C=C1)Cl)N2C=NC=N2)O',1.59560643486560 +'CCCCCCCCc1cc(N(=O)(=O))c(OC(=O)C=CC)c(c1)N(=O)(=O)',1.69897000433602 +'c1cc(OC(F)(F)F)ccc1C(O)(C(C)C)c2cncnc2',1.08278537031645 +'COP(=O)(C(C(Cl)(Cl)Cl)O)OC',1.30102999566398 +'C1=CC(=C(C=C1C(F)(F)F)Cl)OC2=CC(=C(C=C2)[N+](=O)[O-])C(=O)O',2.09691001300806 +'CCCN(CC1CC1)C2=C(C=C(C=C2[N+](=O)[O-])C(F)(F)F)[N+](=O)[O-]',0.698970004336019 +'CCOC(=O)C(C)OC(=O)C1=C(C=CC(=C1)OC2=C(C=C(C=C2)C(F)(F)F)Cl)[N+](=O)[O-]',1.69897000433602 +'CCSC(=O)N1CCCCCC1',1.17055505852121 +'CCC1=CC=C(C=C1)C(=O)NN(C(=O)C2=CC(=CC(=C2)C)C)C(C)(C)C',1.68124123737559 +'ClC(Cl)C(Cl)(Cl)SN2C(=O)C1CC=CCC1C2(=O)',1.17609125905568 +'COC(=O)C1=CC=CC=C1S(=O)(=O)NC(=O)NC2=NC(=CC(=N2)OC(F)F)OC(F)F',2.14612803567824 +'CC(C)(C)C(C(N1C=NC=N1)OC2=CC=C(C=C2)Cl)O',1.39794000867204 +'CC1=C(C=CC(=C1)Cl)OCC(=O)O',0.602059991327962 +'COC=C(C1=CC=CC=C1OC2=NC=NC(=C2)OC3=CC=CC=C3C#N)C(=O)OC',1.79413935576777 +'C1=CC=C(C(=C1)C(C2=CC=C(C=C2)Cl)(C3=CN=CN=C3)O)Cl',0.361727836017593 +'[O-]Br(=O)=O',0.785329835010767 +'OP(=O)OCC',2.60205999132796 +'COP(N)(=O)SC',-1 +'CCOP(=O)(NC(C)C)Oc1ccc(SC)c(C)c1',0.176091259055681 +'CCOP(=S)(OCC)SCCSCC',-1.39794000867204 +'CCOP(=S)(OCC)SCSP(=S)(OCC)OCC',0.301029995663981 +'O=C(OCC(CCCC)CC)CCCCC(=O)OCC(CCCC)CC',3.17609125905568 +'CN(C=Nc1ccc(C)cc1C)C=Nc2ccc(C)cc2C',1 +'[C@@]14([C@@H]5OCC1=CC=C[C@@H]([C@H](O[C@H]2C[C@@H]([C@H]([C@@H](O2)C)O[C@H]3C[C@@H]([C@H]([C@@H](O3)C)O)OC)OC)C(=CC[C@@H]6C[C@H](OC([C@@H]4C=C([C@H]5O)C)=O)C[C@]7(O6)O[C@@H]([C@H](C=C7)C)[C@H](CC)C)C)C)O',0.301029995663981 +'O=C(N(S(=O)(=O)Nc1cccc2)C(C)C)c12',1.54406804435028 +'S=P(OC)(OC)SCN1C(=O)SC(OC)=N1',0.0969100130080564 +'C(#N)Cl',1.84509804001426 +'C(#N)Br',2.08635983067475 +'C1=CC(=CC=C1C(C2=CC=C(C=C2)Cl)C(Cl)(Cl)Cl)Cl',-0.602059991327962 +'c(cccc1)(c1)C(C)C',2.51982799377572 +'CCCN(CCC)C(=O)SCC',1.39794000867204 +'NC(CCCC1)C1',1.77815125038364 +'ClC1CC2C(C1Cl)C3(Cl)C(=C(Cl)C2(Cl)C3(Cl)Cl)Cl',0.778151250383644 +'CC(C)OC(=O)NC1=CC(=CC=C1)Cl',3 +'COC(=O)c1c(Cl)c(Cl)c(C(=O)OC)c(Cl)c1Cl',1 +'COC(=O)C1=CC=C(C=C1)C(=O)OC',2.09691001300806 +'N(C(=S)NC1)C1',-0.602059991327962 +'O=C(N(OC)C)Nc(ccc(c1Cl)Cl)c1',0.397940008672038 +'c(cccc1)(c1)C=C',2.45484486000851 +'COC(=O)c1ccccc1S(=O)(=O)NC(=O)Nc2nc(OC)nc(C)n2',2.39794000867204 +'C1=CC(=CC=C1N)Cl',1.09691001300806 +'FC(F)(F)C(Cl)=CC1C(C)(C)C1C(=O)OC(C(#N))c2cc(Oc3ccccc3)ccc2',1.09691001300806 +'C(Cl)(Br)Br',1.45484486000851 +'C=C(Cl)Cl',1.14612803567824 +'C(C=CCl)Cl',0.707570176097936 +'COP(=O)(OC)OC(=CCl)c1cc(Cl)c(Cl)cc1Cl',1.69897000433602 +'Oc(ccc(c1)C(c(ccc(O)c2)c2)(C)C)c1',1.69897000433602 +'O=C(OCc(cccc1)c1)c(c(ccc2)C(=O)OCCCC)c2',2.67209785793572 +'O=C(NCCCC1)C1',2.09691001300806 +'c(cccc1)(c1)Cl',2.07918124604762 +'C(Cl)(Cl)Cl',1.77815125038364 +'ClCCl',1.72082058177034 +'C1C2C3C(C1C4C2O4)C5(C(=C(C3(C5(Cl)Cl)Cl)Cl)Cl)Cl',-0.903089986991944 +'OCCO',3 +'O=C(C=C(CC1(C)C)C)C1',2.25285303097989 +'C(F)(Cl)(Cl)Cl',2.54282542695918 +'CCc1cccc(CC)c1N(COC)C(=O)CCl',1.14612803567824 +'c1ccccc1c2c(C)c(COC(=O)C3C(C)(C)C3C=C(Cl)C(F)(F)F)ccc2',0.698970004336019 +'n1c(Cl)cc(OC)nc1NC(=O)NS(=O)(=O)c2ccccc2C(=O)OCC',2.09691001300806 +'O=C(NC(=O)c(c(F)ccc1)c1F)Nc(ccc(c2)Cl)c2',0.89209460269048 +'c(cccc1)(c1)CC',2.46389298898591 +'O=C(N(SC(Cl)(Cl)Cl)C(=O)c1cccc2)c12',1.60205999132796 +'Clc1cc(C(F)(F)F)cnc1Oc2ccc(OC(C)C(=O)OC)cc2',0 +'C#N',1.49136169383427 +'ClC(C(OC(C=C2C(=O)OC(C)C(=O)OCC)=CC=C2N(=O)=O)=C1)=CC=C1C(F)(F)F',1.69897000433602 +'c1c(C(F)(F)F)cccc1N2C(=O)C(Cl)=C(NC)C=N2',1.70969386972779 +'O=N(=O)C(C(=C1N(=O)=O)N(C(C)C)C(C)C)=CC(=C1)S(=O)(=O)N',1.65321251377534 +'CN(=CC=C1C(C=C2)=CC=N2C)C=C1',0.574031267727719 +'C1=C(C=C(C=C1[N+](=O)[O-])[N+](=O)[O-])[N+](=O)[O-]',1.12417805547468 +'C(=C)Cl',0.113943352306837 +'C1CCC(=O)CC1',2.95904139232109 +'CC1(C(C1(C)C)C(=O)OC(C#N)C2=CC(=CC=C2)OC3=CC=CC=C3)C',1.39794000867204 +'C1=CC(=O)NNC1(=O)',2.69897000433602 +'CCSC(=O)N1CCCCCC1',0.301029995663981 +'C(C(Cl)(Cl)Cl)(O)O',2.13033376849501 +'ClC2C1OC1C3C2C4(Cl)C(=C(Cl)C3(Cl)C4(Cl)Cl)Cl',-1.60205999132796 +'Clc1cc(C(F)(F)F)ccc1Oc2cc(OCC)c(N(=O)(=O))cc2',1 +'c1cc(Cl)ccc1C(C(#N))(CCCC)Cn2ncnc2',0.992995098431341 +'CC1=C(C=C(C=C1[N+](=O)[O-])[N+](=O)[O-])[N+](=O)[O-]',0.301029995663981 +'CC(C)OC(=O)C(C1=CC=C(C=C1)Br)(C2=CC=C(C=C2)Br)O',1.41497334797082 +'C[N+](C)(C)CCCl',2.11394335230684 +'CCC(=C1C(=O)CC(CC1=O)CC(C)SCC)NOCC=CCl',1.93449845124357 +'CC1=NC(=NC(=C1)C2CC2)NC3=CC=CC=C3',1.55144999797288 +'N(c(cccc1)c1)c(cccc2)c2',1.39794000867204 +'CC1(C(=O)N(C(=O)O1)NC2=CC=CC=C2)C3=CC=C(C=C3)OC4=CC=CC=C4',1.22530928172586 +'CC1(CCCCC1)C(=O)NC2=C(C(=C(C=C2)O)Cl)Cl',2.46538285144842 +'C1=CC(=C2C(=C1)OC(O2)(F)F)C3=CNC=C3C#N',2.04139268515822 +'C(F)(F)(F)c1ccccc1C(=O)Nc2cccc(OC(C)C)c2',1.93951925261862 +'C(CCCCN=C(N)N)CCCNCCCCCCCCN=C(N)N',1.27875360095283 +'C1CN(C(=N1)N[N+](=O)[O-])CC2=CN=C(C=C2)Cl',1.23044892137827 +'COC(=O)C12CC3=C(C1=NN(CO2)C(=O)N(C4=CC=C(C=C4)OC(F)(F)F)C(=O)OC)C=CC(=C3)Cl',0.556302500767287 +'CC1=CC=CC=C1OCC2=CC=CC=C2C(=NOC)C(=O)OC',2.56820172406699 +'CC1=CC(=CC(=C1)C(=O)N(C(C)(C)C)NC(=O)C2=C(C(=CC=C2)OC)C)C',2.61384182187607 +'C1=CC(=C(C(=C1)F)C(=O)NC(=O)NC2=CC(=C(C=C2)OC(C(OC(F)(F)F)F)(F)F)Cl)F',1.55630250076729 +'CC1=CC=C(C=C1)N(SC(F)(Cl)Cl)S(=O)(=O)N(C)C',1.25527250510331 +'CC(C)(C)C1=C(C=CC(=C1)O)O',2.35218251811136 +'CC(=NOCC1=CC=CC=C1C(=NOC)C(=O)OC)C2=CC(=CC=C2)C(F)(F)F',1.77815125038364 +'COC(=O)N(C1=CC=CC=C1COC2=NN(C=C2)C3=CC=C(C=C3)Cl)OC',0.954242509439325 +'CC(C)N1C(=NC(C)(C)C)SCN(C1=O)C2=CC=CC=C2',0.939519252618618 +'C1=CC=C(C(=C1)C2=NN=C(N=N2)C3=CC=CC=C3Cl)Cl',1.23804610312880 +'CCCC(=C1C(=O)CC(CC1=O)C2CCCSC2)NOCC',1.44715803134222 +'C1CC1NC2=NC(=C(C(=N2)N)C#N)N',1.34242268082221 +'C(C=C1)(=N(C=C1)CC2)C(N2=C3)=CC=C3',-0.244125144327509 +'C1=CC=C2C(=C1)C(=O)C3=C(C2=O)SC(=C(S3)C#N)C#N',0.778151250383644 +'CCOC1=CC2=C(C=C1)NC(C=C2C)(C)C',1.07918124604762 +'C1=CC=C(C=C1)C(CCC2=CC=C(C=C2)Cl)(CN3C=NC=N3)C#N',1.47712125471966 +'CC1CN(CC(O1)C)CC(C)CC2=CC=C(C=C2)C(C)(C)C',0.230448921378274 +'C[Si](CN1C=NC=N1)(C2=CC=C(C=C2)F)C3=CC=C(C=C3)F',0.301029995663981 +'c1cc(Cl)cc(Cl)c1C(OCC=C)Cn2cncc2',1.17609125905568 +'CN(=CC=C1C(C=C2)=CC=N2C)C=C1',0.406540180433955 +'CCCCOCCOCCOCC1=CC2=C(C=C1CCC)OCO2',2 +'Clc1cc(Cl)ccc1C2(Cn3ncnc3)OC(CCC)CO2',1.98227123303957 +'C(=CC=C1)(C2=C1)NC(=N2)C(=CS3)N=C3',1.47712125471966 +'CCOC1=CC=C(C=C1)C(C)(C)COCC2=CC(=CC=C2)OC3=CC=CC=C3',1.41497334797082 +'CC(C)(C)c2ccc(OC1CCCCC1OS(=O)OCC#C)cc2',1.27875360095283 +'CC(COC1=CC=C(C=C1)OC2=CC=CC=C2)OC3=CC=CC=N3',2.14612803567824 +'CC(C)(C)C(=O)C(N1C=NC=N1)OC2=CC=C(C=C2)Cl',2.05690485133647 +'CC(C)(C)C(C(N1C=NC=N1)OC2=CC=C(C=C2)Cl)O',2.02118929906994 +'c1ccccc1c2c(C)c(COC(=O)C3C(C)(C)C3C=C(Cl)C(F)(F)F)ccc2',0.903089986991944 +'CC1(C(C1C(=O)OC(C#N)C2=CC(=C(C=C2)F)OC3=CC=CC=C3)C=C(Cl)Cl)C',0.778151250383644 +'CC1(C(C1C(=O)OC(C#N)C2=CC(=C(C=C2)F)OC3=CC=CC=C3)C=C(Cl)Cl)C',1.07918124604762 +'ClC(Cl)=CC1C(C)(C)C1C(=O)OC(C(#N))c2cccc(Oc3ccccc3)c2',1.69897000433602 +'ClC1CC2C(C1Cl)C3(Cl)C(=C(Cl)C2(Cl)C3(Cl)Cl)Cl',-0.602059991327962 +'ClC4=C(Cl)C5(Cl)C3C1CC(C2OC12)C3C4(Cl)C5(Cl)Cl',-1 +'C1C2C3C(C1C4C2O4)C5(C(=C(C3(C5(Cl)Cl)Cl)Cl)Cl)Cl',-0.602059991327962 +'C1(C(C(C(C(C1Cl)Cl)Cl)Cl)Cl)Cl',0.672097857935718 +'CCC(=O)Nc1ccc(Cl)c(Cl)c1',1.88081359228079 +'C1(=C(C(=C(C(=C1Cl)Cl)Cl)Cl)Cl)[N+](=O)[O-]',2.14612803567824 +'C1C2C(COS(=O)O1)C3(C(=C(C2(C3(Cl)Cl)Cl)Cl)Cl)Cl',0.462397997898956 +'O=C(N(SC(Cl)(Cl)Cl)C(=O)c1cccc2)c12',1.69897000433602 +'CC(C(=O)O)OC1=CC=C(C=C1)OC2=C(C=C(C=N2)C(F)(F)F)Cl',-1 +'CCCCC(CN1C=NC=N1)(C#N)C2=CC=C(C=C2)Cl',0.991226075692495 +'Clc1cc(Cl)cc(Cl)c1OCCN(CCC)C(=O)n2cncc2',0.707570176097936 +'COP(=O)(NC(=O)(C))SC',0.397940008672038 +'CCOP(=O)(OCC)OC(=CCl)C1=C(C=C(C=C1)Cl)Cl',0.176091259055681 +'CCOP(=S)(OCC)SCCSCC',-0.657577319177794 +'O=P(O)(O)CCCl',1.07918124604762 +'CCCSP(=O)(OCC)SCCC',0.431363764158987 +'CCOP(=O)(NC(C)C)Oc1ccc(SC)c(C)c1',0.230448921378274 +'COP(=S)(OC)Oc1ccc(SC)c(C)c1',-0.142667503568732 +'OC(=O)C(N)CCP(C)(=O)O',0.544068044350276 +'OC(=O)CNCP(O)(O)=O',2.47712125471966 +'CCOC(=O)CC(SP(=S)(OC)OC)C(=O)OCC',2.55630250076729 +'COP(N)(=O)SC',-0.537602002101044 +'CC(=CC(=O)OC)OP(=O)(OC)OC',-0.455931955649724 +'CCOP(=S)(OCC)SCSCC',-0.795880017344075 +'CCOP(=S)(OCC)SCSC(C)(C)C',-1.22184874961636 +'S=P(OC)(OC)SCN1N=Nc2ccccc2C1(=O)',0.41161970596323 +'CCOP(=S)(OCC)OC1=NC(=C(C=C1Cl)Cl)Cl',0 +'CCOP(=S)(OCC)OC1=NC(=NC(=C1)C)C(C)C',0.763427993562937 +'CCC1=NC(=CC(=N1)OP(=S)(OC)OC)OCC',-0.346787486224656 +'S=P(OC)(OC)SCN1C(=O)SC(OC)=N1',0.204119982655925 +'CCOP(=S)(OCC)SCN1C2=C(C=C(C=C2)Cl)OC1=O',0.301029995663981 +'COP(=S)(OC)SCN2C(=O)c1ccccc1C2(=O)',0.954242509439325 +'CCOC(=O)C1=CN2C(=CC(=N2)OP(=S)(OCC)OCC)N=C1C',0.602059991327962 +'CCOP(=S)(OCC)OC1=NN(C=N1)C2=CC=CC=C2',0.113943352306837 +'O=C(Oc(c(c(ccc1)cc2)c1)c2)NC',1.77815125038364 +'CC1=CC(=CC(=C1SC)C)OC(=O)NC',0.968482948553935 +'CNC(=O)ON=C(C)SC',1.30102999566398 +'CCCOC(=O)NCCCN(C)C',2.83250891270624 +'COC(=O)NC1=NC2=CC=CC=C2N1',1.8750612633917 +'CC1=C(N=C(N=C1OC(=O)N(C)C)N(C)C)C',1.08990511143940 +'CNC(=O)CCSCCSP(=O)(OC)OC',-0.267606240177031 +'N(C(=S)SSC(N(C)C)=S)(C)C',1.07918124604762 +'C1=NNC(=N1)N',0.698970004336019 +'CCCCCCCCc1cc(N(=O)(=O))c(OC(=O)C=CC)c(c1)N(=O)(=O)',1.80617997398389 +'C1=CC=C(C=C1)[Sn](C2=CC=CC=C2)C3=CC=CC=C3',-0.522878745280338 +'O=C(NC(=O)c(c(F)ccc1)c1F)Nc(ccc(c2)Cl)c2',0.845098040014257 +'N(C(=S)NC1)C1',0.0969100130080564 +'C1=CC(=C(C(=C1)F)C(=O)NC(=O)NC2=CC(=C(C(=C2F)Cl)F)Cl)F',1.39794000867204 +'CCCSC1=CC2=C(C=C1)N=C(N2)NC(=O)OC',1.30102999566398 +'C1CN(CCN1CCCC(=O)C2=CC=C(C=C2)F)C3=CC=CC=N3',2.06069784035361 +'CC1(C2C(C3C(C(=O)C(=C(N)O)C(=O)C3(C(=O)C2=C(C4=C(C=CC(=C41)Cl)O)O)O)N(C)C)O)O',3.7160033436348 +'CC1=CC(=C(C=C1NC(=O)C2=CC(=CC(=C2O)I)I)Cl)C(C#N)C3=CC=C(C=C3)Cl',1 +'CN1CC2CC1CN2C3=C(C=C4C(=C3)N(C=C(C4=O)C(=O)O)C5CC5)F',1.69897000433602 +'C1=CC(=CC=C1C(C#N)C2=C(C=CC(=C2Cl)N3C(=O)NC(=O)C=N3)Cl)Cl',1.17609125905568 +'CC1=NC=C(N1C)[N+](=O)[O-]',1.17609125905568 +'CCN1CCN(CC1)C2=C(C=C3C(=C2)N(C=C(C3=O)C(=O)O)C4CC4)F',1.41497334797082 +'CC1C=CC=C2COC3C2(C(C=C(C3O)C)C(=O)OC4CC(CC=C(C1OC5CC(C(C(O5)C)OC6CC(C(C(O6)C)NC(=O)C)OC)OC)C)OC7(C4)C=CC(C(O7)C(C)C)C)O',0 +'COCC(=O)NC1=C(C=CC(=C1)SC2=CC=CC=C2)NC(=NC(=O)OC)NC(=O)OC',1.60205999132796 +'CC1CCC2=C3N1C=C(C(=O)C3=CC(=C2)F)C(=O)O',2.60205999132796 +'COC(=O)NC1=NC2=C(N1)C=C(C=C2)S(=O)C3=CC=CC=C3',0.301029995663981 +'CC1(C2CC3C(C(=O)C(=C(N)O)C(=O)C3(C(=O)C2=C(C4=C1C=CC=C4O)O)O)N(C)C)O',2.17609125905568 +'C1CN(CCN1CCCC(=O)C2=CC=C(C=C2)F)C3=CC=CC=N3',1.47712125471966 +'CC(C)NCC(COC1=CC=CC2=C1C3=CC=CC=C3N2)O',0.845098040014257 +'C1=CC(=CC=C1C(C#N)C2=C(C=CC(=C2Cl)N3C(=O)NC(=O)C=N3)Cl)Cl',1.36172783601759 +'CC1C=CC=C2COC3C2(C(C=C(C3O)C)C(=O)OC4CC(CC=C(C1OC5CC(C(C(O5)C)OC6CC(C(C(O6)C)NC(=O)C)OC)OC)C)OC7(C4)C=CC(C(O7)C(C)C)C)O',0.397940008672038 +'COP(=S)(OC)Oc1ccc(SC)c(C)c1',-0.346787486224656 +'C(C(C(C(C1Cl)Cl)Cl)Cl)(C1Cl)Cl',0.903089986991944 +'C(C(C(C(C1Cl)Cl)Cl)Cl)(C1Cl)Cl',0.602059991327962 +'CC(N(C)C)CN(C(=CC=C3)C1=C3)C(=CC=C2)C(=C2)S1',1.22010808804006 +'C1=C(C=C(C(=C1Cl)N)Cl)[N+](=O)[O-]',2.38021124171161 +'c(cccc1)(c1)C=C',2.60205999132796 diff --git a/original/LOAEL_log_mmol.csv b/original/LOAEL_log_mmol.csv new file mode 100755 index 0000000..6e08c2a --- /dev/null +++ b/original/LOAEL_log_mmol.csv @@ -0,0 +1,563 @@ +SMILES,LOAEL_log_mmol_kg_bw_day +'O1C(=O)C(O)=C(O)C1C(O)CO',1.76137662853832 +'C1(C)=C(C=CC(C)=CC=CC(C)=CC=CC=C(C)C=CC=C(C)C(=O)OC)C(C)(C)CCC1',2.95101092705237 +'c(cccc1)(c1)C(C)C',2.41523206875268 +'O=C(OCCCC)c(c(ccc1)C(=O)OCCCC)c1',2.66642980233607 +'O=C(OCC)c(c(ccc1)C(=O)OCC)c1',1.69992305435084 +'O=C(OC(OC(OC1C)C)C1)C',3.14412407646651 +'Oc(c(ccc1)C)c1C',4.30879341594785 +'Oc(ccc(c1C)C)c1',3.94081663065326 +'O=C(OCC)C=C',2.60605102798022 +'c(cccc1)(c1)CC',2.41532120099855 +'OCCO',2.39492662325430 +'c(ccc1C(=O)OCC(=O)OCC)cc1C(=O)OCC',2.04964162538818 +'O=C',2.56368333860036 +'O=C(O)C=CC(=O)O',2.03090237239810 +'OCC(O)CO',1.12645271808123 +'O=C(OC)c(ccc(O)c1)c1',2.00617304782278 +'O=C(OCCC)c(ccc(O)c1)c1',2.07966468441907 +'CC(CCC(=O)(O))C3CCC4C2CCC1CC(O)CCC1(C)C2CCC34C',2.87687871256153 +'OC(C(CCC1C)C(C)C)C1',2.42080757876423 +'O=C(O)C(=C)C',2.54049719303574 +'O=C(OC)c(c(O)ccc1)c1',2.62596180611118 +'Oc(cccc1)c1',2.43708305310291 +'O=C(OCCC)c(cc(O)c(O)c1O)c1',2.3902301635117 +'OCC(O)C1C(O)=C(O)C(=O)O1',2.05436782171583 +'c(cccc1)(c1)C=C',3.69543631002744 +'O=Cc(occ1)c1',3.20450009536782 +'NCCNc1cccc2ccccc12',3.37247609215110 +'CN(C)(C)CCCl',2.64921593816204 +'O=C(Nc(ccc(c1)C(=O)CCl)c1)C',2.12695072080225 +'c(ccc(c1)Cl)(c1)C(c(ccc(c2)Cl)c2)C(Cl)(Cl)Cl',4.04444942813338 +'CC(Oc1cc(Cl)c(Cl)cc1Cl)C(=O)(O)',4.491054148917 +'O=N(=O)C(=CC=C1OC)C=C1N=NC(C(O)=C2C(=O)NC(=CC=C4)C=C4N(=O)=O)=C(C=C3)C(=C2)C=C3',2.36568501290040 +'O=N(=O)C(C=C1)=CC(OCCO)=C1NCCO',3.02438986505162 +'Cc1cccc(CC)c1N(C(=O)CCl)COCC',3.73201897895503 +'CCc1cccc(CC)c1N(COC)C(=O)CCl',4.25489772423536 +'O=C(Nc(ccc(OCC)c1N)c1)C',2.21459876477238 +'Oc(ccc(N)c1)c1',2.20160364320713 +'CC(N)CC(=CC=C1)C=C1',4.43202666692597 +'O(c(ccc(c1)C=CC)c1)C',2.63429468422019 +'COc1ccc(N)cc1',2.41466474972438 +'O=C(O)c(c(N)ccc1)c1',1.69766082403086 +'Clc2cccc(c2)c1ccccc1',4.67360340221543 +'O=C(NC(C(=O)OC)Cc(cccc1)c1)C(N)CC(=O)O',3.30147753146833 +'n1c2ccc(Cl)cc2ncc1Oc3ccc(OC(C)C(=O)OCC)cc3',5.00327683569969 +'COC(=O)NS(=O)(=O)c1ccc(N)cc1',3.10691015775373 +'S=P(OC)(OC)SCN1N=Nc2ccccc2C1(=O)',5.94520088604013 +'CNC(=O)Oc1ccccc1OC(C)C',3.62167823549204 +'CC(C)(C)C(=O)C(Oc1ccc(Cl)cc1)n2cncn2',4.07003600375764 +'O=S(O)(=O)C(=CC=C1)C=C1CN(CC)=C(C=C2)C=CC2=C(C(C=C3)=CC=C3N(C)C)C(C=C4)=CC=C4N(CC)CC(C=C5)=CC(=C5)S(=O)(=O)O',2.99569446127058 +'c(c(cccc1)c1)(cccc2)c2',2.79016633269067 +'BrC(Cl)Cl',3.10044647372987 +'ClC(Cl)C(Cl)(Cl)SN2C(=O)C1CC=CCC1C2(=O)',4.46372003271591 +'O=C(Oc(c(c(ccc1)cc2)c1)c2)NC',4.11054922260167 +'CC1=C(SCCO1)C(=O)Nc2ccccc2',3.89450458533419 +'ClC1CC2C(C1Cl)C3(Cl)C(=C(Cl)C2(Cl)C3(Cl)Cl)Cl',6.18118555259066 +'O=C(O)CCl',3.49829685836143 +'ClC(=CC=C1N)C=C1',4.32760254782945 +'CC(C)OC(=O)C(O)(c1ccc(Cl)cc1)c2ccc(Cl)cc2',4.57623015760927 +'n1c(OC)nc(C)nc1NC(=O)NS(=O)(=O)c2ccccc2Cl',4.15566728690676 +'OS(=O)(=O)C(C(=CC=C2)C1=C2)=CC=C1N=NC(C(O)=C3N=NC(C(C=C5)=C4C=C5)=CC=C4S(O)(=O)=O)=CC(=C3O)CO',2.91745349144784 +'S=P(OCC)(OCC)Oc1ccc2C(C)=C(Cl)C(=O)Oc2c1',5.65653611167129 +'CNP(=O)(OC)Oc1ccc(cc1Cl)C(C)(C)C',4.86289269710557 +'n1c(N)nc(N)nc1NC2CC2',4.04449742637606 +'COC(=O)c1c(Cl)c(Cl)c(C(=O)OC)c(Cl)c1Cl',2.82212129862366 +'O=C(O)C(Cl)(Cl)C',3.70545399970477 +'Nc1cc(N)c(O)cc1',3.69597355155454 +'FC(F)(Cl)Cl',2.90638355650622 +'ClCCl',3.23010431252803 +'O=P(OC)(OC)OC=C(Cl)Cl',4.98261676287965 +'OC(c1ccc(Cl)cc1)(c2ccc(Cl)cc2)C(Cl)(Cl)Cl',4.26774140719551 +'ClC4=C(Cl)C5(Cl)C3C1CC(C2OC12)C3C4(Cl)C5(Cl)Cl',6.88185159467056 +'CN(=C1C(C=C2)=CC=C2)N(C)C(=C1)C(C=C3)=CC=C3',3.2998650117386 +'O=C(NC(=O)c(c(F)ccc1)c1F)Nc(ccc(c2)Cl)c2',4.58922787551359 +'CC1=C(C)S(=O)(=O)CCS1(=O)=O',4.32277979319225 +'O=C(NC)CSP(OC)(OC)=S',5.96238343177818 +'COc1ccc(N)c(OC)c1',2.74428856020296 +'COP(=O)OC',3.04158586769746 +'CC(=C(N(=O)=O)C=C1N(=O)=O)C=C1',3.72891101170516 +'CN(C)C(=O)C(c1ccccc1)c2ccccc2',3.90184372972497 +'N(c(cccc1)c1)c(cccc2)c2',3.73709625897028 +'C(C=C1)(=N(C=C1)CC2)C(N2=C3)=CC=C3',5.50194904825203 +'CCOP(=S)(OCC)SCCSCC',6.43839047104826 +'NC(=S)NNC(N)=S',2.20039466208170 +'O=C(N(C)C)Nc(ccc(c1Cl)Cl)c1',4.58938077582749 +'O=P(O)(O)CCCl',2.98375855767924 +'O=C(OCC)C(O1)C1(c(cccc2)c2)C',3.07133013436744 +'COC(=O)NC(=NC1=C2)NC1=CC(=C2)SC(C=C3)=CC=C3',4.30008455052816 +'CN1C=C(c2ccccc2)C(=O)C(c3cc(C(F)(F)F)ccc3)=C1',4.11967251914367 +'c1cc(C(F)(F)F)cc(Cl)c1NC(C(C)C)C(=O)OC(C(#N))c2cccc(Oc3ccccc3)c2',5.30355258529792 +'S=P(OCC)(Sc1ccccc1)CC',5.192858916992 +'n1c(C)nc(OC)nc1NC(=O)NS(=O)(=O)c2ccsc2C(=O)OC',4.19021010110931 +'C(C(C(C(C1Cl)Cl)Cl)Cl)(C1Cl)Cl',4.76466896003284 +'O=N(=O)N(CN1N(=O)=O)CN(C1)N(=O)=O',5.17048924956396 +'O=C(N=C(N(C1(=O))C)N(C)C)N1C(CCCC2)C2',3.70296927879496 +'n(c(c(ccc1)cc2)c1O)c2',3.00650487851870 +'c1cc(Cl)cc(Cl)c1C(OCC=C)Cn2cncc2',3.87095923630552 +'COc1cccc(OC)c1C(=O)Nc2onc(C(C)(CC)CC)c2',3.81664542550781 +'n1c(OC)cc(OC)nc1NC(=O)NS(=O)(=O)Cc2ccccc2C(=O)OC',3.12325069281768 +'CCOC(=O)CC(SP(=S)(OC)OC)C(=O)OCC',3.82001485148442 +'CN(C)(CCC1)CC1',2.88160770091708 +'O=P(SCCCC)(SCCCC)SCCCC',5.40072574498715 +'COCC(=O)N(C(C)C(=O)OC)c1c(C)cccc1C',3.65023995836629 +'S=P(OC)(OC)SCN1C(=O)SC(OC)=N1',5.17945311726922 +'CNC(=O)ON=C(C)SC',4.21007789203115 +'COP(=S)(OC)Oc1ccc(cc1)N(=O)(=O)',6.02235818715591 +'O=C1N(N)C(SC)=NN=C1C(C)(C)C',4.15490651136806 +'COP(=O)(OC)OC(Br)C(Cl)(Cl)Br',5.27964840060116 +'OC(C(N)C1O)C(C)OC1(C)OC(CC(C)(C(C2O)C(O)=O)OC(O)(C2)CC(O)CC(C)(O3)C3C=C4)C=CC=CC=CC=CCC(C)OC4=O',3.99258108069112 +'O=N(=O)c(ccc(c1N)C)c1',4.27918373941654 +'O=N(=O)c(c(N)ccc1N)c1',3.24556564669417 +'O=C(O)C(=C(N)C=C1N(=O)=O)C=C1',2.18667157840130 +'O=N(=O)c(c(c(ccc1)cc2)c1)c2',3.0209838975238 +'c12c(N=Nc3ccccc3)c(O)ccc1cc(S(=O)(=O)O)cc2',3.26105456902449 +'CC(C)Oc1cc(c(Cl)cc1Cl)N2N=C(OC2(=O))C(C)(C)C',4.83912722706429 +'CNC(=O)ON=C(SC)C(=O)N(C)C',4.64199221806157 +'CCOP(=S)(OCC)Oc1ccc(cc1)N(=O)=O',4.92021372679140 +'Oc(c(c(c(c1Cl)Cl)Cl)Cl)c1Cl',4.42543075349016 +'NC(=N)NC(=N)NCCc1ccccc1',3.44898061811695 +'COP(=S)(OC)SCN2C(=O)c1ccccc1C2(=O)',4.20046887469431 +'CCN(CC)C(=O)C(Cl)=C(C)OP(=O)(OC)OC',4.38676470716829 +'ClC3C6(Cl)C4C2C1OC1C5C2C3(Cl)C(Cl)(C45)C6(Cl)Cl',5.73572355899233 +'O=C(OC(=O)c1cccc2)c12',2.09688233455707 +'Nc1c(Cl)c(Cl)nc(C(=O)(O))c1Cl',3.60469254298773 +'CCN(CC)c1nc(C)cc(OP(=S)(OC)OC)n1',5.08683453410041 +'Nc3ccc2cc1ccc(N)cc1nc2c3',3.64856042750458 +'CCC(=O)Nc1ccc(Cl)c(Cl)c1',4.03758556402413 +'Clc1cc(Cl)ccc1C2(Cn3ncnc3)OC(CCC)CO2',4.13636586052483 +'O=C(N)c(nccn1)c1',2.19322585277166 +'Oc1cc(O)c2C(=O)C(O)=C(c3cc(O)c(O)cc3)Oc2c1',2.17199481319419 +'CCC(O)(C)C#C',3.32910149752408 +'CC(C(NCC)=C1)=CC(C1=O2)=C(C(C2=C3)=CC(C)=C3NCC)C(=CC=C4)C(=C4)C(=O)OCC',4.56776852431159 +'O=C(NS(=O)(=O)c1cccc2)c12',1.70634501494627 +'c1cc(Cl)ccc1C2SC(=O)N(C(=O)NC3CCCCC3)C2C',3.34350563448343 +'n(c(nc(n1)NCC)NCC)c1Cl',4.60564260851438 +'O=C(OCC(C1OCC(C1O)O)O)CCCCCCCCCCC',1.70187402783236 +'O(CC1O)C(C1O)C(O)COC(=O)CCCCCCCCCCCCCCCCC',1.77657920852493 +'O=S(=O)(Nc(nc(cc1C)C)n1)c(ccc(N)c2)c2',3.92604632938062 +'CCNc1nc(NC(C)(C)C)nc(SC)n1',4.2065674883771 +'Oc(c(cc(c1)C(C)(C)C)Cl)c1',2.93192524190336 +'C(C(Cl)Cl)(Cl)Cl',3.19149572716769 +'COP(=O)(OC)OC(=CCl)c1cc(Cl)c(Cl)cc1Cl',3.5634357799466 +'CCN(CC)C(=O)SCc1ccc(Cl)cc1',4.71227844003234 +'COC(=O)NC(=S)Nc1ccccc1NC(=S)NC(=O)OC',4.0293761165818 +'N(C(=S)SSC(N(C)C)=S)(C)C',4.20490259955842 +'c12OC(CCCC(C)CCCC(C)CCCC(C)C)(C)CCc1c(C)c(OC(=O)C)c(C)c2C',2.37359490910830 +'Cc1cc(N)ccc1NOS(O)(=O)=O',3.07409722667645 +'C(Br)(C(Br)(Br)Br)C1C(C)(C)C1C(=O)OC(C(#N))c2cccc(Oc3ccccc3)c2',5.34570506657104 +'O=C(O)COc(c(cc(c1Cl)Cl)Cl)c1',4.40736115725459 +'FC(F)(F)C(=CC(N(=O)=O)=C1N(C(C)C)C(C)C)C=C1N(=O)=O',3.92334642542511 +'Cc1cc(C)c(N)cc1C',3.33165612180841 +'CC(O)(C(O)C(O1)C)CC1(C)OC(C(C)O2)C(C(O)C2(C)OC(C(C)C(O)CC(=O)OC(CC)C3COC(C(OC)C4OC)OC(C)C4O)C(CC=O)CC(C)C(=O)C=CC(=C3)C)N(C)C',3.27607248348466 +'c1c(Cl)cc(Cl)cc1N2C(=O)C(C)(C=C)OC2(=O)',3.59380666266014 +'O=C(OC(CCCC(O)CCCCCc1cc(O)cc2O)C)c12',6.20735970305 +'COC(=O)C1(C2=CC=CC=C2C3=C1C=C(C=C3)Cl)O',3.26276588262396 +'CC(C(=O)O)OC1=CC(=CC=C1)Cl',3.30237197471763 +'P12P3P1P23',1.92514612424786 +'C(CO)O',2.19080664059838 +'CCCCOCC(C)OCC(C)O',3.17218289921228 +'C(CO)O',1.49183663626236 +'C(CO)O',1.82907880458079 +'[O-][As](=O)([O-])[O-]',4.34688225631145 +'[Si](CN1C=NC=N1)(C2=CC=C(C=C2)F)C3=CC=C(C=C3)F',5.1159116373222 +'N(C(=S)SSC(N(C)C)=S)(C)C',4.32029601826049 +'COP(=O)(N)SC',5.19537431180606 +'N(C(=S)SSC(N(C)C)=S)(C)C',4.64300653228067 +'COP(=O)(NC(=O)(C))SC',3.71877648742193 +'C1=CC=C(C=C1)NC(=O)NC2=CN=NS2',3.86579667362138 +'CCOP(=S)(NC(C)C)OC1=CC=CC=C1C(=O)OC(C)C',5.83934493677328 +'CC(=NOC(=O)N(C)SN(C)C(=O)ON=C(C)SC)SC',4.54957865212472 +'CCOP(=S)(OCC)OC1=NC(=NC(=C1)C)C(C)C',5.3072756271046 +'NC(CCCC1)C1',3.22924248946341 +'CN1C=C(c2ccccc2)C(=O)C(c3cc(C(F)(F)F)ccc3)=C1',4.00572916683684 +'ClC1CC2C(C1Cl)C3(Cl)C(=C(Cl)C2(Cl)C3(Cl)Cl)Cl',5.91357931241363 +'CCCCC(CC)COC(=O)C1=CC=CC=C1C(=O)OCC(CC)CCCC',3.29065345190954 +'OC(=O)CNCP(O)(O)=O',2.22807446683025 +'C1CNC(=S)N1',5.64754514108144 +'O=C(N(OC)C)Nc(ccc(c1Cl)Cl)c1',4.6004830749906 +'C1=CC=C2C(=C1)NC(=S)S2',2.34830823871711 +'CCOP(=S)(OCC)OC1=NC(=C(C=C1Cl)Cl)Cl',4.54479494223028 +'c(c(c(c(c1Cl)Cl)Cl)Cl)(c1Cl)Cl',5.99211484281248 +'COc1ccc(cc1)C(c2ccc(OC)cc2)C(Cl)(Cl)Cl',3.44172416093488 +'C1=CC(=CC=C1Cl)Cl',2.690201870583 +'CC(C)OC(=O)NC1=CC(=CC=C1)Cl',2.63075480518045 +'COP(=O)(OC)OC=C(Cl)Cl',5.01190613898164 +'CCOP(=S)(OCC)Oc1ccc(cc1)N(=O)=O',5.84103248074378 +'CNC(=O)N(C)c1nnc(s1)C(C)(C)C',3.75647357868479 +'CCCCOCCOCCOCC1=CC2=C(C=C1CCC)OCO2',3.13153975286541 +'CC(C(=O)O)OC1=C(C=C(C=C1)Cl)Cl',4.41694364962485 +'CC1(C(C1C(=O)OC(C#N)C2=CC(=C(C=C2)F)OC3=CC=CC=C3)C=C(Cl)Cl)C',4.54086743953507 +'C(#N)c(c(c(c(c1C(#N))Cl)Cl)Cl)c1Cl',4.82267631193248 +'O=C(OCC)C(O)(c(ccc(c1)Cl)c1)c(ccc(c2)Cl)c2',4.24731476483975 +'O=C(N(C)C)Nc(ccc(c1)Cl)c1',3.2011773320931 +'O=C(N(SC(Cl)(Cl)Cl)C(=O)C1CC=CC2)C12',3.47797354595327 +'CCc1cccc(C)c1N(C(C)COC)C(=O)CCl',3.27691146056582 +'C1=CC(=C(C=C1Cl)Cl)OCC(=O)O',4.64549583771218 +'CCNC1=NC(=NC(=N1)Cl)NC(C)(C)C#N',5.2845529417803 +'C(C(C(C(C1Cl)Cl)Cl)Cl)(C1Cl)Cl',4.80088113268728 +'COP(=S)(OC)OC1=CC(=C(C=C1Cl)Cl)Cl',3.80827186579208 +'C1C2C=CC1C3C2C4(C(=C(C3(C4(Cl)Cl)Cl)Cl)Cl)Cl',7.56218566972996 +'CC1(C(C1C(=O)OCC2=CC(=CC=C2)OC3=CC=CC=C3)C=C(Cl)Cl)C',4.19455618753918 +'CCN(CC)C(=O)C(C)OC1=CC=CC2=CC=CC=C21',3.43353645191675 +'ClC1C=CC2C1C3(Cl)C(=C(Cl)C2(Cl)C3(Cl)Cl)Cl',6.17413857281627 +'CC(=CC(=O)NC)OP(=O)(OC)OC',5.6954106911713 +'CC(C)C1(C)N=C(NC1(=O))c3nc2ccccc2cc3C(=O)(O)',4.19219820184676 +'CC(C)Nc1nc(Cl)nc(NC(C)C)n1',3.66220959497816 +'CC(C(=O)O)(Cl)Cl',3.45627084235452 +'CC1(C(C1C(=O)OC(C#N)C2=CC(=C(C=C2)F)OC3=CC=CC=C3)C=C(Cl)Cl)C',4.76271618915143 +'O=C(NC)CSP(OC)(OC)=S',4.6613534361142 +'C12C3(C4(C5(C3(C(C1(C5(C2(C4(Cl)Cl)Cl)Cl)Cl)(Cl)Cl)Cl)Cl)Cl)Cl',7.70850413051807 +'COC(=O)C1=CC=CC=C1C(=O)OC',1.98718344722018 +'CCOP(=S)(OCC)SCSC(C)(C)C',6.76107133056166 +'CCC(C)SP(=O)(OCC)SC(C)CC',6.0340541201743 +'CCOP(=S)(OCC)SCSC(C)(C)C',5.1590113392337 +'C1C(C(C(=O)N1C2=CC=CC(=C2)C(F)(F)F)Cl)CCl',4.79534478918374 +'O=C(O)C(C(C(=O)O)C(O1)CC2)C12',3.20919319571953 +'O=C(Oc(c(OC(C1)(C)C)c1cc2)c2)NC',4.64591798599928 +'Oc(c(c(c(c1)Cl)Cl)Cc(c(c(cc2Cl)Cl)Cl)c2O)c1Cl',4.9105214638308 +'CC1(CON(C1=O)CC2=CC=CC=C2Cl)C',4.04722605916309 +'CCC(C)N1C(=O)C(=C(NC1=O)C)Br',3.6209530011803 +'CC1=CC(=CC(=C1N(C)C)C)OC(=O)NC',5.17081600643967 +'CNC(=O)OC1=CC=CC(=C1)N=CN(C)C',4.24798445482129 +'CC1=NN(C(=O)N1C(F)F)C2=CC(=C(C=C2Cl)Cl)NS(=O)(=O)C',3.76184922452045 +'CCOP(=S)(CC)SC1=CC=CC=C1',4.6925459996104 +'CCOP(=S)(OCC)SC(CCl)N1C(=O)C2=CC=CC=C2C1=O',5.19738625502110 +'N1CC(C)(C)CNC1=NN=C(C=Cc2ccc(C(F)(F)F)cc2)C=Cc3ccc(C(F)(F)F)cc3',4.99517458001903 +'CC1=C(C(=C(C(=C1F)F)COC(=O)C2C(C2(C)C)C=C(C(F)(F)F)Cl)F)F',4.9591800647055 +'CC1=CC(=C(C=C1)N=CN(C)C=NC2=C(C=C(C=C2)C)C)C',4.45886884853594 +'S=P(OC)(OC)SCN1C(=O)SC(OC)=N1',5.57739312594126 +'CC(C)N(C(C)C)C(=O)SCC(Cl)=C(Cl)Cl',4.38691132629296 +'S=P(OC)(OC)SCN1N=Nc2ccccc2C1(=O)',5.14932086869605 +'CC1=NC(=NC(=N1)OC)NC(=O)NS(=O)(=O)C2=CC=CC=C2CCC(F)(F)F',3.72005974473228 +'O=C(N(S(=O)(=O)Nc1cccc2)C(C)C)c12',3.77865560759679 +'CCN(CC)c1nc(C)cc(OP(=S)(OC)OC)n1',4.34489545637121 +'O=C(ON=CC(SC)(C)C)NC',6.27935493374302 +'ClC(Cl)(Cl)CC1(OC1)c2cc(Cl)cc(Cl)c2',4.02860782189294 +'CCC1CCCC(C(C(=O)C2CC3C(C2CC(=O)O1)CCC4C3CC(C4)OC5CC(C(C(C5OC)OC)OC)C)C)OC6CCC(C(O6)C)N(C)C',4.48549336200642 +'CC(C)(C)C(=NOC(=O)NC)CSC',4.56093515068149 +'CON=C(CC1=CN=CC=C1)C2=C(C=C(C=C2)Cl)Cl',3.81685069684023 +'CC(=CC1C(C1(C)C)C(=O)OCN2C(=O)C3=C(C2=O)CCCC3)C',3.12242048929166 +'C1COC(O1)(CN2C=NC=N2)C3=C(C=C(C=C3)Cl)Cl',4.47732480426449 +'CCCOC(=O)C1=CN=C(C=C1)C(=O)OCCC',3.00221511481659 +'CC1=CC(=NC(=N1)NC(=O)NS(=O)(=O)C2=CC=CC=C2C(=O)OC3COC3)C',3.68988952034363 +'C1=C(C(=NC(=C1Cl)Cl)OCC(=O)O)Cl',3.85273501931079 +'CCOCN1C(=C(C(=C1C(F)(F)F)Br)C#N)C2=CC=C(C=C2)Cl',4.47670895789257 +'CC(C)CC1=C(C(=NC(=C1C(=O)SC)C(F)(F)F)C(F)F)C(=O)SC',5.04368703263975 +'CC12CC1(C(=O)N(C2=O)C3=CC(=CC(=C3)Cl)Cl)C',4.27743796844594 +'CC1=CC(=C(C=C1)C(=O)OC)C2=NC(C(=O)N2)(C)C(C)C',3.76093729967937 +'COP(=S)(OC)OC1=NC(=C(C=C1Cl)Cl)Cl',5.03145309127161 +'CC(C)CC1=C(C(=NC(=C1C(=O)OC)C(F)F)C(F)(F)F)C2=NCCS2',3.95268441956944 +'CCOC(=O)C(CC1=CC(=C(C=C1Cl)F)N2C(=O)N(C(=N2)C)C(F)F)Cl',4.53591743757444 +'CC(C)=CC3C(C(=O)OCc2coc(Cc1ccccc1)c2)C3(C)C',3.4325717246993 +'CCCSP(=S)(OCC)OC1=CC=C(C=C1)SC',4.44776025923588 +'CC1=CC(=C(C(=C1)OC(=O)NC)C)C',3.513780491163 +'CC1=CC=CC=C1COC2CC3(CCC2(O3)C)C(C)C',3.26228942932097 +'CC1=C2C(=CC=C1)SC3=NN=CN23',3.78564431476757 +'CCC(=C1C(=O)CC(CC1=O)CC(C)SCC)NOCC=CCl',3.55619540984755 +'CCCN(CCC)C(=O)SCC',4.32294999482974 +'CC(C)OC(=O)C=C(C)C=CCC(C)CCCC(C)(C)OC',3.82926385227003 +'COP(=S)(OC)Oc1ccc(SC)c(C)c1',4.87052572632858 +'COC1=C(C=C(C=C1)C(=CC(=O)N2CCOCC2)C3=CC=C(C=C3)Cl)OC',3.92309028461827 +'CCSC(=O)N(CC(C)C)CC(C)C',3.33720244245390 +'CC(C)OP(=S)(OC(C)C)SCCNS(=O)(=O)C1=CC=CC=C1',4.42326053700057 +'CC(=CC1C(C1(C)C)C(=O)OCC2=CC(=CC=C2)OC3=CC=CC=C3)C',3.36853572230648 +'CC1=CC(=CC(=C1C)C)OC(=O)NC',4.28610219788592 +'CCOP(=S)(OCC)SCSC1=CC=C(C=C1)Cl',5.53512353543065 +'C1CN(CCN1C(C(Cl)(Cl)Cl)NC=O)C(C(Cl)(Cl)Cl)NC=O',3.63845107729718 +'C(=CC=C1)(C2=C1)NC(=N2)C(=CS3)N=C3',5.00270088682186 +'C1(=C(C(=C(C(=C1Cl)Cl)Cl)Cl)Cl)[N+](=O)[O-]',3.37340446386955 +'CCCC(=NOCC)C1C(=O)CC(CC1=O)CC(C)SCC',4.29612718117234 +'ClC2(Cl)C4(Cl)C1(Cl)C5(Cl)C(Cl)(Cl)C3(Cl)C1(Cl)C2(Cl)C3(Cl)C45Cl',5.89173094758972 +'CCN(C1CCCCC1)C(=O)SCC',4.85603479370532 +'CC1=NC(=NC(=N1)OC)NC(=O)NS(=O)(=O)C2=CC=CC=C2OCCCl',3.260038251795 +'C(C(=O)O)OC1=NC(=C(C(=C1Cl)N)Cl)F',2.70762229375841 +'CC1=C(C(=O)CC1OC(=O)C2C(C2(C)C)C=C(C)C)CC#C',3.49996484386965 +'C1C(COC1(CN2C=NC=N2)C3=C(C=C(C=C3)Cl)Cl)Br',4.76483992624863 +'C1=NNC(=N1)N',4.52675248773797 +'C1=CC(=C(C(=C1)F)C(=O)NC(=O)NC2=CC(=C(C(=C2F)Cl)F)Cl)F',4.16607614499238 +'C1=CC(=CC=C1OS(=O)(=O)C2=CC=C(C=C2)Cl)Cl',5.08373349418451 +'FC(F)(F)C(=CC(N(=O)=O)=C1N(C(C)C)C(C)C)C=C1N(=O)=O',2.52540641675307 +'CC1=C(C(=O)CC1OC(=O)C2C(C2(C)C)C=C(C)C)CC=C',3.60553192639024 +'C1=CC(=C(C(=C1)Cl)C#N)Cl',4.83761727241192 +'C1C(O1)COC2=CC=CC=C2C3=CC=CC=C3',2.65565785542345 +'CC1=CC=CC=C1OCC2=CC=CC=C2C(=NOC)C(=O)OC',2.92199532671878 +'O=N(=O)C(C(=C1N(=O)=O)N(C(C)C)C(C)C)=CC(=C1)S(=O)(=O)N',3.97297179822463 +'C1=CC(=C(C2=NC=C(C=C21)Cl)C(=O)O)Cl',2.50482391995124 +'CC(C)NC(=O)N1CC(=O)N(C1=O)C2=CC(=CC(=C2)Cl)Cl',3.85597533208895 +'CCCN(CCCl)C1=C(C=C(C=C1[N+](=O)[O-])C(F)(F)F)[N+](=O)[O-]',3.24487034075484 +'C1=CC=C(C=C1)C2=CC=CC=C2O',2.23097792739447 +'O=C(N(C)C)Nc(cccc1C(F)(F)F)c1',4.18977535089103 +'C1=CC(=NC(=C1)Cl)C(Cl)(Cl)Cl',5.36343657222619 +'Clc1cc(Cl)cc(Cl)c1OCCN(CCC)C(=O)n2cncc2',4.7008945110302 +'CC1=CC(=C(C=C1NC(=O)C)NS(=O)(=O)C(F)(F)F)C',4.05086251778066 +'C(=C(I)I)(I)I',4.02664705683052 +'C1=C(C=C(C(=C1Cl)N2C(=C(C(=N2)C#N)S(=O)C(F)(F)F)N)Cl)C(F)(F)F',6.8624770260417 +'O=C(N(C)C)Nc(ccc(c1Cl)Cl)c1',4.57165200886706 +'CC1=C(C(=O)CC1OC(=O)C2C(C2(C)C)C=C(C)C)CC=C',4.09142710541740 +'CC1=CC2=C(C=C1)N=C3C(=N2)SC(=O)S3',4.49470628000702 +'CC(C)N(C(=O)CCl)c1ccccc1',3.96396832169828 +'CC(C)C1(C(=O)NC(=N1)C2=C(C=CC=N2)C(=O)O)C',2.71813034538638 +'CC1(C(C1(C)C)C(=O)OC(C#N)C2=CC(=CC=C2)OC3=CC=CC=C3)C',4.25443178297333 +'CN1CN(C(=S)SC1)C',3.73313384224274 +'ClC(Cl)=CC1C(C)(C)C1C(=O)OC(C(#N))c2cccc(Oc3ccccc3)c2',3.74434218472656 +'ClC2C1OC1C3C2C4(Cl)C(=C(Cl)C3(Cl)C4(Cl)Cl)Cl',6.28927348401756 +'CCOC(=O)CN1C2=C(C=CC=C2Cl)SC1=O',4.33721159291063 +'CCCN(CCC)C1=C(C=C(C(=C1[N+](=O)[O-])N)C(F)(F)F)[N+](=O)[O-]',4.0760849833355 +'C1=CC=C(C=C1)C(CCC2=CC=C(C=C2)Cl)(CN3C=NC=N3)C#N',3.92533540454444 +'CC(C)(C)C(CCC1=CC=C(C=C1)Cl)(CN2C=NC=N2)O',4.28689742390489 +'CC1=C(C=CC=C1COC(=O)C2C(C2(C)C)C=C(C(F)(F)F)Cl)C3=CC=CC=C3',4.92723460128442 +'C(=CC=C1)(C2=C1)NC(=N2)C(=CS3)N=C3',3.70167089115788 +'C1=C(C=C(C(=C1Cl)N)Cl)[N+](=O)[O-]',3.13990879364539 +'CC1=C(C=C(C=C1C(=O)N)[N+](=O)[O-])[N+](=O)[O-]',4.55660790505055 +'CC(C)OC1=CC=CC(=C1)NC(=O)C2=CC=CC=C2C(F)(F)F',2.81064866255668 +'OC(c1ccc(Cl)cc1)(c2ccc(Cl)cc2)C(Cl)(Cl)Cl',5.17083139418745 +'O=P(O)(O)CCCl',2.51051495802278 +'CN(C(=O)NC1=CC=C(C=C1)Br)OC',4.31655713179121 +'CC1=CC(=CC=C1)NC(=O)OC2=CC=CC(=C2)NC(=O)OC',4.0796286862285 +'CC(C)(C)C1=NN=C(S1)N2C(CN(C2=O)C)O',3.70982035175725 +'S=P(OCC)(OCC)Oc1ccc2C(C)=C(Cl)C(=O)Oc2c1',5.32917717728496 +'COC(=O)c1ccccc1S(=O)(=O)NC(=O)N(C)c2nc(OC)nc(C)n2',4.50011608554638 +'C1=CC=C(C(=C1)NC2=NC(=NC(=N2)Cl)Cl)Cl',5.37945812670042 +'CC1=C(C=CC(=C1)OP(=S)(OC)OC)[N+](=O)[O-]',5.78008872366218 +'COc1c(Cl)ccc(Cl)c1C(=O)(O)',3.28376800169458 +'CC1(C(C1C(=O)OC(C#N)C2=CC(=CC=C2)OC3=CC=CC=C3)C=C(Br)Br)C',5.30552261110582 +'C1=CC=C(C(=C1)C(C2=CC=C(C=C2)F)(C3=CN=CN=C3)O)Cl',5.10001384041789 +'c1ccc2nc(NC(=O)OC)n(C(=O)NCCCC)c2c1',3.40217570413585 +'CCOC(=O)COC(=O)C1=C(C=CC(=C1)OC2=C(C=C(C=C2)C(F)(F)F)Cl)[N+](=O)[O-]',4.25309221972639 +'CC(C)(C)C(C(N1C=NC=N1)OC2=CC=C(C=C2)C3=CC=CC=C3)O',4.13022504615292 +'CCNC(=O)NC(=O)C(=NOC)C#N',3.81561566158005 +'CCOC1=C(C=CC(=C1)OC2=C(C=C(C=C2)C(F)(F)F)Cl)[N+](=O)[O-]',3.95628893719942 +'CC1=NC=C(N1CCO)[N+](=O)[O-]',3.05729569283336 +'O=C(N(SC(Cl)(Cl)Cl)C(=O)c1cccc2)c12',2.77313899543591 +'CC(C)(C)c2ccc(OC1CCCCC1OS(=O)OCC#C)cc2',3.54465374823881 +'CCCCC(CN1C=NC=N1)(C2=C(C=C(C=C2)Cl)Cl)O',4.82512253178873 +'CC(C)(C)C(C(=CC1=C(C=C(C=C1)Cl)Cl)N2C=NC=N2)O',3.81454188371475 +'C1=CC(C2C1C3(C(=C(C2(C3(Cl)Cl)Cl)Cl)Cl)Cl)Cl',5.9922949848715 +'C1=CC=C2C(=C1)C(=O)C3=C(C2=O)SC(=C(S3)C#N)C#N',4.47176647572299 +'CC1=NN(C(=C1C=NOCC2=CC=C(C=C2)C(=O)OC(C)(C)C)OC3=CC=CC=C3)C',5.13623540476555 +'CS(=O)(=O)C1=C(C=CC(=C1)C(F)(F)F)C(=O)C2=C(ON=C2)C3CC3',4.25445174537182 +'CC1=C(N=C(N=C1OC(=O)N(C)C)N(C)C)C',4.28018891498254 +'CCN(CC)C(=O)C(Cl)=C(C)OP(=O)(OC)OC',5.30057855955201 +'C1=CC(=CC=C1C(CN)O)O',2.78725763359614 +'CC1=C(C(=CC=C1)C)N(C(=O)COC)N2CCOC2=O',3.74554900711723 +'c1c(C(F)(F)F)cccc1N2C(=O)C(Cl)=C(NC)C=N2',4.20939714153443 +'CCC(C)NC1=C(C=C(C=C1[N+](=O)[O-])C(C)(C)C)[N+](=O)[O-]',3.77134379610358 +'C1=CC(=CC=C1S(=O)(=O)C2=CC(=C(C=C2Cl)Cl)Cl)Cl',3.18978539843532 +'CCCCC1=C(NC(=NC1=O)NCC)C',3.92280444363211 +'n(c(nc(n1)NCC)NCC)c1Cl',4.58033674324961 +'FC(F)(F)C(C=C1N(=O)=O)=CC(N(=O)=O)=C1N(CC)CC(C)=C',4.42587730748324 +'C1CCC(C1)N(CC2=CC=C(C=C2)Cl)C(=O)NC3=CC=CC=C3',4.11903913677133 +'CS(=O)(=O)NC(=O)C1=C(C=CC(=C1)OC2=C(C=C(C=C2)C(F)(F)F)Cl)[N+](=O)[O-]',3.94325990345253 +'CCOC(=O)C(C)OC1=CC=C(C=C1)OC2=NC3=C(O2)C=C(C=C3)Cl',4.60419765136131 +'CCC1=C(C(=CC=C1)CC)N(CNC(=O)C)C(=O)CCl',3.67657281690409 +'NC(=N)NCCCCCCCCCCCC(OC(=O)C)',3.99309483347533 +'C1=CC(=CC(=C1)Cl)NC(=O)OCC#CCCl',2.75857660132254 +'CC(C)C(C(=O)OC(C(#N))c2cccc(Oc1ccccc1)c2)c3ccc(Cl)cc3',4.22520594870835 +'CC(C)C1=C(C=CC(=C1)C(C)(C)C2=CC(=C(C=C2)O)C(C)C)O',4.09683471023993 +'CCN(CC1=C(C=CC=C1Cl)F)C2=C(C=C(C=C2[N+](=O)[O-])C(F)(F)F)[N+](=O)[O-]',3.92606530797808 +'CCCCCCCCSC(=O)OC1=CC(=NN=C1C2=CC=CC=C2)Cl',3.74923930876524 +'CC1=C(C(=O)CC1OC(=O)C2C(C2(C)C)C=C(C)C)CC=C',4.3407141033807 +'CCCCNC(=O)N1C2=CC=CC=C2N=C1NC(=O)OC',3.06493353581742 +'CC1=C(C(=CC=C1)C)N(C(C)C(=O)OC)C(=O)CC2=CC=CC=C2',3.84966174557959 +'CC(C)C(C1=CC=C(C=C1)OC(F)F)C(=O)OC(C#N)C2=CC(=CC=C2)OC3=CC=CC=C3',4.87646988000983 +'Clc1ccccc1c2nnc(c3ccccc3Cl)nn2',4.1806220183605 +'CCOC(=O)NCCOC1=CC=C(C=C1)OC2=CC=CC=C2',4.4790525467538 +'CCC1=C(C(=CC=C1)CC)N(CC(=O)OCC)C(=O)CCl',3.79491137150459 +'c1(O2)c(CC2(C)C)cccc1OC(=O)N(C)SN(CCCC)CCCC',4.18246564622765 +'CCCCOC(=O)C(C)OC1=CC=C(C=C1)OC2=NC=C(C=C2)C(F)(F)F',5.10648736510651 +'COC1=CC(=C(C=C1Cl)OC)Cl',3.21917344408706 +'CCOP(=S)(OCC)OC1=NN(C(=N1)Cl)C(C)C',4.39966173548004 +'n(c(nc(n1)NC(C)C)NCC)c1Cl',3.93587643048823 +'CC(C)(C)C(C(=CC1=CC=C(C=C1)Cl)N2C=NC=N2)O',3.8694430122441 +'CCCCCCCCc1cc(N(=O)(=O))c(OC(=O)C=CC)c(c1)N(=O)(=O)',3.8625999735624 +'c1cc(OC(F)(F)F)ccc1C(O)(C(C)C)c2cncnc2',4.41176854866759 +'COP(=O)(C(C(Cl)(Cl)Cl)O)OC',4.10964043198952 +'C1=CC(=C(C=C1C(F)(F)F)Cl)OC2=CC(=C(C=C2)[N+](=O)[O-])C(=O)O',3.46138721019571 +'CCCN(CC1CC1)C2=C(C=C(C=C2[N+](=O)[O-])C(F)(F)F)[N+](=O)[O-]',4.8417219607834 +'CCOC(=O)C(C)OC(=O)C1=C(C=CC(=C1)OC2=C(C=C(C=C2)C(F)(F)F)Cl)[N+](=O)[O-]',3.96545863474241 +'CCSC(=O)N1CCCCCC1',4.10198823735002 +'CCC1=CC=C(C=C1)C(=O)NN(C(=O)C2=CC(=CC(=C2)C)C)C(C)(C)C',3.86588082257473 +'ClC(Cl)C(Cl)(Cl)SN2C(=O)C1CC=CCC1C2(=O)',4.36681001970786 +'COC(=O)C1=CC=CC=C1S(=O)(=O)NC(=O)NC2=NC(=CC(=N2)OC(F)F)OC(F)F',3.52443042732356 +'CC(C)(C)C(C(N1C=NC=N1)OC2=CC=C(C=C2)Cl)O',4.07300621285581 +'CC1=C(C=CC(=C1)Cl)OCC(=O)O',4.70031198338967 +'COC=C(C1=CC=CC=C1OC2=NC=NC(=C2)OC3=CC=CC=C3C#N)C(=O)OC',3.81158305905272 +'C1=CC=C(C(=C1)C(C2=CC=C(C=C2)Cl)(C3=CN=CN=C3)O)Cl',5.15835722073531 +'[O-]Br(=O)=O',4.3215481796762 +'OP(=O)OCC',2.4395258763695 +'COP(N)(=O)SC',6.14961682124539 +'CCOP(=O)(NC(C)C)Oc1ccc(SC)c(C)c1',5.30586339308612 +'CCOP(=S)(OCC)SCCSCC',6.8363304797203 +'CCOP(=S)(OCC)SCSP(=S)(OCC)OCC',5.28383935473594 +'O=C(OCC(CCCC)CC)CCCCC(=O)OCC(CCCC)CC',2.39277487311710 +'CN(C=Nc1ccc(C)cc1C)C=Nc2ccc(C)cc2C',4.46746902029786 +'O=C(N(S(=O)(=O)Nc1cccc2)C(C)C)c12',3.83664755457448 +'S=P(OC)(OC)SCN1C(=O)SC(OC)=N1',5.38357309992515 +'C(#N)Cl',2.94356799915553 +'C(#N)Br',2.93862388168010 +'C1=CC(=CC=C1C(C2=CC=C(C=C2)Cl)C(Cl)(Cl)Cl)Cl',6.15165939778125 +'c(cccc1)(c1)C(C)C',2.56004605053309 +'CCCN(CCC)C(=O)SCC',3.87925249559703 +'NC(CCCC1)C1',3.21824710516194 +'ClC1CC2C(C1Cl)C3(Cl)C(=C(Cl)C2(Cl)C3(Cl)Cl)Cl',4.83439806636601 +'CC(C)OC(=O)NC1=CC(=CC=C1)Cl',2.32972480951647 +'COC(=O)c1c(Cl)c(Cl)c(C(=O)OC)c(Cl)c1Cl',4.52109130295968 +'COC(=O)C1=CC=C(C=C1)C(=O)OC',3.19130342987610 +'N(C(=S)NC1)C1',5.611332968427 +'O=C(N(OC)C)Nc(ccc(c1Cl)Cl)c1',4.99842308366263 +'c(cccc1)(c1)C=C',2.56281074475285 +'COC(=O)c1ccccc1S(=O)(=O)NC(=O)Nc2nc(OC)nc(C)n2',3.18339945768247 +'C1=CC(=CC=C1N)Cl',4.00884378520503 +'FC(F)(F)C(Cl)=CC1C(C)(C)C1C(=O)OC(C(#N))c2cc(Oc3ccccc3)ccc2',4.55615777900042 +'C(Cl)(Br)Br',3.86380195834146 +'C=C(Cl)Cl',3.84038967397096 +'C(C=CCl)Cl',4.33763486202989 +'COP(=O)(OC)OC(=CCl)c1cc(Cl)c(Cl)cc1Cl',3.86446577561058 +'Oc(ccc(c1)C(c(ccc(O)c2)c2)(C)C)c1',3.65950992099517 +'O=C(OCc(cccc1)c1)c(c(ccc2)C(=O)OCCCC)c2',2.82255713911138 +'O=C(NCCCC1)C1',2.95677386828604 +'c(cccc1)(c1)Cl',2.97219087736775 +'C(Cl)(Cl)Cl',3.29877173860401 +'ClCCl',3.20825373509371 +'C1C2C3C(C1C4C2O4)C5(C(=C(C3(C5(Cl)Cl)Cl)Cl)Cl)Cl',6.48391158599853 +'OCCO',1.79286663192634 +'O=C(C=C(CC1(C)C)C)C1',2.88767656912200 +'C(F)(Cl)(Cl)Cl',2.59506047452425 +'CCc1cccc(CC)c1N(COC)C(=O)CCl',4.28486094761281 +'c1ccccc1c2c(C)c(COC(=O)C3C(C)(C)C3C=C(Cl)C(F)(F)F)ccc2',4.92723460128442 +'n1c(Cl)cc(OC)nc1NC(=O)NS(=O)(=O)c2ccccc2C(=O)OCC',3.52095051170688 +'O=C(NC(=O)c(c(F)ccc1)c1F)Nc(ccc(c2)Cl)c2',4.60022325981506 +'c(cccc1)(c1)CC',2.56208837510252 +'O=C(N(SC(Cl)(Cl)Cl)C(=O)c1cccc2)c12',3.87004900844397 +'Clc1cc(C(F)(F)F)cnc1Oc2ccc(OC(C)C(=O)OC)cc2',5.57487232351041 +'C#N',2.94040947259108 +'ClC(C(OC(C=C2C(=O)OC(C)C(=O)OCC)=CC=C2N(=O)=O)=C1)=CC=C1C(F)(F)F',3.96545863474241 +'c1c(C(F)(F)F)cccc1N2C(=O)C(Cl)=C(NC)C=N2',3.77270454387038 +'O=N(=O)C(C(=C1N(=O)=O)N(C(C)C)C(C)C)=CC(=C1)S(=O)(=O)N',3.88631461533234 +'CN(=CC=C1C(C=C2)=CC=N2C)C=C1',4.69607191571383 +'C1=C(C=C(C=C1[N+](=O)[O-])[N+](=O)[O-])[N+](=O)[O-]',4.20441460583146 +'C(=C)Cl',4.68192429615426 +'C1CCC(=O)CC1',2.03281793688456 +'CC1(C(C1(C)C)C(=O)OC(C#N)C2=CC(=CC=C2)OC3=CC=CC=C3)C',4.14541137996302 +'C1=CC(=O)NNC1(=O)',2.35058431121584 +'CCSC(=O)N1CCCCCC1',4.97151330020725 +'C(C(Cl)(Cl)Cl)(O)O',3.08555504738041 +'ClC2C1OC1C3C2C4(Cl)C(=C(Cl)C3(Cl)C4(Cl)Cl)Cl',7.1923634710095 +'Clc1cc(C(F)(F)F)ccc1Oc2cc(OCC)c(N(=O)(=O))cc2',4.55834892852739 +'c1cc(Cl)ccc1C(C(#N))(CCCC)Cn2ncnc2',4.46756491519242 +'CC1=C(C=C(C=C1[N+](=O)[O-])[N+](=O)[O-])[N+](=O)[O-]',5.055246608541 +'CC(C)OC(=O)C(C1=CC=C(C=C1)Br)(C2=CC=C(C=C2)Br)O',4.21658723866328 +'C[N+](C)(C)CCCl',2.97460527968547 +'CCC(=C1C(=O)CC(CC1=O)CC(C)SCC)NOCC=CCl',3.62169695860399 +'CC1=NC(=NC(=C1)C2CC2)NC3=CC=CC=C3',3.80128998933051 +'N(c(cccc1)c1)c(cccc2)c2',3.83051794413252 +'CC1(C(=O)N(C(=O)O1)NC2=CC=CC=C2)C3=CC=C(C=C3)OC4=CC=CC=C4',4.34801416963502 +'CC1(CCCCC1)C(=O)NC2=C(C(=C(C=C2)O)Cl)Cl',3.01490626247445 +'C1=CC(=C2C(=C1)OC(O2)(F)F)C3=CNC=C3C#N',3.35338292576111 +'C(F)(F)(F)c1ccccc1C(=O)Nc2cccc(OC(C)C)c2',3.57009941427408 +'C(CCCCN=C(N)N)CCCNCCCCCCCCN=C(N)N',4.27216545257855 +'C1CN(C(=N1)N[N+](=O)[O-])CC2=CN=C(C=C2)Cl',4.17721556192143 +'COC(=O)C12CC3=C(C1=NN(CO2)C(=O)N(C4=CC=C(C=C4)OC(F)(F)F)C(=O)OC)C=CC(=C3)Cl',5.16619526358129 +'CC1=CC=CC=C1OCC2=CC=CC=C2C(=NOC)C(=O)OC',2.92782487037951 +'CC1=CC(=CC(=C1)C(=O)N(C(C)(C)C)NC(=O)C2=C(C(=CC=C2)OC)C)C',2.95255951099906 +'C1=CC(=C(C(=C1)F)C(=O)NC(=O)NC2=CC(=C(C=C2)OC(C(OC(F)(F)F)F)(F)F)Cl)F',4.13628410350378 +'CC1=CC=C(C=C1)N(SC(F)(Cl)Cl)S(=O)(=O)N(C)C',4.28537828278078 +'CC(C)(C)C1=C(C=CC(=C1)O)O',2.86849281697225 +'CC(=NOCC1=CC=CC=C1C(=NOC)C(=O)OC)C2=CC(=CC=C2)C(F)(F)F',3.83290371721801 +'COC(=O)N(C1=CC=CC=C1COC2=NN(C=C2)C3=CC=C(C=C3)Cl)OC',4.63438424347854 +'CC(C)N1C(=NC(C)(C)C)SCN(C1=O)C2=CC=CC=C2',4.54540426969100 +'C1=CC=C(C(=C1)C2=NN=C(N=N2)C3=CC=CC=C3Cl)Cl',4.24360591089568 +'CCCC(=C1C(=O)CC(CC1=O)C2CCCSC2)NOCC',4.0653478352871 +'C1CC1NC2=NC(=C(C(=N2)N)C#N)N',3.93679970507275 +'C(C=C1)(=N(C=C1)CC2)C(N2=C3)=CC=C3',5.50950218614247 +'C1=CC=C2C(=C1)C(=O)C3=C(C2=O)SC(=C(S3)C#N)C#N',4.69361522533935 +'CCOC1=CC2=C(C=C1)NC(C=C2C)(C)C',4.25789199055837 +'C1=CC=C(C=C1)C(CCC2=CC=C(C=C2)Cl)(CN3C=NC=N3)C#N',4.05027414115274 +'CC1CN(CC(O1)C)CC(C)CC2=CC=C(C=C2)C(C)(C)C',5.25168418782516 +'C[Si](CN1C=NC=N1)(C2=CC=C(C=C2)F)C3=CC=C(C=C3)F',5.19782165018731 +'c1cc(Cl)cc(Cl)c1C(OCC=C)Cn2cncc2',4.29692796857781 +'CN(=CC=C1C(C=C2)=CC=N2C)C=C1',4.86356300300759 +'CCCCOCCOCCOCC1=CC2=C(C=C1CCC)OCO2',3.52947976153744 +'Clc1cc(Cl)ccc1C2(Cn3ncnc3)OC(CCC)CO2',3.5520346361573 +'C(=CC=C1)(C2=C1)NC(=N2)C(=CS3)N=C3',3.82660962776618 +'CCOC1=CC=C(C=C1)C(C)(C)COCC2=CC(=CC=C2)OC3=CC=CC=C3',4.16077781336093 +'CC(C)(C)c2ccc(OC1CCCCC1OS(=O)OCC#C)cc2',4.26590014728598 +'CC(COC1=CC=C(C=C1)OC2=CC=CC=C2)OC3=CC=CC=N3',3.36087697276960 +'CC(C)(C)C(=O)C(N1C=NC=N1)OC2=CC=C(C=C2)Cl',3.41107116109321 +'CC(C)(C)C(C(N1C=NC=N1)OC2=CC=C(C=C2)Cl)O',3.44975692245790 +'c1ccccc1c2c(C)c(COC(=O)C3C(C)(C)C3C=C(Cl)C(F)(F)F)ccc2',4.7231146186285 +'CC1(C(C1C(=O)OC(C#N)C2=CC(=C(C=C2)F)OC3=CC=CC=C3)C=C(Cl)Cl)C',4.85962620215948 +'CC1(C(C1C(=O)OC(C#N)C2=CC(=C(C=C2)F)OC3=CC=CC=C3)C=C(Cl)Cl)C',4.5585962064955 +'ClC(Cl)=CC1C(C)(C)C1C(=O)OC(C(#N))c2cccc(Oc3ccccc3)c2',3.92043344378224 +'ClC1CC2C(C1Cl)C3(Cl)C(=C(Cl)C2(Cl)C3(Cl)Cl)Cl',6.21460930807761 +'ClC4=C(Cl)C5(Cl)C3C1CC(C2OC12)C3C4(Cl)C5(Cl)Cl',6.58082159900658 +'C1C2C3C(C1C4C2O4)C5(C(=C(C3(C5(Cl)Cl)Cl)Cl)Cl)Cl',6.18288159033454 +'C1(C(C(C(C(C1Cl)Cl)Cl)Cl)Cl)Cl',4.79154110643314 +'CCC(=O)Nc1ccc(Cl)c(Cl)c1',3.45780196740732 +'C1(=C(C(=C(C(=C1Cl)Cl)Cl)Cl)Cl)[N+](=O)[O-]',3.32418644119937 +'C1C2C(COS(=O)O1)C3(C(=C(C2(C3(Cl)Cl)Cl)Cl)Cl)Cl',5.14711652367221 +'O=C(N(SC(Cl)(Cl)Cl)C(=O)c1cccc2)c12',3.77313899543591 +'CC(C(=O)O)OC1=CC=C(C=C1)OC2=C(C=C(C=N2)C(F)(F)F)Cl',6.55834892852739 +'CCCCC(CN1C=NC=N1)(C#N)C2=CC=C(C=C2)Cl',4.46933393793126 +'Clc1cc(Cl)cc(Cl)c1OCCN(CCC)C(=O)n2cncc2',4.86838559832397 +'COP(=O)(NC(=O)(C))SC',4.86490452310016 +'CCOP(=O)(OCC)OC(=CCl)C1=C(C=C(C=C1)Cl)Cl',5.3796920956126 +'CCOP(=S)(OCC)SCCSCC',6.09596779022605 +'O=P(O)(O)CCCl',4.0806685706873 +'CCCSP(=O)(OCC)SCCC',4.95305958493745 +'CCOP(=O)(NC(C)C)Oc1ccc(SC)c(C)c1',5.25150573076352 +'COP(=S)(OC)Oc1ccc(SC)c(C)c1',5.58722449762503 +'OC(=O)C(N)CCP(C)(=O)O',4.71391476838473 +'OC(=O)CNCP(O)(O)=O',2.75095321211059 +'CCOC(=O)CC(SP(=S)(OC)OC)C(=O)OCC',2.96268235505315 +'COP(N)(=O)SC',5.68721882334643 +'CC(=CC(=O)OC)OP(=O)(OC)OC',5.80646736824669 +'CCOP(=S)(OCC)SCSCC',6.2114833717655 +'CCOP(=S)(OCC)SCSC(C)(C)C',6.68189008451404 +'S=P(OC)(OC)SCN1N=Nc2ccccc2C1(=O)',5.08988368084419 +'CCOP(=S)(OCC)OC1=NC(=C(C=C1Cl)Cl)Cl',5.54479494223028 +'CCOP(=S)(OCC)OC1=NC(=NC(=C1)C)C(C)C',4.71993889259734 +'CCC1=NC(=CC(=N1)OP(=S)(OC)OC)OCC',5.8126040303238 +'S=P(OC)(OC)SCN1C(=O)SC(OC)=N1',5.27636313027728 +'CCOP(=S)(OCC)SCN1C2=C(C=C(C=C2)Cl)OC1=O',5.26459183786176 +'COP(=S)(OC)SCN2C(=O)c1ccccc1C2(=O)',4.54725636091897 +'CCOC(=O)C1=CN2C(=CC(=N2)OP(=S)(OCC)OCC)N=C1C',4.97007298557879 +'CCOP(=S)(OCC)OC1=NN(C=N1)C2=CC=CC=C2',5.38203437103643 +'O=C(Oc(c(c(ccc1)cc2)c1)c2)NC',3.52552257057249 +'CC1=CC(=CC(=C1SC)C)OC(=O)NC',4.38429231462288 +'CNC(=O)ON=C(C)SC',3.90904789636717 +'CCCOC(=O)NCCCN(C)C',2.44226598159187 +'COC(=O)NC1=NC2=CC=CC=C2N1',3.40639632281981 +'CC1=C(N=C(N=C1OC(=O)N(C)C)N(C)C)C',4.2871938165512 +'CNC(=O)CCSCCSP(=O)(OC)OC',5.72599715999116 +'N(C(=S)SSC(N(C)C)=S)(C)C',4.30181261256647 +'C1=NNC(=N1)N',4.22572249207399 +'CCCCCCCCc1cc(N(=O)(=O))c(OC(=O)C=CC)c(c1)N(=O)(=O)',3.75539000391453 +'C1=CC=C(C=C1)[Sn](C2=CC=CC=C2)C3=CC=CC=C3',6.0669625480302 +'O=C(NC(=O)c(c(F)ccc1)c1F)Nc(ccc(c2)Cl)c2',4.64721982249128 +'N(C(=S)NC1)C1',4.91236296409098 +'C1=CC(=C(C(=C1)F)C(=O)NC(=O)NC2=CC(=C(C(=C2F)Cl)F)Cl)F',4.18310948429116 +'CCCSC1=CC2=C(C=C1)N=C(N2)NC(=O)OC',4.12275865288522 +'C1CN(CCN1CCCC(=O)C2=CC=C(C=C2)F)C3=CC=CC=N3',3.45437537377312 +'CC1(C2C(C3C(C(=O)C(=C(N)O)C(=O)C3(C(=O)C2=C(C4=C(C=CC(=C41)Cl)O)O)O)N(C)C)O)O',1.97849569899962 +'CC1=CC(=C(C=C1NC(=O)C2=CC(=CC(=C2O)I)I)Cl)C(C#N)C3=CC=C(C=C3)Cl',4.82156180249896 +'CN1CC2CC1CN2C3=C(C=C4C(=C3)N(C=C(C4=O)C(=O)O)C5CC5)F',3.85415878578584 +'C1=CC(=CC=C1C(C#N)C2=C(C=CC(=C2Cl)N3C(=O)NC(=O)C=N3)Cl)Cl',4.43418336046643 +'CC1=NC=C(N1C)[N+](=O)[O-]',3.97352186635665 +'CCN1CCN(CC1)C2=C(C=C3C(=C2)N(C=C(C3=O)C(=O)O)C4CC4)F',4.14059829999974 +'CC1C=CC=C2COC3C2(C(C=C(C3O)C)C(=O)OC4CC(CC=C(C1OC5CC(C(C(O5)C)OC6CC(C(C(O6)C)NC(=O)C)OC)OC)C)OC7(C4)C=CC(C(O7)C(C)C)C)O',5.95429183284051 +'COCC(=O)NC1=C(C=CC(=C1)SC2=CC=CC=C2)NC(=NC(=O)OC)NC(=O)OC',4.04773898332238 +'CC1CCC2=C3N1C=C(C(=O)C3=CC(=C2)F)C(=O)O',2.81499362006104 +'COC(=O)NC1=NC2=C(N1)C=C(C=C2)S(=O)C3=CC=CC=C3',5.1977587356423 +'CC1(C2CC3C(C(=O)C(=C(N)O)C(=O)C3(C(=O)C2=C(C4=C1C=CC=C4O)O)O)N(C)C)O',3.47171656401627 +'C1CN(CCN1CCCC(=O)C2=CC=C(C=C2)F)C3=CC=CC=N3',4.03795195940707 +'CC(C)NCC(COC1=CC=CC2=C1C3=CC=CC=C3N2)O',4.62967091273678 +'C1=CC(=CC=C1C(C#N)C2=C(C=CC(=C2Cl)N3C(=O)NC(=O)C=N3)Cl)Cl',4.24854678350451 +'CC1C=CC=C2COC3C2(C(C=C(C3O)C)C(=O)OC4CC(CC=C(C1OC5CC(C(C(O5)C)OC6CC(C(C(O6)C)NC(=O)C)OC)OC)C)OC7(C4)C=CC(C(O7)C(C)C)C)O',5.55635182416848 +'COP(=S)(OC)Oc1ccc(SC)c(C)c1',5.79134448028095 +'C(C(C(C(C1Cl)Cl)Cl)Cl)(C1Cl)Cl',4.56054897737691 +'C(C(C(C(C1Cl)Cl)Cl)Cl)(C1Cl)Cl',4.86157897304089 +'CC(N(C)C)CN(C(=CC=C3)C1=C3)C(=CC=C2)C(=C2)S1',4.23385066979149 +'C1=C(C=C(C(=C1Cl)N)Cl)[N+](=O)[O-]',2.93578881098946 +'c(cccc1)(c1)C=C',2.41559561343340 diff --git a/original/LOAEL_log_mmol_corrected_smiles.csv b/original/LOAEL_log_mmol_corrected_smiles.csv new file mode 100755 index 0000000..237830e --- /dev/null +++ b/original/LOAEL_log_mmol_corrected_smiles.csv @@ -0,0 +1,568 @@ +SMILES,LOAEL_log_mmol_kg_bw_day +'C1=C(C(=CC(=C1NN=C3C2=C(C=C([S]([O-])(=O)=O)C=C2)C=CC3=O)OC)[S]([O-])(=O)=O)C.[Na+].[Na+]',2.12309380508316 +'O1C(=O)C(O)=C(O)C1C(O)CO',1.76137662853832 +'C1(C)=C(C=CC(C)=CC=CC(C)=CC=CC=C(C)C=CC=C(C)C(=O)OC)C(C)(C)CCC1',2.95101092705237 +'c(cccc1)(c1)C(C)C',2.41523206875268 +'O=C(OCCCC)c(c(ccc1)C(=O)OCCCC)c1',2.66642980233607 +'O=C(OCC)c(c(ccc1)C(=O)OCC)c1',1.69992305435084 +'O=C(OC(OC(OC1C)C)C1)C',3.14412407646651 +'Oc(c(ccc1)C)c1C',4.30879341594785 +'Oc(ccc(c1C)C)c1',3.94081663065326 +'O=C(OCC)C=C',2.60605102798022 +'c(cccc1)(c1)CC',2.41532120099855 +'OCCO',2.39492662325430 +'c(ccc1C(=O)OCC(=O)OCC)cc1C(=O)OCC',2.04964162538818 +'O=C',2.56368333860036 +'O=C(O)C=CC(=O)O',2.03090237239810 +'OCC(O)CO',1.12645271808123 +'O=C(OC)c(ccc(O)c1)c1',2.00617304782278 +'O=C(OCCC)c(ccc(O)c1)c1',2.07966468441907 +'CC(CCC(=O)(O))C3CCC4C2CCC1CC(O)CCC1(C)C2CCC34C',2.87687871256153 +'OC(C(CCC1C)C(C)C)C1',2.42080757876423 +'O=C(O)C(=C)C',2.54049719303574 +'O=C(OC)c(c(O)ccc1)c1',2.62596180611118 +'Oc(cccc1)c1',2.43708305310291 +'O=C(OCCC)c(cc(O)c(O)c1O)c1',2.3902301635117 +'OCC(O)C1C(O)=C(O)C(=O)O1',2.05436782171583 +'c(cccc1)(c1)C=C',3.69543631002744 +'O=Cc(occ1)c1',3.20450009536782 +'NCCNc1cccc2ccccc12',3.37247609215110 +'CN(C)(C)CCCl',2.64921593816204 +'O=C(Nc(ccc(c1)C(=O)CCl)c1)C',2.12695072080225 +'c(ccc(c1)Cl)(c1)C(c(ccc(c2)Cl)c2)C(Cl)(Cl)Cl',4.04444942813338 +'CC(Oc1cc(Cl)c(Cl)cc1Cl)C(=O)(O)',4.491054148917 +'O=N(=O)C(=CC=C1OC)C=C1N=NC(C(O)=C2C(=O)NC(=CC=C4)C=C4N(=O)=O)=C(C=C3)C(=C2)C=C3',2.36568501290040 +'O=N(=O)C(C=C1)=CC(OCCO)=C1NCCO',3.02438986505162 +'Cc1cccc(CC)c1N(C(=O)CCl)COCC',3.73201897895503 +'C1=C(C(=CC=C1OC2=CC=C(C=C2Cl)C(F)(F)F)[N+](=O)[O-])C(=O)[O-].[Na+]',3.32865137721601 +'CCc1cccc(CC)c1N(COC)C(=O)CCl',4.25489772423536 +'O=C(Nc(ccc(OCC)c1N)c1)C',2.21459876477238 +'Oc(ccc(N)c1)c1',2.20160364320713 +'CC(N)CC(=CC=C1)C=C1',4.43202666692597 +'O(c(ccc(c1)C=CC)c1)C',2.63429468422019 +'COc1ccc(N)cc1',2.41466474972438 +'O=C(O)c(c(N)ccc1)c1',1.69766082403086 +'Clc2cccc(c2)c1ccccc1',4.67360340221543 +'O=C(NC(C(=O)OC)Cc(cccc1)c1)C(N)CC(=O)O',3.30147753146833 +'n1c2ccc(Cl)cc2ncc1Oc3ccc(OC(C)C(=O)OCC)cc3',5.00327683569969 +'COC(=O)NS(=O)(=O)c1ccc(N)cc1',3.10691015775373 +'S=P(OC)(OC)SCN1N=Nc2ccccc2C1(=O)',5.94520088604013 +'CNC(=O)Oc1ccccc1OC(C)C',3.62167823549204 +'CC(C)(C)C(=O)C(Oc1ccc(Cl)cc1)n2cncn2',4.07003600375764 +'O=S(O)(=O)C(=CC=C1)C=C1CN(CC)=C(C=C2)C=CC2=C(C(C=C3)=CC=C3N(C)C)C(C=C4)=CC=C4N(CC)CC(C=C5)=CC(=C5)S(=O)(=O)O',2.99569446127058 +'c(c(cccc1)c1)(cccc2)c2',2.79016633269067 +'BrC(Cl)Cl',3.10044647372987 +'ClC(Cl)C(Cl)(Cl)SN2C(=O)C1CC=CCC1C2(=O)',4.46372003271591 +'O=C(Oc(c(c(ccc1)cc2)c1)c2)NC',4.11054922260167 +'CC1=C(SCCO1)C(=O)Nc2ccccc2',3.89450458533419 +'ClC1CC2C(C1Cl)C3(Cl)C(=C(Cl)C2(Cl)C3(Cl)Cl)Cl',6.18118555259066 +'O=C(O)CCl',3.49829685836143 +'ClC(=CC=C1N)C=C1',4.32760254782945 +'CC(C)OC(=O)C(O)(c1ccc(Cl)cc1)c2ccc(Cl)cc2',4.57623015760927 +'n1c(OC)nc(C)nc1NC(=O)NS(=O)(=O)c2ccccc2Cl',4.15566728690676 +'OS(=O)(=O)C(C(=CC=C2)C1=C2)=CC=C1N=NC(C(O)=C3N=NC(C(C=C5)=C4C=C5)=CC=C4S(O)(=O)=O)=CC(=C3O)CO',2.91745349144784 +'S=P(OCC)(OCC)Oc1ccc2C(C)=C(Cl)C(=O)Oc2c1',5.65653611167129 +'CNP(=O)(OC)Oc1ccc(cc1Cl)C(C)(C)C',4.86289269710557 +'C(C1C2C(C(O)C(O1)OC8C(OC(OC7C(OC(OC6C(OC(OC5C(C(C(OC4C(C(C(OC3C(C(C(O2)OC3CO)O)O)OC4CO)O)O)OC5CO)O)O)C(C6O)O)CO)C(C7O)O)CO)C(C8O)O)CO)O)O',2.85087205247326 +'n1c(N)nc(N)nc1NC2CC2',4.04449742637606 +'COC(=O)c1c(Cl)c(Cl)c(C(=O)OC)c(Cl)c1Cl',2.82212129862366 +'O=C(O)C(Cl)(Cl)C',3.70545399970477 +'Nc1cc(N)c(O)cc1',3.69597355155454 +'FC(F)(Cl)Cl',2.90638355650622 +'ClCCl',3.23010431252803 +'O=P(OC)(OC)OC=C(Cl)Cl',4.98261676287965 +'OC(c1ccc(Cl)cc1)(c2ccc(Cl)cc2)C(Cl)(Cl)Cl',4.26774140719551 +'ClC4=C(Cl)C5(Cl)C3C1CC(C2OC12)C3C4(Cl)C5(Cl)Cl',6.88185159467056 +'CN(=C1C(C=C2)=CC=C2)N(C)C(=C1)C(C=C3)=CC=C3',3.2998650117386 +'O=C(NC(=O)c(c(F)ccc1)c1F)Nc(ccc(c2)Cl)c2',4.58922787551359 +'CC1=C(C)S(=O)(=O)CCS1(=O)=O',4.32277979319225 +'O=C(NC)CSP(OC)(OC)=S',5.96238343177818 +'COc1ccc(N)c(OC)c1',2.74428856020296 +'COP(=O)OC',3.04158586769746 +'CC(=C(N(=O)=O)C=C1N(=O)=O)C=C1',3.72891101170516 +'CN(C)C(=O)C(c1ccccc1)c2ccccc2',3.90184372972497 +'N(c(cccc1)c1)c(cccc2)c2',3.73709625897028 +'C(C=C1)(=N(C=C1)CC2)C(N2=C3)=CC=C3',5.50194904825203 +'CCOP(=S)(OCC)SCCSCC',6.43839047104826 +'NC(=S)NNC(N)=S',2.20039466208170 +'O=C(N(C)C)Nc(ccc(c1Cl)Cl)c1',4.58938077582749 +'O=P(O)(O)CCCl',2.98375855767924 +'O=C(OCC)C(O1)C1(c(cccc2)c2)C',3.07133013436744 +'COC(=O)NC(=NC1=C2)NC1=CC(=C2)SC(C=C3)=CC=C3',4.30008455052816 +'CN1C=C(c2ccccc2)C(=O)C(c3cc(C(F)(F)F)ccc3)=C1',4.11967251914367 +'c1cc(C(F)(F)F)cc(Cl)c1NC(C(C)C)C(=O)OC(C(#N))c2cccc(Oc3ccccc3)c2',5.30355258529792 +'S=P(OCC)(Sc1ccccc1)CC',5.192858916992 +'n1c(C)nc(OC)nc1NC(=O)NS(=O)(=O)c2ccsc2C(=O)OC',4.19021010110931 +'C(C(C(C(C1Cl)Cl)Cl)Cl)(C1Cl)Cl',4.76466896003284 +'O=N(=O)N(CN1N(=O)=O)CN(C1)N(=O)=O',5.17048924956396 +'O=C(N=C(N(C1(=O))C)N(C)C)N1C(CCCC2)C2',3.70296927879496 +'n(c(c(ccc1)cc2)c1O)c2',3.00650487851870 +'c1cc(Cl)cc(Cl)c1C(OCC=C)Cn2cncc2',3.87095923630552 +'COc1cccc(OC)c1C(=O)Nc2onc(C(C)(CC)CC)c2',3.81664542550781 +'n1c(OC)cc(OC)nc1NC(=O)NS(=O)(=O)Cc2ccccc2C(=O)OC',3.12325069281768 +'CCOC(=O)CC(SP(=S)(OC)OC)C(=O)OCC',3.82001485148442 +'CN(C)(CCC1)CC1',2.88160770091708 +'O=P(SCCCC)(SCCCC)SCCCC',5.40072574498715 +'COCC(=O)N(C(C)C(=O)OC)c1c(C)cccc1C',3.65023995836629 +'S=P(OC)(OC)SCN1C(=O)SC(OC)=N1',5.17945311726922 +'CNC(=O)ON=C(C)SC',4.21007789203115 +'COP(=S)(OC)Oc1ccc(cc1)N(=O)(=O)',6.02235818715591 +'O=C1N(N)C(SC)=NN=C1C(C)(C)C',4.15490651136806 +'COP(=O)(OC)OC(Br)C(Cl)(Cl)Br',5.27964840060116 +'OC(C(N)C1O)C(C)OC1(C)OC(CC(C)(C(C2O)C(O)=O)OC(O)(C2)CC(O)CC(C)(O3)C3C=C4)C=CC=CC=CC=CCC(C)OC4=O',3.99258108069112 +'O=N(=O)c(ccc(c1N)C)c1',4.27918373941654 +'O=N(=O)c(c(N)ccc1N)c1',3.24556564669417 +'O=C(O)C(=C(N)C=C1N(=O)=O)C=C1',2.18667157840130 +'O=N(=O)c(c(c(ccc1)cc2)c1)c2',3.0209838975238 +'c12c(N=Nc3ccccc3)c(O)ccc1cc(S(=O)(=O)O)cc2',3.26105456902449 +'CC(C)Oc1cc(c(Cl)cc1Cl)N2N=C(OC2(=O))C(C)(C)C',4.83912722706429 +'CNC(=O)ON=C(SC)C(=O)N(C)C',4.64199221806157 +'CCOP(=S)(OCC)Oc1ccc(cc1)N(=O)=O',4.92021372679140 +'Oc(c(c(c(c1Cl)Cl)Cl)Cl)c1Cl',4.42543075349016 +'NC(=N)NC(=N)NCCc1ccccc1',3.44898061811695 +'COP(=S)(OC)SCN2C(=O)c1ccccc1C2(=O)',4.20046887469431 +'CCN(CC)C(=O)C(Cl)=C(C)OP(=O)(OC)OC',4.38676470716829 +'ClC3C6(Cl)C4C2C1OC1C5C2C3(Cl)C(Cl)(C45)C6(Cl)Cl',5.73572355899233 +'O=C(OC(=O)c1cccc2)c12',2.09688233455707 +'Nc1c(Cl)c(Cl)nc(C(=O)(O))c1Cl',3.60469254298773 +'CCN(CC)c1nc(C)cc(OP(=S)(OC)OC)n1',5.08683453410041 +'Nc3ccc2cc1ccc(N)cc1nc2c3',3.64856042750458 +'CCC(=O)Nc1ccc(Cl)c(Cl)c1',4.03758556402413 +'Clc1cc(Cl)ccc1C2(Cn3ncnc3)OC(CCC)CO2',4.13636586052483 +'O=C(N)c(nccn1)c1',2.19322585277166 +'Oc1cc(O)c2C(=O)C(O)=C(c3cc(O)c(O)cc3)Oc2c1',2.17199481319419 +'CCC(O)(C)C#C',3.32910149752408 +'CC(C(NCC)=C1)=CC(C1=O2)=C(C(C2=C3)=CC(C)=C3NCC)C(=CC=C4)C(=C4)C(=O)OCC',4.56776852431159 +'O=C(NS(=O)(=O)c1cccc2)c12',1.70634501494627 +'c1cc(Cl)ccc1C2SC(=O)N(C(=O)NC3CCCCC3)C2C',3.34350563448343 +'n(c(nc(n1)NCC)NCC)c1Cl',4.60564260851438 +'O=[S](NC1CCCCC1)(=O)[O-].[Na+]',1.74712743618051 +'O=C(OCC(C1OCC(C1O)O)O)CCCCCCCCCCC',1.70187402783236 +'O(CC1O)C(C1O)C(O)COC(=O)CCCCCCCCCCCCCCCCC',1.77657920852493 +'O=S(=O)(Nc(nc(cc1C)C)n1)c(ccc(N)c2)c2',3.92604632938062 +'CCNc1nc(NC(C)(C)C)nc(SC)n1',4.2065674883771 +'Oc(c(cc(c1)C(C)(C)C)Cl)c1',2.93192524190336 +'C(C(Cl)Cl)(Cl)Cl',3.19149572716769 +'COP(=O)(OC)OC(=CCl)c1cc(Cl)c(Cl)cc1Cl',3.5634357799466 +'CCN(CC)C(=O)SCc1ccc(Cl)cc1',4.71227844003234 +'COC(=O)NC(=S)Nc1ccccc1NC(=S)NC(=O)OC',4.0293761165818 +'N(C(=S)SSC(N(C)C)=S)(C)C',4.20490259955842 +'c12OC(CCCC(C)CCCC(C)CCCC(C)C)(C)CCc1c(C)c(OC(=O)C)c(C)c2C',2.37359490910830 +'Cc1cc(N)ccc1NOS(O)(=O)=O',3.07409722667645 +'C(Br)(C(Br)(Br)Br)C1C(C)(C)C1C(=O)OC(C(#N))c2cccc(Oc3ccccc3)c2',5.34570506657104 +'O=C(O)COc(c(cc(c1Cl)Cl)Cl)c1',4.40736115725459 +'FC(F)(F)C(=CC(N(=O)=O)=C1N(C(C)C)C(C)C)C=C1N(=O)=O',3.92334642542511 +'Cc1cc(C)c(N)cc1C',3.33165612180841 +'CC(O)(C(O)C(O1)C)CC1(C)OC(C(C)O2)C(C(O)C2(C)OC(C(C)C(O)CC(=O)OC(CC)C3COC(C(OC)C4OC)OC(C)C4O)C(CC=O)CC(C)C(=O)C=CC(=C3)C)N(C)C',3.27607248348466 +'c1c(Cl)cc(Cl)cc1N2C(=O)C(C)(C=C)OC2(=O)',3.59380666266014 +'O=C(OC(CCCC(O)CCCCCc1cc(O)cc2O)C)c12',6.20735970305 +'COC(=O)C1(C2=CC=CC=C2C3=C1C=C(C=C3)Cl)O',3.26276588262396 +'CC(C(=O)O)OC1=CC(=CC=C1)Cl',3.30237197471763 +'P12P3P1P23',1.92514612424786 +'C(CO)O',2.19080664059838 +'CCCCOCC(C)OCC(C)O',3.17218289921228 +'C(CO)O',1.49183663626236 +'C(CO)O',1.82907880458079 +'[O-][As](=O)([O-])[O-]',4.34688225631145 +'[Si](CN1C=NC=N1)(C2=CC=C(C=C2)F)C3=CC=C(C=C3)F',5.1159116373222 +'N(C(=S)SSC(N(C)C)=S)(C)C',4.32029601826049 +'COP(=O)(N)SC',5.19537431180606 +'N(C(=S)SSC(N(C)C)=S)(C)C',4.64300653228067 +'COP(=O)(NC(=O)(C))SC',3.71877648742193 +'C1=CC=C(C=C1)NC(=O)NC2=CN=NS2',3.86579667362138 +'CCOP(=S)(NC(C)C)OC1=CC=CC=C1C(=O)OC(C)C',5.83934493677328 +'CC(=NOC(=O)N(C)SN(C)C(=O)ON=C(C)SC)SC',4.54957865212472 +'CCOP(=S)(OCC)OC1=NC(=NC(=C1)C)C(C)C',5.3072756271046 +'NC(CCCC1)C1',3.22924248946341 +'CN1C=C(c2ccccc2)C(=O)C(c3cc(C(F)(F)F)ccc3)=C1',4.00572916683684 +'ClC1CC2C(C1Cl)C3(Cl)C(=C(Cl)C2(Cl)C3(Cl)Cl)Cl',5.91357931241363 +'CCCCC(CC)COC(=O)C1=CC=CC=C1C(=O)OCC(CC)CCCC',3.29065345190954 +'OC(=O)CNCP(O)(O)=O',2.22807446683025 +'C1CNC(=S)N1',5.64754514108144 +'O=C(N(OC)C)Nc(ccc(c1Cl)Cl)c1',4.6004830749906 +'C1=CC=C2C(=C1)NC(=S)S2',2.34830823871711 +'CCOP(=S)(OCC)OC1=NC(=C(C=C1Cl)Cl)Cl',4.54479494223028 +'c(c(c(c(c1Cl)Cl)Cl)Cl)(c1Cl)Cl',5.99211484281248 +'COc1ccc(cc1)C(c2ccc(OC)cc2)C(Cl)(Cl)Cl',3.44172416093488 +'C1=CC(=CC=C1Cl)Cl',2.690201870583 +'CC(C)OC(=O)NC1=CC(=CC=C1)Cl',2.63075480518045 +'COP(=O)(OC)OC=C(Cl)Cl',5.01190613898164 +'CCOP(=S)(OCC)Oc1ccc(cc1)N(=O)=O',5.84103248074378 +'CNC(=O)N(C)c1nnc(s1)C(C)(C)C',3.75647357868479 +'CCCCOCCOCCOCC1=CC2=C(C=C1CCC)OCO2',3.13153975286541 +'CC(C(=O)O)OC1=C(C=C(C=C1)Cl)Cl',4.41694364962485 +'CC1(C(C1C(=O)OC(C#N)C2=CC(=C(C=C2)F)OC3=CC=CC=C3)C=C(Cl)Cl)C',4.54086743953507 +'C(#N)c(c(c(c(c1C(#N))Cl)Cl)Cl)c1Cl',4.82267631193248 +'O=C(OCC)C(O)(c(ccc(c1)Cl)c1)c(ccc(c2)Cl)c2',4.24731476483975 +'O=C(N(C)C)Nc(ccc(c1)Cl)c1',3.2011773320931 +'O=C(N(SC(Cl)(Cl)Cl)C(=O)C1CC=CC2)C12',3.47797354595327 +'CCc1cccc(C)c1N(C(C)COC)C(=O)CCl',3.27691146056582 +'C1=CC(=C(C=C1Cl)Cl)OCC(=O)O',4.64549583771218 +'CCNC1=NC(=NC(=N1)Cl)NC(C)(C)C#N',5.2845529417803 +'C(C(C(C(C1Cl)Cl)Cl)Cl)(C1Cl)Cl',4.80088113268728 +'COP(=S)(OC)OC1=CC(=C(C=C1Cl)Cl)Cl',3.80827186579208 +'C1C2C=CC1C3C2C4(C(=C(C3(C4(Cl)Cl)Cl)Cl)Cl)Cl',7.56218566972996 +'CC1(C(C1C(=O)OCC2=CC(=CC=C2)OC3=CC=CC=C3)C=C(Cl)Cl)C',4.19455618753918 +'CCN(CC)C(=O)C(C)OC1=CC=CC2=CC=CC=C21',3.43353645191675 +'ClC1C=CC2C1C3(Cl)C(=C(Cl)C2(Cl)C3(Cl)Cl)Cl',6.17413857281627 +'CC(=CC(=O)NC)OP(=O)(OC)OC',5.6954106911713 +'CC(C)C1(C)N=C(NC1(=O))c3nc2ccccc2cc3C(=O)(O)',4.19219820184676 +'CC(C)Nc1nc(Cl)nc(NC(C)C)n1',3.66220959497816 +'CC(C(=O)O)(Cl)Cl',3.45627084235452 +'CC1(C(C1C(=O)OC(C#N)C2=CC(=C(C=C2)F)OC3=CC=CC=C3)C=C(Cl)Cl)C',4.76271618915143 +'O=C(NC)CSP(OC)(OC)=S',4.6613534361142 +'C12C3(C4(C5(C3(C(C1(C5(C2(C4(Cl)Cl)Cl)Cl)Cl)(Cl)Cl)Cl)Cl)Cl)Cl',7.70850413051807 +'COC(=O)C1=CC=CC=C1C(=O)OC',1.98718344722018 +'CCOP(=S)(OCC)SCSC(C)(C)C',6.76107133056166 +'CCC(C)SP(=O)(OCC)SC(C)CC',6.0340541201743 +'CCOP(=S)(OCC)SCSC(C)(C)C',5.1590113392337 +'C1C(C(C(=O)N1C2=CC=CC(=C2)C(F)(F)F)Cl)CCl',4.79534478918374 +'O=C(O)C(C(C(=O)O)C(O1)CC2)C12',3.20919319571953 +'O=C(Oc(c(OC(C1)(C)C)c1cc2)c2)NC',4.64591798599928 +'Oc(c(c(c(c1)Cl)Cl)Cc(c(c(cc2Cl)Cl)Cl)c2O)c1Cl',4.9105214638308 +'CC1(CON(C1=O)CC2=CC=CC=C2Cl)C',4.04722605916309 +'CCC(C)N1C(=O)C(=C(NC1=O)C)Br',3.6209530011803 +'CC1=CC(=CC(=C1N(C)C)C)OC(=O)NC',5.17081600643967 +'CNC(=O)OC1=CC=CC(=C1)N=CN(C)C',4.24798445482129 +'CC1=NN(C(=O)N1C(F)F)C2=CC(=C(C=C2Cl)Cl)NS(=O)(=O)C',3.76184922452045 +'CCOP(=S)(CC)SC1=CC=CC=C1',4.6925459996104 +'CCOP(=S)(OCC)SC(CCl)N1C(=O)C2=CC=CC=C2C1=O',5.19738625502110 +'N1CC(C)(C)CNC1=NN=C(C=Cc2ccc(C(F)(F)F)cc2)C=Cc3ccc(C(F)(F)F)cc3',4.99517458001903 +'CC1=C(C(=C(C(=C1F)F)COC(=O)C2C(C2(C)C)C=C(C(F)(F)F)Cl)F)F',4.9591800647055 +'CC1=CC(=C(C=C1)N=CN(C)C=NC2=C(C=C(C=C2)C)C)C',4.45886884853594 +'S=P(OC)(OC)SCN1C(=O)SC(OC)=N1',5.57739312594126 +'CC(C)N(C(C)C)C(=O)SCC(Cl)=C(Cl)Cl',4.38691132629296 +'S=P(OC)(OC)SCN1N=Nc2ccccc2C1(=O)',5.14932086869605 +'CC1=NC(=NC(=N1)OC)NC(=O)NS(=O)(=O)C2=CC=CC=C2CCC(F)(F)F',3.72005974473228 +'O=C(N(S(=O)(=O)Nc1cccc2)C(C)C)c12',3.77865560759679 +'CCN(CC)c1nc(C)cc(OP(=S)(OC)OC)n1',4.34489545637121 +'O=C(ON=CC(SC)(C)C)NC',6.27935493374302 +'ClC(Cl)(Cl)CC1(OC1)c2cc(Cl)cc(Cl)c2',4.02860782189294 +'CCC1CCCC(C(C(=O)C2CC3C(C2CC(=O)O1)CCC4C3CC(C4)OC5CC(C(C(C5OC)OC)OC)C)C)OC6CCC(C(O6)C)N(C)C',4.48549336200642 +'CC(C)(C)C(=NOC(=O)NC)CSC',4.56093515068149 +'CON=C(CC1=CN=CC=C1)C2=C(C=C(C=C2)Cl)Cl',3.81685069684023 +'CC(=CC1C(C1(C)C)C(=O)OCN2C(=O)C3=C(C2=O)CCCC3)C',3.12242048929166 +'C1COC(O1)(CN2C=NC=N2)C3=C(C=C(C=C3)Cl)Cl',4.47732480426449 +'CCCOC(=O)C1=CN=C(C=C1)C(=O)OCCC',3.00221511481659 +'CC1=CC(=NC(=N1)NC(=O)NS(=O)(=O)C2=CC=CC=C2C(=O)OC3COC3)C',3.68988952034363 +'C1=C(C(=NC(=C1Cl)Cl)OCC(=O)O)Cl',3.85273501931079 +'CCOCN1C(=C(C(=C1C(F)(F)F)Br)C#N)C2=CC=C(C=C2)Cl',4.47670895789257 +'CC(C)CC1=C(C(=NC(=C1C(=O)SC)C(F)(F)F)C(F)F)C(=O)SC',5.04368703263975 +'CC12CC1(C(=O)N(C2=O)C3=CC(=CC(=C3)Cl)Cl)C',4.27743796844594 +'CC1=CC(=C(C=C1)C(=O)OC)C2=NC(C(=O)N2)(C)C(C)C',3.76093729967937 +'COP(=S)(OC)OC1=NC(=C(C=C1Cl)Cl)Cl',5.03145309127161 +'CC(C)CC1=C(C(=NC(=C1C(=O)OC)C(F)F)C(F)(F)F)C2=NCCS2',3.95268441956944 +'CCOC(=O)C(CC1=CC(=C(C=C1Cl)F)N2C(=O)N(C(=N2)C)C(F)F)Cl',4.53591743757444 +'CC(C)=CC3C(C(=O)OCc2coc(Cc1ccccc1)c2)C3(C)C',3.4325717246993 +'CCCSP(=S)(OCC)OC1=CC=C(C=C1)SC',4.44776025923588 +'CC1=CC(=C(C(=C1)OC(=O)NC)C)C',3.513780491163 +'CC1=CC=CC=C1COC2CC3(CCC2(O3)C)C(C)C',3.26228942932097 +'CC1=C2C(=CC=C1)SC3=NN=CN23',3.78564431476757 +'CCC(=C1C(=O)CC(CC1=O)CC(C)SCC)NOCC=CCl',3.55619540984755 +'CCCN(CCC)C(=O)SCC',4.32294999482974 +'CC(C)OC(=O)C=C(C)C=CCC(C)CCCC(C)(C)OC',3.82926385227003 +'COP(=S)(OC)Oc1ccc(SC)c(C)c1',4.87052572632858 +'COC1=C(C=C(C=C1)C(=CC(=O)N2CCOCC2)C3=CC=C(C=C3)Cl)OC',3.92309028461827 +'CCSC(=O)N(CC(C)C)CC(C)C',3.33720244245390 +'CC(C)OP(=S)(OC(C)C)SCCNS(=O)(=O)C1=CC=CC=C1',4.42326053700057 +'CC(=CC1C(C1(C)C)C(=O)OCC2=CC(=CC=C2)OC3=CC=CC=C3)C',3.36853572230648 +'CC1=CC(=CC(=C1C)C)OC(=O)NC',4.28610219788592 +'CCOP(=S)(OCC)SCSC1=CC=C(C=C1)Cl',5.53512353543065 +'C1CN(CCN1C(C(Cl)(Cl)Cl)NC=O)C(C(Cl)(Cl)Cl)NC=O',3.63845107729718 +'C(=CC=C1)(C2=C1)NC(=N2)C(=CS3)N=C3',5.00270088682186 +'C1(=C(C(=C(C(=C1Cl)Cl)Cl)Cl)Cl)[N+](=O)[O-]',3.37340446386955 +'CCCC(=NOCC)C1C(=O)CC(CC1=O)CC(C)SCC',4.29612718117234 +'ClC2(Cl)C4(Cl)C1(Cl)C5(Cl)C(Cl)(Cl)C3(Cl)C1(Cl)C2(Cl)C3(Cl)C45Cl',5.89173094758972 +'CCN(C1CCCCC1)C(=O)SCC',4.85603479370532 +'CC1=NC(=NC(=N1)OC)NC(=O)NS(=O)(=O)C2=CC=CC=C2OCCCl',3.260038251795 +'C(C(=O)O)OC1=NC(=C(C(=C1Cl)N)Cl)F',2.70762229375841 +'CC1=C(C(=O)CC1OC(=O)C2C(C2(C)C)C=C(C)C)CC#C',3.49996484386965 +'C1C(COC1(CN2C=NC=N2)C3=C(C=C(C=C3)Cl)Cl)Br',4.76483992624863 +'C1=NNC(=N1)N',4.52675248773797 +'C1=CC(=C(C(=C1)F)C(=O)NC(=O)NC2=CC(=C(C(=C2F)Cl)F)Cl)F',4.16607614499238 +'C1=CC(=CC=C1OS(=O)(=O)C2=CC=C(C=C2)Cl)Cl',5.08373349418451 +'FC(F)(F)C(=CC(N(=O)=O)=C1N(C(C)C)C(C)C)C=C1N(=O)=O',2.52540641675307 +'CC1=C(C(=O)CC1OC(=O)C2C(C2(C)C)C=C(C)C)CC=C',3.60553192639024 +'C1=CC(=C(C(=C1)Cl)C#N)Cl',4.83761727241192 +'C1C(O1)COC2=CC=CC=C2C3=CC=CC=C3',2.65565785542345 +'CC1=CC=CC=C1OCC2=CC=CC=C2C(=NOC)C(=O)OC',2.92199532671878 +'O=N(=O)C(C(=C1N(=O)=O)N(C(C)C)C(C)C)=CC(=C1)S(=O)(=O)N',3.97297179822463 +'C1=CC(=C(C2=NC=C(C=C21)Cl)C(=O)O)Cl',2.50482391995124 +'CC(C)NC(=O)N1CC(=O)N(C1=O)C2=CC(=CC(=C2)Cl)Cl',3.85597533208895 +'CCCN(CCCl)C1=C(C=C(C=C1[N+](=O)[O-])C(F)(F)F)[N+](=O)[O-]',3.24487034075484 +'C1=CC=C(C=C1)C2=CC=CC=C2O',2.23097792739447 +'O=C(N(C)C)Nc(cccc1C(F)(F)F)c1',4.18977535089103 +'C1=CC(=NC(=C1)Cl)C(Cl)(Cl)Cl',5.36343657222619 +'Clc1cc(Cl)cc(Cl)c1OCCN(CCC)C(=O)n2cncc2',4.7008945110302 +'CC1=CC(=C(C=C1NC(=O)C)NS(=O)(=O)C(F)(F)F)C',4.05086251778066 +'C(=C(I)I)(I)I',4.02664705683052 +'C1=C(C=C(C(=C1Cl)N2C(=C(C(=N2)C#N)S(=O)C(F)(F)F)N)Cl)C(F)(F)F',6.8624770260417 +'O=C(N(C)C)Nc(ccc(c1Cl)Cl)c1',4.57165200886706 +'CC1=C(C(=O)CC1OC(=O)C2C(C2(C)C)C=C(C)C)CC=C',4.09142710541740 +'CC1=CC2=C(C=C1)N=C3C(=N2)SC(=O)S3',4.49470628000702 +'CC(C)N(C(=O)CCl)c1ccccc1',3.96396832169828 +'CC(C)C1(C(=O)NC(=N1)C2=C(C=CC=N2)C(=O)O)C',2.71813034538638 +'CC1(C(C1(C)C)C(=O)OC(C#N)C2=CC(=CC=C2)OC3=CC=CC=C3)C',4.25443178297333 +'CN1CN(C(=S)SC1)C',3.73313384224274 +'ClC(Cl)=CC1C(C)(C)C1C(=O)OC(C(#N))c2cccc(Oc3ccccc3)c2',3.74434218472656 +'ClC2C1OC1C3C2C4(Cl)C(=C(Cl)C3(Cl)C4(Cl)Cl)Cl',6.28927348401756 +'CCOC(=O)CN1C2=C(C=CC=C2Cl)SC1=O',4.33721159291063 +'CCCN(CCC)C1=C(C=C(C(=C1[N+](=O)[O-])N)C(F)(F)F)[N+](=O)[O-]',4.0760849833355 +'C1=CC=C(C=C1)C(CCC2=CC=C(C=C2)Cl)(CN3C=NC=N3)C#N',3.92533540454444 +'CC(C)(C)C(CCC1=CC=C(C=C1)Cl)(CN2C=NC=N2)O',4.28689742390489 +'CC1=C(C=CC=C1COC(=O)C2C(C2(C)C)C=C(C(F)(F)F)Cl)C3=CC=CC=C3',4.92723460128442 +'C(=CC=C1)(C2=C1)NC(=N2)C(=CS3)N=C3',3.70167089115788 +'C1=C(C=C(C(=C1Cl)N)Cl)[N+](=O)[O-]',3.13990879364539 +'CC1=C(C=C(C=C1C(=O)N)[N+](=O)[O-])[N+](=O)[O-]',4.55660790505055 +'CC(C)OC1=CC=CC(=C1)NC(=O)C2=CC=CC=C2C(F)(F)F',2.81064866255668 +'OC(c1ccc(Cl)cc1)(c2ccc(Cl)cc2)C(Cl)(Cl)Cl',5.17083139418745 +'O=P(O)(O)CCCl',2.51051495802278 +'CN(C(=O)NC1=CC=C(C=C1)Br)OC',4.31655713179121 +'CC1=CC(=CC=C1)NC(=O)OC2=CC=CC(=C2)NC(=O)OC',4.0796286862285 +'CC(C)(C)C1=NN=C(S1)N2C(CN(C2=O)C)O',3.70982035175725 +'S=P(OCC)(OCC)Oc1ccc2C(C)=C(Cl)C(=O)Oc2c1',5.32917717728496 +'COC(=O)c1ccccc1S(=O)(=O)NC(=O)N(C)c2nc(OC)nc(C)n2',4.50011608554638 +'C1=CC=C(C(=C1)NC2=NC(=NC(=N2)Cl)Cl)Cl',5.37945812670042 +'CC1=C(C=CC(=C1)OP(=S)(OC)OC)[N+](=O)[O-]',5.78008872366218 +'COc1c(Cl)ccc(Cl)c1C(=O)(O)',3.28376800169458 +'CC1(C(C1C(=O)OC(C#N)C2=CC(=CC=C2)OC3=CC=CC=C3)C=C(Br)Br)C',5.30552261110582 +'C1=CC=C(C(=C1)C(C2=CC=C(C=C2)F)(C3=CN=CN=C3)O)Cl',5.10001384041789 +'c1ccc2nc(NC(=O)OC)n(C(=O)NCCCC)c2c1',3.40217570413585 +'CCOC(=O)COC(=O)C1=C(C=CC(=C1)OC2=C(C=C(C=C2)C(F)(F)F)Cl)[N+](=O)[O-]',4.25309221972639 +'CC(C)(C)C(C(N1C=NC=N1)OC2=CC=C(C=C2)C3=CC=CC=C3)O',4.13022504615292 +'CCNC(=O)NC(=O)C(=NOC)C#N',3.81561566158005 +'CCOC1=C(C=CC(=C1)OC2=C(C=C(C=C2)C(F)(F)F)Cl)[N+](=O)[O-]',3.95628893719942 +'CC1=NC=C(N1CCO)[N+](=O)[O-]',3.05729569283336 +'O=C(N(SC(Cl)(Cl)Cl)C(=O)c1cccc2)c12',2.77313899543591 +'CC(C)(C)c2ccc(OC1CCCCC1OS(=O)OCC#C)cc2',3.54465374823881 +'CCCCC(CN1C=NC=N1)(C2=C(C=C(C=C2)Cl)Cl)O',4.82512253178873 +'CC(C)(C)C(C(=CC1=C(C=C(C=C1)Cl)Cl)N2C=NC=N2)O',3.81454188371475 +'C1=CC(C2C1C3(C(=C(C2(C3(Cl)Cl)Cl)Cl)Cl)Cl)Cl',5.9922949848715 +'C1=CC=C2C(=C1)C(=O)C3=C(C2=O)SC(=C(S3)C#N)C#N',4.47176647572299 +'CC1=NN(C(=C1C=NOCC2=CC=C(C=C2)C(=O)OC(C)(C)C)OC3=CC=CC=C3)C',5.13623540476555 +'CS(=O)(=O)C1=C(C=CC(=C1)C(F)(F)F)C(=O)C2=C(ON=C2)C3CC3',4.25445174537182 +'CC1=C(N=C(N=C1OC(=O)N(C)C)N(C)C)C',4.28018891498254 +'CCN(CC)C(=O)C(Cl)=C(C)OP(=O)(OC)OC',5.30057855955201 +'C1=CC(=CC=C1C(CN)O)O',2.78725763359614 +'CC1=C(C(=CC=C1)C)N(C(=O)COC)N2CCOC2=O',3.74554900711723 +'c1c(C(F)(F)F)cccc1N2C(=O)C(Cl)=C(NC)C=N2',4.20939714153443 +'CCC(C)NC1=C(C=C(C=C1[N+](=O)[O-])C(C)(C)C)[N+](=O)[O-]',3.77134379610358 +'C1=CC(=CC=C1S(=O)(=O)C2=CC(=C(C=C2Cl)Cl)Cl)Cl',3.18978539843532 +'CCCCC1=C(NC(=NC1=O)NCC)C',3.92280444363211 +'n(c(nc(n1)NCC)NCC)c1Cl',4.58033674324961 +'FC(F)(F)C(C=C1N(=O)=O)=CC(N(=O)=O)=C1N(CC)CC(C)=C',4.42587730748324 +'C1CCC(C1)N(CC2=CC=C(C=C2)Cl)C(=O)NC3=CC=CC=C3',4.11903913677133 +'CS(=O)(=O)NC(=O)C1=C(C=CC(=C1)OC2=C(C=C(C=C2)C(F)(F)F)Cl)[N+](=O)[O-]',3.94325990345253 +'CCOC(=O)C(C)OC1=CC=C(C=C1)OC2=NC3=C(O2)C=C(C=C3)Cl',4.60419765136131 +'CCC1=C(C(=CC=C1)CC)N(CNC(=O)C)C(=O)CCl',3.67657281690409 +'NC(=N)NCCCCCCCCCCCC(OC(=O)C)',3.99309483347533 +'C1=CC(=CC(=C1)Cl)NC(=O)OCC#CCCl',2.75857660132254 +'CC(C)C(C(=O)OC(C(#N))c2cccc(Oc1ccccc1)c2)c3ccc(Cl)cc3',4.22520594870835 +'CC(C)C1=C(C=CC(=C1)C(C)(C)C2=CC(=C(C=C2)O)C(C)C)O',4.09683471023993 +'CCN(CC1=C(C=CC=C1Cl)F)C2=C(C=C(C=C2[N+](=O)[O-])C(F)(F)F)[N+](=O)[O-]',3.92606530797808 +'CCCCCCCCSC(=O)OC1=CC(=NN=C1C2=CC=CC=C2)Cl',3.74923930876524 +'CC1=C(C(=O)CC1OC(=O)C2C(C2(C)C)C=C(C)C)CC=C',4.3407141033807 +'CCCCNC(=O)N1C2=CC=CC=C2N=C1NC(=O)OC',3.06493353581742 +'CC1=C(C(=CC=C1)C)N(C(C)C(=O)OC)C(=O)CC2=CC=CC=C2',3.84966174557959 +'CC(C)C(C1=CC=C(C=C1)OC(F)F)C(=O)OC(C#N)C2=CC(=CC=C2)OC3=CC=CC=C3',4.87646988000983 +'Clc1ccccc1c2nnc(c3ccccc3Cl)nn2',4.1806220183605 +'CCOC(=O)NCCOC1=CC=C(C=C1)OC2=CC=CC=C2',4.4790525467538 +'CCC1=C(C(=CC=C1)CC)N(CC(=O)OCC)C(=O)CCl',3.79491137150459 +'c1(O2)c(CC2(C)C)cccc1OC(=O)N(C)SN(CCCC)CCCC',4.18246564622765 +'CCCCOC(=O)C(C)OC1=CC=C(C=C1)OC2=NC=C(C=C2)C(F)(F)F',5.10648736510651 +'COC1=CC(=C(C=C1Cl)OC)Cl',3.21917344408706 +'CCOP(=S)(OCC)OC1=NN(C(=N1)Cl)C(C)C',4.39966173548004 +'n(c(nc(n1)NC(C)C)NCC)c1Cl',3.93587643048823 +'CC(C)(C)C(C(=CC1=CC=C(C=C1)Cl)N2C=NC=N2)O',3.8694430122441 +'CCCCCCCCc1cc(N(=O)(=O))c(OC(=O)C=CC)c(c1)N(=O)(=O)',3.8625999735624 +'c1cc(OC(F)(F)F)ccc1C(O)(C(C)C)c2cncnc2',4.41176854866759 +'COP(=O)(C(C(Cl)(Cl)Cl)O)OC',4.10964043198952 +'C1=CC(=C(C=C1C(F)(F)F)Cl)OC2=CC(=C(C=C2)[N+](=O)[O-])C(=O)O',3.46138721019571 +'CCCN(CC1CC1)C2=C(C=C(C=C2[N+](=O)[O-])C(F)(F)F)[N+](=O)[O-]',4.8417219607834 +'CCOC(=O)C(C)OC(=O)C1=C(C=CC(=C1)OC2=C(C=C(C=C2)C(F)(F)F)Cl)[N+](=O)[O-]',3.96545863474241 +'CCSC(=O)N1CCCCCC1',4.10198823735002 +'CCC1=CC=C(C=C1)C(=O)NN(C(=O)C2=CC(=CC(=C2)C)C)C(C)(C)C',3.86588082257473 +'ClC(Cl)C(Cl)(Cl)SN2C(=O)C1CC=CCC1C2(=O)',4.36681001970786 +'COC(=O)C1=CC=CC=C1S(=O)(=O)NC(=O)NC2=NC(=CC(=N2)OC(F)F)OC(F)F',3.52443042732356 +'CC(C)(C)C(C(N1C=NC=N1)OC2=CC=C(C=C2)Cl)O',4.07300621285581 +'CC1=C(C=CC(=C1)Cl)OCC(=O)O',4.70031198338967 +'COC=C(C1=CC=CC=C1OC2=NC=NC(=C2)OC3=CC=CC=C3C#N)C(=O)OC',3.81158305905272 +'C1=CC=C(C(=C1)C(C2=CC=C(C=C2)Cl)(C3=CN=CN=C3)O)Cl',5.15835722073531 +'[O-]Br(=O)=O',4.3215481796762 +'OP(=O)OCC',2.4395258763695 +'COP(N)(=O)SC',6.14961682124539 +'CCOP(=O)(NC(C)C)Oc1ccc(SC)c(C)c1',5.30586339308612 +'CCOP(=S)(OCC)SCCSCC',6.8363304797203 +'CCOP(=S)(OCC)SCSP(=S)(OCC)OCC',5.28383935473594 +'O=C(OCC(CCCC)CC)CCCCC(=O)OCC(CCCC)CC',2.39277487311710 +'CN(C=Nc1ccc(C)cc1C)C=Nc2ccc(C)cc2C',4.46746902029786 +[C@@]14([C@@H]5OCC1=CC=C[C@@H]([C@H](O[C@H]2C[C@@H]([C@H]([C@@H](O2)C)O[C@H]3C[C@@H]([C@H]([C@@H](O3)C)O)OC)OC)C(=CC[C@@H]6C[C@H](OC([C@@H]4C=C([C@H]5O)C)=O)C[C@]7(O6)O[C@@H]([C@H](C=C7)C)[C@H](CC)C)C)C)O,5.64002822248439 +'O=C(N(S(=O)(=O)Nc1cccc2)C(C)C)c12',3.83664755457448 +'S=P(OC)(OC)SCN1C(=O)SC(OC)=N1',5.38357309992515 +'C(#N)Cl',2.94356799915553 +'C(#N)Br',2.93862388168010 +'C1=CC(=CC=C1C(C2=CC=C(C=C2)Cl)C(Cl)(Cl)Cl)Cl',6.15165939778125 +'c(cccc1)(c1)C(C)C',2.56004605053309 +'CCCN(CCC)C(=O)SCC',3.87925249559703 +'NC(CCCC1)C1',3.21824710516194 +'ClC1CC2C(C1Cl)C3(Cl)C(=C(Cl)C2(Cl)C3(Cl)Cl)Cl',4.83439806636601 +'CC(C)OC(=O)NC1=CC(=CC=C1)Cl',2.32972480951647 +'COC(=O)c1c(Cl)c(Cl)c(C(=O)OC)c(Cl)c1Cl',4.52109130295968 +'COC(=O)C1=CC=C(C=C1)C(=O)OC',3.19130342987610 +'N(C(=S)NC1)C1',5.611332968427 +'O=C(N(OC)C)Nc(ccc(c1Cl)Cl)c1',4.99842308366263 +'c(cccc1)(c1)C=C',2.56281074475285 +'COC(=O)c1ccccc1S(=O)(=O)NC(=O)Nc2nc(OC)nc(C)n2',3.18339945768247 +'C1=CC(=CC=C1N)Cl',4.00884378520503 +'FC(F)(F)C(Cl)=CC1C(C)(C)C1C(=O)OC(C(#N))c2cc(Oc3ccccc3)ccc2',4.55615777900042 +'C(Cl)(Br)Br',3.86380195834146 +'C=C(Cl)Cl',3.84038967397096 +'C(C=CCl)Cl',4.33763486202989 +'COP(=O)(OC)OC(=CCl)c1cc(Cl)c(Cl)cc1Cl',3.86446577561058 +'Oc(ccc(c1)C(c(ccc(O)c2)c2)(C)C)c1',3.65950992099517 +'O=C(OCc(cccc1)c1)c(c(ccc2)C(=O)OCCCC)c2',2.82255713911138 +'O=C(NCCCC1)C1',2.95677386828604 +'c(cccc1)(c1)Cl',2.97219087736775 +'C(Cl)(Cl)Cl',3.29877173860401 +'ClCCl',3.20825373509371 +'C1C2C3C(C1C4C2O4)C5(C(=C(C3(C5(Cl)Cl)Cl)Cl)Cl)Cl',6.48391158599853 +'OCCO',1.79286663192634 +'O=C(C=C(CC1(C)C)C)C1',2.88767656912200 +'C(F)(Cl)(Cl)Cl',2.59506047452425 +'CCc1cccc(CC)c1N(COC)C(=O)CCl',4.28486094761281 +'c1ccccc1c2c(C)c(COC(=O)C3C(C)(C)C3C=C(Cl)C(F)(F)F)ccc2',4.92723460128442 +'n1c(Cl)cc(OC)nc1NC(=O)NS(=O)(=O)c2ccccc2C(=O)OCC',3.52095051170688 +'O=C(NC(=O)c(c(F)ccc1)c1F)Nc(ccc(c2)Cl)c2',4.60022325981506 +'c(cccc1)(c1)CC',2.56208837510252 +'O=C(N(SC(Cl)(Cl)Cl)C(=O)c1cccc2)c12',3.87004900844397 +'Clc1cc(C(F)(F)F)cnc1Oc2ccc(OC(C)C(=O)OC)cc2',5.57487232351041 +'C#N',2.94040947259108 +'ClC(C(OC(C=C2C(=O)OC(C)C(=O)OCC)=CC=C2N(=O)=O)=C1)=CC=C1C(F)(F)F',3.96545863474241 +'c1c(C(F)(F)F)cccc1N2C(=O)C(Cl)=C(NC)C=N2',3.77270454387038 +'O=N(=O)C(C(=C1N(=O)=O)N(C(C)C)C(C)C)=CC(=C1)S(=O)(=O)N',3.88631461533234 +'CN(=CC=C1C(C=C2)=CC=N2C)C=C1',4.69607191571383 +'C1=C(C=C(C=C1[N+](=O)[O-])[N+](=O)[O-])[N+](=O)[O-]',4.20441460583146 +'C(=C)Cl',4.68192429615426 +'C1CCC(=O)CC1',2.03281793688456 +'CC1(C(C1(C)C)C(=O)OC(C#N)C2=CC(=CC=C2)OC3=CC=CC=C3)C',4.14541137996302 +'C1=CC(=O)NNC1(=O)',2.35058431121584 +'CCSC(=O)N1CCCCCC1',4.97151330020725 +'C(C(Cl)(Cl)Cl)(O)O',3.08555504738041 +'ClC2C1OC1C3C2C4(Cl)C(=C(Cl)C3(Cl)C4(Cl)Cl)Cl',7.1923634710095 +'Clc1cc(C(F)(F)F)ccc1Oc2cc(OCC)c(N(=O)(=O))cc2',4.55834892852739 +'c1cc(Cl)ccc1C(C(#N))(CCCC)Cn2ncnc2',4.46756491519242 +'CC1=C(C=C(C=C1[N+](=O)[O-])[N+](=O)[O-])[N+](=O)[O-]',5.055246608541 +'CC(C)OC(=O)C(C1=CC=C(C=C1)Br)(C2=CC=C(C=C2)Br)O',4.21658723866328 +'C[N+](C)(C)CCCl',2.97460527968547 +'CCC(=C1C(=O)CC(CC1=O)CC(C)SCC)NOCC=CCl',3.62169695860399 +'CC1=NC(=NC(=C1)C2CC2)NC3=CC=CC=C3',3.80128998933051 +'N(c(cccc1)c1)c(cccc2)c2',3.83051794413252 +'CC1(C(=O)N(C(=O)O1)NC2=CC=CC=C2)C3=CC=C(C=C3)OC4=CC=CC=C4',4.34801416963502 +'CC1(CCCCC1)C(=O)NC2=C(C(=C(C=C2)O)Cl)Cl',3.01490626247445 +'C1=CC(=C2C(=C1)OC(O2)(F)F)C3=CNC=C3C#N',3.35338292576111 +'C(F)(F)(F)c1ccccc1C(=O)Nc2cccc(OC(C)C)c2',3.57009941427408 +'C(CCCCN=C(N)N)CCCNCCCCCCCCN=C(N)N',4.27216545257855 +'C1CN(C(=N1)N[N+](=O)[O-])CC2=CN=C(C=C2)Cl',4.17721556192143 +'COC(=O)C12CC3=C(C1=NN(CO2)C(=O)N(C4=CC=C(C=C4)OC(F)(F)F)C(=O)OC)C=CC(=C3)Cl',5.16619526358129 +'CC1=CC=CC=C1OCC2=CC=CC=C2C(=NOC)C(=O)OC',2.92782487037951 +'CC1=CC(=CC(=C1)C(=O)N(C(C)(C)C)NC(=O)C2=C(C(=CC=C2)OC)C)C',2.95255951099906 +'C1=CC(=C(C(=C1)F)C(=O)NC(=O)NC2=CC(=C(C=C2)OC(C(OC(F)(F)F)F)(F)F)Cl)F',4.13628410350378 +'CC1=CC=C(C=C1)N(SC(F)(Cl)Cl)S(=O)(=O)N(C)C',4.28537828278078 +'CC(C)(C)C1=C(C=CC(=C1)O)O',2.86849281697225 +'CC(=NOCC1=CC=CC=C1C(=NOC)C(=O)OC)C2=CC(=CC=C2)C(F)(F)F',3.83290371721801 +'COC(=O)N(C1=CC=CC=C1COC2=NN(C=C2)C3=CC=C(C=C3)Cl)OC',4.63438424347854 +'CC(C)N1C(=NC(C)(C)C)SCN(C1=O)C2=CC=CC=C2',4.54540426969100 +'C1=CC=C(C(=C1)C2=NN=C(N=N2)C3=CC=CC=C3Cl)Cl',4.24360591089568 +'CCCC(=C1C(=O)CC(CC1=O)C2CCCSC2)NOCC',4.0653478352871 +'C1CC1NC2=NC(=C(C(=N2)N)C#N)N',3.93679970507275 +'C(C=C1)(=N(C=C1)CC2)C(N2=C3)=CC=C3',5.50950218614247 +'C1=CC=C2C(=C1)C(=O)C3=C(C2=O)SC(=C(S3)C#N)C#N',4.69361522533935 +'CCOC1=CC2=C(C=C1)NC(C=C2C)(C)C',4.25789199055837 +'C1=CC=C(C=C1)C(CCC2=CC=C(C=C2)Cl)(CN3C=NC=N3)C#N',4.05027414115274 +'CC1CN(CC(O1)C)CC(C)CC2=CC=C(C=C2)C(C)(C)C',5.25168418782516 +'C[Si](CN1C=NC=N1)(C2=CC=C(C=C2)F)C3=CC=C(C=C3)F',5.19782165018731 +'c1cc(Cl)cc(Cl)c1C(OCC=C)Cn2cncc2',4.29692796857781 +'CN(=CC=C1C(C=C2)=CC=N2C)C=C1',4.86356300300759 +'CCCCOCCOCCOCC1=CC2=C(C=C1CCC)OCO2',3.52947976153744 +'Clc1cc(Cl)ccc1C2(Cn3ncnc3)OC(CCC)CO2',3.5520346361573 +'C(=CC=C1)(C2=C1)NC(=N2)C(=CS3)N=C3',3.82660962776618 +'CCOC1=CC=C(C=C1)C(C)(C)COCC2=CC(=CC=C2)OC3=CC=CC=C3',4.16077781336093 +'CC(C)(C)c2ccc(OC1CCCCC1OS(=O)OCC#C)cc2',4.26590014728598 +'CC(COC1=CC=C(C=C1)OC2=CC=CC=C2)OC3=CC=CC=N3',3.36087697276960 +'CC(C)(C)C(=O)C(N1C=NC=N1)OC2=CC=C(C=C2)Cl',3.41107116109321 +'CC(C)(C)C(C(N1C=NC=N1)OC2=CC=C(C=C2)Cl)O',3.44975692245790 +'c1ccccc1c2c(C)c(COC(=O)C3C(C)(C)C3C=C(Cl)C(F)(F)F)ccc2',4.7231146186285 +'CC1(C(C1C(=O)OC(C#N)C2=CC(=C(C=C2)F)OC3=CC=CC=C3)C=C(Cl)Cl)C',4.85962620215948 +'CC1(C(C1C(=O)OC(C#N)C2=CC(=C(C=C2)F)OC3=CC=CC=C3)C=C(Cl)Cl)C',4.5585962064955 +'ClC(Cl)=CC1C(C)(C)C1C(=O)OC(C(#N))c2cccc(Oc3ccccc3)c2',3.92043344378224 +'ClC1CC2C(C1Cl)C3(Cl)C(=C(Cl)C2(Cl)C3(Cl)Cl)Cl',6.21460930807761 +'ClC4=C(Cl)C5(Cl)C3C1CC(C2OC12)C3C4(Cl)C5(Cl)Cl',6.58082159900658 +'C1C2C3C(C1C4C2O4)C5(C(=C(C3(C5(Cl)Cl)Cl)Cl)Cl)Cl',6.18288159033454 +'C1(C(C(C(C(C1Cl)Cl)Cl)Cl)Cl)Cl',4.79154110643314 +'CCC(=O)Nc1ccc(Cl)c(Cl)c1',3.45780196740732 +'C1(=C(C(=C(C(=C1Cl)Cl)Cl)Cl)Cl)[N+](=O)[O-]',3.32418644119937 +'C1C2C(COS(=O)O1)C3(C(=C(C2(C3(Cl)Cl)Cl)Cl)Cl)Cl',5.14711652367221 +'O=C(N(SC(Cl)(Cl)Cl)C(=O)c1cccc2)c12',3.77313899543591 +'CC(C(=O)O)OC1=CC=C(C=C1)OC2=C(C=C(C=N2)C(F)(F)F)Cl',6.55834892852739 +'CCCCC(CN1C=NC=N1)(C#N)C2=CC=C(C=C2)Cl',4.46933393793126 +'Clc1cc(Cl)cc(Cl)c1OCCN(CCC)C(=O)n2cncc2',4.86838559832397 +'COP(=O)(NC(=O)(C))SC',4.86490452310016 +'CCOP(=O)(OCC)OC(=CCl)C1=C(C=C(C=C1)Cl)Cl',5.3796920956126 +'CCOP(=S)(OCC)SCCSCC',6.09596779022605 +'O=P(O)(O)CCCl',4.0806685706873 +'CCCSP(=O)(OCC)SCCC',4.95305958493745 +'CCOP(=O)(NC(C)C)Oc1ccc(SC)c(C)c1',5.25150573076352 +'COP(=S)(OC)Oc1ccc(SC)c(C)c1',5.58722449762503 +'OC(=O)C(N)CCP(C)(=O)O',4.71391476838473 +'OC(=O)CNCP(O)(O)=O',2.75095321211059 +'CCOC(=O)CC(SP(=S)(OC)OC)C(=O)OCC',2.96268235505315 +'COP(N)(=O)SC',5.68721882334643 +'CC(=CC(=O)OC)OP(=O)(OC)OC',5.80646736824669 +'CCOP(=S)(OCC)SCSCC',6.2114833717655 +'CCOP(=S)(OCC)SCSC(C)(C)C',6.68189008451404 +'S=P(OC)(OC)SCN1N=Nc2ccccc2C1(=O)',5.08988368084419 +'CCOP(=S)(OCC)OC1=NC(=C(C=C1Cl)Cl)Cl',5.54479494223028 +'CCOP(=S)(OCC)OC1=NC(=NC(=C1)C)C(C)C',4.71993889259734 +'CCC1=NC(=CC(=N1)OP(=S)(OC)OC)OCC',5.8126040303238 +'S=P(OC)(OC)SCN1C(=O)SC(OC)=N1',5.27636313027728 +'CCOP(=S)(OCC)SCN1C2=C(C=C(C=C2)Cl)OC1=O',5.26459183786176 +'COP(=S)(OC)SCN2C(=O)c1ccccc1C2(=O)',4.54725636091897 +'CCOC(=O)C1=CN2C(=CC(=N2)OP(=S)(OCC)OCC)N=C1C',4.97007298557879 +'CCOP(=S)(OCC)OC1=NN(C=N1)C2=CC=CC=C2',5.38203437103643 +'O=C(Oc(c(c(ccc1)cc2)c1)c2)NC',3.52552257057249 +'CC1=CC(=CC(=C1SC)C)OC(=O)NC',4.38429231462288 +'CNC(=O)ON=C(C)SC',3.90904789636717 +'CCCOC(=O)NCCCN(C)C',2.44226598159187 +'COC(=O)NC1=NC2=CC=CC=C2N1',3.40639632281981 +'CC1=C(N=C(N=C1OC(=O)N(C)C)N(C)C)C',4.2871938165512 +'CNC(=O)CCSCCSP(=O)(OC)OC',5.72599715999116 +'N(C(=S)SSC(N(C)C)=S)(C)C',4.30181261256647 +'C1=NNC(=N1)N',4.22572249207399 +'CCCCCCCCc1cc(N(=O)(=O))c(OC(=O)C=CC)c(c1)N(=O)(=O)',3.75539000391453 +'C1=CC=C(C=C1)[Sn](C2=CC=CC=C2)C3=CC=CC=C3',6.0669625480302 +'O=C(NC(=O)c(c(F)ccc1)c1F)Nc(ccc(c2)Cl)c2',4.64721982249128 +'N(C(=S)NC1)C1',4.91236296409098 +'C1=CC(=C(C(=C1)F)C(=O)NC(=O)NC2=CC(=C(C(=C2F)Cl)F)Cl)F',4.18310948429116 +'CCCSC1=CC2=C(C=C1)N=C(N2)NC(=O)OC',4.12275865288522 +'C1CN(CCN1CCCC(=O)C2=CC=C(C=C2)F)C3=CC=CC=N3',3.45437537377312 +'CC1(C2C(C3C(C(=O)C(=C(N)O)C(=O)C3(C(=O)C2=C(C4=C(C=CC(=C41)Cl)O)O)O)N(C)C)O)O',1.97849569899962 +'CC1=CC(=C(C=C1NC(=O)C2=CC(=CC(=C2O)I)I)Cl)C(C#N)C3=CC=C(C=C3)Cl',4.82156180249896 +'CN1CC2CC1CN2C3=C(C=C4C(=C3)N(C=C(C4=O)C(=O)O)C5CC5)F',3.85415878578584 +'C1=CC(=CC=C1C(C#N)C2=C(C=CC(=C2Cl)N3C(=O)NC(=O)C=N3)Cl)Cl',4.43418336046643 +'CC1=NC=C(N1C)[N+](=O)[O-]',3.97352186635665 +'CCN1CCN(CC1)C2=C(C=C3C(=C2)N(C=C(C3=O)C(=O)O)C4CC4)F',4.14059829999974 +'CC1C=CC=C2COC3C2(C(C=C(C3O)C)C(=O)OC4CC(CC=C(C1OC5CC(C(C(O5)C)OC6CC(C(C(O6)C)NC(=O)C)OC)OC)C)OC7(C4)C=CC(C(O7)C(C)C)C)O',5.95429183284051 +'COCC(=O)NC1=C(C=CC(=C1)SC2=CC=CC=C2)NC(=NC(=O)OC)NC(=O)OC',4.04773898332238 +'CC1CCC2=C3N1C=C(C(=O)C3=CC(=C2)F)C(=O)O',2.81499362006104 +'COC(=O)NC1=NC2=C(N1)C=C(C=C2)S(=O)C3=CC=CC=C3',5.1977587356423 +'CC1(C2CC3C(C(=O)C(=C(N)O)C(=O)C3(C(=O)C2=C(C4=C1C=CC=C4O)O)O)N(C)C)O',3.47171656401627 +'C1CN(CCN1CCCC(=O)C2=CC=C(C=C2)F)C3=CC=CC=N3',4.03795195940707 +'CC(C)NCC(COC1=CC=CC2=C1C3=CC=CC=C3N2)O',4.62967091273678 +'C1=CC(=CC=C1C(C#N)C2=C(C=CC(=C2Cl)N3C(=O)NC(=O)C=N3)Cl)Cl',4.24854678350451 +'CC1C=CC=C2COC3C2(C(C=C(C3O)C)C(=O)OC4CC(CC=C(C1OC5CC(C(C(O5)C)OC6CC(C(C(O6)C)NC(=O)C)OC)OC)C)OC7(C4)C=CC(C(O7)C(C)C)C)O',5.55635182416848 +'COP(=S)(OC)Oc1ccc(SC)c(C)c1',5.79134448028095 +'C(C(C(C(C1Cl)Cl)Cl)Cl)(C1Cl)Cl',4.56054897737691 +'C(C(C(C(C1Cl)Cl)Cl)Cl)(C1Cl)Cl',4.86157897304089 +'CC(N(C)C)CN(C(=CC=C3)C1=C3)C(=CC=C2)C(=C2)S1',4.23385066979149 +'C1=C(C=C(C(=C1Cl)N)Cl)[N+](=O)[O-]',2.93578881098946 +'c(cccc1)(c1)C=C',2.41559561343340 diff --git a/original/LOAEL_mg.csv b/original/LOAEL_mg.csv new file mode 100755 index 0000000..30dea21 --- /dev/null +++ b/original/LOAEL_mg.csv @@ -0,0 +1,566 @@ +SMILES,LOAEL_mg_kg_bw_day +'COc1cc(c(C)cc1N=Nc2c(O)ccc3cc(ccc23)S(OH)(=O)=O)S(OH)(=O)=O',3739 +'O1C(=O)C(O)=C(O)C1C(O)CO',3051 +'C1(C)=C(C=CC(C)=CC=CC(C)=CC=CC=C(C)C=CC=C(C)C(=O)OC)C(C)(C)CCC1',500 +'c(cccc1)(c1)C(C)C',462 +'O=C(OCCCC)c(c(ccc1)C(=O)OCCCC)c1',600 +'O=C(OCC)c(c(ccc1)C(=O)OCC)c1',4435 +'O=C(OC(OC(OC1C)C)C1)C',125 +'Oc(c(ccc1)C)c1C',6 +'Oc(ccc(c1C)C)c1',14 +'O=C(OCC)C=C',248 +'c(cccc1)(c1)CC',408 +'OCCO',250 +'c(ccc1C(=O)OCC(=O)OCC)cc1C(=O)OCC',2500 +'O=C',82 +'O=C(O)C=CC(=O)O',1081 +'OCC(O)CO',6883 +'O=C(OC)c(ccc(O)c1)c1',1500 +'O=C(OCCC)c(ccc(O)c1)c1',1500 +'CC(CCC(=O)(O))C3CCC4C2CCC1CC(O)CCC1(C)C2CCC34C',500 +'OC(C(CCC1C)C(C)C)C1',593 +'O=C(O)C(=C)C',248 +'O=C(OC)c(c(O)ccc1)c1',360 +'Oc(cccc1)c1',344 +'O=C(OCCC)c(cc(O)c(O)c1O)c1',864 +'OCC(O)C1C(O)=C(O)C(=O)O1',1554 +'c(cccc1)(c1)C=C',21 +'O=Cc(occ1)c1',60 +'NCCNc1cccc2ccccc12',79 +'CN(C)(C)CCCl',275 +'O=C(Nc(ccc(c1)C(=O)CCl)c1)C',1580 +'c(ccc(c1)Cl)(c1)C(c(ccc(c2)Cl)c2)C(Cl)(Cl)Cl',32 +'CC(Oc1cc(Cl)c(Cl)cc1Cl)C(=O)(O)',8.7 +'O=N(=O)C(=CC=C1OC)C=C1N=NC(C(O)=C2C(=O)NC(=CC=C4)C=C4N(=O)=O)=C(C=C3)C(=C2)C=C3',2100 +'O=N(=O)C(C=C1)=CC(OCCO)=C1NCCO',229 +'Cc1cccc(CC)c1N(C(=O)CCl)COCC',50 +'Clc(cc(c1)C(F)(F)F)c(c1)Oc(ccc2N(=O)(=O))cc2C(=O)OH',180 +'CCc1cccc(CC)c1N(COC)C(=O)CCl',15 +'O=C(Nc(ccc(OCC)c1N)c1)C',1185 +'Oc(ccc(N)c1)c1',686 +'CC(N)CC(=CC=C1)C=C1',5 +'O(c(ccc(c1)C=CC)c1)C',344 +'COc1ccc(N)cc1',474 +'O=C(O)c(c(N)ccc1)c1',2751 +'Clc2cccc(c2)c1ccccc1',4 +'O=C(NC(C(=O)OC)Cc(cccc1)c1)C(N)CC(=O)O',147 +'n1c2ccc(Cl)cc2ncc1Oc3ccc(OC(C)C(=O)OCC)cc3',3.7 +'COC(=O)NS(=O)(=O)c1ccc(N)cc1',180 +'S=P(OC)(OC)SCN1N=Nc2ccccc2C1(=O)',0.36 +'CNC(=O)Oc1ccccc1OC(C)C',50 +'CC(C)(C)C(=O)C(Oc1ccc(Cl)cc1)n2cncn2',25 +'O=S(O)(=O)C(=CC=C1)C=C1CN(CC)=C(C=C2)C=CC2=C(C(C=C3)=CC=C3N(C)C)C(C=C4)=CC=C4N(CC)CC(C=C5)=CC(=C5)S(=O)(=O)O',720 +'c(c(cccc1)c1)(cccc2)c2',250 +'BrC(Cl)Cl',130 +'ClC(Cl)C(Cl)(Cl)SN2C(=O)C1CC=CCC1C2(=O)',12 +'O=C(Oc(c(c(ccc1)cc2)c1)c2)NC',15.6 +'CC1=C(SCCO1)C(=O)Nc2ccccc2',30 +'ClC1CC2C(C1Cl)C3(Cl)C(=C(Cl)C2(Cl)C3(Cl)Cl)Cl',0.27 +'O=C(O)CCl',30 +'ClC(=CC=C1N)C=C1',6 +'CC(C)OC(=O)C(O)(c1ccc(Cl)cc1)c2ccc(Cl)cc2',9 +'n1c(OC)nc(C)nc1NC(=O)NS(=O)(=O)c2ccccc2Cl',25 +'OS(=O)(=O)C(C(=CC=C2)C1=C2)=CC=C1N=NC(C(O)=C3N=NC(C(C=C5)=C4C=C5)=CC=C4S(O)(=O)=O)=CC(=C3O)CO',736 +'S=P(OCC)(OCC)Oc1ccc2C(C)=C(Cl)C(=O)Oc2c1',0.8 +'CNP(=O)(OC)Oc1ccc(cc1Cl)C(C)(C)C',4 +'n1c(N)nc(N)nc1NC2CC2',15 +'COC(=O)c1c(Cl)c(Cl)c(C(=O)OC)c(Cl)c1Cl',500 +'O=C(O)C(Cl)(Cl)C',28.17 +'Nc1cc(N)c(O)cc1',25 +'FC(F)(Cl)Cl',150 +'ClCCl',50 +'O=P(OC)(OC)OC=C(Cl)Cl',2.3 +'OC(c1ccc(Cl)cc1)(c2ccc(Cl)cc2)C(Cl)(Cl)Cl',20 +'ClC4=C(Cl)C5(Cl)C3C1CC(C2OC12)C3C4(Cl)C5(Cl)Cl',0.05 +'CN(=C1C(C=C2)=CC=C2)N(C)C(=C1)C(C=C3)=CC=C3',125 +'O=C(NC(=O)c(c(F)ccc1)c1F)Nc(ccc(c2)Cl)c2',8 +'CC1=C(C)S(=O)(=O)CCS1(=O)=O',10 +'O=C(NC)CSP(OC)(OC)=S',0.25 +'COc1ccc(N)c(OC)c1',276 +'COP(=O)OC',100 +'CC(=C(N(=O)=O)C=C1N(=O)=O)C=C1',34 +'CN(C)C(=O)C(c1ccccc1)c2ccccc2',30 +'N(c(cccc1)c1)c(cccc2)c2',31 +'C(C=C1)(=N(C=C1)CC2)C(N2=C3)=CC=C3',0.58 +'CCOP(=S)(OCC)SCCSCC',0.1 +'NC(=S)NNC(N)=S',947 +'O=C(N(C)C)Nc(ccc(c1Cl)Cl)c1',6 +'O=P(O)(O)CCCl',150 +'O=C(OCC)C(O1)C1(c(cccc2)c2)C',175 +'COC(=O)NC(=NC1=C2)NC1=CC(=C2)SC(C=C3)=CC=C3',15 +'CN1C=C(c2ccccc2)C(=O)C(c3cc(C(F)(F)F)ccc3)=C1',25 +'c1cc(C(F)(F)F)cc(Cl)c1NC(C(C)C)C(=O)OC(C(#N))c2cccc(Oc3ccccc3)c2',2.5 +'S=P(OCC)(Sc1ccccc1)CC',1.58 +'n1c(C)nc(OC)nc1NC(=O)NS(=O)(=O)c2ccsc2C(=O)OC',25 +'C(C(C(C(C1Cl)Cl)Cl)Cl)(C1Cl)Cl',5 +'O=N(=O)N(CN1N(=O)=O)CN(C1)N(=O)=O',1.5 +'O=C(N=C(N(C1(=O))C)N(C)C)N1C(CCCC2)C2',50 +'n(c(c(ccc1)cc2)c1O)c2',143 +'c1cc(Cl)cc(Cl)c1C(OCC=C)Cn2cncc2',40 +'COc1cccc(OC)c1C(=O)Nc2onc(C(C)(CC)CC)c2',50.7 +'n1c(OC)cc(OC)nc1NC(=O)NS(=O)(=O)Cc2ccccc2C(=O)OC',309 +'CCOC(=O)CC(SP(=S)(OC)OC)C(=O)OCC',50 +'CN(C)(CCC1)CC1',150 +'O=P(SCCCC)(SCCCC)SCCCC',1.25 +'COCC(=O)N(C(C)C(=O)OC)c1c(C)cccc1C',62.5 +'S=P(OC)(OC)SCN1C(=O)SC(OC)=N1',2 +'CNC(=O)ON=C(C)SC',10 +'COP(=S)(OC)Oc1ccc(cc1)N(=O)(=O)',0.25 +'O=C1N(N)C(SC)=NN=C1C(C)(C)C',15 +'COP(=O)(OC)OC(Br)C(Cl)(Cl)Br',2 +'OC(C(N)C1O)C(C)OC1(C)OC(CC(C)(C(C2O)C(O)=O)OC(O)(C2)CC(O)CC(C)(O3)C3C=C4)C=CC=CC=CC=CCC(C)OC4=O',72 +'O=N(=O)c(ccc(c1N)C)c1',8 +'O=N(=O)c(c(N)ccc1N)c1',87 +'O=C(O)C(=C(N)C=C1N(=O)=O)C=C1',1185 +'O=N(=O)c(c(c(ccc1)cc2)c1)c2',165 +'c12c(N=Nc3ccccc3)c(O)ccc1cc(S(=O)(=O)O)cc2',180 +'CC(C)Oc1cc(c(Cl)cc1Cl)N2N=C(OC2(=O))C(C)(C)C',5 +'CNC(=O)ON=C(SC)C(=O)N(C)C',5 +'CCOP(=S)(OCC)Oc1ccc(cc1)N(=O)=O',3.5 +'Oc(c(c(c(c1Cl)Cl)Cl)Cl)c1Cl',10 +'NC(=N)NC(=N)NCCc1ccccc1',73 +'COP(=S)(OC)SCN2C(=O)c1ccccc1C2(=O)',20 +'CCN(CC)C(=O)C(Cl)=C(C)OP(=O)(OC)OC',12.3 +'ClC3C6(Cl)C4C2C1OC1C5C2C3(Cl)C(Cl)(C45)C6(Cl)Cl',0.7 +'O=C(OC(=O)c1cccc2)c12',1185 +'Nc1c(Cl)c(Cl)nc(C(=O)(O))c1Cl',60 +'CCN(CC)c1nc(C)cc(OP(=S)(OC)OC)n1',2.5 +'Nc3ccc2cc1ccc(N)cc1nc2c3',47 +'CCC(=O)Nc1ccc(Cl)c(Cl)c1',20 +'Clc1cc(Cl)ccc1C2(Cn3ncnc3)OC(CCC)CO2',25 +'O=C(N)c(nccn1)c1',789 +'Oc1cc(O)c2C(=O)C(O)=C(c3cc(O)c(O)cc3)Oc2c1',2034 +'CCC(O)(C)C#C',46 +'CC(C(NCC)=C1)=CC(C1=O2)=C(C(C2=C3)=CC(C)=C3NCC)C(=CC=C4)C(=C4)C(=O)OCC',12 +'O=C(NS(=O)(=O)c1cccc2)c12',3602 +'c1cc(Cl)ccc1C2SC(=O)N(C(=O)NC3CCCCC3)C2C',160 +'n(c(nc(n1)NCC)NCC)c1Cl',5 +'HOS(=O)(=O)NC1CCCCC1',3602 +'O=C(OCC(C1OCC(C1O)O)O)CCCCCCCCCCC',6883 +'O(CC1O)C(C1O)C(O)COC(=O)CCCCCCCCCCCCCCCCC',7203 +'O=S(=O)(Nc(nc(cc1C)C)n1)c(ccc(N)c2)c2',33 +'CCNc1nc(NC(C)(C)C)nc(SC)n1',15 +'Oc(c(cc(c1)C(C)(C)C)Cl)c1',216 +'C(C(Cl)Cl)(Cl)Cl',108 +'COP(=O)(OC)OC(=CCl)c1cc(Cl)c(Cl)cc1Cl',100 +'CCN(CC)C(=O)SCc1ccc(Cl)cc1',5 +'COC(=O)NC(=S)Nc1ccccc1NC(=S)NC(=O)OC',32 +'N(C(=S)SSC(N(C)C)=S)(C)C',15 +'c12OC(CCCC(C)CCCC(C)CCCC(C)C)(C)CCc1c(C)c(OC(=O)C)c(C)c2C',2000 +'Cc1cc(N)ccc1NOS(O)(=O)=O',184 +'C(Br)(C(Br)(Br)Br)C1C(C)(C)C1C(=O)OC(C(#N))c2cccc(Oc3ccccc3)c2',3 +'O=C(O)COc(c(cc(c1Cl)Cl)Cl)c1',10 +'FC(F)(F)C(=CC(N(=O)=O)=C1N(C(C)C)C(C)C)C=C1N(=O)=O',40 +'Cc1cc(C)c(N)cc1C',63 +'CC(O)(C(O)C(O1)C)CC1(C)OC(C(C)O2)C(C(O)C2(C)OC(C(C)C(O)CC(=O)OC(CC)C3COC(C(OC)C4OC)OC(C)C4O)C(CC=O)CC(C)C(=O)C=CC(=C3)C)N(C)C',500 +'c1c(Cl)cc(Cl)cc1N2C(=O)C(C)(C=C)OC2(=O)',72.9 +'O=C(OC(CCCC(O)CCCCCc1cc(O)cc2O)C)c12',0.2 +'COC(=O)C1(C2=CC=CC=C2C3=C1C=C(C=C3)Cl)O',150 +'CC(C(=O)O)OC1=CC(=CC=C1)Cl',100 +'P12P3P1P23',1472 +'C(CO)O',400 +'CCCCOCC(C)OCC(C)O',128 +'C(CO)O',2000 +'C(CO)O',920 +'[O-][As](=O)([O-])[O-]',6.25 +'[Si](CN1C=NC=N1)(C2=CC=C(C=C2)F)C3=CC=C(C=C3)F',2.3 +'N(C(=S)SSC(N(C)C)=S)(C)C',11.5 +'COP(=O)(N)SC',0.9 +'N(C(=S)SSC(N(C)C)=S)(C)C',5.47 +'COP(=O)(NC(=O)(C))SC',35 +'C1=CC=C(C=C1)NC(=O)NC2=CN=NS2',30 +'CCOP(=S)(NC(C)C)OC1=CC=CC=C1C(=O)OC(C)C',0.5 +'CC(=NOC(=O)N(C)SN(C)C(=O)ON=C(C)SC)SC',10 +'CCOP(=S)(OCC)OC1=NC(=NC(=C1)C)C(C)C',1.5 +'NC(CCCC1)C1',58.5 +'CN1C=C(c2ccccc2)C(=O)C(c3cc(C(F)(F)F)ccc3)=C1',32.5 +'ClC1CC2C(C1Cl)C3(Cl)C(=C(Cl)C2(Cl)C3(Cl)Cl)Cl',0.5 +'CCCCC(CC)COC(=O)C1=CC=CC=C1C(=O)OCC(CC)CCCC',200 +'OC(=O)CNCP(O)(O)=O',1000 +'C1CNC(=S)N1',0.23 +'O=C(N(OC)C)Nc(ccc(c1Cl)Cl)c1',6.25 +'C1=CC=C2C(=C1)NC(=S)S2',750 +'CCOP(=S)(OCC)OC1=NC(=C(C=C1Cl)Cl)Cl',10 +'c(c(c(c(c1Cl)Cl)Cl)Cl)(c1Cl)Cl',0.29 +'COc1ccc(cc1)C(c2ccc(OC)cc2)C(Cl)(Cl)Cl',125 +'C1=CC(=CC=C1Cl)Cl',300 +'CC(C)OC(=O)NC1=CC(=CC=C1)Cl',500 +'COP(=O)(OC)OC=C(Cl)Cl',2.15 +'CCOP(=S)(OCC)Oc1ccc(cc1)N(=O)=O',0.42 +'CNC(=O)N(C)c1nnc(s1)C(C)(C)C',40 +'CCCCOCCOCCOCC1=CC2=C(C=C1CCC)OCO2',250 +'CC(C(=O)O)OC1=C(C=C(C=C1)Cl)Cl',9 +'CC1(C(C1C(=O)OC(C#N)C2=CC(=C(C=C2)F)OC3=CC=CC=C3)C=C(Cl)Cl)C',12.5 +'C(#N)c(c(c(c(c1C(#N))Cl)Cl)Cl)c1Cl',4 +'O=C(OCC)C(O)(c(ccc(c1)Cl)c1)c(ccc(c2)Cl)c2',18.4 +'O=C(N(C)C)Nc(ccc(c1)Cl)c1',125 +'O=C(N(SC(Cl)(Cl)Cl)C(=O)C1CC=CC2)C12',100 +'CCc1cccc(C)c1N(C(C)COC)C(=O)CCl',150 +'C1=CC(=C(C=C1Cl)Cl)OCC(=O)O',5 +'CCNC1=NC(=NC(=N1)Cl)NC(C)(C)C#N',1.25 +'C(C(C(C(C1Cl)Cl)Cl)Cl)(C1Cl)Cl',4.6 +'COP(=S)(OC)OC1=CC(=C(C=C1Cl)Cl)Cl',50 +'C1C2C=CC1C3C2C4(C(=C(C3(C4(Cl)Cl)Cl)Cl)Cl)Cl',0.01 +'CC1(C(C1C(=O)OCC2=CC(=CC=C2)OC3=CC=CC=C3)C=C(Cl)Cl)C',25 +'CCN(CC)C(=O)C(C)OC1=CC=CC2=CC=CC=C21',100 +'ClC1C=CC2C1C3(Cl)C(=C(Cl)C2(Cl)C3(Cl)Cl)Cl',0.25 +'CC(=CC(=O)NC)OP(=O)(OC)OC',0.45 +'CC(C)C1(C)N=C(NC1(=O))c3nc2ccccc2cc3C(=O)(O)',20 +'CC(C)Nc1nc(Cl)nc(NC(C)C)n1',50 +'CC(C(=O)O)(Cl)Cl',50 +'CC1(C(C1C(=O)OC(C#N)C2=CC(=C(C=C2)F)OC3=CC=CC=C3)C=C(Cl)Cl)C',7.5 +'O=C(NC)CSP(OC)(OC)=S',5 +'C12C3(C4(C5(C3(C(C1(C5(C2(C4(Cl)Cl)Cl)Cl)Cl)(Cl)Cl)Cl)Cl)Cl)Cl',0.01 +'COC(=O)C1=CC=CC=C1C(=O)OC',2000 +'CCOP(=S)(OCC)SCSC(C)(C)C',0.05 +'CCC(C)SP(=O)(OCC)SC(C)CC',0.25 +'CCOP(=S)(OCC)SCSC(C)(C)C',2 +'C1C(C(C(=O)N1C2=CC=CC(=C2)C(F)(F)F)Cl)CCl',5 +'O=C(O)C(C(C(=O)O)C(O1)CC2)C12',115 +'O=C(Oc(c(OC(C1)(C)C)c1cc2)c2)NC',5 +'Oc(c(c(c(c1)Cl)Cl)Cc(c(c(cc2Cl)Cl)Cl)c2O)c1Cl',5 +'CC1(CON(C1=O)CC2=CC=CC=C2Cl)C',21.5 +'CCC(C)N1C(=O)C(=C(NC1=O)C)Br',62.5 +'CC1=CC(=CC(=C1N(C)C)C)OC(=O)NC',1.5 +'CNC(=O)OC1=CC=CC(=C1)N=CN(C)C',12.5 +'CC1=NN(C(=O)N1C(F)F)C2=CC(=C(C=C2Cl)Cl)NS(=O)(=O)C',67 +'CCOP(=S)(CC)SC1=CC=CC=C1',5 +'CCOP(=S)(OCC)SC(CCl)N1C(=O)C2=CC=CC=C2C1=O',2.5 +'N1CC(C)(C)CNC1=NN=C(C=Cc2ccc(C(F)(F)F)cc2)C=Cc3ccc(C(F)(F)F)cc3',5 +'CC1=C(C(=C(C(=C1F)F)COC(=O)C2C(C2(C)C)C=C(C(F)(F)F)Cl)F)F',4.6 +'CC1=CC(=C(C=C1)N=CN(C)C=NC2=C(C=C(C=C2)C)C)C',10.2 +'S=P(OC)(OC)SCN1C(=O)SC(OC)=N1',0.8 +'CC(C)N(C(C)C)C(=O)SCC(Cl)=C(Cl)Cl',12.5 +'S=P(OC)(OC)SCN1N=Nc2ccccc2C1(=O)',2.25 +'CC1=NC(=NC(=N1)OC)NC(=O)NS(=O)(=O)C2=CC=CC=C2CCC(F)(F)F',79.9 +'O=C(N(S(=O)(=O)Nc1cccc2)C(C)C)c12',40 +'CCN(CC)c1nc(C)cc(OP(=S)(OC)OC)n1',13.8 +'O=C(ON=CC(SC)(C)C)NC',0.1 +'ClC(Cl)(Cl)CC1(OC1)c2cc(Cl)cc(Cl)c2',30 +'CCC1CCCC(C(C(=O)C2CC3C(C2CC(=O)O1)CCC4C3CC(C4)OC5CC(C(C(C5OC)OC)OC)C)C)OC6CCC(C(O6)C)N(C)C',24 +'CC(C)(C)C(=NOC(=O)NC)CSC',6 +'CON=C(CC1=CN=CC=C1)C2=C(C=C(C=C2)Cl)Cl',45 +'CC(=CC1C(C1(C)C)C(=O)OCN2C(=O)C3=C(C2=O)CCCC3)C',250 +'C1COC(O1)(CN2C=NC=N2)C3=C(C=C(C=C3)Cl)Cl',10 +'CCCOC(=O)C1=CN=C(C=C1)C(=O)OCCC',250 +'CC1=CC(=NC(=N1)NC(=O)NS(=O)(=O)C2=CC=CC=C2C(=O)OC3COC3)C',83 +'C1=C(C(=NC(=C1Cl)Cl)OCC(=O)O)Cl',36 +'CCOCN1C(=C(C(=C1C(F)(F)F)Br)C#N)C2=CC=C(C=C2)Cl',13.6 +'CC(C)CC1=C(C(=NC(=C1C(=O)SC)C(F)(F)F)C(F)F)C(=O)SC',3.63 +'CC12CC1(C(=O)N(C2=O)C3=CC(=CC(=C3)Cl)Cl)C',15 +'CC1=CC(=C(C=C1)C(=O)OC)C2=NC(C(=O)N2)(C)C(C)C',50 +'COP(=S)(OC)OC1=NC(=C(C=C1Cl)Cl)Cl',3 +'CC(C)CC1=C(C(=NC(=C1C(=O)OC)C(F)F)C(F)(F)F)C2=NCCS2',44.2 +'CCOC(=O)C(CC1=CC(=C(C=C1Cl)F)N2C(=O)N(C(=N2)C)C(F)F)Cl',12 +'CC(C)=CC3C(C(=O)OCc2coc(Cc1ccccc1)c2)C3(C)C',125 +'CCCSP(=S)(OCC)OC1=CC=C(C=C1)SC',11.5 +'CC1=CC(=C(C(=C1)OC(=O)NC)C)C',59.2 +'CC1=CC=CC=C1COC2CC3(CCC2(O3)C)C(C)C',150 +'CC1=C2C(=CC=C1)SC3=NN=CN23',31 +'CCC(=C1C(=O)CC(CC1=O)CC(C)SCC)NOCC=CCl',100 +'CCCN(CCC)C(=O)SCC',9 +'CC(C)OC(=O)C=C(C)C=CCC(C)CCCC(C)(C)OC',46 +'COP(=S)(OC)Oc1ccc(SC)c(C)c1',3.75 +'COC1=C(C=C(C=C1)C(=CC(=O)N2CCOCC2)C3=CC=C(C=C3)Cl)OC',46.3 +'CCSC(=O)N(CC(C)C)CC(C)C',100 +'CC(C)OP(=S)(OC(C)C)SCCNS(=O)(=O)C1=CC=CC=C1',15 +'CC(=CC1C(C1(C)C)C(=O)OCC2=CC(=CC=C2)OC3=CC=CC=C3)C',150 +'CC1=CC(=CC(=C1C)C)OC(=O)NC',10 +'CCOP(=S)(OCC)SCSC1=CC=C(C=C1)Cl',1 +'C1CN(CCN1C(C(Cl)(Cl)Cl)NC=O)C(C(Cl)(Cl)Cl)NC=O',100 +'C(=CC=C1)(C2=C1)NC(=N2)C(=CS3)N=C3',2 +'C1(=C(C(=C(C(=C1Cl)Cl)Cl)Cl)Cl)[N+](=O)[O-]',125 +'CCCC(=NOCC)C1C(=O)CC(CC1=O)CC(C)SCC',16.56 +'ClC2(Cl)C4(Cl)C1(Cl)C5(Cl)C(Cl)(Cl)C3(Cl)C1(Cl)C2(Cl)C3(Cl)C45Cl',0.7 +'CCN(C1CCCCC1)C(=O)SCC',3 +'CC1=NC(=NC(=N1)OC)NC(=O)NS(=O)(=O)C2=CC=CC=C2OCCCl',220.8 +'C(C(=O)O)OC1=NC(=C(C(=C1Cl)N)Cl)F',500 +'CC1=C(C(=O)CC1OC(=O)C2C(C2(C)C)C=C(C)C)CC#C',95 +'C1C(COC1(CN2C=NC=N2)C3=C(C=C(C=C3)Cl)Cl)Br',6.48 +'C1=NNC(=N1)N',2.5 +'C1=CC(=C(C(=C1)F)C(=O)NC(=O)NC2=CC(=C(C(=C2F)Cl)F)Cl)F',26 +'C1=CC(=CC=C1OS(=O)(=O)C2=CC=C(C=C2)Cl)Cl',2.5 +'FC(F)(F)C(=CC(N(=O)=O)=C1N(C(C)C)C(C)C)C=C1N(=O)=O',1000 +'CC1=C(C(=O)CC1OC(=O)C2C(C2(C)C)C=C(C)C)CC=C',75 +'C1=CC(=C(C(=C1)Cl)C#N)Cl',2.5 +'C1C(O1)COC2=CC=CC=C2C3=CC=CC=C3',500 +'CC1=CC=CC=C1OCC2=CC=CC=C2C(=NOC)C(=O)OC',375 +'O=N(=O)C(C(=C1N(=O)=O)N(C(C)C)C(C)C)=CC(=C1)S(=O)(=O)N',36.86 +'C1=CC(=C(C2=NC=C(C=C21)Cl)C(=O)O)Cl',757 +'CC(C)NC(=O)N1CC(=O)N(C1=O)C2=CC(=CC(=C2)Cl)Cl',46 +'CCCN(CCCl)C1=C(C=C(C=C1[N+](=O)[O-])C(F)(F)F)[N+](=O)[O-]',202.4 +'C1=CC=C(C=C1)C2=CC=CC=C2O',1000 +'O=C(N(C)C)Nc(cccc1C(F)(F)F)c1',15 +'C1=CC(=NC(=C1)Cl)C(Cl)(Cl)Cl',1 +'Clc1cc(Cl)cc(Cl)c1OCCN(CCC)C(=O)n2cncc2',7.5 +'CC1=CC(=C(C=C1NC(=O)C)NS(=O)(=O)C(F)(F)F)C',27.6 +'C(=C(I)I)(I)I',50 +'C1=C(C=C(C(=C1Cl)N2C(=C(C(=N2)C#N)S(=O)C(F)(F)F)N)Cl)C(F)(F)F',0.06 +'O=C(N(C)C)Nc(ccc(c1Cl)Cl)c1',6.25 +'CC1=C(C(=O)CC1OC(=O)C2C(C2(C)C)C=C(C)C)CC=C',24.5 +'CC1=CC2=C(C=C1)N=C3C(=N2)SC(=O)S3',7.5 +'CC(C)N(C(=O)CCl)c1ccccc1',23 +'CC(C)C1(C(=O)NC(=N1)C2=C(C=CC=N2)C(=O)O)C',500 +'CC1(C(C1(C)C)C(=O)OC(C#N)C2=CC(=CC=C2)OC3=CC=CC=C3)C',19.45 +'CN1CN(C(=S)SC1)C',30 +'ClC(Cl)=CC1C(C)(C)C1C(=O)OC(C(#N))c2cccc(Oc3ccccc3)c2',75 +'ClC2C1OC1C3C2C4(Cl)C(=C(Cl)C3(Cl)C4(Cl)Cl)Cl',0.2 +'CCOC(=O)CN1C2=C(C=CC=C2Cl)SC1=O',12.5 +'CCCN(CCC)C1=C(C=C(C(=C1[N+](=O)[O-])N)C(F)(F)F)[N+](=O)[O-]',29.4 +'C1=CC=C(C=C1)C(CCC2=CC=C(C=C2)Cl)(CN3C=NC=N3)C#N',40 +'CC(C)(C)C(CCC1=CC=C(C=C1)Cl)(CN2C=NC=N2)O',15.9 +'CC1=C(C=CC=C1COC(=O)C2C(C2(C)C)C=C(C(F)(F)F)Cl)C3=CC=CC=C3',5 +'C(=CC=C1)(C2=C1)NC(=N2)C(=CS3)N=C3',40 +'C1=C(C=C(C(=C1Cl)N)Cl)[N+](=O)[O-]',150 +'CC1=C(C=C(C=C1C(=O)N)[N+](=O)[O-])[N+](=O)[O-]',6.25 +'CC(C)OC1=CC=CC(=C1)NC(=O)C2=CC=CC=C2C(F)(F)F',500 +'OC(c1ccc(Cl)cc1)(c2ccc(Cl)cc2)C(Cl)(Cl)Cl',2.5 +'O=P(O)(O)CCCl',446 +'CN(C(=O)NC1=CC=C(C=C1)Br)OC',12.5 +'CC1=CC(=CC=C1)NC(=O)OC2=CC=CC(=C2)NC(=O)OC',25 +'CC(C)(C)C1=NN=C(S1)N2C(CN(C2=O)C)O',50 +'S=P(OCC)(OCC)Oc1ccc2C(C)=C(Cl)C(=O)Oc2c1',1.7 +'COC(=O)c1ccccc1S(=O)(=O)NC(=O)N(C)c2nc(OC)nc(C)n2',12.5 +'C1=CC=C(C(=C1)NC2=NC(=NC(=N2)Cl)Cl)Cl',1.15 +'CC1=C(C=CC(=C1)OP(=S)(OC)OC)[N+](=O)[O-]',0.46 +'COc1c(Cl)ccc(Cl)c1C(=O)(O)',115 +'CC1(C(C1C(=O)OC(C#N)C2=CC(=CC=C2)OC3=CC=CC=C3)C=C(Br)Br)C',2.5 +'C1=CC=C(C(=C1)C(C2=CC=C(C=C2)F)(C3=CN=CN=C3)O)Cl',2.5 +'c1ccc2nc(NC(=O)OC)n(C(=O)NCCCC)c2c1',115 +'CCOC(=O)COC(=O)C1=C(C=CC(=C1)OC2=C(C=C(C=C2)C(F)(F)F)Cl)[N+](=O)[O-]',25 +'CC(C)(C)C(C(N1C=NC=N1)OC2=CC=C(C=C2)C3=CC=CC=C3)O',25 +'CCNC(=O)NC(=O)C(=NOC)C#N',30.3 +'CCOC1=C(C=CC(=C1)OC2=C(C=C(C=C2)C(F)(F)F)Cl)[N+](=O)[O-]',40 +'CC1=NC=C(N1CCO)[N+](=O)[O-]',150 +'O=C(N(SC(Cl)(Cl)Cl)C(=O)c1cccc2)c12',500 +'CC(C)(C)c2ccc(OC1CCCCC1OS(=O)OCC#C)cc2',100 +'CCCCC(CN1C=NC=N1)(C2=C(C=C(C=C2)Cl)Cl)O',4.7 +'CC(C)(C)C(C(=CC1=C(C=C(C=C1)Cl)Cl)N2C=NC=N2)O',50 +'C1=CC(C2C1C3(C(=C(C2(C3(Cl)Cl)Cl)Cl)Cl)Cl)Cl',0.38 +'C1=CC=C2C(=C1)C(=O)C3=C(C2=O)SC(=C(S3)C#N)C#N',10 +'CC1=NN(C(=C1C=NOCC2=CC=C(C=C2)C(=O)OC(C)(C)C)OC3=CC=CC=C3)C',3.08 +'CS(=O)(=O)C1=C(C=CC(=C1)C(F)(F)F)C(=O)C2=C(ON=C2)C3CC3',20 +'CC1=C(N=C(N=C1OC(=O)N(C)C)N(C)C)C',12.5 +'CCN(CC)C(=O)C(Cl)=C(C)OP(=O)(OC)OC',1.5 +'C1=CC(=CC=C1C(CN)O)O',250 +'CC1=C(C(=CC=C1)C)N(C(=O)COC)N2CCOC2=O',50 +'c1c(C(F)(F)F)cccc1N2C(=O)C(Cl)=C(NC)C=N2',18.75 +'CCC(C)NC1=C(C=C(C=C1[N+](=O)[O-])C(C)(C)C)[N+](=O)[O-]',50 +'C1=CC(=CC=C1S(=O)(=O)C2=CC(=C(C=C2Cl)Cl)Cl)Cl',230 +'CCCCC1=C(NC(=NC1=O)NCC)C',25 +'n(c(nc(n1)NCC)NCC)c1Cl',5.3 +'FC(F)(F)C(C=C1N(=O)=O)=CC(N(=O)=O)=C1N(CC)CC(C)=C',12.5 +'C1CCC(C1)N(CC2=CC=C(C=C2)Cl)C(=O)NC3=CC=CC=C3',25 +'CS(=O)(=O)NC(=O)C1=C(C=CC(=C1)OC2=C(C=C(C=C2)C(F)(F)F)Cl)[N+](=O)[O-]',50 +'CCOC(=O)C(C)OC1=CC=C(C=C1)OC2=NC3=C(O2)C=C(C=C3)Cl',9 +'CCC1=C(C(=CC=C1)CC)N(CNC(=O)C)C(=O)CCl',62.5 +'NC(=N)NCCCCCCCCCCCC(OC(=O)C)',29 +'C1=CC(=CC(=C1)Cl)NC(=O)OCC#CCCl',450 +'CC(C)C(C(=O)OC(C(#N))c2cccc(Oc1ccccc1)c2)c3ccc(Cl)cc3',25 +'CC(C)C1=C(C=CC(=C1)C(C)(C)C2=CC(=C(C=C2)O)C(C)C)O',25 +'CCN(CC1=C(C=CC=C1Cl)F)C2=C(C=C(C=C2[N+](=O)[O-])C(F)(F)F)[N+](=O)[O-]',50 +'CCCCCCCCSC(=O)OC1=CC(=NN=C1C2=CC=CC=C2)Cl',67.5 +'CC1=C(C(=O)CC1OC(=O)C2C(C2(C)C)C=C(C)C)CC=C',13.8 +'CCCCNC(=O)N1C2=CC=CC=C2N=C1NC(=O)OC',250 +'CC1=C(C(=CC=C1)C)N(C(C)C(=O)OC)C(=O)CC2=CC=CC=C2',46 +'CC(C)C(C1=CC=C(C=C1)OC(F)F)C(=O)OC(C#N)C2=CC(=CC=C2)OC3=CC=CC=C3',6 +'Clc1ccccc1c2nnc(c3ccccc3Cl)nn2',20 +'CCOC(=O)NCCOC1=CC=C(C=C1)OC2=CC=CC=C2',10 +'CCC1=C(C(=CC=C1)CC)N(CC(=O)OCC)C(=O)CCl',50 +'c1(O2)c(CC2(C)C)cccc1OC(=O)N(C)SN(CCCC)CCCC',25 +'CCCCOC(=O)C(C)OC1=CC=C(C=C1)OC2=NC=C(C=C2)C(F)(F)F',3 +'COC1=CC(=C(C=C1Cl)OC)Cl',125 +'CCOP(=S)(OCC)OC1=NN(C(=N1)Cl)C(C)C',12.5 +'n(c(nc(n1)NC(C)C)NCC)c1Cl',25 +'CC(C)(C)C(C(=CC1=CC=C(C=C1)Cl)N2C=NC=N2)O',39.41 +'CCCCCCCCc1cc(N(=O)(=O))c(OC(=O)C=CC)c(c1)N(=O)(=O)',50 +'c1cc(OC(F)(F)F)ccc1C(O)(C(C)C)c2cncnc2',12.1 +'COP(=O)(C(C(Cl)(Cl)Cl)O)OC',20 +'C1=CC(=C(C=C1C(F)(F)F)Cl)OC2=CC(=C(C=C2)[N+](=O)[O-])C(=O)O',125 +'CCCN(CC1CC1)C2=C(C=C(C=C2[N+](=O)[O-])C(F)(F)F)[N+](=O)[O-]',5 +'CCOC(=O)C(C)OC(=O)C1=C(C=CC(=C1)OC2=C(C=C(C=C2)C(F)(F)F)Cl)[N+](=O)[O-]',50 +'CCSC(=O)N1CCCCCC1',14.81 +'CCC1=CC=C(C=C1)C(=O)NN(C(=O)C2=CC(=CC(=C2)C)C)C(C)(C)C',48 +'ClC(Cl)C(Cl)(Cl)SN2C(=O)C1CC=CCC1C2(=O)',15 +'COC(=O)C1=CC=CC=C1S(=O)(=O)NC(=O)NC2=NC(=CC(=N2)OC(F)F)OC(F)F',140 +'CC(C)(C)C(C(N1C=NC=N1)OC2=CC=C(C=C2)Cl)O',25 +'CC1=C(C=CC(=C1)Cl)OCC(=O)O',4 +'COC=C(C1=CC=CC=C1OC2=NC=NC(=C2)OC3=CC=CC=C3C#N)C(=O)OC',62.25 +'C1=CC=C(C(=C1)C(C2=CC=C(C=C2)Cl)(C3=CN=CN=C3)O)Cl',2.3 +'[O-]Br(=O)=O',6.1 +'OP(=O)OCC',400 +'COP(N)(=O)SC',0.1 +'CCOP(=O)(NC(C)C)Oc1ccc(SC)c(C)c1',1.5 +'CCOP(=S)(OCC)SCCSCC',0.04 +'CCOP(=S)(OCC)SCSP(=S)(OCC)OCC',2 +'O=C(OCC(CCCC)CC)CCCCC(=O)OCC(CCCC)CC',1500 +'CN(C=Nc1ccc(C)cc1C)C=Nc2ccc(C)cc2C',10 +'O=C(N(S(=O)(=O)Nc1cccc2)C(C)C)c12',35 +'S=P(OC)(OC)SCN1C(=O)SC(OC)=N1',1.25 +'C(#N)Cl',70 +'C(#N)Br',122 +'C1=CC(=CC=C1C(C2=CC=C(C=C2)Cl)C(Cl)(Cl)Cl)Cl',0.25 +'c(cccc1)(c1)C(C)C',331 +'CCCN(CCC)C(=O)SCC',25 +'NC(CCCC1)C1',60 +'ClC1CC2C(C1Cl)C3(Cl)C(=C(Cl)C2(Cl)C3(Cl)Cl)Cl',6 +'CC(C)OC(=O)NC1=CC(=CC=C1)Cl',1000 +'COC(=O)c1c(Cl)c(Cl)c(C(=O)OC)c(Cl)c1Cl',10 +'COC(=O)C1=CC=C(C=C1)C(=O)OC',125 +'N(C(=S)NC1)C1',0.25 +'O=C(N(OC)C)Nc(ccc(c1Cl)Cl)c1',2.5 +'c(cccc1)(c1)C=C',285 +'COC(=O)c1ccccc1S(=O)(=O)NC(=O)Nc2nc(OC)nc(C)n2',250 +'C1=CC(=CC=C1N)Cl',12.5 +'FC(F)(F)C(Cl)=CC1C(C)(C)C1C(=O)OC(C(#N))c2cc(Oc3ccccc3)ccc2',12.5 +'C(Cl)(Br)Br',28.5 +'C=C(Cl)Cl',14 +'C(C=CCl)Cl',5.1 +'COP(=O)(OC)OC(=CCl)c1cc(Cl)c(Cl)cc1Cl',50 +'Oc(ccc(c1)C(c(ccc(O)c2)c2)(C)C)c1',50 +'O=C(OCc(cccc1)c1)c(c(ccc2)C(=O)OCCCC)c2',470 +'O=C(NCCCC1)C1',125 +'c(cccc1)(c1)Cl',120 +'C(Cl)(Cl)Cl',60 +'ClCCl',52.58 +'C1C2C3C(C1C4C2O4)C5(C(=C(C3(C5(Cl)Cl)Cl)Cl)Cl)Cl',0.125 +'OCCO',1000 +'O=C(C=C(CC1(C)C)C)C1',179 +'C(F)(Cl)(Cl)Cl',349 +'CCc1cccc(CC)c1N(COC)C(=O)CCl',14 +'c1ccccc1c2c(C)c(COC(=O)C3C(C)(C)C3C=C(Cl)C(F)(F)F)ccc2',5 +'n1c(Cl)cc(OC)nc1NC(=O)NS(=O)(=O)c2ccccc2C(=O)OCC',125 +'O=C(NC(=O)c(c(F)ccc1)c1F)Nc(ccc(c2)Cl)c2',7.8 +'c(cccc1)(c1)CC',291 +'O=C(N(SC(Cl)(Cl)Cl)C(=O)c1cccc2)c12',40 +'Clc1cc(C(F)(F)F)cnc1Oc2ccc(OC(C)C(=O)OC)cc2',1 +'C#N',31 +'ClC(C(OC(C=C2C(=O)OC(C)C(=O)OCC)=CC=C2N(=O)=O)=C1)=CC=C1C(F)(F)F',50 +'c1c(C(F)(F)F)cccc1N2C(=O)C(Cl)=C(NC)C=N2',51.25 +'O=N(=O)C(C(=C1N(=O)=O)N(C(C)C)C(C)C)=CC(=C1)S(=O)(=O)N',45 +'CN(=CC=C1C(C=C2)=CC=N2C)C=C1',3.75 +'C1=C(C=C(C=C1[N+](=O)[O-])[N+](=O)[O-])[N+](=O)[O-]',13.31 +'C(=C)Cl',1.3 +'C1CCC(=O)CC1',910 +'CC1(C(C1(C)C)C(=O)OC(C#N)C2=CC(=CC=C2)OC3=CC=CC=C3)C',25 +'C1=CC(=O)NNC1(=O)',500 +'CCSC(=O)N1CCCCCC1',2 +'C(C(Cl)(Cl)Cl)(O)O',135 +'ClC2C1OC1C3C2C4(Cl)C(=C(Cl)C3(Cl)C4(Cl)Cl)Cl',0.025 +'Clc1cc(C(F)(F)F)ccc1Oc2cc(OCC)c(N(=O)(=O))cc2',10 +'c1cc(Cl)ccc1C(C(#N))(CCCC)Cn2ncnc2',9.84 +'CC1=C(C=C(C=C1[N+](=O)[O-])[N+](=O)[O-])[N+](=O)[O-]',2 +'CC(C)OC(=O)C(C1=CC=C(C=C1)Br)(C2=CC=C(C=C2)Br)O',26 +'C[N+](C)(C)CCCl',130 +'CCC(=C1C(=O)CC(CC1=O)CC(C)SCC)NOCC=CCl',86 +'CC1=NC(=NC(=C1)C2CC2)NC3=CC=CC=C3',35.6 +'N(c(cccc1)c1)c(cccc2)c2',25 +'CC1(C(=O)N(C(=O)O1)NC2=CC=CC=C2)C3=CC=C(C=C3)OC4=CC=CC=C4',16.8 +'CC1(CCCCC1)C(=O)NC2=C(C(=C(C=C2)O)Cl)Cl',292 +'C1=CC(=C2C(=C1)OC(O2)(F)F)C3=CNC=C3C#N',110 +'C(F)(F)(F)c1ccccc1C(=O)Nc2cccc(OC(C)C)c2',87 +'C(CCCCN=C(N)N)CCCNCCCCCCCCN=C(N)N',19 +'C1CN(C(=N1)N[N+](=O)[O-])CC2=CN=C(C=C2)Cl',17 +'COC(=O)C12CC3=C(C1=NN(CO2)C(=O)N(C4=CC=C(C=C4)OC(F)(F)F)C(=O)OC)C=CC(=C3)Cl',3.6 +'CC1=CC=CC=C1OCC2=CC=CC=C2C(=NOC)C(=O)OC',370 +'CC1=CC(=CC(=C1)C(=O)N(C(C)(C)C)NC(=O)C2=C(C(=CC=C2)OC)C)C',411 +'C1=CC(=C(C(=C1)F)C(=O)NC(=O)NC2=CC(=C(C=C2)OC(C(OC(F)(F)F)F)(F)F)Cl)F',36 +'CC1=CC=C(C=C1)N(SC(F)(Cl)Cl)S(=O)(=O)N(C)C',18 +'CC(C)(C)C1=C(C=CC(=C1)O)O',225 +'CC(=NOCC1=CC=CC=C1C(=NOC)C(=O)OC)C2=CC(=CC=C2)C(F)(F)F',60 +'COC(=O)N(C1=CC=CC=C1COC2=NN(C=C2)C3=CC=C(C=C3)Cl)OC',9 +'CC(C)N1C(=NC(C)(C)C)SCN(C1=O)C2=CC=CC=C2',8.7 +'C1=CC=C(C(=C1)C2=NN=C(N=N2)C3=CC=CC=C3Cl)Cl',17.3 +'CCCC(=C1C(=O)CC(CC1=O)C2CCCSC2)NOCC',28 +'C1CC1NC2=NC(=C(C(=N2)N)C#N)N',22 +'C(C=C1)(=N(C=C1)CC2)C(N2=C3)=CC=C3',0.57 +'C1=CC=C2C(=C1)C(=O)C3=C(C2=O)SC(=C(S3)C#N)C#N',6 +'CCOC1=CC2=C(C=C1)NC(C=C2C)(C)C',12 +'C1=CC=C(C=C1)C(CCC2=CC=C(C=C2)Cl)(CN3C=NC=N3)C#N',30 +'CC1CN(CC(O1)C)CC(C)CC2=CC=C(C=C2)C(C)(C)C',1.7 +'C[Si](CN1C=NC=N1)(C2=CC=C(C=C2)F)C3=CC=C(C=C3)F',2 +'c1cc(Cl)cc(Cl)c1C(OCC=C)Cn2cncc2',15 +'CN(=CC=C1C(C=C2)=CC=N2C)C=C1',2.55 +'CCCCOCCOCCOCC1=CC2=C(C=C1CCC)OCO2',100 +'Clc1cc(Cl)ccc1C2(Cn3ncnc3)OC(CCC)CO2',96 +'C(=CC=C1)(C2=C1)NC(=N2)C(=CS3)N=C3',30 +'CCOC1=CC=C(C=C1)C(C)(C)COCC2=CC(=CC=C2)OC3=CC=CC=C3',26 +'CC(C)(C)c2ccc(OC1CCCCC1OS(=O)OCC#C)cc2',19 +'CC(COC1=CC=C(C=C1)OC2=CC=CC=C2)OC3=CC=CC=N3',140 +'CC(C)(C)C(=O)C(N1C=NC=N1)OC2=CC=C(C=C2)Cl',114 +'CC(C)(C)C(C(N1C=NC=N1)OC2=CC=C(C=C2)Cl)O',105 +'c1ccccc1c2c(C)c(COC(=O)C3C(C)(C)C3C=C(Cl)C(F)(F)F)ccc2',8 +'CC1(C(C1C(=O)OC(C#N)C2=CC(=C(C=C2)F)OC3=CC=CC=C3)C=C(Cl)Cl)C',6 +'CC1(C(C1C(=O)OC(C#N)C2=CC(=C(C=C2)F)OC3=CC=CC=C3)C=C(Cl)Cl)C',12 +'ClC(Cl)=CC1C(C)(C)C1C(=O)OC(C(#N))c2cccc(Oc3ccccc3)c2',50 +'ClC1CC2C(C1Cl)C3(Cl)C(=C(Cl)C2(Cl)C3(Cl)Cl)Cl',0.25 +'ClC4=C(Cl)C5(Cl)C3C1CC(C2OC12)C3C4(Cl)C5(Cl)Cl',0.1 +'C1C2C3C(C1C4C2O4)C5(C(=C(C3(C5(Cl)Cl)Cl)Cl)Cl)Cl',0.25 +'C1(C(C(C(C(C1Cl)Cl)Cl)Cl)Cl)Cl',4.7 +'CCC(=O)Nc1ccc(Cl)c(Cl)c1',76 +'C1(=C(C(=C(C(=C1Cl)Cl)Cl)Cl)Cl)[N+](=O)[O-]',140 +'C1C2C(COS(=O)O1)C3(C(=C(C2(C3(Cl)Cl)Cl)Cl)Cl)Cl',2.9 +'O=C(N(SC(Cl)(Cl)Cl)C(=O)c1cccc2)c12',50 +'CC(C(=O)O)OC1=CC=C(C=C1)OC2=C(C=C(C=N2)C(F)(F)F)Cl',0.1 +'CCCCC(CN1C=NC=N1)(C#N)C2=CC=C(C=C2)Cl',9.8 +'Clc1cc(Cl)cc(Cl)c1OCCN(CCC)C(=O)n2cncc2',5.1 +'COP(=O)(NC(=O)(C))SC',2.5 +'CCOP(=O)(OCC)OC(=CCl)C1=C(C=C(C=C1)Cl)Cl',1.5 +'CCOP(=S)(OCC)SCCSCC',0.22 +'O=P(O)(O)CCCl',12 +'CCCSP(=O)(OCC)SCCC',2.7 +'CCOP(=O)(NC(C)C)Oc1ccc(SC)c(C)c1',1.7 +'COP(=S)(OC)Oc1ccc(SC)c(C)c1',0.72 +'OC(=O)C(N)CCP(C)(=O)O',3.5 +'OC(=O)CNCP(O)(O)=O',300 +'CCOC(=O)CC(SP(=S)(OC)OC)C(=O)OCC',360 +'COP(N)(=O)SC',0.29 +'CC(=CC(=O)OC)OP(=O)(OC)OC',0.35 +'CCOP(=S)(OCC)SCSCC',0.16 +'CCOP(=S)(OCC)SCSC(C)(C)C',0.06 +'S=P(OC)(OC)SCN1N=Nc2ccccc2C1(=O)',2.58 +'CCOP(=S)(OCC)OC1=NC(=C(C=C1Cl)Cl)Cl',1 +'CCOP(=S)(OCC)OC1=NC(=NC(=C1)C)C(C)C',5.8 +'CCC1=NC(=CC(=N1)OP(=S)(OC)OC)OCC',0.45 +'S=P(OC)(OC)SCN1C(=O)SC(OC)=N1',1.6 +'CCOP(=S)(OCC)SCN1C2=C(C=C(C=C2)Cl)OC1=O',2 +'COP(=S)(OC)SCN2C(=O)c1ccccc1C2(=O)',9 +'CCOC(=O)C1=CN2C(=CC(=N2)OP(=S)(OCC)OCC)N=C1C',4 +'CCOP(=S)(OCC)OC1=NN(C=N1)C2=CC=CC=C2',1.3 +'O=C(Oc(c(c(ccc1)cc2)c1)c2)NC',60 +'CC1=CC(=CC(=C1SC)C)OC(=O)NC',9.3 +'CNC(=O)ON=C(C)SC',20 +'CCCOC(=O)NCCCN(C)C',680 +'COC(=O)NC1=NC2=CC=CC=C2N1',75 +'CC1=C(N=C(N=C1OC(=O)N(C)C)N(C)C)C',12.3 +'CNC(=O)CCSCCSP(=O)(OC)OC',0.54 +'N(C(=S)SSC(N(C)C)=S)(C)C',12 +'C1=NNC(=N1)N',5 +'CCCCCCCCc1cc(N(=O)(=O))c(OC(=O)C=CC)c(c1)N(=O)(=O)',64 +'C1=CC=C(C=C1)[Sn](C2=CC=CC=C2)C3=CC=CC=C3',0.3 +'O=C(NC(=O)c(c(F)ccc1)c1F)Nc(ccc(c2)Cl)c2',7 +'N(C(=S)NC1)C1',1.25 +'C1=CC(=C(C(=C1)F)C(=O)NC(=O)NC2=CC(=C(C(=C2F)Cl)F)Cl)F',25 +'CCCSC1=CC2=C(C=C1)N=C(N2)NC(=O)OC',20 +'C1CN(CCN1CCCC(=O)C2=CC=C(C=C2)F)C3=CC=CC=N3',115 +'CC1(C2C(C3C(C(=O)C(=C(N)O)C(=O)C3(C(=O)C2=C(C4=C(C=CC(=C41)Cl)O)O)O)N(C)C)O)O',5200 +'CC1=CC(=C(C=C1NC(=O)C2=CC(=CC(=C2O)I)I)Cl)C(C#N)C3=CC=C(C=C3)Cl',10 +'CN1CC2CC1CN2C3=C(C=C4C(=C3)N(C=C(C4=O)C(=O)O)C5CC5)F',50 +'C1=CC(=CC=C1C(C#N)C2=C(C=CC(=C2Cl)N3C(=O)NC(=O)C=N3)Cl)Cl',15 +'CC1=NC=C(N1C)[N+](=O)[O-]',15 +'CCN1CCN(CC1)C2=C(C=C3C(=C2)N(C=C(C3=O)C(=O)O)C4CC4)F',26 +'CC1C=CC=C2COC3C2(C(C=C(C3O)C)C(=O)OC4CC(CC=C(C1OC5CC(C(C(O5)C)OC6CC(C(C(O6)C)NC(=O)C)OC)OC)C)OC7(C4)C=CC(C(O7)C(C)C)C)O',1 +'COCC(=O)NC1=C(C=CC(=C1)SC2=CC=CC=C2)NC(=NC(=O)OC)NC(=O)OC',40 +'CC1CCC2=C3N1C=C(C(=O)C3=CC(=C2)F)C(=O)O',400 +'COC(=O)NC1=NC2=C(N1)C=C(C=C2)S(=O)C3=CC=CC=C3',2 +'CC1(C2CC3C(C(=O)C(=C(N)O)C(=O)C3(C(=O)C2=C(C4=C1C=CC=C4O)O)O)N(C)C)O',150 +'C1CN(CCN1CCCC(=O)C2=CC=C(C=C2)F)C3=CC=CC=N3',30 +'CC(C)NCC(COC1=CC=CC2=C1C3=CC=CC=C3N2)O',7 +'C1=CC(=CC=C1C(C#N)C2=C(C=CC(=C2Cl)N3C(=O)NC(=O)C=N3)Cl)Cl',23 +'CC1C=CC=C2COC3C2(C(C=C(C3O)C)C(=O)OC4CC(CC=C(C1OC5CC(C(C(O5)C)OC6CC(C(C(O6)C)NC(=O)C)OC)OC)C)OC7(C4)C=CC(C(O7)C(C)C)C)O',2.5 +'COP(=S)(OC)Oc1ccc(SC)c(C)c1',0.45 +'C(C(C(C(C1Cl)Cl)Cl)Cl)(C1Cl)Cl',8 +'C(C(C(C(C1Cl)Cl)Cl)Cl)(C1Cl)Cl',4 +'CC(N(C)C)CN(C(=CC=C3)C1=C3)C(=CC=C2)C(=C2)S1',16.6 +'C1=C(C=C(C(=C1Cl)N)Cl)[N+](=O)[O-]',240 +'c(cccc1)(c1)C=C',400 diff --git a/original/LOAEL_mg_corrected_smiles.csv b/original/LOAEL_mg_corrected_smiles.csv new file mode 100755 index 0000000..e86ca2c --- /dev/null +++ b/original/LOAEL_mg_corrected_smiles.csv @@ -0,0 +1,568 @@ +SMILES,LOAEL_mg_kg_bw_day +'C1=C(C(=CC(=C1NN=C3C2=C(C=C([S]([O-])(=O)=O)C=C2)C=CC3=O)OC)[S]([O-])(=O)=O)C.[Na+].[Na+]',3739 +'O1C(=O)C(O)=C(O)C1C(O)CO',3051 +'C1(C)=C(C=CC(C)=CC=CC(C)=CC=CC=C(C)C=CC=C(C)C(=O)OC)C(C)(C)CCC1',500 +'c(cccc1)(c1)C(C)C',462 +'O=C(OCCCC)c(c(ccc1)C(=O)OCCCC)c1',600 +'O=C(OCC)c(c(ccc1)C(=O)OCC)c1',4435 +'O=C(OC(OC(OC1C)C)C1)C',125 +'Oc(c(ccc1)C)c1C',6 +'Oc(ccc(c1C)C)c1',14 +'O=C(OCC)C=C',248 +'c(cccc1)(c1)CC',408 +'OCCO',250 +'c(ccc1C(=O)OCC(=O)OCC)cc1C(=O)OCC',2500 +'O=C',82 +'O=C(O)C=CC(=O)O',1081 +'OCC(O)CO',6883 +'O=C(OC)c(ccc(O)c1)c1',1500 +'O=C(OCCC)c(ccc(O)c1)c1',1500 +'CC(CCC(=O)(O))C3CCC4C2CCC1CC(O)CCC1(C)C2CCC34C',500 +'OC(C(CCC1C)C(C)C)C1',593 +'O=C(O)C(=C)C',248 +'O=C(OC)c(c(O)ccc1)c1',360 +'Oc(cccc1)c1',344 +'O=C(OCCC)c(cc(O)c(O)c1O)c1',864 +'OCC(O)C1C(O)=C(O)C(=O)O1',1554 +'c(cccc1)(c1)C=C',21 +'O=Cc(occ1)c1',60 +'NCCNc1cccc2ccccc12',79 +'CN(C)(C)CCCl',275 +'O=C(Nc(ccc(c1)C(=O)CCl)c1)C',1580 +'c(ccc(c1)Cl)(c1)C(c(ccc(c2)Cl)c2)C(Cl)(Cl)Cl',32 +'CC(Oc1cc(Cl)c(Cl)cc1Cl)C(=O)(O)',8.7 +'O=N(=O)C(=CC=C1OC)C=C1N=NC(C(O)=C2C(=O)NC(=CC=C4)C=C4N(=O)=O)=C(C=C3)C(=C2)C=C3',2100 +'O=N(=O)C(C=C1)=CC(OCCO)=C1NCCO',229 +'Cc1cccc(CC)c1N(C(=O)CCl)COCC',50 +'C1=C(C(=CC=C1OC2=CC=C(C=C2Cl)C(F)(F)F)[N+](=O)[O-])C(=O)[O-].[Na+]',180 +'CCc1cccc(CC)c1N(COC)C(=O)CCl',15 +'O=C(Nc(ccc(OCC)c1N)c1)C',1185 +'Oc(ccc(N)c1)c1',686 +'CC(N)CC(=CC=C1)C=C1',5 +'O(c(ccc(c1)C=CC)c1)C',344 +'COc1ccc(N)cc1',474 +'O=C(O)c(c(N)ccc1)c1',2751 +'Clc2cccc(c2)c1ccccc1',4 +'O=C(NC(C(=O)OC)Cc(cccc1)c1)C(N)CC(=O)O',147 +'n1c2ccc(Cl)cc2ncc1Oc3ccc(OC(C)C(=O)OCC)cc3',3.7 +'COC(=O)NS(=O)(=O)c1ccc(N)cc1',180 +'S=P(OC)(OC)SCN1N=Nc2ccccc2C1(=O)',0.36 +'CNC(=O)Oc1ccccc1OC(C)C',50 +'CC(C)(C)C(=O)C(Oc1ccc(Cl)cc1)n2cncn2',25 +'O=S(O)(=O)C(=CC=C1)C=C1CN(CC)=C(C=C2)C=CC2=C(C(C=C3)=CC=C3N(C)C)C(C=C4)=CC=C4N(CC)CC(C=C5)=CC(=C5)S(=O)(=O)O',720 +'c(c(cccc1)c1)(cccc2)c2',250 +'BrC(Cl)Cl',130 +'ClC(Cl)C(Cl)(Cl)SN2C(=O)C1CC=CCC1C2(=O)',12 +'O=C(Oc(c(c(ccc1)cc2)c1)c2)NC',15.6 +'CC1=C(SCCO1)C(=O)Nc2ccccc2',30 +'ClC1CC2C(C1Cl)C3(Cl)C(=C(Cl)C2(Cl)C3(Cl)Cl)Cl',0.27 +'O=C(O)CCl',30 +'ClC(=CC=C1N)C=C1',6 +'CC(C)OC(=O)C(O)(c1ccc(Cl)cc1)c2ccc(Cl)cc2',9 +'n1c(OC)nc(C)nc1NC(=O)NS(=O)(=O)c2ccccc2Cl',25 +'OS(=O)(=O)C(C(=CC=C2)C1=C2)=CC=C1N=NC(C(O)=C3N=NC(C(C=C5)=C4C=C5)=CC=C4S(O)(=O)=O)=CC(=C3O)CO',736 +'S=P(OCC)(OCC)Oc1ccc2C(C)=C(Cl)C(=O)Oc2c1',0.8 +'CNP(=O)(OC)Oc1ccc(cc1Cl)C(C)(C)C',4 +'C(C1C2C(C(O)C(O1)OC8C(OC(OC7C(OC(OC6C(OC(OC5C(C(C(OC4C(C(C(OC3C(C(C(O2)OC3CO)O)O)OC4CO)O)O)OC5CO)O)O)C(C6O)O)CO)C(C7O)O)CO)C(C8O)O)CO)O)O',1600 +'n1c(N)nc(N)nc1NC2CC2',15 +'COC(=O)c1c(Cl)c(Cl)c(C(=O)OC)c(Cl)c1Cl',500 +'O=C(O)C(Cl)(Cl)C',28.17 +'Nc1cc(N)c(O)cc1',25 +'FC(F)(Cl)Cl',150 +'ClCCl',50 +'O=P(OC)(OC)OC=C(Cl)Cl',2.3 +'OC(c1ccc(Cl)cc1)(c2ccc(Cl)cc2)C(Cl)(Cl)Cl',20 +'ClC4=C(Cl)C5(Cl)C3C1CC(C2OC12)C3C4(Cl)C5(Cl)Cl',0.05 +'CN(=C1C(C=C2)=CC=C2)N(C)C(=C1)C(C=C3)=CC=C3',125 +'O=C(NC(=O)c(c(F)ccc1)c1F)Nc(ccc(c2)Cl)c2',8 +'CC1=C(C)S(=O)(=O)CCS1(=O)=O',10 +'O=C(NC)CSP(OC)(OC)=S',0.25 +'COc1ccc(N)c(OC)c1',276 +'COP(=O)OC',100 +'CC(=C(N(=O)=O)C=C1N(=O)=O)C=C1',34 +'CN(C)C(=O)C(c1ccccc1)c2ccccc2',30 +'N(c(cccc1)c1)c(cccc2)c2',31 +'C(C=C1)(=N(C=C1)CC2)C(N2=C3)=CC=C3',0.58 +'CCOP(=S)(OCC)SCCSCC',0.1 +'NC(=S)NNC(N)=S',947 +'O=C(N(C)C)Nc(ccc(c1Cl)Cl)c1',6 +'O=P(O)(O)CCCl',150 +'O=C(OCC)C(O1)C1(c(cccc2)c2)C',175 +'COC(=O)NC(=NC1=C2)NC1=CC(=C2)SC(C=C3)=CC=C3',15 +'CN1C=C(c2ccccc2)C(=O)C(c3cc(C(F)(F)F)ccc3)=C1',25 +'c1cc(C(F)(F)F)cc(Cl)c1NC(C(C)C)C(=O)OC(C(#N))c2cccc(Oc3ccccc3)c2',2.5 +'S=P(OCC)(Sc1ccccc1)CC',1.58 +'n1c(C)nc(OC)nc1NC(=O)NS(=O)(=O)c2ccsc2C(=O)OC',25 +'C(C(C(C(C1Cl)Cl)Cl)Cl)(C1Cl)Cl',5 +'O=N(=O)N(CN1N(=O)=O)CN(C1)N(=O)=O',1.5 +'O=C(N=C(N(C1(=O))C)N(C)C)N1C(CCCC2)C2',50 +'n(c(c(ccc1)cc2)c1O)c2',143 +'c1cc(Cl)cc(Cl)c1C(OCC=C)Cn2cncc2',40 +'COc1cccc(OC)c1C(=O)Nc2onc(C(C)(CC)CC)c2',50.7 +'n1c(OC)cc(OC)nc1NC(=O)NS(=O)(=O)Cc2ccccc2C(=O)OC',309 +'CCOC(=O)CC(SP(=S)(OC)OC)C(=O)OCC',50 +'CN(C)(CCC1)CC1',150 +'O=P(SCCCC)(SCCCC)SCCCC',1.25 +'COCC(=O)N(C(C)C(=O)OC)c1c(C)cccc1C',62.5 +'S=P(OC)(OC)SCN1C(=O)SC(OC)=N1',2 +'CNC(=O)ON=C(C)SC',10 +'COP(=S)(OC)Oc1ccc(cc1)N(=O)(=O)',0.25 +'O=C1N(N)C(SC)=NN=C1C(C)(C)C',15 +'COP(=O)(OC)OC(Br)C(Cl)(Cl)Br',2 +'OC(C(N)C1O)C(C)OC1(C)OC(CC(C)(C(C2O)C(O)=O)OC(O)(C2)CC(O)CC(C)(O3)C3C=C4)C=CC=CC=CC=CCC(C)OC4=O',72 +'O=N(=O)c(ccc(c1N)C)c1',8 +'O=N(=O)c(c(N)ccc1N)c1',87 +'O=C(O)C(=C(N)C=C1N(=O)=O)C=C1',1185 +'O=N(=O)c(c(c(ccc1)cc2)c1)c2',165 +'c12c(N=Nc3ccccc3)c(O)ccc1cc(S(=O)(=O)O)cc2',180 +'CC(C)Oc1cc(c(Cl)cc1Cl)N2N=C(OC2(=O))C(C)(C)C',5 +'CNC(=O)ON=C(SC)C(=O)N(C)C',5 +'CCOP(=S)(OCC)Oc1ccc(cc1)N(=O)=O',3.5 +'Oc(c(c(c(c1Cl)Cl)Cl)Cl)c1Cl',10 +'NC(=N)NC(=N)NCCc1ccccc1',73 +'COP(=S)(OC)SCN2C(=O)c1ccccc1C2(=O)',20 +'CCN(CC)C(=O)C(Cl)=C(C)OP(=O)(OC)OC',12.3 +'ClC3C6(Cl)C4C2C1OC1C5C2C3(Cl)C(Cl)(C45)C6(Cl)Cl',0.7 +'O=C(OC(=O)c1cccc2)c12',1185 +'Nc1c(Cl)c(Cl)nc(C(=O)(O))c1Cl',60 +'CCN(CC)c1nc(C)cc(OP(=S)(OC)OC)n1',2.5 +'Nc3ccc2cc1ccc(N)cc1nc2c3',47 +'CCC(=O)Nc1ccc(Cl)c(Cl)c1',20 +'Clc1cc(Cl)ccc1C2(Cn3ncnc3)OC(CCC)CO2',25 +'O=C(N)c(nccn1)c1',789 +'Oc1cc(O)c2C(=O)C(O)=C(c3cc(O)c(O)cc3)Oc2c1',2034 +'CCC(O)(C)C#C',46 +'CC(C(NCC)=C1)=CC(C1=O2)=C(C(C2=C3)=CC(C)=C3NCC)C(=CC=C4)C(=C4)C(=O)OCC',12 +'O=C(NS(=O)(=O)c1cccc2)c12',3602 +'c1cc(Cl)ccc1C2SC(=O)N(C(=O)NC3CCCCC3)C2C',160 +'n(c(nc(n1)NCC)NCC)c1Cl',5 +'O=[S](NC1CCCCC1)(=O)[O-].[Na+]',3602 +'O=C(OCC(C1OCC(C1O)O)O)CCCCCCCCCCC',6883 +'O(CC1O)C(C1O)C(O)COC(=O)CCCCCCCCCCCCCCCCC',7203 +'O=S(=O)(Nc(nc(cc1C)C)n1)c(ccc(N)c2)c2',33 +'CCNc1nc(NC(C)(C)C)nc(SC)n1',15 +'Oc(c(cc(c1)C(C)(C)C)Cl)c1',216 +'C(C(Cl)Cl)(Cl)Cl',108 +'COP(=O)(OC)OC(=CCl)c1cc(Cl)c(Cl)cc1Cl',100 +'CCN(CC)C(=O)SCc1ccc(Cl)cc1',5 +'COC(=O)NC(=S)Nc1ccccc1NC(=S)NC(=O)OC',32 +'N(C(=S)SSC(N(C)C)=S)(C)C',15 +'c12OC(CCCC(C)CCCC(C)CCCC(C)C)(C)CCc1c(C)c(OC(=O)C)c(C)c2C',2000 +'Cc1cc(N)ccc1NOS(O)(=O)=O',184 +'C(Br)(C(Br)(Br)Br)C1C(C)(C)C1C(=O)OC(C(#N))c2cccc(Oc3ccccc3)c2',3 +'O=C(O)COc(c(cc(c1Cl)Cl)Cl)c1',10 +'FC(F)(F)C(=CC(N(=O)=O)=C1N(C(C)C)C(C)C)C=C1N(=O)=O',40 +'Cc1cc(C)c(N)cc1C',63 +'CC(O)(C(O)C(O1)C)CC1(C)OC(C(C)O2)C(C(O)C2(C)OC(C(C)C(O)CC(=O)OC(CC)C3COC(C(OC)C4OC)OC(C)C4O)C(CC=O)CC(C)C(=O)C=CC(=C3)C)N(C)C',500 +'c1c(Cl)cc(Cl)cc1N2C(=O)C(C)(C=C)OC2(=O)',72.9 +'O=C(OC(CCCC(O)CCCCCc1cc(O)cc2O)C)c12',0.2 +'COC(=O)C1(C2=CC=CC=C2C3=C1C=C(C=C3)Cl)O',150 +'CC(C(=O)O)OC1=CC(=CC=C1)Cl',100 +'P12P3P1P23',1472 +'C(CO)O',400 +'CCCCOCC(C)OCC(C)O',128 +'C(CO)O',2000 +'C(CO)O',920 +'[O-][As](=O)([O-])[O-]',6.25 +'[Si](CN1C=NC=N1)(C2=CC=C(C=C2)F)C3=CC=C(C=C3)F',2.3 +'N(C(=S)SSC(N(C)C)=S)(C)C',11.5 +'COP(=O)(N)SC',0.9 +'N(C(=S)SSC(N(C)C)=S)(C)C',5.47 +'COP(=O)(NC(=O)(C))SC',35 +'C1=CC=C(C=C1)NC(=O)NC2=CN=NS2',30 +'CCOP(=S)(NC(C)C)OC1=CC=CC=C1C(=O)OC(C)C',0.5 +'CC(=NOC(=O)N(C)SN(C)C(=O)ON=C(C)SC)SC',10 +'CCOP(=S)(OCC)OC1=NC(=NC(=C1)C)C(C)C',1.5 +'NC(CCCC1)C1',58.5 +'CN1C=C(c2ccccc2)C(=O)C(c3cc(C(F)(F)F)ccc3)=C1',32.5 +'ClC1CC2C(C1Cl)C3(Cl)C(=C(Cl)C2(Cl)C3(Cl)Cl)Cl',0.5 +'CCCCC(CC)COC(=O)C1=CC=CC=C1C(=O)OCC(CC)CCCC',200 +'OC(=O)CNCP(O)(O)=O',1000 +'C1CNC(=S)N1',0.23 +'O=C(N(OC)C)Nc(ccc(c1Cl)Cl)c1',6.25 +'C1=CC=C2C(=C1)NC(=S)S2',750 +'CCOP(=S)(OCC)OC1=NC(=C(C=C1Cl)Cl)Cl',10 +'c(c(c(c(c1Cl)Cl)Cl)Cl)(c1Cl)Cl',0.29 +'COc1ccc(cc1)C(c2ccc(OC)cc2)C(Cl)(Cl)Cl',125 +'C1=CC(=CC=C1Cl)Cl',300 +'CC(C)OC(=O)NC1=CC(=CC=C1)Cl',500 +'COP(=O)(OC)OC=C(Cl)Cl',2.15 +'CCOP(=S)(OCC)Oc1ccc(cc1)N(=O)=O',0.42 +'CNC(=O)N(C)c1nnc(s1)C(C)(C)C',40 +'CCCCOCCOCCOCC1=CC2=C(C=C1CCC)OCO2',250 +'CC(C(=O)O)OC1=C(C=C(C=C1)Cl)Cl',9 +'CC1(C(C1C(=O)OC(C#N)C2=CC(=C(C=C2)F)OC3=CC=CC=C3)C=C(Cl)Cl)C',12.5 +'C(#N)c(c(c(c(c1C(#N))Cl)Cl)Cl)c1Cl',4 +'O=C(OCC)C(O)(c(ccc(c1)Cl)c1)c(ccc(c2)Cl)c2',18.4 +'O=C(N(C)C)Nc(ccc(c1)Cl)c1',125 +'O=C(N(SC(Cl)(Cl)Cl)C(=O)C1CC=CC2)C12',100 +'CCc1cccc(C)c1N(C(C)COC)C(=O)CCl',150 +'C1=CC(=C(C=C1Cl)Cl)OCC(=O)O',5 +'CCNC1=NC(=NC(=N1)Cl)NC(C)(C)C#N',1.25 +'C(C(C(C(C1Cl)Cl)Cl)Cl)(C1Cl)Cl',4.6 +'COP(=S)(OC)OC1=CC(=C(C=C1Cl)Cl)Cl',50 +'C1C2C=CC1C3C2C4(C(=C(C3(C4(Cl)Cl)Cl)Cl)Cl)Cl',0.01 +'CC1(C(C1C(=O)OCC2=CC(=CC=C2)OC3=CC=CC=C3)C=C(Cl)Cl)C',25 +'CCN(CC)C(=O)C(C)OC1=CC=CC2=CC=CC=C21',100 +'ClC1C=CC2C1C3(Cl)C(=C(Cl)C2(Cl)C3(Cl)Cl)Cl',0.25 +'CC(=CC(=O)NC)OP(=O)(OC)OC',0.45 +'CC(C)C1(C)N=C(NC1(=O))c3nc2ccccc2cc3C(=O)(O)',20 +'CC(C)Nc1nc(Cl)nc(NC(C)C)n1',50 +'CC(C(=O)O)(Cl)Cl',50 +'CC1(C(C1C(=O)OC(C#N)C2=CC(=C(C=C2)F)OC3=CC=CC=C3)C=C(Cl)Cl)C',7.5 +'O=C(NC)CSP(OC)(OC)=S',5 +'C12C3(C4(C5(C3(C(C1(C5(C2(C4(Cl)Cl)Cl)Cl)Cl)(Cl)Cl)Cl)Cl)Cl)Cl',0.01 +'COC(=O)C1=CC=CC=C1C(=O)OC',2000 +'CCOP(=S)(OCC)SCSC(C)(C)C',0.05 +'CCC(C)SP(=O)(OCC)SC(C)CC',0.25 +'CCOP(=S)(OCC)SCSC(C)(C)C',2 +'C1C(C(C(=O)N1C2=CC=CC(=C2)C(F)(F)F)Cl)CCl',5 +'O=C(O)C(C(C(=O)O)C(O1)CC2)C12',115 +'O=C(Oc(c(OC(C1)(C)C)c1cc2)c2)NC',5 +'Oc(c(c(c(c1)Cl)Cl)Cc(c(c(cc2Cl)Cl)Cl)c2O)c1Cl',5 +'CC1(CON(C1=O)CC2=CC=CC=C2Cl)C',21.5 +'CCC(C)N1C(=O)C(=C(NC1=O)C)Br',62.5 +'CC1=CC(=CC(=C1N(C)C)C)OC(=O)NC',1.5 +'CNC(=O)OC1=CC=CC(=C1)N=CN(C)C',12.5 +'CC1=NN(C(=O)N1C(F)F)C2=CC(=C(C=C2Cl)Cl)NS(=O)(=O)C',67 +'CCOP(=S)(CC)SC1=CC=CC=C1',5 +'CCOP(=S)(OCC)SC(CCl)N1C(=O)C2=CC=CC=C2C1=O',2.5 +'N1CC(C)(C)CNC1=NN=C(C=Cc2ccc(C(F)(F)F)cc2)C=Cc3ccc(C(F)(F)F)cc3',5 +'CC1=C(C(=C(C(=C1F)F)COC(=O)C2C(C2(C)C)C=C(C(F)(F)F)Cl)F)F',4.6 +'CC1=CC(=C(C=C1)N=CN(C)C=NC2=C(C=C(C=C2)C)C)C',10.2 +'S=P(OC)(OC)SCN1C(=O)SC(OC)=N1',0.8 +'CC(C)N(C(C)C)C(=O)SCC(Cl)=C(Cl)Cl',12.5 +'S=P(OC)(OC)SCN1N=Nc2ccccc2C1(=O)',2.25 +'CC1=NC(=NC(=N1)OC)NC(=O)NS(=O)(=O)C2=CC=CC=C2CCC(F)(F)F',79.9 +'O=C(N(S(=O)(=O)Nc1cccc2)C(C)C)c12',40 +'CCN(CC)c1nc(C)cc(OP(=S)(OC)OC)n1',13.8 +'O=C(ON=CC(SC)(C)C)NC',0.1 +'ClC(Cl)(Cl)CC1(OC1)c2cc(Cl)cc(Cl)c2',30 +'CCC1CCCC(C(C(=O)C2CC3C(C2CC(=O)O1)CCC4C3CC(C4)OC5CC(C(C(C5OC)OC)OC)C)C)OC6CCC(C(O6)C)N(C)C',24 +'CC(C)(C)C(=NOC(=O)NC)CSC',6 +'CON=C(CC1=CN=CC=C1)C2=C(C=C(C=C2)Cl)Cl',45 +'CC(=CC1C(C1(C)C)C(=O)OCN2C(=O)C3=C(C2=O)CCCC3)C',250 +'C1COC(O1)(CN2C=NC=N2)C3=C(C=C(C=C3)Cl)Cl',10 +'CCCOC(=O)C1=CN=C(C=C1)C(=O)OCCC',250 +'CC1=CC(=NC(=N1)NC(=O)NS(=O)(=O)C2=CC=CC=C2C(=O)OC3COC3)C',83 +'C1=C(C(=NC(=C1Cl)Cl)OCC(=O)O)Cl',36 +'CCOCN1C(=C(C(=C1C(F)(F)F)Br)C#N)C2=CC=C(C=C2)Cl',13.6 +'CC(C)CC1=C(C(=NC(=C1C(=O)SC)C(F)(F)F)C(F)F)C(=O)SC',3.63 +'CC12CC1(C(=O)N(C2=O)C3=CC(=CC(=C3)Cl)Cl)C',15 +'CC1=CC(=C(C=C1)C(=O)OC)C2=NC(C(=O)N2)(C)C(C)C',50 +'COP(=S)(OC)OC1=NC(=C(C=C1Cl)Cl)Cl',3 +'CC(C)CC1=C(C(=NC(=C1C(=O)OC)C(F)F)C(F)(F)F)C2=NCCS2',44.2 +'CCOC(=O)C(CC1=CC(=C(C=C1Cl)F)N2C(=O)N(C(=N2)C)C(F)F)Cl',12 +'CC(C)=CC3C(C(=O)OCc2coc(Cc1ccccc1)c2)C3(C)C',125 +'CCCSP(=S)(OCC)OC1=CC=C(C=C1)SC',11.5 +'CC1=CC(=C(C(=C1)OC(=O)NC)C)C',59.2 +'CC1=CC=CC=C1COC2CC3(CCC2(O3)C)C(C)C',150 +'CC1=C2C(=CC=C1)SC3=NN=CN23',31 +'CCC(=C1C(=O)CC(CC1=O)CC(C)SCC)NOCC=CCl',100 +'CCCN(CCC)C(=O)SCC',9 +'CC(C)OC(=O)C=C(C)C=CCC(C)CCCC(C)(C)OC',46 +'COP(=S)(OC)Oc1ccc(SC)c(C)c1',3.75 +'COC1=C(C=C(C=C1)C(=CC(=O)N2CCOCC2)C3=CC=C(C=C3)Cl)OC',46.3 +'CCSC(=O)N(CC(C)C)CC(C)C',100 +'CC(C)OP(=S)(OC(C)C)SCCNS(=O)(=O)C1=CC=CC=C1',15 +'CC(=CC1C(C1(C)C)C(=O)OCC2=CC(=CC=C2)OC3=CC=CC=C3)C',150 +'CC1=CC(=CC(=C1C)C)OC(=O)NC',10 +'CCOP(=S)(OCC)SCSC1=CC=C(C=C1)Cl',1 +'C1CN(CCN1C(C(Cl)(Cl)Cl)NC=O)C(C(Cl)(Cl)Cl)NC=O',100 +'C(=CC=C1)(C2=C1)NC(=N2)C(=CS3)N=C3',2 +'C1(=C(C(=C(C(=C1Cl)Cl)Cl)Cl)Cl)[N+](=O)[O-]',125 +'CCCC(=NOCC)C1C(=O)CC(CC1=O)CC(C)SCC',16.56 +'ClC2(Cl)C4(Cl)C1(Cl)C5(Cl)C(Cl)(Cl)C3(Cl)C1(Cl)C2(Cl)C3(Cl)C45Cl',0.7 +'CCN(C1CCCCC1)C(=O)SCC',3 +'CC1=NC(=NC(=N1)OC)NC(=O)NS(=O)(=O)C2=CC=CC=C2OCCCl',220.8 +'C(C(=O)O)OC1=NC(=C(C(=C1Cl)N)Cl)F',500 +'CC1=C(C(=O)CC1OC(=O)C2C(C2(C)C)C=C(C)C)CC#C',95 +'C1C(COC1(CN2C=NC=N2)C3=C(C=C(C=C3)Cl)Cl)Br',6.48 +'C1=NNC(=N1)N',2.5 +'C1=CC(=C(C(=C1)F)C(=O)NC(=O)NC2=CC(=C(C(=C2F)Cl)F)Cl)F',26 +'C1=CC(=CC=C1OS(=O)(=O)C2=CC=C(C=C2)Cl)Cl',2.5 +'FC(F)(F)C(=CC(N(=O)=O)=C1N(C(C)C)C(C)C)C=C1N(=O)=O',1000 +'CC1=C(C(=O)CC1OC(=O)C2C(C2(C)C)C=C(C)C)CC=C',75 +'C1=CC(=C(C(=C1)Cl)C#N)Cl',2.5 +'C1C(O1)COC2=CC=CC=C2C3=CC=CC=C3',500 +'CC1=CC=CC=C1OCC2=CC=CC=C2C(=NOC)C(=O)OC',375 +'O=N(=O)C(C(=C1N(=O)=O)N(C(C)C)C(C)C)=CC(=C1)S(=O)(=O)N',36.86 +'C1=CC(=C(C2=NC=C(C=C21)Cl)C(=O)O)Cl',757 +'CC(C)NC(=O)N1CC(=O)N(C1=O)C2=CC(=CC(=C2)Cl)Cl',46 +'CCCN(CCCl)C1=C(C=C(C=C1[N+](=O)[O-])C(F)(F)F)[N+](=O)[O-]',202.4 +'C1=CC=C(C=C1)C2=CC=CC=C2O',1000 +'O=C(N(C)C)Nc(cccc1C(F)(F)F)c1',15 +'C1=CC(=NC(=C1)Cl)C(Cl)(Cl)Cl',1 +'Clc1cc(Cl)cc(Cl)c1OCCN(CCC)C(=O)n2cncc2',7.5 +'CC1=CC(=C(C=C1NC(=O)C)NS(=O)(=O)C(F)(F)F)C',27.6 +'C(=C(I)I)(I)I',50 +'C1=C(C=C(C(=C1Cl)N2C(=C(C(=N2)C#N)S(=O)C(F)(F)F)N)Cl)C(F)(F)F',0.06 +'O=C(N(C)C)Nc(ccc(c1Cl)Cl)c1',6.25 +'CC1=C(C(=O)CC1OC(=O)C2C(C2(C)C)C=C(C)C)CC=C',24.5 +'CC1=CC2=C(C=C1)N=C3C(=N2)SC(=O)S3',7.5 +'CC(C)N(C(=O)CCl)c1ccccc1',23 +'CC(C)C1(C(=O)NC(=N1)C2=C(C=CC=N2)C(=O)O)C',500 +'CC1(C(C1(C)C)C(=O)OC(C#N)C2=CC(=CC=C2)OC3=CC=CC=C3)C',19.45 +'CN1CN(C(=S)SC1)C',30 +'ClC(Cl)=CC1C(C)(C)C1C(=O)OC(C(#N))c2cccc(Oc3ccccc3)c2',75 +'ClC2C1OC1C3C2C4(Cl)C(=C(Cl)C3(Cl)C4(Cl)Cl)Cl',0.2 +'CCOC(=O)CN1C2=C(C=CC=C2Cl)SC1=O',12.5 +'CCCN(CCC)C1=C(C=C(C(=C1[N+](=O)[O-])N)C(F)(F)F)[N+](=O)[O-]',29.4 +'C1=CC=C(C=C1)C(CCC2=CC=C(C=C2)Cl)(CN3C=NC=N3)C#N',40 +'CC(C)(C)C(CCC1=CC=C(C=C1)Cl)(CN2C=NC=N2)O',15.9 +'CC1=C(C=CC=C1COC(=O)C2C(C2(C)C)C=C(C(F)(F)F)Cl)C3=CC=CC=C3',5 +'C(=CC=C1)(C2=C1)NC(=N2)C(=CS3)N=C3',40 +'C1=C(C=C(C(=C1Cl)N)Cl)[N+](=O)[O-]',150 +'CC1=C(C=C(C=C1C(=O)N)[N+](=O)[O-])[N+](=O)[O-]',6.25 +'CC(C)OC1=CC=CC(=C1)NC(=O)C2=CC=CC=C2C(F)(F)F',500 +'OC(c1ccc(Cl)cc1)(c2ccc(Cl)cc2)C(Cl)(Cl)Cl',2.5 +'O=P(O)(O)CCCl',446 +'CN(C(=O)NC1=CC=C(C=C1)Br)OC',12.5 +'CC1=CC(=CC=C1)NC(=O)OC2=CC=CC(=C2)NC(=O)OC',25 +'CC(C)(C)C1=NN=C(S1)N2C(CN(C2=O)C)O',50 +'S=P(OCC)(OCC)Oc1ccc2C(C)=C(Cl)C(=O)Oc2c1',1.7 +'COC(=O)c1ccccc1S(=O)(=O)NC(=O)N(C)c2nc(OC)nc(C)n2',12.5 +'C1=CC=C(C(=C1)NC2=NC(=NC(=N2)Cl)Cl)Cl',1.15 +'CC1=C(C=CC(=C1)OP(=S)(OC)OC)[N+](=O)[O-]',0.46 +'COc1c(Cl)ccc(Cl)c1C(=O)(O)',115 +'CC1(C(C1C(=O)OC(C#N)C2=CC(=CC=C2)OC3=CC=CC=C3)C=C(Br)Br)C',2.5 +'C1=CC=C(C(=C1)C(C2=CC=C(C=C2)F)(C3=CN=CN=C3)O)Cl',2.5 +'c1ccc2nc(NC(=O)OC)n(C(=O)NCCCC)c2c1',115 +'CCOC(=O)COC(=O)C1=C(C=CC(=C1)OC2=C(C=C(C=C2)C(F)(F)F)Cl)[N+](=O)[O-]',25 +'CC(C)(C)C(C(N1C=NC=N1)OC2=CC=C(C=C2)C3=CC=CC=C3)O',25 +'CCNC(=O)NC(=O)C(=NOC)C#N',30.3 +'CCOC1=C(C=CC(=C1)OC2=C(C=C(C=C2)C(F)(F)F)Cl)[N+](=O)[O-]',40 +'CC1=NC=C(N1CCO)[N+](=O)[O-]',150 +'O=C(N(SC(Cl)(Cl)Cl)C(=O)c1cccc2)c12',500 +'CC(C)(C)c2ccc(OC1CCCCC1OS(=O)OCC#C)cc2',100 +'CCCCC(CN1C=NC=N1)(C2=C(C=C(C=C2)Cl)Cl)O',4.7 +'CC(C)(C)C(C(=CC1=C(C=C(C=C1)Cl)Cl)N2C=NC=N2)O',50 +'C1=CC(C2C1C3(C(=C(C2(C3(Cl)Cl)Cl)Cl)Cl)Cl)Cl',0.38 +'C1=CC=C2C(=C1)C(=O)C3=C(C2=O)SC(=C(S3)C#N)C#N',10 +'CC1=NN(C(=C1C=NOCC2=CC=C(C=C2)C(=O)OC(C)(C)C)OC3=CC=CC=C3)C',3.08 +'CS(=O)(=O)C1=C(C=CC(=C1)C(F)(F)F)C(=O)C2=C(ON=C2)C3CC3',20 +'CC1=C(N=C(N=C1OC(=O)N(C)C)N(C)C)C',12.5 +'CCN(CC)C(=O)C(Cl)=C(C)OP(=O)(OC)OC',1.5 +'C1=CC(=CC=C1C(CN)O)O',250 +'CC1=C(C(=CC=C1)C)N(C(=O)COC)N2CCOC2=O',50 +'c1c(C(F)(F)F)cccc1N2C(=O)C(Cl)=C(NC)C=N2',18.75 +'CCC(C)NC1=C(C=C(C=C1[N+](=O)[O-])C(C)(C)C)[N+](=O)[O-]',50 +'C1=CC(=CC=C1S(=O)(=O)C2=CC(=C(C=C2Cl)Cl)Cl)Cl',230 +'CCCCC1=C(NC(=NC1=O)NCC)C',25 +'n(c(nc(n1)NCC)NCC)c1Cl',5.3 +'FC(F)(F)C(C=C1N(=O)=O)=CC(N(=O)=O)=C1N(CC)CC(C)=C',12.5 +'C1CCC(C1)N(CC2=CC=C(C=C2)Cl)C(=O)NC3=CC=CC=C3',25 +'CS(=O)(=O)NC(=O)C1=C(C=CC(=C1)OC2=C(C=C(C=C2)C(F)(F)F)Cl)[N+](=O)[O-]',50 +'CCOC(=O)C(C)OC1=CC=C(C=C1)OC2=NC3=C(O2)C=C(C=C3)Cl',9 +'CCC1=C(C(=CC=C1)CC)N(CNC(=O)C)C(=O)CCl',62.5 +'NC(=N)NCCCCCCCCCCCC(OC(=O)C)',29 +'C1=CC(=CC(=C1)Cl)NC(=O)OCC#CCCl',450 +'CC(C)C(C(=O)OC(C(#N))c2cccc(Oc1ccccc1)c2)c3ccc(Cl)cc3',25 +'CC(C)C1=C(C=CC(=C1)C(C)(C)C2=CC(=C(C=C2)O)C(C)C)O',25 +'CCN(CC1=C(C=CC=C1Cl)F)C2=C(C=C(C=C2[N+](=O)[O-])C(F)(F)F)[N+](=O)[O-]',50 +'CCCCCCCCSC(=O)OC1=CC(=NN=C1C2=CC=CC=C2)Cl',67.5 +'CC1=C(C(=O)CC1OC(=O)C2C(C2(C)C)C=C(C)C)CC=C',13.8 +'CCCCNC(=O)N1C2=CC=CC=C2N=C1NC(=O)OC',250 +'CC1=C(C(=CC=C1)C)N(C(C)C(=O)OC)C(=O)CC2=CC=CC=C2',46 +'CC(C)C(C1=CC=C(C=C1)OC(F)F)C(=O)OC(C#N)C2=CC(=CC=C2)OC3=CC=CC=C3',6 +'Clc1ccccc1c2nnc(c3ccccc3Cl)nn2',20 +'CCOC(=O)NCCOC1=CC=C(C=C1)OC2=CC=CC=C2',10 +'CCC1=C(C(=CC=C1)CC)N(CC(=O)OCC)C(=O)CCl',50 +'c1(O2)c(CC2(C)C)cccc1OC(=O)N(C)SN(CCCC)CCCC',25 +'CCCCOC(=O)C(C)OC1=CC=C(C=C1)OC2=NC=C(C=C2)C(F)(F)F',3 +'COC1=CC(=C(C=C1Cl)OC)Cl',125 +'CCOP(=S)(OCC)OC1=NN(C(=N1)Cl)C(C)C',12.5 +'n(c(nc(n1)NC(C)C)NCC)c1Cl',25 +'CC(C)(C)C(C(=CC1=CC=C(C=C1)Cl)N2C=NC=N2)O',39.41 +'CCCCCCCCc1cc(N(=O)(=O))c(OC(=O)C=CC)c(c1)N(=O)(=O)',50 +'c1cc(OC(F)(F)F)ccc1C(O)(C(C)C)c2cncnc2',12.1 +'COP(=O)(C(C(Cl)(Cl)Cl)O)OC',20 +'C1=CC(=C(C=C1C(F)(F)F)Cl)OC2=CC(=C(C=C2)[N+](=O)[O-])C(=O)O',125 +'CCCN(CC1CC1)C2=C(C=C(C=C2[N+](=O)[O-])C(F)(F)F)[N+](=O)[O-]',5 +'CCOC(=O)C(C)OC(=O)C1=C(C=CC(=C1)OC2=C(C=C(C=C2)C(F)(F)F)Cl)[N+](=O)[O-]',50 +'CCSC(=O)N1CCCCCC1',14.81 +'CCC1=CC=C(C=C1)C(=O)NN(C(=O)C2=CC(=CC(=C2)C)C)C(C)(C)C',48 +'ClC(Cl)C(Cl)(Cl)SN2C(=O)C1CC=CCC1C2(=O)',15 +'COC(=O)C1=CC=CC=C1S(=O)(=O)NC(=O)NC2=NC(=CC(=N2)OC(F)F)OC(F)F',140 +'CC(C)(C)C(C(N1C=NC=N1)OC2=CC=C(C=C2)Cl)O',25 +'CC1=C(C=CC(=C1)Cl)OCC(=O)O',4 +'COC=C(C1=CC=CC=C1OC2=NC=NC(=C2)OC3=CC=CC=C3C#N)C(=O)OC',62.25 +'C1=CC=C(C(=C1)C(C2=CC=C(C=C2)Cl)(C3=CN=CN=C3)O)Cl',2.3 +'[O-]Br(=O)=O',6.1 +'OP(=O)OCC',400 +'COP(N)(=O)SC',0.1 +'CCOP(=O)(NC(C)C)Oc1ccc(SC)c(C)c1',1.5 +'CCOP(=S)(OCC)SCCSCC',0.04 +'CCOP(=S)(OCC)SCSP(=S)(OCC)OCC',2 +'O=C(OCC(CCCC)CC)CCCCC(=O)OCC(CCCC)CC',1500 +'CN(C=Nc1ccc(C)cc1C)C=Nc2ccc(C)cc2C',10 +'[C@@]14([C@@H]5OCC1=CC=C[C@@H]([C@H](O[C@H]2C[C@@H]([C@H]([C@@H](O2)C)O[C@H]3C[C@@H]([C@H]([C@@H](O3)C)O)OC)OC)C(=CC[C@@H]6C[C@H](OC([C@@H]4C=C([C@H]5O)C)=O)C[C@]7(O6)O[C@@H]([C@H](C=C7)C)[C@H](CC)C)C)C)O',2 +'O=C(N(S(=O)(=O)Nc1cccc2)C(C)C)c12',35 +'S=P(OC)(OC)SCN1C(=O)SC(OC)=N1',1.25 +'C(#N)Cl',70 +'C(#N)Br',122 +'C1=CC(=CC=C1C(C2=CC=C(C=C2)Cl)C(Cl)(Cl)Cl)Cl',0.25 +'c(cccc1)(c1)C(C)C',331 +'CCCN(CCC)C(=O)SCC',25 +'NC(CCCC1)C1',60 +'ClC1CC2C(C1Cl)C3(Cl)C(=C(Cl)C2(Cl)C3(Cl)Cl)Cl',6 +'CC(C)OC(=O)NC1=CC(=CC=C1)Cl',1000 +'COC(=O)c1c(Cl)c(Cl)c(C(=O)OC)c(Cl)c1Cl',10 +'COC(=O)C1=CC=C(C=C1)C(=O)OC',125 +'N(C(=S)NC1)C1',0.25 +'O=C(N(OC)C)Nc(ccc(c1Cl)Cl)c1',2.5 +'c(cccc1)(c1)C=C',285 +'COC(=O)c1ccccc1S(=O)(=O)NC(=O)Nc2nc(OC)nc(C)n2',250 +'C1=CC(=CC=C1N)Cl',12.5 +'FC(F)(F)C(Cl)=CC1C(C)(C)C1C(=O)OC(C(#N))c2cc(Oc3ccccc3)ccc2',12.5 +'C(Cl)(Br)Br',28.5 +'C=C(Cl)Cl',14 +'C(C=CCl)Cl',5.1 +'COP(=O)(OC)OC(=CCl)c1cc(Cl)c(Cl)cc1Cl',50 +'Oc(ccc(c1)C(c(ccc(O)c2)c2)(C)C)c1',50 +'O=C(OCc(cccc1)c1)c(c(ccc2)C(=O)OCCCC)c2',470 +'O=C(NCCCC1)C1',125 +'c(cccc1)(c1)Cl',120 +'C(Cl)(Cl)Cl',60 +'ClCCl',52.58 +'C1C2C3C(C1C4C2O4)C5(C(=C(C3(C5(Cl)Cl)Cl)Cl)Cl)Cl',0.125 +'OCCO',1000 +'O=C(C=C(CC1(C)C)C)C1',179 +'C(F)(Cl)(Cl)Cl',349 +'CCc1cccc(CC)c1N(COC)C(=O)CCl',14 +'c1ccccc1c2c(C)c(COC(=O)C3C(C)(C)C3C=C(Cl)C(F)(F)F)ccc2',5 +'n1c(Cl)cc(OC)nc1NC(=O)NS(=O)(=O)c2ccccc2C(=O)OCC',125 +'O=C(NC(=O)c(c(F)ccc1)c1F)Nc(ccc(c2)Cl)c2',7.8 +'c(cccc1)(c1)CC',291 +'O=C(N(SC(Cl)(Cl)Cl)C(=O)c1cccc2)c12',40 +'Clc1cc(C(F)(F)F)cnc1Oc2ccc(OC(C)C(=O)OC)cc2',1 +'C#N',31 +'ClC(C(OC(C=C2C(=O)OC(C)C(=O)OCC)=CC=C2N(=O)=O)=C1)=CC=C1C(F)(F)F',50 +'c1c(C(F)(F)F)cccc1N2C(=O)C(Cl)=C(NC)C=N2',51.25 +'O=N(=O)C(C(=C1N(=O)=O)N(C(C)C)C(C)C)=CC(=C1)S(=O)(=O)N',45 +'CN(=CC=C1C(C=C2)=CC=N2C)C=C1',3.75 +'C1=C(C=C(C=C1[N+](=O)[O-])[N+](=O)[O-])[N+](=O)[O-]',13.31 +'C(=C)Cl',1.3 +'C1CCC(=O)CC1',910 +'CC1(C(C1(C)C)C(=O)OC(C#N)C2=CC(=CC=C2)OC3=CC=CC=C3)C',25 +'C1=CC(=O)NNC1(=O)',500 +'CCSC(=O)N1CCCCCC1',2 +'C(C(Cl)(Cl)Cl)(O)O',135 +'ClC2C1OC1C3C2C4(Cl)C(=C(Cl)C3(Cl)C4(Cl)Cl)Cl',0.025 +'Clc1cc(C(F)(F)F)ccc1Oc2cc(OCC)c(N(=O)(=O))cc2',10 +'c1cc(Cl)ccc1C(C(#N))(CCCC)Cn2ncnc2',9.84 +'CC1=C(C=C(C=C1[N+](=O)[O-])[N+](=O)[O-])[N+](=O)[O-]',2 +'CC(C)OC(=O)C(C1=CC=C(C=C1)Br)(C2=CC=C(C=C2)Br)O',26 +'C[N+](C)(C)CCCl',130 +'CCC(=C1C(=O)CC(CC1=O)CC(C)SCC)NOCC=CCl',86 +'CC1=NC(=NC(=C1)C2CC2)NC3=CC=CC=C3',35.6 +'N(c(cccc1)c1)c(cccc2)c2',25 +'CC1(C(=O)N(C(=O)O1)NC2=CC=CC=C2)C3=CC=C(C=C3)OC4=CC=CC=C4',16.8 +'CC1(CCCCC1)C(=O)NC2=C(C(=C(C=C2)O)Cl)Cl',292 +'C1=CC(=C2C(=C1)OC(O2)(F)F)C3=CNC=C3C#N',110 +'C(F)(F)(F)c1ccccc1C(=O)Nc2cccc(OC(C)C)c2',87 +'C(CCCCN=C(N)N)CCCNCCCCCCCCN=C(N)N',19 +'C1CN(C(=N1)N[N+](=O)[O-])CC2=CN=C(C=C2)Cl',17 +'COC(=O)C12CC3=C(C1=NN(CO2)C(=O)N(C4=CC=C(C=C4)OC(F)(F)F)C(=O)OC)C=CC(=C3)Cl',3.6 +'CC1=CC=CC=C1OCC2=CC=CC=C2C(=NOC)C(=O)OC',370 +'CC1=CC(=CC(=C1)C(=O)N(C(C)(C)C)NC(=O)C2=C(C(=CC=C2)OC)C)C',411 +'C1=CC(=C(C(=C1)F)C(=O)NC(=O)NC2=CC(=C(C=C2)OC(C(OC(F)(F)F)F)(F)F)Cl)F',36 +'CC1=CC=C(C=C1)N(SC(F)(Cl)Cl)S(=O)(=O)N(C)C',18 +'CC(C)(C)C1=C(C=CC(=C1)O)O',225 +'CC(=NOCC1=CC=CC=C1C(=NOC)C(=O)OC)C2=CC(=CC=C2)C(F)(F)F',60 +'COC(=O)N(C1=CC=CC=C1COC2=NN(C=C2)C3=CC=C(C=C3)Cl)OC',9 +'CC(C)N1C(=NC(C)(C)C)SCN(C1=O)C2=CC=CC=C2',8.7 +'C1=CC=C(C(=C1)C2=NN=C(N=N2)C3=CC=CC=C3Cl)Cl',17.3 +'CCCC(=C1C(=O)CC(CC1=O)C2CCCSC2)NOCC',28 +'C1CC1NC2=NC(=C(C(=N2)N)C#N)N',22 +'C(C=C1)(=N(C=C1)CC2)C(N2=C3)=CC=C3',0.57 +'C1=CC=C2C(=C1)C(=O)C3=C(C2=O)SC(=C(S3)C#N)C#N',6 +'CCOC1=CC2=C(C=C1)NC(C=C2C)(C)C',12 +'C1=CC=C(C=C1)C(CCC2=CC=C(C=C2)Cl)(CN3C=NC=N3)C#N',30 +'CC1CN(CC(O1)C)CC(C)CC2=CC=C(C=C2)C(C)(C)C',1.7 +'C[Si](CN1C=NC=N1)(C2=CC=C(C=C2)F)C3=CC=C(C=C3)F',2 +'c1cc(Cl)cc(Cl)c1C(OCC=C)Cn2cncc2',15 +'CN(=CC=C1C(C=C2)=CC=N2C)C=C1',2.55 +'CCCCOCCOCCOCC1=CC2=C(C=C1CCC)OCO2',100 +'Clc1cc(Cl)ccc1C2(Cn3ncnc3)OC(CCC)CO2',96 +'C(=CC=C1)(C2=C1)NC(=N2)C(=CS3)N=C3',30 +'CCOC1=CC=C(C=C1)C(C)(C)COCC2=CC(=CC=C2)OC3=CC=CC=C3',26 +'CC(C)(C)c2ccc(OC1CCCCC1OS(=O)OCC#C)cc2',19 +'CC(COC1=CC=C(C=C1)OC2=CC=CC=C2)OC3=CC=CC=N3',140 +'CC(C)(C)C(=O)C(N1C=NC=N1)OC2=CC=C(C=C2)Cl',114 +'CC(C)(C)C(C(N1C=NC=N1)OC2=CC=C(C=C2)Cl)O',105 +'c1ccccc1c2c(C)c(COC(=O)C3C(C)(C)C3C=C(Cl)C(F)(F)F)ccc2',8 +'CC1(C(C1C(=O)OC(C#N)C2=CC(=C(C=C2)F)OC3=CC=CC=C3)C=C(Cl)Cl)C',6 +'CC1(C(C1C(=O)OC(C#N)C2=CC(=C(C=C2)F)OC3=CC=CC=C3)C=C(Cl)Cl)C',12 +'ClC(Cl)=CC1C(C)(C)C1C(=O)OC(C(#N))c2cccc(Oc3ccccc3)c2',50 +'ClC1CC2C(C1Cl)C3(Cl)C(=C(Cl)C2(Cl)C3(Cl)Cl)Cl',0.25 +'ClC4=C(Cl)C5(Cl)C3C1CC(C2OC12)C3C4(Cl)C5(Cl)Cl',0.1 +'C1C2C3C(C1C4C2O4)C5(C(=C(C3(C5(Cl)Cl)Cl)Cl)Cl)Cl',0.25 +'C1(C(C(C(C(C1Cl)Cl)Cl)Cl)Cl)Cl',4.7 +'CCC(=O)Nc1ccc(Cl)c(Cl)c1',76 +'C1(=C(C(=C(C(=C1Cl)Cl)Cl)Cl)Cl)[N+](=O)[O-]',140 +'C1C2C(COS(=O)O1)C3(C(=C(C2(C3(Cl)Cl)Cl)Cl)Cl)Cl',2.9 +'O=C(N(SC(Cl)(Cl)Cl)C(=O)c1cccc2)c12',50 +'CC(C(=O)O)OC1=CC=C(C=C1)OC2=C(C=C(C=N2)C(F)(F)F)Cl',0.1 +'CCCCC(CN1C=NC=N1)(C#N)C2=CC=C(C=C2)Cl',9.8 +'Clc1cc(Cl)cc(Cl)c1OCCN(CCC)C(=O)n2cncc2',5.1 +'COP(=O)(NC(=O)(C))SC',2.5 +'CCOP(=O)(OCC)OC(=CCl)C1=C(C=C(C=C1)Cl)Cl',1.5 +'CCOP(=S)(OCC)SCCSCC',0.22 +'O=P(O)(O)CCCl',12 +'CCCSP(=O)(OCC)SCCC',2.7 +'CCOP(=O)(NC(C)C)Oc1ccc(SC)c(C)c1',1.7 +'COP(=S)(OC)Oc1ccc(SC)c(C)c1',0.72 +'OC(=O)C(N)CCP(C)(=O)O',3.5 +'OC(=O)CNCP(O)(O)=O',300 +'CCOC(=O)CC(SP(=S)(OC)OC)C(=O)OCC',360 +'COP(N)(=O)SC',0.29 +'CC(=CC(=O)OC)OP(=O)(OC)OC',0.35 +'CCOP(=S)(OCC)SCSCC',0.16 +'CCOP(=S)(OCC)SCSC(C)(C)C',0.06 +'S=P(OC)(OC)SCN1N=Nc2ccccc2C1(=O)',2.58 +'CCOP(=S)(OCC)OC1=NC(=C(C=C1Cl)Cl)Cl',1 +'CCOP(=S)(OCC)OC1=NC(=NC(=C1)C)C(C)C',5.8 +'CCC1=NC(=CC(=N1)OP(=S)(OC)OC)OCC',0.45 +'S=P(OC)(OC)SCN1C(=O)SC(OC)=N1',1.6 +'CCOP(=S)(OCC)SCN1C2=C(C=C(C=C2)Cl)OC1=O',2 +'COP(=S)(OC)SCN2C(=O)c1ccccc1C2(=O)',9 +'CCOC(=O)C1=CN2C(=CC(=N2)OP(=S)(OCC)OCC)N=C1C',4 +'CCOP(=S)(OCC)OC1=NN(C=N1)C2=CC=CC=C2',1.3 +'O=C(Oc(c(c(ccc1)cc2)c1)c2)NC',60 +'CC1=CC(=CC(=C1SC)C)OC(=O)NC',9.3 +'CNC(=O)ON=C(C)SC',20 +'CCCOC(=O)NCCCN(C)C',680 +'COC(=O)NC1=NC2=CC=CC=C2N1',75 +'CC1=C(N=C(N=C1OC(=O)N(C)C)N(C)C)C',12.3 +'CNC(=O)CCSCCSP(=O)(OC)OC',0.54 +'N(C(=S)SSC(N(C)C)=S)(C)C',12 +'C1=NNC(=N1)N',5 +'CCCCCCCCc1cc(N(=O)(=O))c(OC(=O)C=CC)c(c1)N(=O)(=O)',64 +'C1=CC=C(C=C1)[Sn](C2=CC=CC=C2)C3=CC=CC=C3',0.3 +'O=C(NC(=O)c(c(F)ccc1)c1F)Nc(ccc(c2)Cl)c2',7 +'N(C(=S)NC1)C1',1.25 +'C1=CC(=C(C(=C1)F)C(=O)NC(=O)NC2=CC(=C(C(=C2F)Cl)F)Cl)F',25 +'CCCSC1=CC2=C(C=C1)N=C(N2)NC(=O)OC',20 +'C1CN(CCN1CCCC(=O)C2=CC=C(C=C2)F)C3=CC=CC=N3',115 +'CC1(C2C(C3C(C(=O)C(=C(N)O)C(=O)C3(C(=O)C2=C(C4=C(C=CC(=C41)Cl)O)O)O)N(C)C)O)O',5200 +'CC1=CC(=C(C=C1NC(=O)C2=CC(=CC(=C2O)I)I)Cl)C(C#N)C3=CC=C(C=C3)Cl',10 +'CN1CC2CC1CN2C3=C(C=C4C(=C3)N(C=C(C4=O)C(=O)O)C5CC5)F',50 +'C1=CC(=CC=C1C(C#N)C2=C(C=CC(=C2Cl)N3C(=O)NC(=O)C=N3)Cl)Cl',15 +'CC1=NC=C(N1C)[N+](=O)[O-]',15 +'CCN1CCN(CC1)C2=C(C=C3C(=C2)N(C=C(C3=O)C(=O)O)C4CC4)F',26 +'CC1C=CC=C2COC3C2(C(C=C(C3O)C)C(=O)OC4CC(CC=C(C1OC5CC(C(C(O5)C)OC6CC(C(C(O6)C)NC(=O)C)OC)OC)C)OC7(C4)C=CC(C(O7)C(C)C)C)O',1 +'COCC(=O)NC1=C(C=CC(=C1)SC2=CC=CC=C2)NC(=NC(=O)OC)NC(=O)OC',40 +'CC1CCC2=C3N1C=C(C(=O)C3=CC(=C2)F)C(=O)O',400 +'COC(=O)NC1=NC2=C(N1)C=C(C=C2)S(=O)C3=CC=CC=C3',2 +'CC1(C2CC3C(C(=O)C(=C(N)O)C(=O)C3(C(=O)C2=C(C4=C1C=CC=C4O)O)O)N(C)C)O',150 +'C1CN(CCN1CCCC(=O)C2=CC=C(C=C2)F)C3=CC=CC=N3',30 +'CC(C)NCC(COC1=CC=CC2=C1C3=CC=CC=C3N2)O',7 +'C1=CC(=CC=C1C(C#N)C2=C(C=CC(=C2Cl)N3C(=O)NC(=O)C=N3)Cl)Cl',23 +'CC1C=CC=C2COC3C2(C(C=C(C3O)C)C(=O)OC4CC(CC=C(C1OC5CC(C(C(O5)C)OC6CC(C(C(O6)C)NC(=O)C)OC)OC)C)OC7(C4)C=CC(C(O7)C(C)C)C)O',2.5 +'COP(=S)(OC)Oc1ccc(SC)c(C)c1',0.45 +'C(C(C(C(C1Cl)Cl)Cl)Cl)(C1Cl)Cl',8 +'C(C(C(C(C1Cl)Cl)Cl)Cl)(C1Cl)Cl',4 +'CC(N(C)C)CN(C(=CC=C3)C1=C3)C(=CC=C2)C(=C2)S1',16.6 +'C1=C(C=C(C(=C1Cl)N)Cl)[N+](=O)[O-]',240 +'c(cccc1)(c1)C=C',400 diff --git a/original/NOAEL-LOAEL_dv.xlsx b/original/NOAEL-LOAEL_dv.xlsx new file mode 100644 index 0000000..34361cf Binary files /dev/null and b/original/NOAEL-LOAEL_dv.xlsx differ diff --git a/original/NOAEL-LOAEL_elena_email_20150306.xlsx b/original/NOAEL-LOAEL_elena_email_20150306.xlsx new file mode 100644 index 0000000..be6065a Binary files /dev/null and b/original/NOAEL-LOAEL_elena_email_20150306.xlsx differ diff --git a/original/box.png b/original/box.png new file mode 100755 index 0000000..9b450e5 Binary files /dev/null and b/original/box.png differ diff --git a/original/deviation_analysis.R b/original/deviation_analysis.R new file mode 100755 index 0000000..7e94616 --- /dev/null +++ b/original/deviation_analysis.R @@ -0,0 +1,30 @@ +# GID ("group id") indicates groups (measurements per molecule) +# MMOL indicates measurements +mydata = read.csv("LOAEL-Duplicates-mmol.csv") + + +# list of per-group deviations from the means (errors) +group_deviation = lapply(split(mydata,mydata$GID),function(x) + +# list of per-group variances +group_var=lapply(group_deviation, function(x) var(x)) + +# list of per-group means +group_mean = lapply(split(mydata, mydata$GID), function(x) mean(x$MMOL)) + +# gr mean vs gr var +png("gr_m_var.png") +plot(log(unlist(lapply(group_deviation, function(x) var(x)))) ~ unlist(group_mean), ylab='Group variance of residuals (ln)', xlab='Group mean', main="Group mean vs Group variance") +dev.off() + +# pooled residuals (plot result shows no interaction) +pooled_residuals = as.vector(unlist(group_deviation)) + +# S-form indicates heavier tails of standard normal, but no skew visible +png("qq_resid.png") +qqnorm(pooled_residuals,main="QQ pooled residuals") +dev.off() + + +cat(paste("SD of pooled residuals:",sd(pooled_residuals),"\n")) + diff --git a/original/gr_m_var.png b/original/gr_m_var.png new file mode 100755 index 0000000..78e4df6 Binary files /dev/null and b/original/gr_m_var.png differ diff --git a/original/loael_in_drei_formaten.R b/original/loael_in_drei_formaten.R new file mode 100755 index 0000000..6d6ee47 Binary files /dev/null and b/original/loael_in_drei_formaten.R differ diff --git a/original/loael_in_drei_formaten_corrected_smiles.R b/original/loael_in_drei_formaten_corrected_smiles.R new file mode 100755 index 0000000..2d7f5f9 Binary files /dev/null and b/original/loael_in_drei_formaten_corrected_smiles.R differ diff --git a/original/qq.png b/original/qq.png new file mode 100755 index 0000000..d8aae52 Binary files /dev/null and b/original/qq.png differ diff --git a/original/qq_resid.png b/original/qq_resid.png new file mode 100755 index 0000000..c0ad8ce Binary files /dev/null and b/original/qq_resid.png differ diff --git a/paper/SMARTS_InteLigand.txt b/paper/SMARTS_InteLigand.txt new file mode 100644 index 0000000..23bc6e2 --- /dev/null +++ b/paper/SMARTS_InteLigand.txt @@ -0,0 +1,983 @@ +# +# SMARTS Patterns for Functional Group Classification +# +# written by Christian Laggner +# Copyright 2005 Inte:Ligand Software-Entwicklungs und Consulting GmbH +# +# Released under the Lesser General Public License (LGPL license) +# see http://www.gnu.org/copyleft/lesser.html +# Modified from Version 221105 +##################################################################################################### + +# General Stuff: +# These patters were written in an attempt to represent the classification of organic compounds +# from the viewpoint of an organic chemist. +# They are often very restrictive. This may be generally a good thing, but it also takes some time +# for filtering/indexing large compound sets. +# For filtering undesired groups (in druglike compounds) one will want to have more general patterns +# (e.g. you don't want *any* halide of *any* acid, *neither* aldehyde *nor* formyl esters and amides, ...). +# + +# Part I: Carbon +# ============== + + +# I.1: Carbon-Carbon Bonds +# ------------------------ + +# I.1.1 Alkanes: + +Primary_carbon: [CX4H3][#6] + +Secondary_carbon: [CX4H2]([#6])[#6] + +Tertiary_carbon: [CX4H1]([#6])([#6])[#6] + +Quaternary_carbon: [CX4]([#6])([#6])([#6])[#6] + + +# I.1.2 C-C double and Triple Bonds + +Alkene: [CX3;$([H2]),$([H1][#6]),$(C([#6])[#6])]=[CX3;$([H2]),$([H1][#6]),$(C([#6])[#6])] +# sp2 C may be substituted only by C or H - +# does not hit ketenes and allenes, nor enamines, enols and the like + +Alkyne: [CX2]#[CX2] +# non-carbon substituents (e.g. alkynol ethers) are rather rare, thus no further discrimination + +Allene: [CX3]=[CX2]=[CX3] + + +# I.2: One Carbon-Hetero Bond +# --------------------------- + + +# I.2.1 Alkyl Halogenides + +Alkylchloride: [ClX1][CX4] +# will also hit chloromethylethers and the like, but no chloroalkenes, -alkynes or -aromats +# a more restrictive version can be obtained by modifying the Alcohol string. + +Alkylfluoride: [FX1][CX4] + +Alkylbromide: [BrX1][CX4] + +Alkyliodide: [IX1][CX4] + + +# I.2.2 Alcohols and Ethers + +Alcohol: [OX2H][CX4;!$(C([OX2H])[O,S,#7,#15])] +# nonspecific definition, no acetals, aminals, and the like + +Primary_alcohol: [OX2H][CX4H2;!$(C([OX2H])[O,S,#7,#15])] + +Secondary_alcohol: [OX2H][CX4H;!$(C([OX2H])[O,S,#7,#15])] + +Tertiary_alcohol: [OX2H][CX4D4;!$(C([OX2H])[O,S,#7,#15])] + +Dialkylether: [OX2]([CX4;!$(C([OX2])[O,S,#7,#15,F,Cl,Br,I])])[CX4;!$(C([OX2])[O,S,#7,#15])] +# no acetals and the like; no enolethers + +Dialkylthioether: [SX2]([CX4;!$(C([OX2])[O,S,#7,#15,F,Cl,Br,I])])[CX4;!$(C([OX2])[O,S,#7,#15])] +# no acetals and the like; no enolethers + +Alkylarylether: [OX2](c)[CX4;!$(C([OX2])[O,S,#7,#15,F,Cl,Br,I])] +# no acetals and the like; no enolethers + +Diarylether: [c][OX2][c] + +Alkylarylthioether: [SX2](c)[CX4;!$(C([OX2])[O,S,#7,#15,F,Cl,Br,I])] + +Diarylthioether: [c][SX2][c] + +Oxonium: [O+;!$([O]~[!#6]);!$([S]*~[#7,#8,#15,#16])] +# can't be aromatic, thus O and not #8 + +# I.2.3 Amines + +Amine: [NX3+0,NX4+;!$([N]~[!#6]);!$([N]*~[#7,#8,#15,#16])] +# hits all amines (prim/sec/tert/quart), including ammonium salts, also enamines, but not amides, imides, aminals, ... + +# the following amines include also the protonated forms + +Primary_aliph_amine: [NX3H2+0,NX4H3+;!$([N][!C]);!$([N]*~[#7,#8,#15,#16])] + +Secondary_aliph_amine: [NX3H1+0,NX4H2+;!$([N][!C]);!$([N]*~[#7,#8,#15,#16])] + +Tertiary_aliph_amine: [NX3H0+0,NX4H1+;!$([N][!C]);!$([N]*~[#7,#8,#15,#16])] + +Quaternary_aliph_ammonium: [NX4H0+;!$([N][!C]);!$([N]*~[#7,#8,#15,#16])] + +Primary_arom_amine: [NX3H2+0,NX4H3+]c + +Secondary_arom_amine: [NX3H1+0,NX4H2+;!$([N][!c]);!$([N]*~[#7,#8,#15,#16])] + +Tertiary_arom_amine: [NX3H0+0,NX4H1+;!$([N][!c]);!$([N]*~[#7,#8,#15,#16])] + +Quaternary_arom_ammonium: [NX4H0+;!$([N][!c]);!$([N]*~[#7,#8,#15,#16])] + +Secondary_mixed_amine: [NX3H1+0,NX4H2+;$([N]([c])[C]);!$([N]*~[#7,#8,#15,#16])] + +Tertiary_mixed_amine: [NX3H0+0,NX4H1+;$([N]([c])([C])[#6]);!$([N]*~[#7,#8,#15,#16])] + +Quaternary_mixed_ammonium: [NX4H0+;$([N]([c])([C])[#6][#6]);!$([N]*~[#7,#8,#15,#16])] + +Ammonium: [N+;!$([N]~[!#6]);!$(N=*);!$([N]*~[#7,#8,#15,#16])] +# only C and H substituents allowed. Quaternary or protonated amines +# NX4+ or Nv4+ is not recognized by Daylight's depictmatch if less than four C are present + + +# I.2.4 Others + +Alkylthiol: [SX2H][CX4;!$(C([SX2H])~[O,S,#7,#15])] + +Dialkylthioether: [SX2]([CX4;!$(C([SX2])[O,S,#7,#15,F,Cl,Br,I])])[CX4;!$(C([SX2])[O,S,#7,#15])] + +Alkylarylthioether: [SX2](c)[CX4;!$(C([SX2])[O,S,#7,#15])] + +Disulfide: [SX2D2][SX2D2] + +1,2-Aminoalcohol: [OX2H][CX4;!$(C([OX2H])[O,S,#7,#15,F,Cl,Br,I])][CX4;!$(C([N])[O,S,#7,#15])][NX3;!$(NC=[O,S,N])] +# does not hit alpha-amino acids, enaminoalcohols, 1,2-aminoacetals, o-aminophenols, etc. + +1,2-Diol: [OX2H][CX4;!$(C([OX2H])[O,S,#7,#15])][CX4;!$(C([OX2H])[O,S,#7,#15])][OX2H] +# does not hit alpha-hydroxy acids, enolalcohols, 1,2-hydroxyacetals, 1,2-diphenols, etc. + +1,1-Diol: [OX2H][CX4;!$(C([OX2H])([OX2H])[O,S,#7,#15])][OX2H] + +Hydroperoxide: [OX2H][OX2] +#does not neccessarily have to be connected to a carbon atom, includes also hydrotrioxides + +Peroxo: [OX2D2][OX2D2] + +Organolithium_compounds: [LiX1][#6,#14] + +Organomagnesium_compounds: [MgX2][#6,#14] +# not restricted to Grignard compounds, also dialkyl Mg + +Organometallic_compounds: [!#1;!#5;!#6;!#7;!#8;!#9;!#14;!#15;!#16;!#17;!#33;!#34;!#35;!#52;!#53;!#85]~[#6;!-] +# very general, includes all metals covalently bound to carbon + + +# I.3: Two Carbon-Hetero Bonds (Carbonyl and Derivatives) +# ---------------------------- + +# I.3.1 Double Bond to Hetero + +Aldehyde: [$([CX3H][#6]),$([CX3H2])]=[OX1] +# hits aldehydes including formaldehyde + +Ketone: [#6][CX3](=[OX1])[#6] +# does not include oxo-groups connected to a (hetero-) aromatic ring + +Thioaldehyde: [$([CX3H][#6]),$([CX3H2])]=[SX1] + +Thioketone: [#6][CX3](=[SX1])[#6] +# does not include thioxo-groups connected to a (hetero-) aromatic ring + +Imine: [NX2;$([N][#6]),$([NH]);!$([N][CX3]=[#7,#8,#15,#16])]=[CX3;$([CH2]),$([CH][#6]),$([C]([#6])[#6])] +# nitrogen is not part of an amidelike strukture, nor of an aromatic ring, but can be part of an aminal or similar + +Immonium: [NX3+;!$([N][!#6]);!$([N][CX3]=[#7,#8,#15,#16])] + +Oxime: [NX2](=[CX3;$([CH2]),$([CH][#6]),$([C]([#6])[#6])])[OX2H] + +Oximether: [NX2](=[CX3;$([CH2]),$([CH][#6]),$([C]([#6])[#6])])[OX2][#6;!$(C=[#7,#8])] +# ether, not ester or amide; does not hit isoxazole + + +# I.3.2. Two Single Bonds to Hetero + +Acetal: [OX2]([#6;!$(C=[O,S,N])])[CX4;!$(C(O)(O)[!#6])][OX2][#6;!$(C=[O,S,N])] +# does not hit hydroxy-methylesters, ketenacetals, hemiacetals, orthoesters, etc. + +Hemiacetal: [OX2H][CX4;!$(C(O)(O)[!#6])][OX2][#6;!$(C=[O,S,N])] + +Aminal: [NX3v3;!$(NC=[#7,#8,#15,#16])]([#6])[CX4;!$(C(N)(N)[!#6])][NX3v3;!$(NC=[#7,#8,#15,#16])][#6] +# Ns are not part of an amide or similar. v3 ist to exclude nitro and similar groups + +Hemiaminal: [NX3v3;!$(NC=[#7,#8,#15,#16])]([#6])[CX4;!$(C(N)(N)[!#6])][OX2H] + +Thioacetal: [SX2]([#6;!$(C=[O,S,N])])[CX4;!$(C(S)(S)[!#6])][SX2][#6;!$(C=[O,S,N])] + +Thiohemiacetal: [SX2]([#6;!$(C=[O,S,N])])[CX4;!$(C(S)(S)[!#6])][OX2H] + +Halogen_acetal_like: [NX3v3,SX2,OX2;!$(*C=[#7,#8,#15,#16])][CX4;!$(C([N,S,O])([N,S,O])[!#6])][FX1,ClX1,BrX1,IX1] +# hits chloromethylenethers and other reactive alkylating agents + +Acetal_like: [NX3v3,SX2,OX2;!$(*C=[#7,#8,#15,#16])][CX4;!$(C([N,S,O])([N,S,O])[!#6])][FX1,ClX1,BrX1,IX1,NX3v3,SX2,OX2;!$(*C=[#7,#8,#15,#16])] +# includes all of the above and other combinations (S-C-N, hydrates, ...), but still no aminomethylenesters and similar + +Halogenmethylen_ester_and_similar: [NX3v3,SX2,OX2;$(**=[#7,#8,#15,#16])][CX4;!$(C([N,S,O])([N,S,O])[!#6])][FX1,ClX1,BrX1,IX1] +# also reactive alkylating agents. Acid does not have to be carboxylic acid, also S- and P-based acids allowed + +NOS_methylen_ester_and_similar: [NX3v3,SX2,OX2;$(**=[#7,#8,#15,#16])][CX4;!$(C([N,S,O])([N,S,O])[!#6])][NX3v3,SX2,OX2;!$(*C=[#7,#8,#15,#16])] +# Same as above, but N,O or S instead of halogen. Ester/amide allowed only on one side + +Hetero_methylen_ester_and_similar: [NX3v3,SX2,OX2;$(**=[#7,#8,#15,#16])][CX4;!$(C([N,S,O])([N,S,O])[!#6])][FX1,ClX1,BrX1,IX1,NX3v3,SX2,OX2;!$(*C=[#7,#8,#15,#16])] +# Combination of the last two patterns + +Cyanhydrine: [NX1]#[CX2][CX4;$([CH2]),$([CH]([CX2])[#6]),$(C([CX2])([#6])[#6])][OX2H] + + +# I.3.3 Single Bond to Hetero, C=C Double Bond (Enols and Similar) + +Chloroalkene: [ClX1][CX3]=[CX3] + +Fluoroalkene: [FX1][CX3]=[CX3] + +Bromoalkene: [BrX1][CX3]=[CX3] + +Iodoalkene: [IX1][CX3]=[CX3] + +Enol: [OX2H][CX3;$([H1]),$(C[#6])]=[CX3] +# no phenols + +Endiol: [OX2H][CX3;$([H1]),$(C[#6])]=[CX3;$([H1]),$(C[#6])][OX2H] +# no 1,2-diphenols, ketenacetals, ... + +Enolether: [OX2]([#6;!$(C=[N,O,S])])[CX3;$([H0][#6]),$([H1])]=[CX3] +# finds also endiodiethers, but not enolesters, no aromats + +Enolester: [OX2]([CX3]=[OX1])[#6X3;$([#6][#6]),$([H1])]=[#6X3;!$(C[OX2H])] + + +Enamine: [NX3;$([NH2][CX3]),$([NH1]([CX3])[#6]),$([N]([CX3])([#6])[#6]);!$([N]*=[#7,#8,#15,#16])][CX3;$([CH]),$([C][#6])]=[CX3] +# does not hit amines attached to aromatic rings, nor may the nitrogen be aromatic + +Thioenol: [SX2H][CX3;$([H1]),$(C[#6])]=[CX3] + +Thioenolether: [SX2]([#6;!$(C=[N,O,S])])[CX3;$(C[#6]),$([CH])]=[CX3] + + +# I.4: Three Carbon-Hetero Bonds (Carboxyl and Derivatives) +# ------------------------------ + +Acylchloride: [CX3;$([R0][#6]),$([H1R0])](=[OX1])[ClX1] + +Acylfluoride: [CX3;$([R0][#6]),$([H1R0])](=[OX1])[FX1] + +Acylbromide: [CX3;$([R0][#6]),$([H1R0])](=[OX1])[BrX1] + +Acyliodide: [CX3;$([R0][#6]),$([H1R0])](=[OX1])[IX1] + +Acylhalide: [CX3;$([R0][#6]),$([H1R0])](=[OX1])[FX1,ClX1,BrX1,IX1] +# all of the above + + +# The following contains all simple carboxylic combinations of O, N, S, & Hal - +# - acids, esters, amides, ... as well as a few extra cases (anhydride, hydrazide...) +# Cyclic structures (including aromats) like lactones, lactames, ... got their own +# definitions. Structures where both heteroatoms are part of an aromatic ring +# (oxazoles, imidazoles, ...) were excluded. + +Carboxylic_acid: [CX3;$([R0][#6]),$([H1R0])](=[OX1])[$([OX2H]),$([OX1-])] +# includes carboxylate anions + +Carboxylic_ester: [CX3;$([R0][#6]),$([H1R0])](=[OX1])[OX2][#6;!$(C=[O,N,S])] +# does not hit anhydrides or lactones + +Lactone: [#6][#6X3R](=[OX1])[#8X2][#6;!$(C=[O,N,S])] +# may also be aromatic + +Carboxylic_anhydride: [CX3;$([H0][#6]),$([H1])](=[OX1])[#8X2][CX3;$([H0][#6]),$([H1])](=[OX1]) +# anhydride formed by two carboxylic acids, no mixed anhydrides (e.g. between carboxylic acid and sulfuric acid); may be part of a ring, even aromatic + +Carboxylic_acid_derivative: [$([#6X3H0][#6]),$([#6X3H])](=[!#6])[!#6] +# includes most of the structures of I.4 and many more, also 1,3-heteroaromatics such as isoxazole + +Carbothioic_acid: [CX3;!R;$([C][#6]),$([CH]);$([C](=[OX1])[$([SX2H]),$([SX1-])]),$([C](=[SX1])[$([OX2H]),$([OX1-])])] +# hits both tautomeric forms, as well as anions + +Carbothioic_S_ester: [CX3;$([R0][#6]),$([H1R0])](=[OX1])[SX2][#6;!$(C=[O,N,S])] + +Carbothioic_S_lactone: [#6][#6X3R](=[OX1])[#16X2][#6;!$(C=[O,N,S])] +# may also be aromatic + +Carbothioic_O_ester: [CX3;$([H0][#6]),$([H1])](=[SX1])[OX2][#6;!$(C=[O,N,S])] + +Carbothioic_O_lactone: [#6][#6X3R](=[SX1])[#8X2][#6;!$(C=[O,N,S])] + +Carbothioic_halide: [CX3;$([H0][#6]),$([H1])](=[SX1])[FX1,ClX1,BrX1,IX1] + +Carbodithioic_acid: [CX3;!R;$([C][#6]),$([CH]);$([C](=[SX1])[SX2H])] + +Carbodithioic_ester: [CX3;!R;$([C][#6]),$([CH]);$([C](=[SX1])[SX2][#6;!$(C=[O,N,S])])] + +Carbodithiolactone: [#6][#6X3R](=[SX1])[#16X2][#6;!$(C=[O,N,S])] + + +Amide: [CX3;$([R0][#6]),$([H1R0])](=[OX1])[#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])] +# does not hit lactames + +Primary_amide: [CX3;$([R0][#6]),$([H1R0])](=[OX1])[NX3H2] + +Secondary_amide: [CX3;$([R0][#6]),$([H1R0])](=[OX1])[#7X3H1][#6;!$(C=[O,N,S])] + +Tertiary_amide: [CX3;$([R0][#6]),$([H1R0])](=[OX1])[#7X3H0]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])] + +Lactam: [#6R][#6X3R](=[OX1])[#7X3;$([H1][#6;!$(C=[O,N,S])]),$([H0]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])] +# cyclic amides, may also be aromatic + +Alkyl_imide: [#6X3;$([H0][#6]),$([H1])](=[OX1])[#7X3H0]([#6])[#6X3;$([H0][#6]),$([H1])](=[OX1]) +# may be part of a ring, even aromatic. only C allowed at central N. May also be triacyl amide + +N_hetero_imide: [#6X3;$([H0][#6]),$([H1])](=[OX1])[#7X3H0]([!#6])[#6X3;$([H0][#6]),$([H1])](=[OX1]) +# everything else than H or C at central N + +Imide_acidic: [#6X3;$([H0][#6]),$([H1])](=[OX1])[#7X3H1][#6X3;$([H0][#6]),$([H1])](=[OX1]) +# can be deprotonated + +Thioamide: [$([CX3;!R][#6]),$([CX3H;!R])](=[SX1])[#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])] +# does not hit thiolactames + +Thiolactam: [#6R][#6X3R](=[SX1])[#7X3;$([H1][#6;!$(C=[O,N,S])]),$([H0]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])] +# cyclic thioamides, may also be aromatic + + +Oximester: [#6X3;$([H0][#6]),$([H1])](=[OX1])[#8X2][#7X2]=,:[#6X3;$([H0]([#6])[#6]),$([H1][#6]),$([H2])] +# may also be part of a ring / aromatic + +Amidine: [NX3;!$(NC=[O,S])][CX3;$([CH]),$([C][#6])]=[NX2;!$(NC=[O,S])] +# only basic amidines, not as part of aromatic ring (e.g. imidazole) + +Hydroxamic_acid: [CX3;$([H0][#6]),$([H1])](=[OX1])[#7X3;$([H1]),$([H0][#6;!$(C=[O,N,S])])][$([OX2H]),$([OX1-])] + +Hydroxamic_acid_ester: [CX3;$([H0][#6]),$([H1])](=[OX1])[#7X3;$([H1]),$([H0][#6;!$(C=[O,N,S])])][OX2][#6;!$(C=[O,N,S])] +# does not hit anhydrides of carboxylic acids withs hydroxamic acids + + +Imidoacid: [CX3R0;$([H0][#6]),$([H1])](=[NX2;$([H1]),$([H0][#6;!$(C=[O,N,S])])])[$([OX2H]),$([OX1-])] +# not cyclic + +Imidoacid_cyclic: [#6R][#6X3R](=,:[#7X2;$([H1]),$([H0][#6;!$(C=[O,N,S])])])[$([OX2H]),$([OX1-])] +# the enamide-form of lactames. may be aromatic like 2-hydroxypyridine + +Imidoester: [CX3R0;$([H0][#6]),$([H1])](=[NX2;$([H1]),$([H0][#6;!$(C=[O,N,S])])])[OX2][#6;!$(C=[O,N,S])] +# esters of the above structures. no anhydrides. + +Imidolactone: [#6R][#6X3R](=,:[#7X2;$([H1]),$([H0][#6;!$(C=[O,N,S])])])[OX2][#6;!$(C=[O,N,S])] +# no oxazoles and similar + +Imidothioacid: [CX3R0;$([H0][#6]),$([H1])](=[NX2;$([H1]),$([H0][#6;!$(C=[O,N,S])])])[$([SX2H]),$([SX1-])] +# not cyclic + +Imidothioacid_cyclic: [#6R][#6X3R](=,:[#7X2;$([H1]),$([H0][#6;!$(C=[O,N,S])])])[$([SX2H]),$([SX1-])] +# the enamide-form of thiolactames. may be aromatic like 2-thiopyridine + +Imidothioester: [CX3R0;$([H0][#6]),$([H1])](=[NX2;$([H1]),$([H0][#6;!$(C=[O,N,S])])])[SX2][#6;!$(C=[O,N,S])] +# thioesters of the above structures. no anhydrides. + +Imidothiolactone: [#6R][#6X3R](=,:[#7X2;$([H1]),$([H0][#6;!$(C=[O,N,S])])])[SX2][#6;!$(C=[O,N,S])] +# no thioxazoles and similar + +Amidine: [#7X3v3;!$(N([#6X3]=[#7X2])C=[O,S])][CX3R0;$([H1]),$([H0][#6])]=[NX2v3;!$(N(=[#6X3][#7X3])C=[O,S])] +# only basic amidines, not substituted by carbonyl or thiocarbonyl, not as part of a ring + +Imidolactam: [#6][#6X3R;$([H0](=[NX2;!$(N(=[#6X3][#7X3])C=[O,S])])[#7X3;!$(N([#6X3]=[#7X2])C=[O,S])]),$([H0](-[NX3;!$(N([#6X3]=[#7X2])C=[O,S])])=,:[#7X2;!$(N(=[#6X3][#7X3])C=[O,S])])] +# one of the two C~N bonds is part of a ring (may be aromatic), but not both - thus no imidazole + +Imidoylhalide: [CX3R0;$([H0][#6]),$([H1])](=[NX2;$([H1]),$([H0][#6;!$(C=[O,N,S])])])[FX1,ClX1,BrX1,IX1] +# not cyclic + +Imidoylhalide_cyclic: [#6R][#6X3R](=,:[#7X2;$([H1]),$([H0][#6;!$(C=[O,N,S])])])[FX1,ClX1,BrX1,IX1] +# may also be aromatic + +# may be ring, aromatic, substituted with carbonyls, hetero, ... +# (everything else would get too complicated) + +Amidrazone: [$([$([#6X3][#6]),$([#6X3H])](=[#7X2v3])[#7X3v3][#7X3v3]),$([$([#6X3][#6]),$([#6X3H])]([#7X3v3])=[#7X2v3][#7X3v3])] +# hits both tautomers. as above, it may be ring, aromatic, substituted with carbonyls, hetero, ... + + +Alpha_aminoacid: [NX3,NX4+;!$([N]~[!#6]);!$([N]*~[#7,#8,#15,#16])][C][CX3](=[OX1])[OX2H,OX1-] +# N may be alkylated, but not part of an amide (as in peptides), ionic forms are included +# includes also non-natural aminoacids with double-bonded or two aliph./arom. substituents at alpha-C +# N may not be aromatic as in 1H-pyrrole-2-carboxylic acid + +Alpha_hydroxyacid: [OX2H][C][CX3](=[OX1])[OX2H,OX1-] + +Peptide_middle: [NX3;$([N][CX3](=[OX1])[C][NX3,NX4+])][C][CX3](=[OX1])[NX3;$([N][C][CX3](=[OX1])[NX3,OX2,OX1-])] +# finds peptidic structures which are neither C- nor N-terminal. Both neighbours must be amino-acids/peptides + +Peptide_C_term: [NX3;$([N][CX3](=[OX1])[C][NX3,NX4+])][C][CX3](=[OX1])[OX2H,OX1-] +# finds C-terminal amino acids + +Peptide_N_term: [NX3,NX4+;!$([N]~[!#6]);!$([N]*~[#7,#8,#15,#16])][C][CX3](=[OX1])[NX3;$([N][C][CX3](=[OX1])[NX3,OX2,OX1-])] +# finds N-terminal amino acids. As above, N may be substituted, but not part of an amide-bond. + + +Carboxylic_orthoester: [#6][OX2][CX4;$(C[#6]),$([CH])]([OX2][#6])[OX2][#6] +# hits also anhydride like struktures (e. g. HC(OMe)2-OC=O residues) + +Ketene: [CX3]=[CX2]=[OX1] + +Ketenacetal: [#7X2,#8X3,#16X2;$(*[#6,#14])][#6X3]([#7X2,#8X3,#16X2;$(*[#6,#14])])=[#6X3] +# includes aminals, silylacetals, ketenesters, etc. C=C DB is not aromatic, everything else may be + +Nitrile: [NX1]#[CX2] +# includes cyanhydrines + +Isonitrile: [CX1-]#[NX2+] + + +Vinylogous_carbonyl_or_carboxyl_derivative: [#6X3](=[OX1])[#6X3]=,:[#6X3][#7,#8,#16,F,Cl,Br,I] +# may be part of a ring, even aromatic + +Vinylogous_acid: [#6X3](=[OX1])[#6X3]=,:[#6X3][$([OX2H]),$([OX1-])] + +Vinylogous_ester: [#6X3](=[OX1])[#6X3]=,:[#6X3][#6;!$(C=[O,N,S])] + +Vinylogous_amide: [#6X3](=[OX1])[#6X3]=,:[#6X3][#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])] + +Vinylogous_halide: [#6X3](=[OX1])[#6X3]=,:[#6X3][FX1,ClX1,BrX1,IX1] + + + +# I.5: Four Carbon-Hetero Bonds (Carbonic Acid and Derivatives) +# ----------------------------- + +Carbonic_acid_dieester: [#6;!$(C=[O,N,S])][#8X2][#6X3](=[OX1])[#8X2][#6;!$(C=[O,N,S])] +# may be part of a ring, even aromatic + +Carbonic_acid_esterhalide: [#6;!$(C=[O,N,S])][OX2;!R][CX3](=[OX1])[OX2][FX1,ClX1,BrX1,IX1] + +Carbonic_acid_monoester: [#6;!$(C=[O,N,S])][OX2;!R][CX3](=[OX1])[$([OX2H]),$([OX1-])] +# unstable + +Carbonic_acid_derivatives: [!#6][#6X3](=[!#6])[!#6] + + +Thiocarbonic_acid_dieester: [#6;!$(C=[O,N,S])][#8X2][#6X3](=[SX1])[#8X2][#6;!$(C=[O,N,S])] +# may be part of a ring, even aromatic + +Thiocarbonic_acid_esterhalide: [#6;!$(C=[O,N,S])][OX2;!R][CX3](=[SX1])[OX2][FX1,ClX1,BrX1,IX1] + +Thiocarbonic_acid_monoester: [#6;!$(C=[O,N,S])][OX2;!R][CX3](=[SX1])[$([OX2H]),$([OX1-])] + + +Urea:[#7X3;!$([#7][!#6])][#6X3](=[OX1])[#7X3;!$([#7][!#6])] +# no check whether part of imide, biuret, etc. Aromatic structures are only hit if +# both N share no double bonds, like in the dioxo-form of uracil + +Thiourea: [#7X3;!$([#7][!#6])][#6X3](=[SX1])[#7X3;!$([#7][!#6])] + +Isourea: [#7X2;!$([#7][!#6])]=,:[#6X3]([#8X2&!$([#8][!#6]),OX1-])[#7X3;!$([#7][!#6])] +# O may be substituted. no check whether further amide-like bonds are present. Aromatic +# structures are only hit if single bonded N shares no additional double bond, like in +# the 1-hydroxy-3-oxo form of uracil + +Isothiourea: [#7X2;!$([#7][!#6])]=,:[#6X3]([#16X2&!$([#16][!#6]),SX1-])[#7X3;!$([#7][!#6])] + +Guanidine: [N;v3X3,v4X4+][CX3](=[N;v3X2,v4X3+])[N;v3X3,v4X4+] +# also hits guanidinium salts. v3 and v4 to avoid nitroamidines + +Carbaminic_acid: [NX3]C(=[OX1])[O;X2H,X1-] +# quite unstable, unlikely to be found. Also hits salts + +Urethan: [#7X3][#6](=[OX1])[#8X2][#6] +# also hits when part of a ring, no check whether the last C is part of carbonyl + +Biuret: [#7X3][#6](=[OX1])[#7X3][#6](=[OX1])[#7X3] + +Semicarbazide: [#7X3][#7X3][#6X3]([#7X3;!$([#7][#7])])=[OX1] + +Carbazide: [#7X3][#7X3][#6X3]([#7X3][#7X3])=[OX1] + +Semicarbazone: [#7X2](=[#6])[#7X3][#6X3]([#7X3;!$([#7][#7])])=[OX1] + +Carbazone: [#7X2](=[#6])[#7X3][#6X3]([#7X3][#7X3])=[OX1] + +Thiosemicarbazide: [#7X3][#7X3][#6X3]([#7X3;!$([#7][#7])])=[SX1] + +Thiocarbazide: [#7X3][#7X3][#6X3]([#7X3][#7X3])=[SX1] + +Thiosemicarbazone: [#7X2](=[#6])[#7X3][#6X3]([#7X3;!$([#7][#7])])=[SX1] + +Thiocarbazone: [#7X2](=[#6])[#7X3][#6X3]([#7X3][#7X3])=[SX1] + + +Isocyanate: [NX2]=[CX2]=[OX1] + +Cyanate: [OX2][CX2]#[NX1] + +Isothiocyanate: [NX2]=[CX2]=[SX1] + +Thiocyanate: [SX2][CX2]#[NX1] + +Carbodiimide: [NX2]=[CX2]=[NX2] + +Orthocarbonic_derivatives: [CX4H0]([O,S,#7])([O,S,#7])([O,S,#7])[O,S,#7,F,Cl,Br,I] +# halogen allowed just once, to avoid mapping to -OCF3 and similar groups (much more +# stable as for example C(OCH3)4) + + +# I.6 Aromatics +# ------------- + +# I know that this classification is not very logical, arylamines are found under I.2 ... + +Phenol: [OX2H][c] + +1,2-Diphenol: [OX2H][c][c][OX2H] + +Arylchloride: [Cl][c] + +Arylfluoride: [F][c] + +Arylbromide: [Br][c] + +Aryliodide: [I][c] + +Arylthiol: [SX2H][c] + +Iminoarene: [c]=[NX2;$([H1]),$([H0][#6;!$([C]=[N,S,O])])] +# N may be substituted with H or C, but not carbonyl or similar +# aromatic atom is always C, not S or P (these are not planar when substituted) + +Oxoarene: [c]=[OX1] + +Thioarene: [c]=[SX1] + +Hetero_N_basic_H: [nX3H1+0] +# as in pyrole. uncharged to exclude pyridinium ions + +Hetero_N_basic_no_H: [nX3H0+0] +# as in N-methylpyrole. uncharged to exclude pyridinium ions + +Hetero_N_nonbasic: [nX2,nX3+] +# as in pyridine, pyridinium + +Hetero_O: [o] + +Hetero_S: [sX2] +# X2 because Daylight's depictmatch falsely describes C1=CS(=O)C=C1 as aromatic +# (is not planar because of lonepair at S) + +Heteroaromatic: [a;!c] + + +# Part II: N, S, P, Si, B +# ======================= + + +# II.1 Nitrogen +# ------------- + +Nitrite: [NX2](=[OX1])[O;$([X2]),$([X1-])] +# hits nitrous acid, its anion, esters, and other O-substituted derivatives + +Thionitrite: [SX2][NX2]=[OX1] + +Nitrate: [$([NX3](=[OX1])(=[OX1])[O;$([X2]),$([X1-])]),$([NX3+]([OX1-])(=[OX1])[O;$([X2]),$([X1-])])] +# hits nitric acid, its anion, esters, and other O-substituted derivatives + +Nitro: [$([NX3](=O)=O),$([NX3+](=O)[O-])][!#8] +# hits nitro groups attached to C,N, ... but not nitrates + +Nitroso: [NX2](=[OX1])[!#7;!#8] +# no nitrites, no nitrosamines + +Azide: [NX1]~[NX2]~[NX2,NX1] +# hits both mesomeric forms, also anion + +Acylazide: [CX3](=[OX1])[NX2]~[NX2]~[NX1] + +Diazo: [$([#6]=[NX2+]=[NX1-]),$([#6-]-[NX2+]#[NX1])] + +Diazonium: [#6][NX2+]#[NX1] + +Nitrosamine: [#7;!$(N*=O)][NX2]=[OX1] + +Nitrosamide: [NX2](=[OX1])N-*=O +# includes nitrososulfonamides + +N-Oxide: [$([#7+][OX1-]),$([#7v5]=[OX1]);!$([#7](~[O])~[O]);!$([#7]=[#7])] +# Hits both forms. Won't hit azoxy, nitro, nitroso, or nitrate. + + +Hydrazine: [NX3;$([H2]),$([H1][#6]),$([H0]([#6])[#6]);!$(NC=[O,N,S])][NX3;$([H2]),$([H1][#6]),$([H0]([#6])[#6]);!$(NC=[O,N,S])] +# no hydrazides + +Hydrazone: [NX3;$([H2]),$([H1][#6]),$([H0]([#6])[#6]);!$(NC=[O,N,S])][NX2]=[#6] + +Hydroxylamine: [NX3;$([H2]),$([H1][#6]),$([H0]([#6])[#6]);!$(NC=[O,N,S])][OX2;$([H1]),$(O[#6;!$(C=[N,O,S])])] +# no discrimination between O-, N-, and O,N-substitution + + +# II.2 Sulfur +# ----------- + +Sulfon: [$([SX4](=[OX1])(=[OX1])([#6])[#6]),$([SX4+2]([OX1-])([OX1-])([#6])[#6])] +# can't be aromatic, thus S and not #16 + +Sulfoxide: [$([SX3](=[OX1])([#6])[#6]),$([SX3+]([OX1-])([#6])[#6])] + +Sulfonium: [S+;!$([S]~[!#6]);!$([S]*~[#7,#8,#15,#16])] +# can't be aromatic, thus S and not #16 + +Sulfuric_acid: [SX4](=[OX1])(=[OX1])([$([OX2H]),$([OX1-])])[$([OX2H]),$([OX1-])] +# includes anions + +Sulfuric_monoester: [SX4](=[OX1])(=[OX1])([$([OX2H]),$([OX1-])])[OX2][#6;!$(C=[O,N,S])] + +Sulfuric_diester: [SX4](=[OX1])(=[OX1])([OX2][#6;!$(C=[O,N,S])])[OX2][#6;!$(C=[O,N,S])] + +Sulfuric_monoamide: [SX4](=[OX1])(=[OX1])([#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])])[$([OX2H]),$([OX1-])] + +Sulfuric_diamide: [SX4](=[OX1])(=[OX1])([#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])])[#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])] + +Sulfuric_esteramide: [SX4](=[OX1])(=[OX1])([#7X3][#6;!$(C=[O,N,S])])[OX2][#6;!$(C=[O,N,S])] + +Sulfuric_derivative: [SX4D4](=[!#6])(=[!#6])([!#6])[!#6] +# everything else (would not be a "true" derivative of sulfuric acid, if one of the substituents were less electronegative +# than sulfur, but this should be very very rare, anyway) + + + +#### sulfurous acid and derivatives missing!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!! + + + + +Sulfonic_acid: [SX4;$([H1]),$([H0][#6])](=[OX1])(=[OX1])[$([OX2H]),$([OX1-])] + +Sulfonamide: [SX4;$([H1]),$([H0][#6])](=[OX1])(=[OX1])[#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])] + +Sulfonic_ester: [SX4;$([H1]),$([H0][#6])](=[OX1])(=[OX1])[OX2][#6;!$(C=[O,N,S])] + +Sulfonic_halide: [SX4;$([H1]),$([H0][#6])](=[OX1])(=[OX1])[FX1,ClX1,BrX1,IX1] + +Sulfonic_derivative: [SX4;$([H1]),$([H0][#6])](=[!#6])(=[!#6])[!#6] +# includes all of the above and many more +# for comparison: this is what "all sulfonic derivatives but not the ones above" would look like: +# [$([SX4;$([H1]),$([H0][#6])](=[!#6])(=[!#6;!O])[!#6]),$([SX4;$([H1]),$([H0][#6])](=[OX1])(=[OX1])[!$([FX1,ClX1,BrX1,IX1]);!$([#6]);!$([OX2H]);!$([OX1-]);!$([OX2][#6;!$(C=[O,N,S])]);!$([#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])])])] + + +Sulfinic_acid: [SX3;$([H1]),$([H0][#6])](=[OX1])[$([OX2H]),$([OX1-])] + +Sulfinic_amide: [SX3;$([H1]),$([H0][#6])](=[OX1])[#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])] + +Sulfinic_ester: [SX3;$([H1]),$([H0][#6])](=[OX1])[OX2][#6;!$(C=[O,N,S])] + +Sulfinic_halide: [SX3;$([H1]),$([H0][#6])](=[OX1])[FX1,ClX1,BrX1,IX1] + +Sulfinic_derivative: [SX3;$([H1]),$([H0][#6])](=[!#6])[!#6] + +Sulfenic_acid: [SX2;$([H1]),$([H0][#6])][$([OX2H]),$([OX1-])] + +Sulfenic_amide: [SX2;$([H1]),$([H0][#6])][#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])] + +Sulfenic_ester: [SX2;$([H1]),$([H0][#6])][OX2][#6;!$(C=[O,N,S])] + +Sulfenic_halide: [SX2;$([H1]),$([H0][#6])][FX1,ClX1,BrX1,IX1] + +Sulfenic_derivative: [SX2;$([H1]),$([H0][#6])][!#6] + + +# II.3 Phosphorous +# ---------------- + +Phosphine: [PX3;$([H3]),$([H2][#6]),$([H1]([#6])[#6]),$([H0]([#6])([#6])[#6])] +# similar to amine, but less restrictive: includes also amide- and aminal-analogues + +Phosphine_oxide: [PX4;$([H3]=[OX1]),$([H2](=[OX1])[#6]),$([H1](=[OX1])([#6])[#6]),$([H0](=[OX1])([#6])([#6])[#6])] + +Phosphonium: [P+;!$([P]~[!#6]);!$([P]*~[#7,#8,#15,#16])] +# similar to Ammonium + +Phosphorylen: [PX4;$([H3]=[CX3]),$([H2](=[CX3])[#6]),$([H1](=[CX3])([#6])[#6]),$([H0](=[CX3])([#6])([#6])[#6])] + + +# conventions for the following acids and derivatives: +# acids find protonated and deprotonated acids +# esters do not find mixed anhydrides ( ...P-O-C(=O)) +# derivatives: subtituents which go in place of the OH and =O are not H or C (may also be O, +# thus including acids and esters) + +Phosphonic_acid: [PX4;$([H1]),$([H0][#6])](=[OX1])([$([OX2H]),$([OX1-])])[$([OX2H]),$([OX1-])] +# includes anions + +Phosphonic_monoester: [PX4;$([H1]),$([H0][#6])](=[OX1])([$([OX2H]),$([OX1-])])[OX2][#6;!$(C=[O,N,S])] + +Phosphonic_diester: [PX4;$([H1]),$([H0][#6])](=[OX1])([OX2][#6;!$(C=[O,N,S])])[OX2][#6;!$(C=[O,N,S])] + +Phosphonic_monoamide: [PX4;$([H1]),$([H0][#6])](=[OX1])([$([OX2H]),$([OX1-])])[#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])] + +Phosphonic_diamide: [PX4;$([H1]),$([H0][#6])](=[OX1])([#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])])[#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])] + +Phosphonic_esteramide: [PX4;$([H1]),$([H0][#6])](=[OX1])([OX2][#6;!$(C=[O,N,S])])[#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])] + +Phosphonic_acid_derivative: [PX4;$([H1]),$([H0][#6])](=[!#6])([!#6])[!#6] +# all of the above and much more + + +Phosphoric_acid: [PX4D4](=[OX1])([$([OX2H]),$([OX1-])])([$([OX2H]),$([OX1-])])[$([OX2H]),$([OX1-])] +# includes anions + +Phosphoric_monoester: [PX4D4](=[OX1])([$([OX2H]),$([OX1-])])([$([OX2H]),$([OX1-])])[OX2][#6;!$(C=[O,N,S])] + +Phosphoric_diester: [PX4D4](=[OX1])([$([OX2H]),$([OX1-])])([OX2][#6;!$(C=[O,N,S])])[OX2][#6;!$(C=[O,N,S])] + +Phosphoric_triester: [PX4D4](=[OX1])([OX2][#6;!$(C=[O,N,S])])([OX2][#6;!$(C=[O,N,S])])[OX2][#6;!$(C=[O,N,S])] + +Phosphoric_monoamide: [PX4D4](=[OX1])([$([OX2H]),$([OX1-])])([$([OX2H]),$([OX1-])])[#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])] + +Phosphoric_diamide: [PX4D4](=[OX1])([$([OX2H]),$([OX1-])])([#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])])[#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])] + +Phosphoric_triamide: [PX4D4](=[OX1])([#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])])([#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])])[#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])] + +Phosphoric_monoestermonoamide: [PX4D4](=[OX1])([$([OX2H]),$([OX1-])])([OX2][#6;!$(C=[O,N,S])])[#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])] + +Phosphoric_diestermonoamide: [PX4D4](=[OX1])([OX2][#6;!$(C=[O,N,S])])([OX2][#6;!$(C=[O,N,S])])[#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])] + +Phosphoric_monoesterdiamide: [PX4D4](=[OX1])([OX2][#6;!$(C=[O,N,S])])([#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])])[#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])] + +Phosphoric_acid_derivative: [PX4D4](=[!#6])([!#6])([!#6])[!#6] + + +Phosphinic_acid: [PX4;$([H2]),$([H1][#6]),$([H0]([#6])[#6])](=[OX1])[$([OX2H]),$([OX1-])] + +Phosphinic_ester: [PX4;$([H2]),$([H1][#6]),$([H0]([#6])[#6])](=[OX1])[OX2][#6;!$(C=[O,N,S])] + +Phosphinic_amide: [PX4;$([H2]),$([H1][#6]),$([H0]([#6])[#6])](=[OX1])[#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])] + +Phosphinic_acid_derivative: [PX4;$([H2]),$([H1][#6]),$([H0]([#6])[#6])](=[!#6])[!#6] + + +Phosphonous_acid: [PX3;$([H1]),$([H0][#6])]([$([OX2H]),$([OX1-])])[$([OX2H]),$([OX1-])] + +Phosphonous_monoester: [PX3;$([H1]),$([H0][#6])]([$([OX2H]),$([OX1-])])[OX2][#6;!$(C=[O,N,S])] + +Phosphonous_diester: [PX3;$([H1]),$([H0][#6])]([OX2][#6;!$(C=[O,N,S])])[OX2][#6;!$(C=[O,N,S])] + +Phosphonous_monoamide: [PX3;$([H1]),$([H0][#6])]([$([OX2H]),$([OX1-])])[#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])] + +Phosphonous_diamide: [PX3;$([H1]),$([H0][#6])]([#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])])[#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])] + +Phosphonous_esteramide: [PX3;$([H1]),$([H0][#6])]([OX2][#6;!$(C=[O,N,S])])[#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])] + +Phosphonous_derivatives: [PX3;$([D2]),$([D3][#6])]([!#6])[!#6] + + +Phosphinous_acid: [PX3;$([H2]),$([H1][#6]),$([H0]([#6])[#6])][$([OX2H]),$([OX1-])] + +Phosphinous_ester: [PX3;$([H2]),$([H1][#6]),$([H0]([#6])[#6])][OX2][#6;!$(C=[O,N,S])] + +Phosphinous_amide: [PX3;$([H2]),$([H1][#6]),$([H0]([#6])[#6])][#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])] + +Phosphinous_derivatives: [PX3;$([H2]),$([H1][#6]),$([H0]([#6])[#6])][!#6] + + +# II.4 Silicon +# ------------ + +Quart_silane: [SiX4]([#6])([#6])([#6])[#6] +# four C-substituents. non-reactive, non-toxic, in experimental phase for drug development + +Non-quart_silane: [SiX4;$([H1]([#6])([#6])[#6]),$([H2]([#6])[#6]),$([H3][#6]),$([H4])] +# has 1-4 hydride(s), reactive. Daylight's depictmatch does not add hydrogens automatically to +# the free positions at Si, thus Hs had to be added implicitly + +Silylmonohalide: [SiX4]([FX1,ClX1,BrX1,IX1])([#6])([#6])[#6] +# reagents for inserting protection groups + +Het_trialkylsilane: [SiX4]([!#6])([#6])([#6])[#6] +# mostly acid-labile protection groups such as trimethylsilyl-ethers + +Dihet_dialkylsilane: [SiX4]([!#6])([!#6])([#6])[#6] + +Trihet_alkylsilane: [SiX4]([!#6])([!#6])([!#6])[#6] + +Silicic_acid_derivative: [SiX4]([!#6])([!#6])([!#6])[!#6] +# four substituent which are neither C nor H + + +# II.5 Boron +# ---------- + +Trialkylborane: [BX3]([#6])([#6])[#6] +# also carbonyls allowed + +Boric_acid_derivatives: [BX3]([!#6])([!#6])[!#6] +# includes acids, esters, amides, ... H-substituent at B is very rare. + +Boronic_acid_derivative: [BX3]([!#6])([!#6])[!#6] +# # includes acids, esters, amides, ... + +Borohydride: [BH1,BH2,BH3,BH4] +# at least one H attached to B + +Quaternary_boron: [BX4] +# mostly borates (negative charge), in complex with Lewis-base + + + +# Part III: Some Special Patterns +# =============================== + + +# III.1 Chains +# ------------ + +# some simple chains + + + +# III.2 Rings +# ----------- + +Aromatic: a + +Heterocyclic: [!#6;!R0] +# may be aromatic or not + +Epoxide: [OX2r3]1[#6r3][#6r3]1 +# toxic/reactive. may be annelated to aromat, but must not be aromatic itself (oxirane-2,3-dione) + +NH_aziridine: [NX3H1r3]1[#6r3][#6r3]1 +# toxic/reactive according to Maybridge's garbage filter + +Spiro: [D4R;$(*(@*)(@*)(@*)@*)] +# at least two different rings can be found which are sharing just one atom. +# these two rings can be connected by a third ring, so it matches also some +# bridged systems, like morphine + +Annelated_rings: [R;$(*(@*)(@*)@*);!$([R2;$(*(@*)(@*)(@*)@*)])]@[R;$(*(@*)(@*)@*);!$([R2;$(*(@*)(@*)(@*)@*)])] +# two different rings sharing exactly two atoms + +Bridged_rings: [R;$(*(@*)(@*)@*);!$([D4R;$(*(@*)(@*)(@*)@*)]);!$([R;$(*(@*)(@*)@*);!$([R2;$(*(@*)(@*)(@*)@*)])]@[R;$(*(@*)(@*)@*);!$([R2;$(*(@*)(@*)(@*)@*)])])] +# part of two or more rings, not spiro, not annelated -> finds bridgehead atoms, +# but only if they are not annelated at the same time - otherwise impossible (?) +# to distinguish from non-bridgehead annelated atoms + +# some basic ring-patterns (just size, no other information): + + + + + +# III.3 Sugars and Nucleosides/Nucleotides, Steroids +# -------------------------------------------------- + +# because of the large variety of sugar derivatives, different patterns can be applied. +# The choice of patterns and their combinations will depend on the contents of the database +# e.g. natural products, nucleoside analoges with modified sugars, ... as well as on the +# desired restriction + + +Sugar_pattern_1: [OX2;$([r5]1@C@C@C(O)@C1),$([r6]1@C@C@C(O)@C(O)@C1)] +# 5 or 6-membered ring containing one O and at least one (r5) or two (r6) oxygen-substituents. + +Sugar_pattern_2: [OX2;$([r5]1@C(!@[OX2,NX3,SX2,FX1,ClX1,BrX1,IX1])@C@C@C1),$([r6]1@C(!@[OX2,NX3,SX2,FX1,ClX1,BrX1,IX1])@C@C@C@C1)] +# 5 or 6-membered ring containing one O and an acetal-like bond at postion 2. + +Sugar_pattern_combi: [OX2;$([r5]1@C(!@[OX2,NX3,SX2,FX1,ClX1,BrX1,IX1])@C@C(O)@C1),$([r6]1@C(!@[OX2,NX3,SX2,FX1,ClX1,BrX1,IX1])@C@C(O)@C(O)@C1)] +# combination of the two above + +Sugar_pattern_2_reducing: [OX2;$([r5]1@C(!@[OX2H1])@C@C@C1),$([r6]1@C(!@[OX2H1])@C@C@C@C1)] +# 5 or 6-membered cyclic hemi-acetal + +Sugar_pattern_2_alpha: [OX2;$([r5]1@[C@@](!@[OX2,NX3,SX2,FX1,ClX1,BrX1,IX1])@C@C@C1),$([r6]1@[C@@](!@[OX2,NX3,SX2,FX1,ClX1,BrX1,IX1])@C@C@C@C1)] +# 5 or 6-membered cyclic hemi-acetal + +Sugar_pattern_2_beta: [OX2;$([r5]1@[C@](!@[OX2,NX3,SX2,FX1,ClX1,BrX1,IX1])@C@C@C1),$([r6]1@[C@](!@[OX2,NX3,SX2,FX1,ClX1,BrX1,IX1])@C@C@C@C1)] +# 5 or 6-membered cyclic hemi-acetal + +##Poly_sugar_1: ([OX2;$([r5]1@C@C@C(O)@C1),$([r6]1@C@C@C(O)@C(O)@C1)].[OX2;$([r5]1@C@C@C(O)@C1),$([r6]1@C@C@C(O)@C(O)@C1)]) +# pattern1 occours more than once (in same molecule, but moieties don't have to be adjacent!) + +##Poly_sugar_2: ([OX2;$([r5]1@C(!@[OX2,NX3,SX2,FX1,ClX1,BrX1,IX1])@C@C@C1),$([r6]1@C(!@[OX2,NX3,SX2,FX1,ClX1,BrX1,IX1])@C@C@C@C1)].[OX2;$([r5]1@C(!@[OX2,NX3,SX2,FX1,ClX1,BrX1,IX1])@C@C@C1),$([r6]1@C(!@[OX2,NX3,SX2,FX1,ClX1,BrX1,IX1])@C@C@C@C1)]) +# pattern2 occours more than once (in same molecule, but moieties don't have to be adjacent!) + + +# III.4 Everything else... +# ------------------------ + +Conjugated_double_bond: *=*[*]=,#,:[*] + +Conjugated_tripple_bond: *#*[*]=,#,:[*] + +Cis_double_bond: */[D2]=[D2]\* +# only one single-bonded substituent on each DB-atom. no aromats. +# only found when character of DB is explicitely stated. + +Trans_double_bond: */[D2]=[D2]/* +# analog + +Mixed_anhydrides: [$(*=O),$([#16,#14,#5]),$([#7]([#6]=[OX1]))][#8X2][$(*=O),$([#16,#14,#5]),$([#7]([#6]=[OX1]))] +# should hits all combinations of two acids + +Halogen_on_hetero: [FX1,ClX1,BrX1,IX1][!#6] + +Halogen_multi_subst: [F,Cl,Br,I;!$([X1]);!$([X0-])] +# Halogen which is not mono-substituted nor an anion, e.g. chlorate. +# Most of these cases should be also filtered by Halogen_on_hetero. + +Trifluoromethyl: [FX1][CX4;!$([H0][Cl,Br,I]);!$([F][C]([F])([F])[F])]([FX1])([FX1]) +# C with three F attached, connected to anything which is not another halogen + +C_ONS_bond: [#6]~[#7,#8,#16] +# probably all drug-like molecules have at least one O, N, or S connected to a C -> nice filter + +## Mixture: (*).(*) +# two or more seperate parts, may also be salt +# component-level grouping is not yet supported in Open Babel Version 2.0 + + +Charged: [!+0] + +Anion: [-1,-2,-3,-4,-5,-6,-7] + +Kation: [+1,+2,+3,+4,+5,+6,+7] + +Salt: ([-1,-2,-3,-4,-5,-6,-7]).([+1,+2,+3,+4,+5,+6,+7]) +# two or more seperate components with opposite charges + +##Zwitterion: ([-1,-2,-3,-4,-5,-6,-7].[+1,+2,+3,+4,+5,+6,+7]) +# both negative and positive charges somewhere within the same molecule. + +1,3-Tautomerizable: [$([#7X2,OX1,SX1]=*[!H0;!$([a;!n])]),$([#7X3,OX2,SX2;!H0]*=*),$([#7X3,OX2,SX2;!H0]*:n)] +# 1,3 migration of H allowed. Includes keto/enol and amide/enamide. +# Aromatic rings must stay aromatic - no keto form of phenol + +1,5-Tautomerizable: [$([#7X2,OX1,SX1]=,:**=,:*[!H0;!$([a;!n])]),$([#7X3,OX2,SX2;!H0]*=**=*),$([#7X3,OX2,SX2;!H0]*=,:**:n)] + +Rotatable_bond: [!$(*#*)&!D1]-!@[!$(*#*)&!D1] +# taken from http://www.daylight.com/support/contrib/smarts/content.html + +Michael_acceptor: [CX3]=[CX3][$([CX3]=[O,N,S]),$(C#[N]),$([S,P]=[OX1]),$([NX3]=O),$([NX3+](=O)[O-])] +# the classical case: C=C near carbonyl, nitrile, nitro, or similar +# Oxo-heteroaromats and similar are not included. + +Dicarbodiazene: [CX3](=[OX1])[NX2]=[NX2][CX3](=[OX1]) +# Michael-like acceptor, see Mitsunobu reaction + +# H-Bond_donor: + +# H-Bond_acceptor: + +# Pos_ionizable: + +# Neg_ionizable: + +# Unlikely_ions: +# O+,N-,C+,C-, ... + +CH-acidic: [$([CX4;!$([H0]);!$(C[!#6;!$([P,S]=O);!$(N(~O)~O)])][$([CX3]=[O,N,S]),$(C#[N]),$([S,P]=[OX1]),$([NX3]=O),$([NX3+](=O)[O-]);!$(*[S,O,N;H1,H2]);!$([*+0][S,O;X1-])]),$([CX4;!$([H0])]1[CX3]=[CX3][CX3]=[CX3]1)] +# C-H alpha to carbony, nitro or similar, C is not double-bonded, only C, H, S,P=O and nitro substituents allowed. +# pentadiene is included. acids, their salts, prim./sec. amides, and imides are excluded. +# hits also CH-acidic_strong + +CH-acidic_strong: [CX4;!$([H0]);!$(C[!#6;!$([P,S]=O);!$(N(~O)~O)])]([$([CX3]=[O,N,S]),$(C#[N]),$([S,P]=[OX1]),$([NX3]=O),$([NX3+](=O)[O-]);!$(*[S,O,N;H1,H2]);!$([*+0][S,O;X1-])])[$([CX3]=[O,N,S]),$(C#[N]),$([S,P]=[OX1]),$([NX3]=O),$([NX3+](=O)[O-]);!$(*[S,O,N;H1,H2]);!$([*+0][S,O;X1-])] +# same as above (without pentadiene), but carbonyl or similar on two or three sides + +Chiral_center_specified: [$([*@](~*)(~*)(*)*),$([*@H](*)(*)*),$([*@](~*)(*)*),$([*@H](~*)~*)] +# Hits atoms with tetrahedral chirality, if chiral center is specified in the SMILES string +# depictmach does not find oxonium, sulfonium, or sulfoxides! + +# Chiral_center_unspecified: [$([*@?](~*)(~*)(*)*),$([*@?H](*)(*)*),$([*@?](~*)(*)*),$([*@?H](~*)~*)] +# Hits atoms with tetrahedral chirality, if chiral center is not specified in the SMILES string +# "@?" (unspecified chirality) is not yet supported in Open Babel Version 2.0 + \ No newline at end of file diff --git a/paper/functional-groups.csv b/paper/functional-groups.csv new file mode 100644 index 0000000..414c28c --- /dev/null +++ b/paper/functional-groups.csv @@ -0,0 +1,307 @@ +Primary_carbon, 303, 287 +Secondary_carbon, 147, 149 +Tertiary_carbon, 91, 73 +Quaternary_carbon, 58, 60 +Alkene, 39, 30 +Alkyne, 5, 8 +Allene, 0, 0 +Alkylchloride, 71, 41 +Alkylfluoride, 52, 74 +Alkylbromide, 5, 3 +Alkyliodide, 0, 0 +Alcohol, 44, 27 +Primary_alcohol, 12, 2 +Secondary_alcohol, 23, 10 +Tertiary_alcohol, 18, 21 +Dialkylether, 35, 32 +Dialkylthioether, 14, 6 +Alkylarylether, 62, 90 +Diarylether, 35, 47 +Alkylarylthioether, 11, 10 +Diarylthioether, 3, 0 +Oxonium, 0, 0 +Amine, 66, 41 +Primary_aliph_amine, 8, 3 +Secondary_aliph_amine, 2, 2 +Tertiary_aliph_amine, 16, 9 +Quaternary_aliph_ammonium, 1, 6 +Primary_arom_amine, 26, 15 +Secondary_arom_amine, 2, 1 +Tertiary_arom_amine, 19, 0 +Quaternary_arom_ammonium, 0, 0 +Secondary_mixed_amine, 8, 3 +Tertiary_mixed_amine, 14, 7 +Quaternary_mixed_ammonium, 0, 0 +Ammonium, 1, 6 +Alkylthiol, 0, 0 +Dialkylthioether, 10, 4 +Alkylarylthioether, 10, 10 +Disulfide, 4, 2 +1,2-Aminoalcohol, 5, 0 +1,2-Diol, 12, 3 +1,1-Diol, 1, 0 +Hydroperoxide, 0, 0 +Peroxo, 0, 0 +Organolithium_compounds, 0, 0 +Organomagnesium_compounds, 0, 0 +Organometallic_compounds, 1, 5 +Aldehyde, 3, 1 +Ketone, 21, 25 +Thioaldehyde, 0, 0 +Thioketone, 0, 0 +Imine, 0, 0 +Immonium, 0, 0 +Oxime, 0, 0 +Oximether, 7, 15 +Acetal, 13, 13 +Hemiacetal, 1, 0 +Aminal, 1, 0 +Hemiaminal, 0, 0 +Thioacetal, 0, 0 +Thiohemiacetal, 0, 0 +Halogen_acetal_like, 13, 14 +Acetal_like, 34, 30 +Halogenmethylen_ester_and_similar, 1, 0 +NOS_methylen_ester_and_similar, 18, 19 +Hetero_methylen_ester_and_similar, 19, 19 +Cyanhydrine, 0, 0 +Chloroalkene, 39, 21 +Fluoroalkene, 0, 1 +Bromoalkene, 1, 2 +Iodoalkene, 1, 0 +Enol, 4, 5 +Endiol, 2, 0 +Enolether, 2, 4 +Enolester, 0, 6 +Enamine, 0, 1 +Thioenol, 0, 0 +Thioenolether, 1, 1 +Acylchloride, 0, 0 +Acylfluoride, 0, 0 +Acylbromide, 0, 0 +Acyliodide, 0, 0 +Acylhalide, 0, 0 +Carboxylic_acid, 33, 38 +Carboxylic_ester, 0, 0 +Lactone, 11, 10 +Carboxylic_anhydride, 1, 0 +Carboxylic_acid_derivative, 215, 227 +Carbothioic_acid, 0, 0 +Carbothioic_S_ester, 1, 1 +Carbothioic_S_lactone, 0, 0 +Carbothioic_O_ester, 0, 0 +Carbothioic_O_lactone, 0, 0 +Carbothioic_halide, 0, 0 +Carbodithioic_acid, 0, 0 +Carbodithioic_ester, 0, 0 +Carbodithiolactone, 0, 0 +Amide, 38, 60 +Primary_amide, 2, 1 +Secondary_amide, 22, 36 +Tertiary_amide, 15, 23 +Lactam, 12, 18 +Alkyl_imide, 5, 4 +N_hetero_imide, 6, 3 +Imide_acidic, 0, 0 +Thioamide, 0, 0 +Thiolactam, 0, 0 +Oximester, 0, 0 +Amidine, 3, 4 +Hydroxamic_acid, 0, 0 +Hydroxamic_acid_ester, 1, 1 +Imidoacid, 0, 0 +Imidoacid_cyclic, 0, 2 +Imidoester, 0, 0 +Imidolactone, 13, 32 +Imidothioacid, 0, 0 +Imidothioacid_cyclic, 0, 0 +Imidothioester, 0, 0 +Imidothiolactone, 1, 1 +Amidine, 3, 5 +Imidolactam, 3, 2 +Imidoylhalide, 0, 0 +Imidoylhalide_cyclic, 10, 19 +Amidrazone, 0, 0 +Alpha_aminoacid, 1, 1 +Alpha_hydroxyacid, 0, 0 +Peptide_middle, 0, 0 +Peptide_C_term, 0, 0 +Peptide_N_term, 1, 0 +Carboxylic_orthoester, 0, 0 +Ketene, 0, 0 +Ketenacetal, 0, 0 +Nitrile, 35, 39 +Isonitrile, 0, 0 +Vinylogous_carbonyl_or_carboxyl_derivative, 70, 97 +Vinylogous_acid, 9, 8 +Vinylogous_ester, 113, 120 +Vinylogous_amide, 19, 24 +Vinylogous_halide, 11, 27 +Carbonic_acid_dieester, 0, 2 +Carbonic_acid_esterhalide, 0, 0 +Carbonic_acid_monoester, 0, 0 +Carbonic_acid_derivatives, 109, 131 +Thiocarbonic_acid_dieester, 0, 0 +Thiocarbonic_acid_esterhalide, 0, 0 +Thiocarbonic_acid_monoester, 0, 0 +Urea, 23, 21 +Thiourea, 4, 4 +Isourea, 0, 1 +Isothiourea, 1, 3 +Guanidine, 6, 7 +Carbaminic_acid, 0, 0 +Urethan, 34, 35 +Biuret, 1, 4 +Semicarbazide, 0, 0 +Carbazide, 0, 0 +Semicarbazone, 1, 3 +Carbazone, 0, 0 +Thiosemicarbazide, 1, 0 +Thiocarbazide, 0, 0 +Thiosemicarbazone, 0, 0 +Thiocarbazone, 0, 0 +Isocyanate, 0, 0 +Cyanate, 0, 0 +Isothiocyanate, 0, 0 +Thiocyanate, 0, 0 +Carbodiimide, 0, 0 +Orthocarbonic_derivatives, 0, 0 +Phenol, 27, 9 +1,2-Diphenol, 2, 0 +Arylchloride, 142, 163 +Arylfluoride, 22, 41 +Arylbromide, 4, 8 +Aryliodide, 1, 4 +Arylthiol, 0, 0 +Iminoarene, 0, 1 +Oxoarene, 32, 29 +Thioarene, 1, 2 +Hetero_N_basic_H, 17, 11 +Hetero_N_basic_no_H, 59, 90 +Hetero_N_nonbasic, 127, 191 +Hetero_O, 10, 12 +Hetero_S, 17, 18 +Heteroaromatic, 147, 205 +Nitrite, 0, 0 +Thionitrite, 0, 0 +Nitrate, 0, 0 +Nitro, 42, 31 +Nitroso, 0, 0 +Azide, 0, 0 +Acylazide, 0, 0 +Diazo, 0, 0 +Diazonium, 0, 0 +Nitrosamine, 0, 0 +Nitrosamide, 0, 0 +N-Oxide, 0, 1 +Hydrazine, 1, 0 +Hydrazone, 1, 0 +Hydroxylamine, 3, 0 +Sulfon, 3, 14 +Sulfoxide, 2, 3 +Sulfonium, 0, 0 +Sulfuric_acid, 0, 0 +Sulfuric_monoester, 0, 0 +Sulfuric_diester, 0, 0 +Sulfuric_monoamide, 1, 0 +Sulfuric_diamide, 0, 0 +Sulfuric_esteramide, 0, 1 +Sulfuric_derivative, 5, 8 +Sulfonic_acid, 4, 0 +Sulfonamide, 6, 9 +Sulfonic_ester, 1, 0 +Sulfonic_halide, 0, 0 +Sulfonic_derivative, 24, 29 +Sulfinic_acid, 0, 0 +Sulfinic_amide, 0, 0 +Sulfinic_ester, 0, 0 +Sulfinic_halide, 0, 0 +Sulfinic_derivative, 0, 0 +Sulfenic_acid, 0, 0 +Sulfenic_amide, 0, 0 +Sulfenic_ester, 0, 0 +Sulfenic_halide, 0, 0 +Sulfenic_derivative, 48, 34 +Phosphine, 0, 0 +Phosphine_oxide, 0, 0 +Phosphonium, 0, 0 +Phosphorylen, 0, 0 +Phosphonic_acid, 5, 5 +Phosphonic_monoester, 1, 1 +Phosphonic_diester, 2, 1 +Phosphonic_monoamide, 0, 0 +Phosphonic_diamide, 0, 0 +Phosphonic_esteramide, 0, 0 +Phosphonic_acid_derivative, 10, 7 +Phosphoric_acid, 0, 0 +Phosphoric_monoester, 0, 0 +Phosphoric_diester, 0, 0 +Phosphoric_triester, 10, 3 +Phosphoric_monoamide, 0, 0 +Phosphoric_diamide, 0, 0 +Phosphoric_triamide, 0, 0 +Phosphoric_monoestermonoamide, 0, 0 +Phosphoric_diestermonoamide, 3, 2 +Phosphoric_monoesterdiamide, 0, 0 +Phosphoric_acid_derivative, 70, 44 +Phosphinic_acid, 1, 1 +Phosphinic_ester, 0, 0 +Phosphinic_amide, 0, 0 +Phosphinic_acid_derivative, 1, 1 +Phosphonous_acid, 0, 0 +Phosphonous_monoester, 0, 0 +Phosphonous_diester, 0, 0 +Phosphonous_monoamide, 0, 0 +Phosphonous_diamide, 0, 0 +Phosphonous_esteramide, 0, 0 +Phosphonous_derivatives, 0, 0 +Phosphinous_acid, 0, 0 +Phosphinous_ester, 0, 0 +Phosphinous_amide, 0, 0 +Phosphinous_derivatives, 0, 0 +Quart_silane, 1, 2 +Non-quart_silane, 0, 0 +Silylmonohalide, 0, 0 +Het_trialkylsilane, 0, 0 +Dihet_dialkylsilane, 0, 0 +Trihet_alkylsilane, 0, 0 +Silicic_acid_derivative, 0, 0 +Trialkylborane, 0, 0 +Boric_acid_derivatives, 0, 0 +Boronic_acid_derivative, 0, 0 +Borohydride, 0, 0 +Quaternary_boron, 0, 0 +Aromatic, 402, 396 +Heterocyclic, 228, 272 +Epoxide, 11, 2 +NH_aziridine, 0, 0 +Spiro, 3, 10 +Annelated_rings, 97, 73 +Bridged_rings, 8, 4 +Sugar_pattern_1, 10, 9 +Sugar_pattern_2, 6, 7 +Sugar_pattern_combi, 4, 5 +Sugar_pattern_2_reducing, 1, 0 +Sugar_pattern_2_alpha, 1, 1 +Sugar_pattern_2_beta, 1, 1 +Conjugated_double_bond, 207, 213 +Conjugated_tripple_bond, 10, 19 +Cis_double_bond, 31, 19 +Trans_double_bond, 31, 19 +Mixed_anhydrides, 1, 0 +Halogen_on_hetero, 0, 0 +Halogen_multi_subst, 1, 6 +Trifluoromethyl, 44, 63 +C_ONS_bond, 520, 484 +Charged, 27, 51 +Anion, 26, 45 +Kation, 25, 51 +Salt, 26, 45 +1,3-Tautomerizable, 265, 296 +1,5-Tautomerizable, 124, 148 +Rotatable_bond, 488, 462 +Michael_acceptor, 33, 33 +Dicarbodiazene, 0, 0 +CH-acidic, 60, 73 +CH-acidic_strong, 1, 4 +Chiral_center_specified, 1, 2 diff --git a/paper/functional-groups.rb b/paper/functional-groups.rb new file mode 100644 index 0000000..e961b92 --- /dev/null +++ b/paper/functional-groups.rb @@ -0,0 +1,31 @@ +require_relative '../../lazar/lib/lazar' +include OpenTox +old = Dataset.from_csv_file File.join(File.dirname(__FILE__),"..","regression","LOAEL_mg_corrected_smiles_mmol.csv") +new = Dataset.from_csv_file File.join(File.dirname(__FILE__),"..","regression","swissRat_chron_LOAEL_mmol.csv") + +functional_groups = {} +#functional_groups[:old] = {} +#functional_groups[:new] = {} +table = [] +#File.open("functional-groups.csv","w+") do |file| + File.open("functional-groups.txt").each_line do |line| + name, smarts = line.chomp.split ": " + if smarts + smarts_feature = Smarts.from_smarts smarts + oldcount = 0 + old.compounds.each do |c| + oldcount += Algorithm::Descriptor.smarts_match(c,smarts_feature).first.to_i + end + newcount = 0 + new.compounds.each do |c| + newcount += Algorithm::Descriptor.smarts_match(c,smarts_feature).first.to_i + end + puts "#{name}, #{oldcount}, #{newcount}" + else + p name, smarts + end + #table << [name, oldcount, newcount] + end +#end +#print table.to_csv +#old_fp = old.compounds.collect{|c| c.fingerprint("FP4")} diff --git a/paper/functional-groups.txt b/paper/functional-groups.txt new file mode 100644 index 0000000..e14fd6c --- /dev/null +++ b/paper/functional-groups.txt @@ -0,0 +1,307 @@ +Primary_carbon: [CX4H3][#6] +Secondary_carbon: [CX4H2]([#6])[#6] +Tertiary_carbon: [CX4H1]([#6])([#6])[#6] +Quaternary_carbon: [CX4]([#6])([#6])([#6])[#6] +Alkene: [CX3;$([H2]),$([H1][#6]),$(C([#6])[#6])]=[CX3;$([H2]),$([H1][#6]),$(C([#6])[#6])] +Alkyne: [CX2]#[CX2] +Allene: [CX3]=[CX2]=[CX3] +Alkylchloride: [ClX1][CX4] +Alkylfluoride: [FX1][CX4] +Alkylbromide: [BrX1][CX4] +Alkyliodide: [IX1][CX4] +Alcohol: [OX2H][CX4;!$(C([OX2H])[O,S,#7,#15])] +Primary_alcohol: [OX2H][CX4H2;!$(C([OX2H])[O,S,#7,#15])] +Secondary_alcohol: [OX2H][CX4H;!$(C([OX2H])[O,S,#7,#15])] +Tertiary_alcohol: [OX2H][CX4D4;!$(C([OX2H])[O,S,#7,#15])] +Dialkylether: [OX2]([CX4;!$(C([OX2])[O,S,#7,#15,F,Cl,Br,I])])[CX4;!$(C([OX2])[O,S,#7,#15])] +Dialkylthioether: [SX2]([CX4;!$(C([OX2])[O,S,#7,#15,F,Cl,Br,I])])[CX4;!$(C([OX2])[O,S,#7,#15])] +Alkylarylether: [OX2](c)[CX4;!$(C([OX2])[O,S,#7,#15,F,Cl,Br,I])] +Diarylether: [c][OX2][c] +Alkylarylthioether: [SX2](c)[CX4;!$(C([OX2])[O,S,#7,#15,F,Cl,Br,I])] +Diarylthioether: [c][SX2][c] +Oxonium: [O+;!$([O]~[!#6]);!$([S]*~[#7,#8,#15,#16])] +Amine: [NX3+0,NX4+;!$([N]~[!#6]);!$([N]*~[#7,#8,#15,#16])] +Primary_aliph_amine: [NX3H2+0,NX4H3+;!$([N][!C]);!$([N]*~[#7,#8,#15,#16])] +Secondary_aliph_amine: [NX3H1+0,NX4H2+;!$([N][!C]);!$([N]*~[#7,#8,#15,#16])] +Tertiary_aliph_amine: [NX3H0+0,NX4H1+;!$([N][!C]);!$([N]*~[#7,#8,#15,#16])] +Quaternary_aliph_ammonium: [NX4H0+;!$([N][!C]);!$([N]*~[#7,#8,#15,#16])] +Primary_arom_amine: [NX3H2+0,NX4H3+]c +Secondary_arom_amine: [NX3H1+0,NX4H2+;!$([N][!c]);!$([N]*~[#7,#8,#15,#16])] +Tertiary_arom_amine: [NX3H0+0,NX4H1+;!$([N][!c]);!$([N]*~[#7,#8,#15,#16])] +Quaternary_arom_ammonium: [NX4H0+;!$([N][!c]);!$([N]*~[#7,#8,#15,#16])] +Secondary_mixed_amine: [NX3H1+0,NX4H2+;$([N]([c])[C]);!$([N]*~[#7,#8,#15,#16])] +Tertiary_mixed_amine: [NX3H0+0,NX4H1+;$([N]([c])([C])[#6]);!$([N]*~[#7,#8,#15,#16])] +Quaternary_mixed_ammonium: [NX4H0+;$([N]([c])([C])[#6][#6]);!$([N]*~[#7,#8,#15,#16])] +Ammonium: [N+;!$([N]~[!#6]);!$(N=*);!$([N]*~[#7,#8,#15,#16])] +Alkylthiol: [SX2H][CX4;!$(C([SX2H])~[O,S,#7,#15])] +Dialkylthioether: [SX2]([CX4;!$(C([SX2])[O,S,#7,#15,F,Cl,Br,I])])[CX4;!$(C([SX2])[O,S,#7,#15])] +Alkylarylthioether: [SX2](c)[CX4;!$(C([SX2])[O,S,#7,#15])] +Disulfide: [SX2D2][SX2D2] +1,2-Aminoalcohol: [OX2H][CX4;!$(C([OX2H])[O,S,#7,#15,F,Cl,Br,I])][CX4;!$(C([N])[O,S,#7,#15])][NX3;!$(NC=[O,S,N])] +1,2-Diol: [OX2H][CX4;!$(C([OX2H])[O,S,#7,#15])][CX4;!$(C([OX2H])[O,S,#7,#15])][OX2H] +1,1-Diol: [OX2H][CX4;!$(C([OX2H])([OX2H])[O,S,#7,#15])][OX2H] +Hydroperoxide: [OX2H][OX2] +Peroxo: [OX2D2][OX2D2] +Organolithium_compounds: [LiX1][#6,#14] +Organomagnesium_compounds: [MgX2][#6,#14] +Organometallic_compounds: [!#1;!#5;!#6;!#7;!#8;!#9;!#14;!#15;!#16;!#17;!#33;!#34;!#35;!#52;!#53;!#85]~[#6;!-] +Aldehyde: [$([CX3H][#6]),$([CX3H2])]=[OX1] +Ketone: [#6][CX3](=[OX1])[#6] +Thioaldehyde: [$([CX3H][#6]),$([CX3H2])]=[SX1] +Thioketone: [#6][CX3](=[SX1])[#6] +Imine: [NX2;$([N][#6]),$([NH]);!$([N][CX3]=[#7,#8,#15,#16])]=[CX3;$([CH2]),$([CH][#6]),$([C]([#6])[#6])] +Immonium: [NX3+;!$([N][!#6]);!$([N][CX3]=[#7,#8,#15,#16])] +Oxime: [NX2](=[CX3;$([CH2]),$([CH][#6]),$([C]([#6])[#6])])[OX2H] +Oximether: [NX2](=[CX3;$([CH2]),$([CH][#6]),$([C]([#6])[#6])])[OX2][#6;!$(C=[#7,#8])] +Acetal: [OX2]([#6;!$(C=[O,S,N])])[CX4;!$(C(O)(O)[!#6])][OX2][#6;!$(C=[O,S,N])] +Hemiacetal: [OX2H][CX4;!$(C(O)(O)[!#6])][OX2][#6;!$(C=[O,S,N])] +Aminal: [NX3v3;!$(NC=[#7,#8,#15,#16])]([#6])[CX4;!$(C(N)(N)[!#6])][NX3v3;!$(NC=[#7,#8,#15,#16])][#6] +Hemiaminal: [NX3v3;!$(NC=[#7,#8,#15,#16])]([#6])[CX4;!$(C(N)(N)[!#6])][OX2H] +Thioacetal: [SX2]([#6;!$(C=[O,S,N])])[CX4;!$(C(S)(S)[!#6])][SX2][#6;!$(C=[O,S,N])] +Thiohemiacetal: [SX2]([#6;!$(C=[O,S,N])])[CX4;!$(C(S)(S)[!#6])][OX2H] +Halogen_acetal_like: [NX3v3,SX2,OX2;!$(*C=[#7,#8,#15,#16])][CX4;!$(C([N,S,O])([N,S,O])[!#6])][FX1,ClX1,BrX1,IX1] +Acetal_like: [NX3v3,SX2,OX2;!$(*C=[#7,#8,#15,#16])][CX4;!$(C([N,S,O])([N,S,O])[!#6])][FX1,ClX1,BrX1,IX1,NX3v3,SX2,OX2;!$(*C=[#7,#8,#15,#16])] +Halogenmethylen_ester_and_similar: [NX3v3,SX2,OX2;$(**=[#7,#8,#15,#16])][CX4;!$(C([N,S,O])([N,S,O])[!#6])][FX1,ClX1,BrX1,IX1] +NOS_methylen_ester_and_similar: [NX3v3,SX2,OX2;$(**=[#7,#8,#15,#16])][CX4;!$(C([N,S,O])([N,S,O])[!#6])][NX3v3,SX2,OX2;!$(*C=[#7,#8,#15,#16])] +Hetero_methylen_ester_and_similar: [NX3v3,SX2,OX2;$(**=[#7,#8,#15,#16])][CX4;!$(C([N,S,O])([N,S,O])[!#6])][FX1,ClX1,BrX1,IX1,NX3v3,SX2,OX2;!$(*C=[#7,#8,#15,#16])] +Cyanhydrine: [NX1]#[CX2][CX4;$([CH2]),$([CH]([CX2])[#6]),$(C([CX2])([#6])[#6])][OX2H] +Chloroalkene: [ClX1][CX3]=[CX3] +Fluoroalkene: [FX1][CX3]=[CX3] +Bromoalkene: [BrX1][CX3]=[CX3] +Iodoalkene: [IX1][CX3]=[CX3] +Enol: [OX2H][CX3;$([H1]),$(C[#6])]=[CX3] +Endiol: [OX2H][CX3;$([H1]),$(C[#6])]=[CX3;$([H1]),$(C[#6])][OX2H] +Enolether: [OX2]([#6;!$(C=[N,O,S])])[CX3;$([H0][#6]),$([H1])]=[CX3] +Enolester: [OX2]([CX3]=[OX1])[#6X3;$([#6][#6]),$([H1])]=[#6X3;!$(C[OX2H])] +Enamine: [NX3;$([NH2][CX3]),$([NH1]([CX3])[#6]),$([N]([CX3])([#6])[#6]);!$([N]*=[#7,#8,#15,#16])][CX3;$([CH]),$([C][#6])]=[CX3] +Thioenol: [SX2H][CX3;$([H1]),$(C[#6])]=[CX3] +Thioenolether: [SX2]([#6;!$(C=[N,O,S])])[CX3;$(C[#6]),$([CH])]=[CX3] +Acylchloride: [CX3;$([R0][#6]),$([H1R0])](=[OX1])[ClX1] +Acylfluoride: [CX3;$([R0][#6]),$([H1R0])](=[OX1])[FX1] +Acylbromide: [CX3;$([R0][#6]),$([H1R0])](=[OX1])[BrX1] +Acyliodide: [CX3;$([R0][#6]),$([H1R0])](=[OX1])[IX1] +Acylhalide: [CX3;$([R0][#6]),$([H1R0])](=[OX1])[FX1,ClX1,BrX1,IX1] +Carboxylic_acid: [CX3;$([R0][#6]),$([H1R0])](=[OX1])[$([OX2H]),$([OX1-])] +Carboxylic_ester: [CX3;$([R0][#6]),$([H1R0])](=[OX1])[OX2][#6;!$(C=[O,N,S])] +Lactone: [#6][#6X3R](=[OX1])[#8X2][#6;!$(C=[O,N,S])] +Carboxylic_anhydride: [CX3;$([H0][#6]),$([H1])](=[OX1])[#8X2][CX3;$([H0][#6]),$([H1])](=[OX1]) +Carboxylic_acid_derivative: [$([#6X3H0][#6]),$([#6X3H])](=[!#6])[!#6] +Carbothioic_acid: [CX3;!R;$([C][#6]),$([CH]);$([C](=[OX1])[$([SX2H]),$([SX1-])]),$([C](=[SX1])[$([OX2H]),$([OX1-])])] +Carbothioic_S_ester: [CX3;$([R0][#6]),$([H1R0])](=[OX1])[SX2][#6;!$(C=[O,N,S])] +Carbothioic_S_lactone: [#6][#6X3R](=[OX1])[#16X2][#6;!$(C=[O,N,S])] +Carbothioic_O_ester: [CX3;$([H0][#6]),$([H1])](=[SX1])[OX2][#6;!$(C=[O,N,S])] +Carbothioic_O_lactone: [#6][#6X3R](=[SX1])[#8X2][#6;!$(C=[O,N,S])] +Carbothioic_halide: [CX3;$([H0][#6]),$([H1])](=[SX1])[FX1,ClX1,BrX1,IX1] +Carbodithioic_acid: [CX3;!R;$([C][#6]),$([CH]);$([C](=[SX1])[SX2H])] +Carbodithioic_ester: [CX3;!R;$([C][#6]),$([CH]);$([C](=[SX1])[SX2][#6;!$(C=[O,N,S])])] +Carbodithiolactone: [#6][#6X3R](=[SX1])[#16X2][#6;!$(C=[O,N,S])] +Amide: [CX3;$([R0][#6]),$([H1R0])](=[OX1])[#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])] +Primary_amide: [CX3;$([R0][#6]),$([H1R0])](=[OX1])[NX3H2] +Secondary_amide: [CX3;$([R0][#6]),$([H1R0])](=[OX1])[#7X3H1][#6;!$(C=[O,N,S])] +Tertiary_amide: [CX3;$([R0][#6]),$([H1R0])](=[OX1])[#7X3H0]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])] +Lactam: [#6R][#6X3R](=[OX1])[#7X3;$([H1][#6;!$(C=[O,N,S])]),$([H0]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])] +Alkyl_imide: [#6X3;$([H0][#6]),$([H1])](=[OX1])[#7X3H0]([#6])[#6X3;$([H0][#6]),$([H1])](=[OX1]) +N_hetero_imide: [#6X3;$([H0][#6]),$([H1])](=[OX1])[#7X3H0]([!#6])[#6X3;$([H0][#6]),$([H1])](=[OX1]) +Imide_acidic: [#6X3;$([H0][#6]),$([H1])](=[OX1])[#7X3H1][#6X3;$([H0][#6]),$([H1])](=[OX1]) +Thioamide: [$([CX3;!R][#6]),$([CX3H;!R])](=[SX1])[#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])] +Thiolactam: [#6R][#6X3R](=[SX1])[#7X3;$([H1][#6;!$(C=[O,N,S])]),$([H0]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])] +Oximester: [#6X3;$([H0][#6]),$([H1])](=[OX1])[#8X2][#7X2]=,:[#6X3;$([H0]([#6])[#6]),$([H1][#6]),$([H2])] +Amidine: [NX3;!$(NC=[O,S])][CX3;$([CH]),$([C][#6])]=[NX2;!$(NC=[O,S])] +Hydroxamic_acid: [CX3;$([H0][#6]),$([H1])](=[OX1])[#7X3;$([H1]),$([H0][#6;!$(C=[O,N,S])])][$([OX2H]),$([OX1-])] +Hydroxamic_acid_ester: [CX3;$([H0][#6]),$([H1])](=[OX1])[#7X3;$([H1]),$([H0][#6;!$(C=[O,N,S])])][OX2][#6;!$(C=[O,N,S])] +Imidoacid: [CX3R0;$([H0][#6]),$([H1])](=[NX2;$([H1]),$([H0][#6;!$(C=[O,N,S])])])[$([OX2H]),$([OX1-])] +Imidoacid_cyclic: [#6R][#6X3R](=,:[#7X2;$([H1]),$([H0][#6;!$(C=[O,N,S])])])[$([OX2H]),$([OX1-])] +Imidoester: [CX3R0;$([H0][#6]),$([H1])](=[NX2;$([H1]),$([H0][#6;!$(C=[O,N,S])])])[OX2][#6;!$(C=[O,N,S])] +Imidolactone: [#6R][#6X3R](=,:[#7X2;$([H1]),$([H0][#6;!$(C=[O,N,S])])])[OX2][#6;!$(C=[O,N,S])] +Imidothioacid: [CX3R0;$([H0][#6]),$([H1])](=[NX2;$([H1]),$([H0][#6;!$(C=[O,N,S])])])[$([SX2H]),$([SX1-])] +Imidothioacid_cyclic: [#6R][#6X3R](=,:[#7X2;$([H1]),$([H0][#6;!$(C=[O,N,S])])])[$([SX2H]),$([SX1-])] +Imidothioester: [CX3R0;$([H0][#6]),$([H1])](=[NX2;$([H1]),$([H0][#6;!$(C=[O,N,S])])])[SX2][#6;!$(C=[O,N,S])] +Imidothiolactone: [#6R][#6X3R](=,:[#7X2;$([H1]),$([H0][#6;!$(C=[O,N,S])])])[SX2][#6;!$(C=[O,N,S])] +Amidine: [#7X3v3;!$(N([#6X3]=[#7X2])C=[O,S])][CX3R0;$([H1]),$([H0][#6])]=[NX2v3;!$(N(=[#6X3][#7X3])C=[O,S])] +Imidolactam: [#6][#6X3R;$([H0](=[NX2;!$(N(=[#6X3][#7X3])C=[O,S])])[#7X3;!$(N([#6X3]=[#7X2])C=[O,S])]),$([H0](-[NX3;!$(N([#6X3]=[#7X2])C=[O,S])])=,:[#7X2;!$(N(=[#6X3][#7X3])C=[O,S])])] +Imidoylhalide: [CX3R0;$([H0][#6]),$([H1])](=[NX2;$([H1]),$([H0][#6;!$(C=[O,N,S])])])[FX1,ClX1,BrX1,IX1] +Imidoylhalide_cyclic: [#6R][#6X3R](=,:[#7X2;$([H1]),$([H0][#6;!$(C=[O,N,S])])])[FX1,ClX1,BrX1,IX1] +Amidrazone: [$([$([#6X3][#6]),$([#6X3H])](=[#7X2v3])[#7X3v3][#7X3v3]),$([$([#6X3][#6]),$([#6X3H])]([#7X3v3])=[#7X2v3][#7X3v3])] +Alpha_aminoacid: [NX3,NX4+;!$([N]~[!#6]);!$([N]*~[#7,#8,#15,#16])][C][CX3](=[OX1])[OX2H,OX1-] +Alpha_hydroxyacid: [OX2H][C][CX3](=[OX1])[OX2H,OX1-] +Peptide_middle: [NX3;$([N][CX3](=[OX1])[C][NX3,NX4+])][C][CX3](=[OX1])[NX3;$([N][C][CX3](=[OX1])[NX3,OX2,OX1-])] +Peptide_C_term: [NX3;$([N][CX3](=[OX1])[C][NX3,NX4+])][C][CX3](=[OX1])[OX2H,OX1-] +Peptide_N_term: [NX3,NX4+;!$([N]~[!#6]);!$([N]*~[#7,#8,#15,#16])][C][CX3](=[OX1])[NX3;$([N][C][CX3](=[OX1])[NX3,OX2,OX1-])] +Carboxylic_orthoester: [#6][OX2][CX4;$(C[#6]),$([CH])]([OX2][#6])[OX2][#6] +Ketene: [CX3]=[CX2]=[OX1] +Ketenacetal: [#7X2,#8X3,#16X2;$(*[#6,#14])][#6X3]([#7X2,#8X3,#16X2;$(*[#6,#14])])=[#6X3] +Nitrile: [NX1]#[CX2] +Isonitrile: [CX1-]#[NX2+] +Vinylogous_carbonyl_or_carboxyl_derivative: [#6X3](=[OX1])[#6X3]=,:[#6X3][#7,#8,#16,F,Cl,Br,I] +Vinylogous_acid: [#6X3](=[OX1])[#6X3]=,:[#6X3][$([OX2H]),$([OX1-])] +Vinylogous_ester: [#6X3](=[OX1])[#6X3]=,:[#6X3][#6;!$(C=[O,N,S])] +Vinylogous_amide: [#6X3](=[OX1])[#6X3]=,:[#6X3][#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])] +Vinylogous_halide: [#6X3](=[OX1])[#6X3]=,:[#6X3][FX1,ClX1,BrX1,IX1] +Carbonic_acid_dieester: [#6;!$(C=[O,N,S])][#8X2][#6X3](=[OX1])[#8X2][#6;!$(C=[O,N,S])] +Carbonic_acid_esterhalide: [#6;!$(C=[O,N,S])][OX2;!R][CX3](=[OX1])[OX2][FX1,ClX1,BrX1,IX1] +Carbonic_acid_monoester: [#6;!$(C=[O,N,S])][OX2;!R][CX3](=[OX1])[$([OX2H]),$([OX1-])] +Carbonic_acid_derivatives: [!#6][#6X3](=[!#6])[!#6] +Thiocarbonic_acid_dieester: [#6;!$(C=[O,N,S])][#8X2][#6X3](=[SX1])[#8X2][#6;!$(C=[O,N,S])] +Thiocarbonic_acid_esterhalide: [#6;!$(C=[O,N,S])][OX2;!R][CX3](=[SX1])[OX2][FX1,ClX1,BrX1,IX1] +Thiocarbonic_acid_monoester: [#6;!$(C=[O,N,S])][OX2;!R][CX3](=[SX1])[$([OX2H]),$([OX1-])] +Urea: [#7X3;!$([#7][!#6])][#6X3](=[OX1])[#7X3;!$([#7][!#6])] +Thiourea: [#7X3;!$([#7][!#6])][#6X3](=[SX1])[#7X3;!$([#7][!#6])] +Isourea: [#7X2;!$([#7][!#6])]=,:[#6X3]([#8X2&!$([#8][!#6]),OX1-])[#7X3;!$([#7][!#6])] +Isothiourea: [#7X2;!$([#7][!#6])]=,:[#6X3]([#16X2&!$([#16][!#6]),SX1-])[#7X3;!$([#7][!#6])] +Guanidine: [N;v3X3,v4X4+][CX3](=[N;v3X2,v4X3+])[N;v3X3,v4X4+] +Carbaminic_acid: [NX3]C(=[OX1])[O;X2H,X1-] +Urethan: [#7X3][#6](=[OX1])[#8X2][#6] +Biuret: [#7X3][#6](=[OX1])[#7X3][#6](=[OX1])[#7X3] +Semicarbazide: [#7X3][#7X3][#6X3]([#7X3;!$([#7][#7])])=[OX1] +Carbazide: [#7X3][#7X3][#6X3]([#7X3][#7X3])=[OX1] +Semicarbazone: [#7X2](=[#6])[#7X3][#6X3]([#7X3;!$([#7][#7])])=[OX1] +Carbazone: [#7X2](=[#6])[#7X3][#6X3]([#7X3][#7X3])=[OX1] +Thiosemicarbazide: [#7X3][#7X3][#6X3]([#7X3;!$([#7][#7])])=[SX1] +Thiocarbazide: [#7X3][#7X3][#6X3]([#7X3][#7X3])=[SX1] +Thiosemicarbazone: [#7X2](=[#6])[#7X3][#6X3]([#7X3;!$([#7][#7])])=[SX1] +Thiocarbazone: [#7X2](=[#6])[#7X3][#6X3]([#7X3][#7X3])=[SX1] +Isocyanate: [NX2]=[CX2]=[OX1] +Cyanate: [OX2][CX2]#[NX1] +Isothiocyanate: [NX2]=[CX2]=[SX1] +Thiocyanate: [SX2][CX2]#[NX1] +Carbodiimide: [NX2]=[CX2]=[NX2] +Orthocarbonic_derivatives: [CX4H0]([O,S,#7])([O,S,#7])([O,S,#7])[O,S,#7,F,Cl,Br,I] +Phenol: [OX2H][c] +1,2-Diphenol: [OX2H][c][c][OX2H] +Arylchloride: [Cl][c] +Arylfluoride: [F][c] +Arylbromide: [Br][c] +Aryliodide: [I][c] +Arylthiol: [SX2H][c] +Iminoarene: [c]=[NX2;$([H1]),$([H0][#6;!$([C]=[N,S,O])])] +Oxoarene: [c]=[OX1] +Thioarene: [c]=[SX1] +Hetero_N_basic_H: [nX3H1+0] +Hetero_N_basic_no_H: [nX3H0+0] +Hetero_N_nonbasic: [nX2,nX3+] +Hetero_O: [o] +Hetero_S: [sX2] +Heteroaromatic: [a;!c] +Nitrite: [NX2](=[OX1])[O;$([X2]),$([X1-])] +Thionitrite: [SX2][NX2]=[OX1] +Nitrate: [$([NX3](=[OX1])(=[OX1])[O;$([X2]),$([X1-])]),$([NX3+]([OX1-])(=[OX1])[O;$([X2]),$([X1-])])] +Nitro: [$([NX3](=O)=O),$([NX3+](=O)[O-])][!#8] +Nitroso: [NX2](=[OX1])[!#7;!#8] +Azide: [NX1]~[NX2]~[NX2,NX1] +Acylazide: [CX3](=[OX1])[NX2]~[NX2]~[NX1] +Diazo: [$([#6]=[NX2+]=[NX1-]),$([#6-]-[NX2+]#[NX1])] +Diazonium: [#6][NX2+]#[NX1] +Nitrosamine: [#7;!$(N*=O)][NX2]=[OX1] +Nitrosamide: [NX2](=[OX1])N-*=O +N-Oxide: [$([#7+][OX1-]),$([#7v5]=[OX1]);!$([#7](~[O])~[O]);!$([#7]=[#7])] +Hydrazine: [NX3;$([H2]),$([H1][#6]),$([H0]([#6])[#6]);!$(NC=[O,N,S])][NX3;$([H2]),$([H1][#6]),$([H0]([#6])[#6]);!$(NC=[O,N,S])] +Hydrazone: [NX3;$([H2]),$([H1][#6]),$([H0]([#6])[#6]);!$(NC=[O,N,S])][NX2]=[#6] +Hydroxylamine: [NX3;$([H2]),$([H1][#6]),$([H0]([#6])[#6]);!$(NC=[O,N,S])][OX2;$([H1]),$(O[#6;!$(C=[N,O,S])])] +Sulfon: [$([SX4](=[OX1])(=[OX1])([#6])[#6]),$([SX4+2]([OX1-])([OX1-])([#6])[#6])] +Sulfoxide: [$([SX3](=[OX1])([#6])[#6]),$([SX3+]([OX1-])([#6])[#6])] +Sulfonium: [S+;!$([S]~[!#6]);!$([S]*~[#7,#8,#15,#16])] +Sulfuric_acid: [SX4](=[OX1])(=[OX1])([$([OX2H]),$([OX1-])])[$([OX2H]),$([OX1-])] +Sulfuric_monoester: [SX4](=[OX1])(=[OX1])([$([OX2H]),$([OX1-])])[OX2][#6;!$(C=[O,N,S])] +Sulfuric_diester: [SX4](=[OX1])(=[OX1])([OX2][#6;!$(C=[O,N,S])])[OX2][#6;!$(C=[O,N,S])] +Sulfuric_monoamide: [SX4](=[OX1])(=[OX1])([#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])])[$([OX2H]),$([OX1-])] +Sulfuric_diamide: [SX4](=[OX1])(=[OX1])([#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])])[#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])] +Sulfuric_esteramide: [SX4](=[OX1])(=[OX1])([#7X3][#6;!$(C=[O,N,S])])[OX2][#6;!$(C=[O,N,S])] +Sulfuric_derivative: [SX4D4](=[!#6])(=[!#6])([!#6])[!#6] +Sulfonic_acid: [SX4;$([H1]),$([H0][#6])](=[OX1])(=[OX1])[$([OX2H]),$([OX1-])] +Sulfonamide: [SX4;$([H1]),$([H0][#6])](=[OX1])(=[OX1])[#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])] +Sulfonic_ester: [SX4;$([H1]),$([H0][#6])](=[OX1])(=[OX1])[OX2][#6;!$(C=[O,N,S])] +Sulfonic_halide: [SX4;$([H1]),$([H0][#6])](=[OX1])(=[OX1])[FX1,ClX1,BrX1,IX1] +Sulfonic_derivative: [SX4;$([H1]),$([H0][#6])](=[!#6])(=[!#6])[!#6] +Sulfinic_acid: [SX3;$([H1]),$([H0][#6])](=[OX1])[$([OX2H]),$([OX1-])] +Sulfinic_amide: [SX3;$([H1]),$([H0][#6])](=[OX1])[#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])] +Sulfinic_ester: [SX3;$([H1]),$([H0][#6])](=[OX1])[OX2][#6;!$(C=[O,N,S])] +Sulfinic_halide: [SX3;$([H1]),$([H0][#6])](=[OX1])[FX1,ClX1,BrX1,IX1] +Sulfinic_derivative: [SX3;$([H1]),$([H0][#6])](=[!#6])[!#6] +Sulfenic_acid: [SX2;$([H1]),$([H0][#6])][$([OX2H]),$([OX1-])] +Sulfenic_amide: [SX2;$([H1]),$([H0][#6])][#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])] +Sulfenic_ester: [SX2;$([H1]),$([H0][#6])][OX2][#6;!$(C=[O,N,S])] +Sulfenic_halide: [SX2;$([H1]),$([H0][#6])][FX1,ClX1,BrX1,IX1] +Sulfenic_derivative: [SX2;$([H1]),$([H0][#6])][!#6] +Phosphine: [PX3;$([H3]),$([H2][#6]),$([H1]([#6])[#6]),$([H0]([#6])([#6])[#6])] +Phosphine_oxide: [PX4;$([H3]=[OX1]),$([H2](=[OX1])[#6]),$([H1](=[OX1])([#6])[#6]),$([H0](=[OX1])([#6])([#6])[#6])] +Phosphonium: [P+;!$([P]~[!#6]);!$([P]*~[#7,#8,#15,#16])] +Phosphorylen: [PX4;$([H3]=[CX3]),$([H2](=[CX3])[#6]),$([H1](=[CX3])([#6])[#6]),$([H0](=[CX3])([#6])([#6])[#6])] +Phosphonic_acid: [PX4;$([H1]),$([H0][#6])](=[OX1])([$([OX2H]),$([OX1-])])[$([OX2H]),$([OX1-])] +Phosphonic_monoester: [PX4;$([H1]),$([H0][#6])](=[OX1])([$([OX2H]),$([OX1-])])[OX2][#6;!$(C=[O,N,S])] +Phosphonic_diester: [PX4;$([H1]),$([H0][#6])](=[OX1])([OX2][#6;!$(C=[O,N,S])])[OX2][#6;!$(C=[O,N,S])] +Phosphonic_monoamide: [PX4;$([H1]),$([H0][#6])](=[OX1])([$([OX2H]),$([OX1-])])[#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])] +Phosphonic_diamide: [PX4;$([H1]),$([H0][#6])](=[OX1])([#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])])[#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])] +Phosphonic_esteramide: [PX4;$([H1]),$([H0][#6])](=[OX1])([OX2][#6;!$(C=[O,N,S])])[#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])] +Phosphonic_acid_derivative: [PX4;$([H1]),$([H0][#6])](=[!#6])([!#6])[!#6] +Phosphoric_acid: [PX4D4](=[OX1])([$([OX2H]),$([OX1-])])([$([OX2H]),$([OX1-])])[$([OX2H]),$([OX1-])] +Phosphoric_monoester: [PX4D4](=[OX1])([$([OX2H]),$([OX1-])])([$([OX2H]),$([OX1-])])[OX2][#6;!$(C=[O,N,S])] +Phosphoric_diester: [PX4D4](=[OX1])([$([OX2H]),$([OX1-])])([OX2][#6;!$(C=[O,N,S])])[OX2][#6;!$(C=[O,N,S])] +Phosphoric_triester: [PX4D4](=[OX1])([OX2][#6;!$(C=[O,N,S])])([OX2][#6;!$(C=[O,N,S])])[OX2][#6;!$(C=[O,N,S])] +Phosphoric_monoamide: [PX4D4](=[OX1])([$([OX2H]),$([OX1-])])([$([OX2H]),$([OX1-])])[#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])] +Phosphoric_diamide: [PX4D4](=[OX1])([$([OX2H]),$([OX1-])])([#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])])[#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])] +Phosphoric_triamide: [PX4D4](=[OX1])([#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])])([#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])])[#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])] +Phosphoric_monoestermonoamide: [PX4D4](=[OX1])([$([OX2H]),$([OX1-])])([OX2][#6;!$(C=[O,N,S])])[#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])] +Phosphoric_diestermonoamide: [PX4D4](=[OX1])([OX2][#6;!$(C=[O,N,S])])([OX2][#6;!$(C=[O,N,S])])[#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])] +Phosphoric_monoesterdiamide: [PX4D4](=[OX1])([OX2][#6;!$(C=[O,N,S])])([#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])])[#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])] +Phosphoric_acid_derivative: [PX4D4](=[!#6])([!#6])([!#6])[!#6] +Phosphinic_acid: [PX4;$([H2]),$([H1][#6]),$([H0]([#6])[#6])](=[OX1])[$([OX2H]),$([OX1-])] +Phosphinic_ester: [PX4;$([H2]),$([H1][#6]),$([H0]([#6])[#6])](=[OX1])[OX2][#6;!$(C=[O,N,S])] +Phosphinic_amide: [PX4;$([H2]),$([H1][#6]),$([H0]([#6])[#6])](=[OX1])[#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])] +Phosphinic_acid_derivative: [PX4;$([H2]),$([H1][#6]),$([H0]([#6])[#6])](=[!#6])[!#6] +Phosphonous_acid: [PX3;$([H1]),$([H0][#6])]([$([OX2H]),$([OX1-])])[$([OX2H]),$([OX1-])] +Phosphonous_monoester: [PX3;$([H1]),$([H0][#6])]([$([OX2H]),$([OX1-])])[OX2][#6;!$(C=[O,N,S])] +Phosphonous_diester: [PX3;$([H1]),$([H0][#6])]([OX2][#6;!$(C=[O,N,S])])[OX2][#6;!$(C=[O,N,S])] +Phosphonous_monoamide: [PX3;$([H1]),$([H0][#6])]([$([OX2H]),$([OX1-])])[#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])] +Phosphonous_diamide: [PX3;$([H1]),$([H0][#6])]([#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])])[#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])] +Phosphonous_esteramide: [PX3;$([H1]),$([H0][#6])]([OX2][#6;!$(C=[O,N,S])])[#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])] +Phosphonous_derivatives: [PX3;$([D2]),$([D3][#6])]([!#6])[!#6] +Phosphinous_acid: [PX3;$([H2]),$([H1][#6]),$([H0]([#6])[#6])][$([OX2H]),$([OX1-])] +Phosphinous_ester: [PX3;$([H2]),$([H1][#6]),$([H0]([#6])[#6])][OX2][#6;!$(C=[O,N,S])] +Phosphinous_amide: [PX3;$([H2]),$([H1][#6]),$([H0]([#6])[#6])][#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])] +Phosphinous_derivatives: [PX3;$([H2]),$([H1][#6]),$([H0]([#6])[#6])][!#6] +Quart_silane: [SiX4]([#6])([#6])([#6])[#6] +Non-quart_silane: [SiX4;$([H1]([#6])([#6])[#6]),$([H2]([#6])[#6]),$([H3][#6]),$([H4])] +Silylmonohalide: [SiX4]([FX1,ClX1,BrX1,IX1])([#6])([#6])[#6] +Het_trialkylsilane: [SiX4]([!#6])([#6])([#6])[#6] +Dihet_dialkylsilane: [SiX4]([!#6])([!#6])([#6])[#6] +Trihet_alkylsilane: [SiX4]([!#6])([!#6])([!#6])[#6] +Silicic_acid_derivative: [SiX4]([!#6])([!#6])([!#6])[!#6] +Trialkylborane: [BX3]([#6])([#6])[#6] +Boric_acid_derivatives: [BX3]([!#6])([!#6])[!#6] +Boronic_acid_derivative: [BX3]([!#6])([!#6])[!#6] +Borohydride: [BH1,BH2,BH3,BH4] +Quaternary_boron: [BX4] +Aromatic: a +Heterocyclic: [!#6;!R0] +Epoxide: [OX2r3]1[#6r3][#6r3]1 +NH_aziridine: [NX3H1r3]1[#6r3][#6r3]1 +Spiro: [D4R;$(*(@*)(@*)(@*)@*)] +Annelated_rings: [R;$(*(@*)(@*)@*);!$([R2;$(*(@*)(@*)(@*)@*)])]@[R;$(*(@*)(@*)@*);!$([R2;$(*(@*)(@*)(@*)@*)])] +Bridged_rings: [R;$(*(@*)(@*)@*);!$([D4R;$(*(@*)(@*)(@*)@*)]);!$([R;$(*(@*)(@*)@*);!$([R2;$(*(@*)(@*)(@*)@*)])]@[R;$(*(@*)(@*)@*);!$([R2;$(*(@*)(@*)(@*)@*)])])] +Sugar_pattern_1: [OX2;$([r5]1@C@C@C(O)@C1),$([r6]1@C@C@C(O)@C(O)@C1)] +Sugar_pattern_2: [OX2;$([r5]1@C(!@[OX2,NX3,SX2,FX1,ClX1,BrX1,IX1])@C@C@C1),$([r6]1@C(!@[OX2,NX3,SX2,FX1,ClX1,BrX1,IX1])@C@C@C@C1)] +Sugar_pattern_combi: [OX2;$([r5]1@C(!@[OX2,NX3,SX2,FX1,ClX1,BrX1,IX1])@C@C(O)@C1),$([r6]1@C(!@[OX2,NX3,SX2,FX1,ClX1,BrX1,IX1])@C@C(O)@C(O)@C1)] +Sugar_pattern_2_reducing: [OX2;$([r5]1@C(!@[OX2H1])@C@C@C1),$([r6]1@C(!@[OX2H1])@C@C@C@C1)] +Sugar_pattern_2_alpha: [OX2;$([r5]1@[C@@](!@[OX2,NX3,SX2,FX1,ClX1,BrX1,IX1])@C@C@C1),$([r6]1@[C@@](!@[OX2,NX3,SX2,FX1,ClX1,BrX1,IX1])@C@C@C@C1)] +Sugar_pattern_2_beta: [OX2;$([r5]1@[C@](!@[OX2,NX3,SX2,FX1,ClX1,BrX1,IX1])@C@C@C1),$([r6]1@[C@](!@[OX2,NX3,SX2,FX1,ClX1,BrX1,IX1])@C@C@C@C1)] +Conjugated_double_bond: *=*[*]=,#,:[*] +Conjugated_tripple_bond: *#*[*]=,#,:[*] +Cis_double_bond: */[D2]=[D2]\* +Trans_double_bond: */[D2]=[D2]/* +Mixed_anhydrides: [$(*=O),$([#16,#14,#5]),$([#7]([#6]=[OX1]))][#8X2][$(*=O),$([#16,#14,#5]),$([#7]([#6]=[OX1]))] +Halogen_on_hetero: [FX1,ClX1,BrX1,IX1][!#6] +Halogen_multi_subst: [F,Cl,Br,I;!$([X1]);!$([X0-])] +Trifluoromethyl: [FX1][CX4;!$([H0][Cl,Br,I]);!$([F][C]([F])([F])[F])]([FX1])([FX1]) +C_ONS_bond: [#6]~[#7,#8,#16] +Charged: [!+0] +Anion: [-1,-2,-3,-4,-5,-6,-7] +Kation: [+1,+2,+3,+4,+5,+6,+7] +Salt: ([-1,-2,-3,-4,-5,-6,-7]).([+1,+2,+3,+4,+5,+6,+7]) +1,3-Tautomerizable: [$([#7X2,OX1,SX1]=*[!H0;!$([a;!n])]),$([#7X3,OX2,SX2;!H0]*=*),$([#7X3,OX2,SX2;!H0]*:n)] +1,5-Tautomerizable: [$([#7X2,OX1,SX1]=,:**=,:*[!H0;!$([a;!n])]),$([#7X3,OX2,SX2;!H0]*=**=*),$([#7X3,OX2,SX2;!H0]*=,:**:n)] +Rotatable_bond: [!$(*#*)&!D1]-!@[!$(*#*)&!D1] +Michael_acceptor: [CX3]=[CX3][$([CX3]=[O,N,S]),$(C#[N]),$([S,P]=[OX1]),$([NX3]=O),$([NX3+](=O)[O-])] +Dicarbodiazene: [CX3](=[OX1])[NX2]=[NX2][CX3](=[OX1]) +CH-acidic: [$([CX4;!$([H0]);!$(C[!#6;!$([P,S]=O);!$(N(~O)~O)])][$([CX3]=[O,N,S]),$(C#[N]),$([S,P]=[OX1]),$([NX3]=O),$([NX3+](=O)[O-]);!$(*[S,O,N;H1,H2]);!$([*+0][S,O;X1-])]),$([CX4;!$([H0])]1[CX3]=[CX3][CX3]=[CX3]1)] +CH-acidic_strong: [CX4;!$([H0]);!$(C[!#6;!$([P,S]=O);!$(N(~O)~O)])]([$([CX3]=[O,N,S]),$(C#[N]),$([S,P]=[OX1]),$([NX3]=O),$([NX3+](=O)[O-]);!$(*[S,O,N;H1,H2]);!$([*+0][S,O;X1-])])[$([CX3]=[O,N,S]),$(C#[N]),$([S,P]=[OX1]),$([NX3]=O),$([NX3+](=O)[O-]);!$(*[S,O,N;H1,H2]);!$([*+0][S,O;X1-])] +Chiral_center_specified: [$([*@](~*)(~*)(*)*),$([*@H](*)(*)*),$([*@](~*)(*)*),$([*@H](~*)~*)] diff --git a/paper/functional-groups.yaml b/paper/functional-groups.yaml new file mode 100644 index 0000000..eb6e5f4 --- /dev/null +++ b/paper/functional-groups.yaml @@ -0,0 +1,309 @@ +Primary_carbon': '[CX4H3][#6]' +Secondary_carbon': '[CX4H2]([#6])[#6]' +Tertiary_carbon': '[CX4H1]([#6])([#6])[#6]' +Quaternary_carbon': '[CX4]([#6])([#6])([#6])[#6]' +Alkene': '[CX3;'([H2]),$([H1][#6]),$(C([#6])[#6])]=[CX3;$([H2]),$([H1][#6]),$(C([#6])[#6])]' +Alkyne': '[CX2]#[CX2]' +Allene': '[CX3]=[CX2]=[CX3]' +Alkylchloride': '[ClX1][CX4]' +Alkylfluoride': '[FX1][CX4]' +Alkylbromide': '[BrX1][CX4]' +Alkyliodide': '[IX1][CX4]' +Alcohol': '[OX2H][CX4;!'(C([OX2H])[O,S,#7,#15])]' +Primary_alcohol': '[OX2H][CX4H2;!'(C([OX2H])[O,S,#7,#15])]' +Secondary_alcohol': '[OX2H][CX4H;!'(C([OX2H])[O,S,#7,#15])]' +Tertiary_alcohol': '[OX2H][CX4D4;!'(C([OX2H])[O,S,#7,#15])]' +Dialkylether': '[OX2]([CX4;!'(C([OX2])[O,S,#7,#15,F,Cl,Br,I])])[CX4;!$(C([OX2])[O,S,#7,#15])]' +Dialkylthioether': '[SX2]([CX4;!'(C([OX2])[O,S,#7,#15,F,Cl,Br,I])])[CX4;!$(C([OX2])[O,S,#7,#15])]' +Alkylarylether': '[OX2](c)[CX4;!'(C([OX2])[O,S,#7,#15,F,Cl,Br,I])]' +Diarylether': '[c][OX2][c]' +Alkylarylthioether': '[SX2](c)[CX4;!'(C([OX2])[O,S,#7,#15,F,Cl,Br,I])]' +Diarylthioether': '[c][SX2][c]' +Oxonium': '[O+;!'([O]~[!#6]);!$([S]*~[#7,#8,#15,#16])]' +Amine': '[NX3+0,NX4+;!'([N]~[!#6]);!$([N]*~[#7,#8,#15,#16])]' +Primary_aliph_amine': '[NX3H2+0,NX4H3+;!'([N][!C]);!$([N]*~[#7,#8,#15,#16])]' +Secondary_aliph_amine': '[NX3H1+0,NX4H2+;!'([N][!C]);!$([N]*~[#7,#8,#15,#16])]' +Tertiary_aliph_amine': '[NX3H0+0,NX4H1+;!'([N][!C]);!$([N]*~[#7,#8,#15,#16])]' +Quaternary_aliph_ammonium': '[NX4H0+;!'([N][!C]);!$([N]*~[#7,#8,#15,#16])]' +Primary_arom_amine': '[NX3H2+0,NX4H3+]c' +Secondary_arom_amine': '[NX3H1+0,NX4H2+;!'([N][!c]);!$([N]*~[#7,#8,#15,#16])]' +Tertiary_arom_amine': '[NX3H0+0,NX4H1+;!'([N][!c]);!$([N]*~[#7,#8,#15,#16])]' +Quaternary_arom_ammonium': '[NX4H0+;!'([N][!c]);!$([N]*~[#7,#8,#15,#16])]' +Secondary_mixed_amine': '[NX3H1+0,NX4H2+;'([N]([c])[C]);!$([N]*~[#7,#8,#15,#16])]' +Tertiary_mixed_amine': '[NX3H0+0,NX4H1+;'([N]([c])([C])[#6]);!$([N]*~[#7,#8,#15,#16])]' +Quaternary_mixed_ammonium': '[NX4H0+;'([N]([c])([C])[#6][#6]);!$([N]*~[#7,#8,#15,#16])]' +Ammonium': '[N+;!'([N]~[!#6]);!$(N=*);!$([N]*~[#7,#8,#15,#16])]' +Alkylthiol': '[SX2H][CX4;!'(C([SX2H])~[O,S,#7,#15])]' +Dialkylthioether': '[SX2]([CX4;!'(C([SX2])[O,S,#7,#15,F,Cl,Br,I])])[CX4;!$(C([SX2])[O,S,#7,#15])]' +Alkylarylthioether': '[SX2](c)[CX4;!'(C([SX2])[O,S,#7,#15])]' +Disulfide': '[SX2D2][SX2D2]' +1,2-Aminoalcohol': '[OX2H][CX4;!'(C([OX2H])[O,S,#7,#15,F,Cl,Br,I])][CX4;!$(C([N])[O,S,#7,#15])][NX3;!$(NC=[O,S,N])]' +1,2-Diol': '[OX2H][CX4;!'(C([OX2H])[O,S,#7,#15])][CX4;!$(C([OX2H])[O,S,#7,#15])][OX2H]' +1,1-Diol': '[OX2H][CX4;!'(C([OX2H])([OX2H])[O,S,#7,#15])][OX2H]' +Hydroperoxide': '[OX2H][OX2]' +Peroxo': '[OX2D2][OX2D2]' +Organolithium_compounds': '[LiX1][#6,#14]' +Organomagnesium_compounds': '[MgX2][#6,#14]' +Organometallic_compounds': '[!#1;!#5;!#6;!#7;!#8;!#9;!#14;!#15;!#16;!#17;!#33;!#34;!#35;!#52;!#53;!#85]~[#6;!-]' +Aldehyde': '['([CX3H][#6]),$([CX3H2])]=[OX1]' +Ketone': '[#6][CX3](=[OX1])[#6]' +Thioaldehyde': '['([CX3H][#6]),$([CX3H2])]=[SX1]' +Thioketone': '[#6][CX3](=[SX1])[#6]' +Imine': '[NX2;'([N][#6]),$([NH]);!$([N][CX3]=[#7,#8,#15,#16])]=[CX3;$([CH2]),$([CH][#6]),$([C]([#6])[#6])]' +Immonium': '[NX3+;!'([N][!#6]);!$([N][CX3]=[#7,#8,#15,#16])]' +Oxime': '[NX2](=[CX3;'([CH2]),$([CH][#6]),$([C]([#6])[#6])])[OX2H]' +Oximether': '[NX2](=[CX3;'([CH2]),$([CH][#6]),$([C]([#6])[#6])])[OX2][#6;!$(C=[#7,#8])]' +Acetal': '[OX2]([#6;!'(C=[O,S,N])])[CX4;!$(C(O)(O)[!#6])][OX2][#6;!$(C=[O,S,N])]' +Hemiacetal': '[OX2H][CX4;!'(C(O)(O)[!#6])][OX2][#6;!$(C=[O,S,N])]' +Aminal': '[NX3v3;!'(NC=[#7,#8,#15,#16])]([#6])[CX4;!$(C(N)(N)[!#6])][NX3v3;!$(NC=[#7,#8,#15,#16])][#6] ' +Hemiaminal': '[NX3v3;!'(NC=[#7,#8,#15,#16])]([#6])[CX4;!$(C(N)(N)[!#6])][OX2H]' +Thioacetal': '[SX2]([#6;!'(C=[O,S,N])])[CX4;!$(C(S)(S)[!#6])][SX2][#6;!$(C=[O,S,N])]' +Thiohemiacetal': '[SX2]([#6;!'(C=[O,S,N])])[CX4;!$(C(S)(S)[!#6])][OX2H]' +Halogen_acetal_like': '[NX3v3,SX2,OX2;!'(*C=[#7,#8,#15,#16])][CX4;!$(C([N,S,O])([N,S,O])[!#6])][FX1,ClX1,BrX1,IX1]' +Acetal_like': '[NX3v3,SX2,OX2;!'(*C=[#7,#8,#15,#16])][CX4;!$(C([N,S,O])([N,S,O])[!#6])][FX1,ClX1,BrX1,IX1,NX3v3,SX2,OX2;!$(*C=[#7,#8,#15,#16])]' +Halogenmethylen_ester_and_similar': '[NX3v3,SX2,OX2;'(**=[#7,#8,#15,#16])][CX4;!$(C([N,S,O])([N,S,O])[!#6])][FX1,ClX1,BrX1,IX1]' +NOS_methylen_ester_and_similar': '[NX3v3,SX2,OX2;'(**=[#7,#8,#15,#16])][CX4;!$(C([N,S,O])([N,S,O])[!#6])][NX3v3,SX2,OX2;!$(*C=[#7,#8,#15,#16])]' +Hetero_methylen_ester_and_similar': '[NX3v3,SX2,OX2;'(**=[#7,#8,#15,#16])][CX4;!$(C([N,S,O])([N,S,O])[!#6])][FX1,ClX1,BrX1,IX1,NX3v3,SX2,OX2;!$(*C=[#7,#8,#15,#16])]' +Cyanhydrine': '[NX1]#[CX2][CX4;'([CH2]),$([CH]([CX2])[#6]),$(C([CX2])([#6])[#6])][OX2H]' +Chloroalkene': '[ClX1][CX3]=[CX3]' +Fluoroalkene': '[FX1][CX3]=[CX3]' +Bromoalkene': '[BrX1][CX3]=[CX3]' +Iodoalkene': '[IX1][CX3]=[CX3]' +Enol': '[OX2H][CX3;'([H1]),$(C[#6])]=[CX3]' +Endiol': '[OX2H][CX3;'([H1]),$(C[#6])]=[CX3;$([H1]),$(C[#6])][OX2H]' +Enolether': '[OX2]([#6;!'(C=[N,O,S])])[CX3;$([H0][#6]),$([H1])]=[CX3]' +Enolester': '[OX2]([CX3]=[OX1])[#6X3;'([#6][#6]),$([H1])]=[#6X3;!$(C[OX2H])]' +Enamine': '[NX3;'([NH2][CX3]),$([NH1]([CX3])[#6]),$([N]([CX3])([#6])[#6]);!$([N]*=[#7,#8,#15,#16])][CX3;$([CH]),$([C][#6])]=[CX3]' +Thioenol': '[SX2H][CX3;'([H1]),$(C[#6])]=[CX3]' +Thioenolether': '[SX2]([#6;!'(C=[N,O,S])])[CX3;$(C[#6]),$([CH])]=[CX3]' +Acylchloride': '[CX3;'([R0][#6]),$([H1R0])](=[OX1])[ClX1] ' +Acylfluoride': '[CX3;'([R0][#6]),$([H1R0])](=[OX1])[FX1] ' +Acylbromide': '[CX3;'([R0][#6]),$([H1R0])](=[OX1])[BrX1] ' +Acyliodide': '[CX3;'([R0][#6]),$([H1R0])](=[OX1])[IX1]' +Acylhalide': '[CX3;'([R0][#6]),$([H1R0])](=[OX1])[FX1,ClX1,BrX1,IX1]' +Carboxylic_acid': '[CX3;'([R0][#6]),$([H1R0])](=[OX1])[$([OX2H]),$([OX1-])]' +Carboxylic_ester': ' [CX3;'([R0][#6]),$([H1R0])](=[OX1])[OX2][#6;!$(C=[O,N,S])]' +Lactone': '[#6][#6X3R](=[OX1])[#8X2][#6;!'(C=[O,N,S])]' +Carboxylic_anhydride': '[CX3;'([H0][#6]),$([H1])](=[OX1])[#8X2][CX3;$([H0][#6]),$([H1])](=[OX1])' +Carboxylic_acid_derivative': '['([#6X3H0][#6]),$([#6X3H])](=[!#6])[!#6]' +Carbothioic_acid': '[CX3;!R;'([C][#6]),$([CH]);$([C](=[OX1])[$([SX2H]),$([SX1-])]),$([C](=[SX1])[$([OX2H]),$([OX1-])])]' +Carbothioic_S_ester': '[CX3;'([R0][#6]),$([H1R0])](=[OX1])[SX2][#6;!$(C=[O,N,S])]' +Carbothioic_S_lactone': '[#6][#6X3R](=[OX1])[#16X2][#6;!'(C=[O,N,S])]' +Carbothioic_O_ester': '[CX3;'([H0][#6]),$([H1])](=[SX1])[OX2][#6;!$(C=[O,N,S])]' +Carbothioic_O_lactone': '[#6][#6X3R](=[SX1])[#8X2][#6;!'(C=[O,N,S])]' +Carbothioic_halide': '[CX3;'([H0][#6]),$([H1])](=[SX1])[FX1,ClX1,BrX1,IX1]' +Carbodithioic_acid': '[CX3;!R;'([C][#6]),$([CH]);$([C](=[SX1])[SX2H])]' +Carbodithioic_ester': '[CX3;!R;'([C][#6]),$([CH]);$([C](=[SX1])[SX2][#6;!$(C=[O,N,S])])]' +Carbodithiolactone': '[#6][#6X3R](=[SX1])[#16X2][#6;!'(C=[O,N,S])]' +Amide': '[CX3;'([R0][#6]),$([H1R0])](=[OX1])[#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])]' +Primary_amide': '[CX3;'([R0][#6]),$([H1R0])](=[OX1])[NX3H2]' +Secondary_amide': '[CX3;'([R0][#6]),$([H1R0])](=[OX1])[#7X3H1][#6;!$(C=[O,N,S])]' +Tertiary_amide': '[CX3;'([R0][#6]),$([H1R0])](=[OX1])[#7X3H0]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])]' +Lactam': '[#6R][#6X3R](=[OX1])[#7X3;'([H1][#6;!$(C=[O,N,S])]),$([H0]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])]' +Alkyl_imide': '[#6X3;'([H0][#6]),$([H1])](=[OX1])[#7X3H0]([#6])[#6X3;$([H0][#6]),$([H1])](=[OX1])' +N_hetero_imide': '[#6X3;'([H0][#6]),$([H1])](=[OX1])[#7X3H0]([!#6])[#6X3;$([H0][#6]),$([H1])](=[OX1])' +Imide_acidic': '[#6X3;'([H0][#6]),$([H1])](=[OX1])[#7X3H1][#6X3;$([H0][#6]),$([H1])](=[OX1])' +Thioamide': '['([CX3;!R][#6]),$([CX3H;!R])](=[SX1])[#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])]' +Thiolactam': '[#6R][#6X3R](=[SX1])[#7X3;'([H1][#6;!$(C=[O,N,S])]),$([H0]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])]' +Oximester': '[#6X3;'([H0][#6]),$([H1])](=[OX1])[#8X2][#7X2]=,:[#6X3;$([H0]([#6])[#6]),$([H1][#6]),$([H2])]' +Amidine': '[NX3;!'(NC=[O,S])][CX3;$([CH]),$([C][#6])]=[NX2;!$(NC=[O,S])]' +Hydroxamic_acid': '[CX3;'([H0][#6]),$([H1])](=[OX1])[#7X3;$([H1]),$([H0][#6;!$(C=[O,N,S])])][$([OX2H]),$([OX1-])]' +Hydroxamic_acid_ester': '[CX3;'([H0][#6]),$([H1])](=[OX1])[#7X3;$([H1]),$([H0][#6;!$(C=[O,N,S])])][OX2][#6;!$(C=[O,N,S])]' +Imidoacid': '[CX3R0;'([H0][#6]),$([H1])](=[NX2;$([H1]),$([H0][#6;!$(C=[O,N,S])])])[$([OX2H]),$([OX1-])]' +Imidoacid_cyclic': '[#6R][#6X3R](=,:[#7X2;'([H1]),$([H0][#6;!$(C=[O,N,S])])])[$([OX2H]),$([OX1-])] ' +Imidoester': '[CX3R0;'([H0][#6]),$([H1])](=[NX2;$([H1]),$([H0][#6;!$(C=[O,N,S])])])[OX2][#6;!$(C=[O,N,S])]' +Imidolactone': '[#6R][#6X3R](=,:[#7X2;'([H1]),$([H0][#6;!$(C=[O,N,S])])])[OX2][#6;!$(C=[O,N,S])]' +Imidothioacid': '[CX3R0;'([H0][#6]),$([H1])](=[NX2;$([H1]),$([H0][#6;!$(C=[O,N,S])])])[$([SX2H]),$([SX1-])]' +Imidothioacid_cyclic': '[#6R][#6X3R](=,:[#7X2;'([H1]),$([H0][#6;!$(C=[O,N,S])])])[$([SX2H]),$([SX1-])] ' +Imidothioester': '[CX3R0;'([H0][#6]),$([H1])](=[NX2;$([H1]),$([H0][#6;!$(C=[O,N,S])])])[SX2][#6;!$(C=[O,N,S])]' +Imidothiolactone': '[#6R][#6X3R](=,:[#7X2;'([H1]),$([H0][#6;!$(C=[O,N,S])])])[SX2][#6;!$(C=[O,N,S])]' +Amidine': '[#7X3v3;!'(N([#6X3]=[#7X2])C=[O,S])][CX3R0;$([H1]),$([H0][#6])]=[NX2v3;!$(N(=[#6X3][#7X3])C=[O,S])]' +Imidolactam': '[#6][#6X3R;'([H0](=[NX2;!$(N(=[#6X3][#7X3])C=[O,S])])[#7X3;!$(N([#6X3]=[#7X2])C=[O,S])]),$([H0](-[NX3;!$(N([#6X3]=[#7X2])C=[O,S])])=,:[#7X2;!$(N(=[#6X3][#7X3])C=[O,S])])] ' +Imidoylhalide': '[CX3R0;'([H0][#6]),$([H1])](=[NX2;$([H1]),$([H0][#6;!$(C=[O,N,S])])])[FX1,ClX1,BrX1,IX1]' +Imidoylhalide_cyclic': '[#6R][#6X3R](=,:[#7X2;'([H1]),$([H0][#6;!$(C=[O,N,S])])])[FX1,ClX1,BrX1,IX1]' + ' +Amidrazone': '['([$([#6X3][#6]),$([#6X3H])](=[#7X2v3])[#7X3v3][#7X3v3]),$([$([#6X3][#6]),$([#6X3H])]([#7X3v3])=[#7X2v3][#7X3v3])]' +Alpha_aminoacid': '[NX3,NX4+;!'([N]~[!#6]);!$([N]*~[#7,#8,#15,#16])][C][CX3](=[OX1])[OX2H,OX1-]' +Alpha_hydroxyacid': '[OX2H][C][CX3](=[OX1])[OX2H,OX1-]' +Peptide_middle': '[NX3;'([N][CX3](=[OX1])[C][NX3,NX4+])][C][CX3](=[OX1])[NX3;$([N][C][CX3](=[OX1])[NX3,OX2,OX1-])]' +Peptide_C_term': '[NX3;'([N][CX3](=[OX1])[C][NX3,NX4+])][C][CX3](=[OX1])[OX2H,OX1-]' +Peptide_N_term': '[NX3,NX4+;!'([N]~[!#6]);!$([N]*~[#7,#8,#15,#16])][C][CX3](=[OX1])[NX3;$([N][C][CX3](=[OX1])[NX3,OX2,OX1-])]' +Carboxylic_orthoester': '[#6][OX2][CX4;'(C[#6]),$([CH])]([OX2][#6])[OX2][#6] ' +Ketene': '[CX3]=[CX2]=[OX1]' +Ketenacetal': '[#7X2,#8X3,#16X2;'(*[#6,#14])][#6X3]([#7X2,#8X3,#16X2;$(*[#6,#14])])=[#6X3]' +Nitrile': '[NX1]#[CX2]' +Isonitrile': '[CX1-]#[NX2+]' +Vinylogous_carbonyl_or_carboxyl_derivative': '[#6X3](=[OX1])[#6X3]=,:[#6X3][#7,#8,#16,F,Cl,Br,I]' +Vinylogous_acid': '[#6X3](=[OX1])[#6X3]=,:[#6X3]['([OX2H]),$([OX1-])]' +Vinylogous_ester': '[#6X3](=[OX1])[#6X3]=,:[#6X3][#6;!'(C=[O,N,S])]' +Vinylogous_amide': '[#6X3](=[OX1])[#6X3]=,:[#6X3][#7X3;'([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])]' +Vinylogous_halide': '[#6X3](=[OX1])[#6X3]=,:[#6X3][FX1,ClX1,BrX1,IX1]' +Carbonic_acid_dieester': '[#6;!'(C=[O,N,S])][#8X2][#6X3](=[OX1])[#8X2][#6;!$(C=[O,N,S])]' +Carbonic_acid_esterhalide': '[#6;!'(C=[O,N,S])][OX2;!R][CX3](=[OX1])[OX2][FX1,ClX1,BrX1,IX1]' +Carbonic_acid_monoester': '[#6;!'(C=[O,N,S])][OX2;!R][CX3](=[OX1])[$([OX2H]),$([OX1-])]' +Carbonic_acid_derivatives': '[!#6][#6X3](=[!#6])[!#6]' +Thiocarbonic_acid_dieester': '[#6;!'(C=[O,N,S])][#8X2][#6X3](=[SX1])[#8X2][#6;!$(C=[O,N,S])]' +Thiocarbonic_acid_esterhalide': '[#6;!'(C=[O,N,S])][OX2;!R][CX3](=[SX1])[OX2][FX1,ClX1,BrX1,IX1]' +Thiocarbonic_acid_monoester': '[#6;!'(C=[O,N,S])][OX2;!R][CX3](=[SX1])[$([OX2H]),$([OX1-])]' +Urea:[#7X3;!'([#7][!#6])][#6X3](=[OX1])[#7X3;!$([#7][!#6])]' +Thiourea': '[#7X3;!'([#7][!#6])][#6X3](=[SX1])[#7X3;!$([#7][!#6])]' +Isourea': '[#7X2;!'([#7][!#6])]=,:[#6X3]([#8X2&!$([#8][!#6]),OX1-])[#7X3;!$([#7][!#6])]' +Isothiourea': '[#7X2;!'([#7][!#6])]=,:[#6X3]([#16X2&!$([#16][!#6]),SX1-])[#7X3;!$([#7][!#6])]' +Guanidine': '[N;v3X3,v4X4+][CX3](=[N;v3X2,v4X3+])[N;v3X3,v4X4+]' +Carbaminic_acid': '[NX3]C(=[OX1])[O;X2H,X1-]' +Urethan': '[#7X3][#6](=[OX1])[#8X2][#6]' +Biuret': '[#7X3][#6](=[OX1])[#7X3][#6](=[OX1])[#7X3]' +Semicarbazide': '[#7X3][#7X3][#6X3]([#7X3;!'([#7][#7])])=[OX1]' +Carbazide': '[#7X3][#7X3][#6X3]([#7X3][#7X3])=[OX1]' +Semicarbazone': '[#7X2](=[#6])[#7X3][#6X3]([#7X3;!'([#7][#7])])=[OX1]' +Carbazone': '[#7X2](=[#6])[#7X3][#6X3]([#7X3][#7X3])=[OX1]' +Thiosemicarbazide': '[#7X3][#7X3][#6X3]([#7X3;!'([#7][#7])])=[SX1]' +Thiocarbazide': '[#7X3][#7X3][#6X3]([#7X3][#7X3])=[SX1]' +Thiosemicarbazone': '[#7X2](=[#6])[#7X3][#6X3]([#7X3;!'([#7][#7])])=[SX1]' +Thiocarbazone': '[#7X2](=[#6])[#7X3][#6X3]([#7X3][#7X3])=[SX1]' +Isocyanate': '[NX2]=[CX2]=[OX1]' +Cyanate': '[OX2][CX2]#[NX1]' +Isothiocyanate': '[NX2]=[CX2]=[SX1]' +Thiocyanate': '[SX2][CX2]#[NX1]' +Carbodiimide': '[NX2]=[CX2]=[NX2]' +Orthocarbonic_derivatives': '[CX4H0]([O,S,#7])([O,S,#7])([O,S,#7])[O,S,#7,F,Cl,Br,I]' +Phenol': '[OX2H][c]' +1,2-Diphenol': '[OX2H][c][c][OX2H]' +Arylchloride': '[Cl][c]' +Arylfluoride': '[F][c]' +Arylbromide': '[Br][c]' +Aryliodide': '[I][c]' +Arylthiol': '[SX2H][c]' +Iminoarene': '[c]=[NX2;'([H1]),$([H0][#6;!$([C]=[N,S,O])])]' +Oxoarene': '[c]=[OX1]' +Thioarene': '[c]=[SX1]' +Hetero_N_basic_H': '[nX3H1+0]' +Hetero_N_basic_no_H': '[nX3H0+0]' +Hetero_N_nonbasic': '[nX2,nX3+]' +Hetero_O': '[o]' +Hetero_S': '[sX2]' +Heteroaromatic': '[a;!c]' +Nitrite': '[NX2](=[OX1])[O;'([X2]),$([X1-])]' +Thionitrite': '[SX2][NX2]=[OX1]' +Nitrate': '['([NX3](=[OX1])(=[OX1])[O;$([X2]),$([X1-])]),$([NX3+]([OX1-])(=[OX1])[O;$([X2]),$([X1-])])] ' +Nitro': '['([NX3](=O)=O),$([NX3+](=O)[O-])][!#8]' +Nitroso': '[NX2](=[OX1])[!#7;!#8]' +Azide': '[NX1]~[NX2]~[NX2,NX1]' +Acylazide': '[CX3](=[OX1])[NX2]~[NX2]~[NX1]' +Diazo': '['([#6]=[NX2+]=[NX1-]),$([#6-]-[NX2+]#[NX1])] ' +Diazonium': '[#6][NX2+]#[NX1]' +Nitrosamine': '[#7;!'(N*=O)][NX2]=[OX1]' +Nitrosamide': '[NX2](=[OX1])N-*=O' +N-Oxide': '['([#7+][OX1-]),$([#7v5]=[OX1]);!$([#7](~[O])~[O]);!$([#7]=[#7])] ' +Hydrazine': '[NX3;'([H2]),$([H1][#6]),$([H0]([#6])[#6]);!$(NC=[O,N,S])][NX3;$([H2]),$([H1][#6]),$([H0]([#6])[#6]);!$(NC=[O,N,S])]' +Hydrazone': '[NX3;'([H2]),$([H1][#6]),$([H0]([#6])[#6]);!$(NC=[O,N,S])][NX2]=[#6]' +Hydroxylamine': '[NX3;'([H2]),$([H1][#6]),$([H0]([#6])[#6]);!$(NC=[O,N,S])][OX2;$([H1]),$(O[#6;!$(C=[N,O,S])])]' +Sulfon': '['([SX4](=[OX1])(=[OX1])([#6])[#6]),$([SX4+2]([OX1-])([OX1-])([#6])[#6])]' +Sulfoxide': '['([SX3](=[OX1])([#6])[#6]),$([SX3+]([OX1-])([#6])[#6])]' +Sulfonium': '[S+;!'([S]~[!#6]);!$([S]*~[#7,#8,#15,#16])]' +Sulfuric_acid': '[SX4](=[OX1])(=[OX1])(['([OX2H]),$([OX1-])])[$([OX2H]),$([OX1-])]' +Sulfuric_monoester': '[SX4](=[OX1])(=[OX1])(['([OX2H]),$([OX1-])])[OX2][#6;!$(C=[O,N,S])]' +Sulfuric_diester': '[SX4](=[OX1])(=[OX1])([OX2][#6;!'(C=[O,N,S])])[OX2][#6;!$(C=[O,N,S])]' +Sulfuric_monoamide': '[SX4](=[OX1])(=[OX1])([#7X3;'([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])])[$([OX2H]),$([OX1-])]' +Sulfuric_diamide': '[SX4](=[OX1])(=[OX1])([#7X3;'([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])])[#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])]' +Sulfuric_esteramide': '[SX4](=[OX1])(=[OX1])([#7X3][#6;!'(C=[O,N,S])])[OX2][#6;!$(C=[O,N,S])]' +Sulfuric_derivative': '[SX4D4](=[!#6])(=[!#6])([!#6])[!#6]' +Sulfonic_acid': '[SX4;'([H1]),$([H0][#6])](=[OX1])(=[OX1])[$([OX2H]),$([OX1-])]' +Sulfonamide': '[SX4;'([H1]),$([H0][#6])](=[OX1])(=[OX1])[#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])]' +Sulfonic_ester': '[SX4;'([H1]),$([H0][#6])](=[OX1])(=[OX1])[OX2][#6;!$(C=[O,N,S])]' +Sulfonic_halide': '[SX4;'([H1]),$([H0][#6])](=[OX1])(=[OX1])[FX1,ClX1,BrX1,IX1]' +Sulfonic_derivative': '[SX4;'([H1]),$([H0][#6])](=[!#6])(=[!#6])[!#6]' +Sulfinic_acid': '[SX3;'([H1]),$([H0][#6])](=[OX1])[$([OX2H]),$([OX1-])]' +Sulfinic_amide': '[SX3;'([H1]),$([H0][#6])](=[OX1])[#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])]' +Sulfinic_ester': '[SX3;'([H1]),$([H0][#6])](=[OX1])[OX2][#6;!$(C=[O,N,S])]' +Sulfinic_halide': '[SX3;'([H1]),$([H0][#6])](=[OX1])[FX1,ClX1,BrX1,IX1]' +Sulfinic_derivative': '[SX3;'([H1]),$([H0][#6])](=[!#6])[!#6]' +Sulfenic_acid': '[SX2;'([H1]),$([H0][#6])][$([OX2H]),$([OX1-])]' +Sulfenic_amide': '[SX2;'([H1]),$([H0][#6])][#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])]' +Sulfenic_ester': '[SX2;'([H1]),$([H0][#6])][OX2][#6;!$(C=[O,N,S])]' +Sulfenic_halide': '[SX2;'([H1]),$([H0][#6])][FX1,ClX1,BrX1,IX1]' +Sulfenic_derivative': '[SX2;'([H1]),$([H0][#6])][!#6]' +Phosphine': '[PX3;'([H3]),$([H2][#6]),$([H1]([#6])[#6]),$([H0]([#6])([#6])[#6])]' +Phosphine_oxide': '[PX4;'([H3]=[OX1]),$([H2](=[OX1])[#6]),$([H1](=[OX1])([#6])[#6]),$([H0](=[OX1])([#6])([#6])[#6])]' +Phosphonium': '[P+;!'([P]~[!#6]);!$([P]*~[#7,#8,#15,#16])]' +Phosphorylen': '[PX4;'([H3]=[CX3]),$([H2](=[CX3])[#6]),$([H1](=[CX3])([#6])[#6]),$([H0](=[CX3])([#6])([#6])[#6])]' +Phosphonic_acid': '[PX4;'([H1]),$([H0][#6])](=[OX1])([$([OX2H]),$([OX1-])])[$([OX2H]),$([OX1-])]' +Phosphonic_monoester': '[PX4;'([H1]),$([H0][#6])](=[OX1])([$([OX2H]),$([OX1-])])[OX2][#6;!$(C=[O,N,S])]' +Phosphonic_diester': '[PX4;'([H1]),$([H0][#6])](=[OX1])([OX2][#6;!$(C=[O,N,S])])[OX2][#6;!$(C=[O,N,S])]' +Phosphonic_monoamide': '[PX4;'([H1]),$([H0][#6])](=[OX1])([$([OX2H]),$([OX1-])])[#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])]' +Phosphonic_diamide': '[PX4;'([H1]),$([H0][#6])](=[OX1])([#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])])[#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])]' +Phosphonic_esteramide': '[PX4;'([H1]),$([H0][#6])](=[OX1])([OX2][#6;!$(C=[O,N,S])])[#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])]' +Phosphonic_acid_derivative': '[PX4;'([H1]),$([H0][#6])](=[!#6])([!#6])[!#6]' +Phosphoric_acid': '[PX4D4](=[OX1])(['([OX2H]),$([OX1-])])([$([OX2H]),$([OX1-])])[$([OX2H]),$([OX1-])]' +Phosphoric_monoester': '[PX4D4](=[OX1])(['([OX2H]),$([OX1-])])([$([OX2H]),$([OX1-])])[OX2][#6;!$(C=[O,N,S])]' +Phosphoric_diester': '[PX4D4](=[OX1])(['([OX2H]),$([OX1-])])([OX2][#6;!$(C=[O,N,S])])[OX2][#6;!$(C=[O,N,S])]' +Phosphoric_triester': '[PX4D4](=[OX1])([OX2][#6;!'(C=[O,N,S])])([OX2][#6;!$(C=[O,N,S])])[OX2][#6;!$(C=[O,N,S])]' +Phosphoric_monoamide': '[PX4D4](=[OX1])(['([OX2H]),$([OX1-])])([$([OX2H]),$([OX1-])])[#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])]' +Phosphoric_diamide': '[PX4D4](=[OX1])(['([OX2H]),$([OX1-])])([#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])])[#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])]' +Phosphoric_triamide': '[PX4D4](=[OX1])([#7X3;'([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])])([#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])])[#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])]' +Phosphoric_monoestermonoamide': '[PX4D4](=[OX1])(['([OX2H]),$([OX1-])])([OX2][#6;!$(C=[O,N,S])])[#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])]' +Phosphoric_diestermonoamide': '[PX4D4](=[OX1])([OX2][#6;!'(C=[O,N,S])])([OX2][#6;!$(C=[O,N,S])])[#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])]' +Phosphoric_monoesterdiamide': '[PX4D4](=[OX1])([OX2][#6;!'(C=[O,N,S])])([#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])])[#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])]' +Phosphoric_acid_derivative': '[PX4D4](=[!#6])([!#6])([!#6])[!#6]' +Phosphinic_acid': '[PX4;'([H2]),$([H1][#6]),$([H0]([#6])[#6])](=[OX1])[$([OX2H]),$([OX1-])]' +Phosphinic_ester': '[PX4;'([H2]),$([H1][#6]),$([H0]([#6])[#6])](=[OX1])[OX2][#6;!$(C=[O,N,S])]' +Phosphinic_amide': '[PX4;'([H2]),$([H1][#6]),$([H0]([#6])[#6])](=[OX1])[#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])]' +Phosphinic_acid_derivative': '[PX4;'([H2]),$([H1][#6]),$([H0]([#6])[#6])](=[!#6])[!#6]' +Phosphonous_acid': '[PX3;'([H1]),$([H0][#6])]([$([OX2H]),$([OX1-])])[$([OX2H]),$([OX1-])]' +Phosphonous_monoester': '[PX3;'([H1]),$([H0][#6])]([$([OX2H]),$([OX1-])])[OX2][#6;!$(C=[O,N,S])]' +Phosphonous_diester': '[PX3;'([H1]),$([H0][#6])]([OX2][#6;!$(C=[O,N,S])])[OX2][#6;!$(C=[O,N,S])]' +Phosphonous_monoamide': '[PX3;'([H1]),$([H0][#6])]([$([OX2H]),$([OX1-])])[#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])]' +Phosphonous_diamide': '[PX3;'([H1]),$([H0][#6])]([#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])])[#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])]' +Phosphonous_esteramide': '[PX3;'([H1]),$([H0][#6])]([OX2][#6;!$(C=[O,N,S])])[#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])]' +Phosphonous_derivatives': '[PX3;'([D2]),$([D3][#6])]([!#6])[!#6]' +Phosphinous_acid': '[PX3;'([H2]),$([H1][#6]),$([H0]([#6])[#6])][$([OX2H]),$([OX1-])]' +Phosphinous_ester': '[PX3;'([H2]),$([H1][#6]),$([H0]([#6])[#6])][OX2][#6;!$(C=[O,N,S])]' +Phosphinous_amide': '[PX3;'([H2]),$([H1][#6]),$([H0]([#6])[#6])][#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])]' +Phosphinous_derivatives': '[PX3;'([H2]),$([H1][#6]),$([H0]([#6])[#6])][!#6]' +Quart_silane': '[SiX4]([#6])([#6])([#6])[#6]' +Non-quart_silane': '[SiX4;'([H1]([#6])([#6])[#6]),$([H2]([#6])[#6]),$([H3][#6]),$([H4])]' +Silylmonohalide': '[SiX4]([FX1,ClX1,BrX1,IX1])([#6])([#6])[#6]' +Het_trialkylsilane': '[SiX4]([!#6])([#6])([#6])[#6]' +Dihet_dialkylsilane': '[SiX4]([!#6])([!#6])([#6])[#6]' +Trihet_alkylsilane': '[SiX4]([!#6])([!#6])([!#6])[#6]' +Silicic_acid_derivative': '[SiX4]([!#6])([!#6])([!#6])[!#6]' +Trialkylborane': '[BX3]([#6])([#6])[#6] ' +Boric_acid_derivatives': '[BX3]([!#6])([!#6])[!#6]' +Boronic_acid_derivative': '[BX3]([!#6])([!#6])[!#6]' +Borohydride': '[BH1,BH2,BH3,BH4]' +Quaternary_boron': '[BX4]' +Aromatic': 'a' +Heterocyclic': '[!#6;!R0]' +Epoxide': '[OX2r3]1[#6r3][#6r3]1' +NH_aziridine': '[NX3H1r3]1[#6r3][#6r3]1' +Spiro': '[D4R;'(*(@*)(@*)(@*)@*)]' +Annelated_rings': '[R;'(*(@*)(@*)@*);!$([R2;$(*(@*)(@*)(@*)@*)])]@[R;$(*(@*)(@*)@*);!$([R2;$(*(@*)(@*)(@*)@*)])]' +Bridged_rings': '[R;'(*(@*)(@*)@*);!$([D4R;$(*(@*)(@*)(@*)@*)]);!$([R;$(*(@*)(@*)@*);!$([R2;$(*(@*)(@*)(@*)@*)])]@[R;$(*(@*)(@*)@*);!$([R2;$(*(@*)(@*)(@*)@*)])])]' +Sugar_pattern_1': '[OX2;'([r5]1@C@C@C(O)@C1),$([r6]1@C@C@C(O)@C(O)@C1)]' +Sugar_pattern_2': '[OX2;'([r5]1@C(!@[OX2,NX3,SX2,FX1,ClX1,BrX1,IX1])@C@C@C1),$([r6]1@C(!@[OX2,NX3,SX2,FX1,ClX1,BrX1,IX1])@C@C@C@C1)]' +Sugar_pattern_combi': '[OX2;'([r5]1@C(!@[OX2,NX3,SX2,FX1,ClX1,BrX1,IX1])@C@C(O)@C1),$([r6]1@C(!@[OX2,NX3,SX2,FX1,ClX1,BrX1,IX1])@C@C(O)@C(O)@C1)]' +Sugar_pattern_2_reducing': '[OX2;'([r5]1@C(!@[OX2H1])@C@C@C1),$([r6]1@C(!@[OX2H1])@C@C@C@C1)]' +Sugar_pattern_2_alpha': '[OX2;'([r5]1@[C@@](!@[OX2,NX3,SX2,FX1,ClX1,BrX1,IX1])@C@C@C1),$([r6]1@[C@@](!@[OX2,NX3,SX2,FX1,ClX1,BrX1,IX1])@C@C@C@C1)]' +Sugar_pattern_2_beta': '[OX2;'([r5]1@[C@](!@[OX2,NX3,SX2,FX1,ClX1,BrX1,IX1])@C@C@C1),$([r6]1@[C@](!@[OX2,NX3,SX2,FX1,ClX1,BrX1,IX1])@C@C@C@C1)]' +Conjugated_double_bond': '*=*[*]=,#,:[*]' +Conjugated_tripple_bond': '*#*[*]=,#,:[*]' +Cis_double_bond': '*/[D2]=[D2]\*' +Trans_double_bond': '*/[D2]=[D2]/*' +Mixed_anhydrides': '['(*=O),$([#16,#14,#5]),$([#7]([#6]=[OX1]))][#8X2][$(*=O),$([#16,#14,#5]),$([#7]([#6]=[OX1]))]' +Halogen_on_hetero': '[FX1,ClX1,BrX1,IX1][!#6]' +Halogen_multi_subst': '[F,Cl,Br,I;!'([X1]);!$([X0-])]' +Trifluoromethyl': '[FX1][CX4;!'([H0][Cl,Br,I]);!$([F][C]([F])([F])[F])]([FX1])([FX1])' +C_ONS_bond': '[#6]~[#7,#8,#16]' +Charged': '[!+0]' +Anion': '[-1,-2,-3,-4,-5,-6,-7]' +Kation': '[+1,+2,+3,+4,+5,+6,+7]' +Salt': '([-1,-2,-3,-4,-5,-6,-7]).([+1,+2,+3,+4,+5,+6,+7])' +1,3-Tautomerizable': '['([#7X2,OX1,SX1]=*[!H0;!$([a;!n])]),$([#7X3,OX2,SX2;!H0]*=*),$([#7X3,OX2,SX2;!H0]*:n)]' +1,5-Tautomerizable': '['([#7X2,OX1,SX1]=,:**=,:*[!H0;!$([a;!n])]),$([#7X3,OX2,SX2;!H0]*=**=*),$([#7X3,OX2,SX2;!H0]*=,:**:n)]' +Rotatable_bond': '[!'(*#*)&!D1]-!@[!$(*#*)&!D1]' +Michael_acceptor': '[CX3]=[CX3]['([CX3]=[O,N,S]),$(C#[N]),$([S,P]=[OX1]),$([NX3]=O),$([NX3+](=O)[O-])]' +Dicarbodiazene': '[CX3](=[OX1])[NX2]=[NX2][CX3](=[OX1])' +CH-acidic': '['([CX4;!$([H0]);!$(C[!#6;!$([P,S]=O);!$(N(~O)~O)])][$([CX3]=[O,N,S]),$(C#[N]),$([S,P]=[OX1]),$([NX3]=O),$([NX3+](=O)[O-]);!$(*[S,O,N;H1,H2]);!$([*+0][S,O;X1-])]),$([CX4;!$([H0])]1[CX3]=[CX3][CX3]=[CX3]1)]' +CH-acidic_strong': '[CX4;!'([H0]);!$(C[!#6;!$([P,S]=O);!$(N(~O)~O)])]([$([CX3]=[O,N,S]),$(C#[N]),$([S,P]=[OX1]),$([NX3]=O),$([NX3+](=O)[O-]);!$(*[S,O,N;H1,H2]);!$([*+0][S,O;X1-])])[$([CX3]=[O,N,S]),$(C#[N]),$([S,P]=[OX1]),$([NX3]=O),$([NX3+](=O)[O-]);!$(*[S,O,N;H1,H2]);!$([*+0][S,O;X1-])]' +Chiral_center_specified': '['([*@](~*)(~*)(*)*),$([*@H](*)(*)*),$([*@](~*)(*)*),$([*@H](~*)~*)]' + ' diff --git a/paper/loael-dataset-comparison-all-compounds.pdf b/paper/loael-dataset-comparison-all-compounds.pdf new file mode 100644 index 0000000..ee34390 Binary files /dev/null and b/paper/loael-dataset-comparison-all-compounds.pdf differ diff --git a/paper/loael-dataset-comparison-all-compounds.svg b/paper/loael-dataset-comparison-all-compounds.svg new file mode 100644 index 0000000..bc5d410 --- /dev/null +++ b/paper/loael-dataset-comparison-all-compounds.svg @@ -0,0 +1,1953 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/paper/loael-dataset-comparison-common-compounds.pdf b/paper/loael-dataset-comparison-common-compounds.pdf new file mode 100644 index 0000000..4dba051 Binary files /dev/null and b/paper/loael-dataset-comparison-common-compounds.pdf differ diff --git a/paper/loael-dataset-comparison-common-compounds.svg b/paper/loael-dataset-comparison-common-compounds.svg new file mode 100644 index 0000000..3898812 --- /dev/null +++ b/paper/loael-dataset-comparison-common-compounds.svg @@ -0,0 +1,1954 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/paper/loael-dataset-comparison.rb b/paper/loael-dataset-comparison.rb new file mode 100644 index 0000000..c1602ad --- /dev/null +++ b/paper/loael-dataset-comparison.rb @@ -0,0 +1,73 @@ +require_relative '../../lazar/lib/lazar' +include OpenTox +#$mongo.database.drop +#$gridfs = $mongo.database.fs # recreate GridFS indexes +old = Dataset.from_csv_file File.join(File.dirname(__FILE__),"..","regression","LOAEL_mg_corrected_smiles_mmol.csv") +new = Dataset.from_csv_file File.join(File.dirname(__FILE__),"..","regression","swissRat_chron_LOAEL_mmol.csv") + +combined_compounds = old.compound_ids & new.compound_ids + +compound_vector = [] +value_vector = [] +dataset_vector = [] + +old_median = [] +new_median = [] + +errors = [] +combined_compounds.each do |cid| + c = Compound.find cid + old_values = old.values(c,old.features.first) + old_median << -Math.log(old_values.mean) + old_values.each do |v| + compound_vector << c.smiles + value_vector << -Math.log(v.to_f) + dataset_vector << old.name + end + new_values = new.values(c,new.features.first) + new_median << -Math.log(new_values.mean) + new_values.each do |v| + compound_vector << c.smiles + value_vector << -Math.log(v) + dataset_vector << new.name + end +end +old_median.each_index do |i| + errors[i] = (old_median[i] - new_median[i]).abs unless old_median[i] == new_median[i] +end +rmse = 0 +mae = 0 +errors.compact.each do |e| + rmse += e**2 + mae += e +end +rmse = Math.sqrt(rmse/errors.size) +mae = mae/errors.size + +=begin +R.assign "smi", compound_vector +R.assign "values", value_vector +R.assign "dataset", dataset_vector +R.eval "df <- data.frame(factor(smi),values,factor(dataset))" +R.eval "df$smi <- reorder(df$factor.smi,df$values)" +R.eval "img <- ggplot(df, aes(smi,values,ymin = min(values), ymax=max(values),color=dataset))" +R.eval "img <- img + ylab('-log(LOAEL mg/kg_bw/day)') + xlab('Compound') + theme(axis.text.x = element_blank())" +R.eval "img <- img + geom_point()" + +R.eval "ggsave(file='/home/ch/opentox/lazar-nestec-data/loael-dataset-comparison-mmol_kg_day.svg', plot=img,width=12, height=8)" +=end + +R.assign "old", old_median +R.assign "new", new_median +=begin +R.eval "df <- data.frame(old,new)" +R.eval "img <- ggplot(df, aes(old,new))" +R.eval "img <- img + geom_point()" +#R.eval "img <- img + geom_smooth(method=lm) " +R.eval "img <- img + geom_abline(intercept=0.0) " +R.eval "ggsave(file='/home/ch/opentox/lazar-nestec-data/loael-dataset-correlation.svg', plot=img,width=12, height=8)" +=end +puts "Correlation old/new:" +puts "\tr^2: #{R.eval("cor(old,new,use='complete')").to_f**2}" +puts "\tRMSE: #{rmse}" +puts "\tMAE: #{mae}" diff --git a/paper/loael-dataset-correlation.pdf b/paper/loael-dataset-correlation.pdf new file mode 100644 index 0000000..3e0a042 Binary files /dev/null and b/paper/loael-dataset-correlation.pdf differ diff --git a/paper/loael-dataset-correlation.svg b/paper/loael-dataset-correlation.svg new file mode 100644 index 0000000..1ce514e --- /dev/null +++ b/paper/loael-dataset-correlation.svg @@ -0,0 +1,387 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/paper/loael-variability.rb b/paper/loael-variability.rb new file mode 100644 index 0000000..ae74c3f --- /dev/null +++ b/paper/loael-variability.rb @@ -0,0 +1,61 @@ +require_relative '../lazar/lib/lazar' +include OpenTox +#$mongo.database.drop +#$gridfs = $mongo.database.fs # recreate GridFS indexes +# compare duplicates within datasets +#old = Dataset.from_csv_file File.join(File.dirname(__FILE__),"regression","LOAEL_mmol_corrected_smiles.csv") +old = Dataset.from_csv_file File.join(File.dirname(__FILE__),"regression","LOAEL_mg_corrected_smiles_mmol.csv") +#new = Dataset.from_csv_file File.join(File.dirname(__FILE__),"regression","swissRat_chron_LOAEL.csv") +new = Dataset.from_csv_file File.join(File.dirname(__FILE__),"regression","swissRat_chron_LOAEL_mmol.csv") +#combined = Dataset.from_csv_file File.join(File.dirname(__FILE__),"regression","LOAEL-rat-combined.csv") + +compound_vector = [] +value_vector = [] +dataset_vector = [] + +vars = [] + +[old, new].each do |dataset| + vars << [] + #vars[dataset.name] = [] + p dataset.name + p dataset.compounds.size + p dataset.duplicates(dataset.features.first).size + dataset.duplicates.each do |cid,values| + R.assign "values", values + var = R.eval("var(-log(values))").to_f + vars.last << var + #smi = Compound.find(cid).smiles + smi = cid.to_s + values.each do |val| + compound_vector << smi + value_vector << - Math.log(val) + dataset_vector << dataset.name + end + #vars << { :var => var, :values => values, :smiles => smi } + end + #vars.sort!{|a,b| a[:var] <=> b[:var]} + #vars.each do |dup| + #dup[:values].each do |v| + #compound_vector << dup[:smiles] + #value_vector << v + #end + #end +end +#p vars +# TODO statistical test for variances +R.assign "vars1", vars[0] +R.assign "vars2", vars[1] +print "p-value: #{R.eval("t.test(vars1,vars2)$p.value").to_f}" + +R.assign "smi", compound_vector +R.assign "values", value_vector +R.assign "dataset", dataset_vector +R.eval "df <- data.frame(factor(smi),values,factor(dataset))" +R.eval "df$smi <- reorder(df$factor.smi,df$values)" +R.eval "img <- ggplot(df, aes(smi,values,ymin = min(values), ymax=max(values),color=dataset))" +R.eval "img <- img + ylab('-log(LOAEL mg/kg_bw/day)') + xlab('Compound') + theme(axis.text.x = element_blank())" +R.eval "img <- img + geom_point()" +#R.eval "img <- img + scale_x_discrete(breaks=NULL) + geom_point() + coord_flip()"# + xlab('-log(LOAEL)'), ylab('Compound')" +#R.eval "ggsave(file='/home/ch/opentox/lazar-nestec-data/loael_variance.svg', plot=img)" +R.eval "ggsave(file='/home/ch/opentox/lazar-nestec-data/loael-variance.svg', plot=img,width=12, height=8)" diff --git a/paper/loael.html b/paper/loael.html new file mode 100644 index 0000000..c8c0a2d --- /dev/null +++ b/paper/loael.html @@ -0,0 +1,384 @@ + + + + + + + + + + +
+ + +
+

Introduction

+
+
+

Data

+
+

LOAEL Values

+
+

Comparison of variances in datasets

+

p-value: 0.4750771581019402

+ +loael-variance.svg +
+
+

Comparison of compounds in both datasets

+ +loael-dataset-comparison-mmol_kg_day.svg +
+
+

Correlation between datasets

+

using means

+ +loael-dataset-correlation.svg +

with "identical" values

+
+r^2: 0.6106457754533314 +RMSE: 1.2228212261024438 +MAE: 0.801626064534318
+
+
+
+
+

Models

+
+
+

Validation

+

Discussion

+
+
+ + diff --git a/paper/loael.pdf b/paper/loael.pdf new file mode 100644 index 0000000..e2edd82 --- /dev/null +++ b/paper/loael.pdf @@ -0,0 +1,205 @@ +%PDF-1.4 +%“Œ‹ž ReportLab Generated PDF document http://www.reportlab.com +1 0 obj +<< /F1 2 0 R /F2 3 0 R >> +endobj +2 0 obj +<< /BaseFont /Helvetica /Encoding /WinAnsiEncoding /Name /F1 /Subtype /Type1 /Type /Font >> +endobj +3 0 obj +<< /BaseFont /Helvetica-Bold /Encoding /WinAnsiEncoding /Name /F2 /Subtype /Type1 /Type /Font >> +endobj +4 0 obj +<< /BitsPerComponent 8 /ColorSpace /DeviceRGB /Filter [ /ASCII85Decode /DCTDecode ] /Height 128 /Length 6363 /Subtype /Image + /Type /XObject /Width 128 >> +stream +s4IA0!"_al8O`[\!Bs4[N@!!<9(!WiE*!WiE*!s8W."p>&3"9\u7"pG2;#RUnF#RLeE$kEaR$P!ON#n7IU%M'*^&J,9X&eblh'+YWc&HCJb6NI8k!sA]/#Qt89&.8dP&.fBa&.fBa&.fBa&.fBa&.fBa&.fBa&.fBa&.fBa&.fBa&.fBa&.fBa&.fBa&.nlW!"fJ:J,k*%!?qLF&HMtG!WU(<*WQ0@!sJ]+zz!!!?+!XSr3"U>;;!WU(<;%N^.!X&Q-"q(kD"UP//!!!$$!rrH-"pY_G&g8tC3'gDc[0[Nb+u35.EMg"j(aC:^6;gcbEfu`^dhNX>OcpSjA'sd&6UZKXU9_Vos24mW!n`PP?'@/9oY(-V,$a=MFuC=1XHjB9,8HB`?*]\rWb%O$?*IrlGh?4Ztusq37UroVF1A!$!*]$&5=#U%IT1lDsj@YuM"ae9sD@H29#k*RoL!4F-cZ8+oJZe9sD@H29O6hujSZt'EQ[\ak]s0HeQ[\a^qItYK8Z>G`tL*cfI1<9-n&Yiaq1]f/Kgb;3a>(F^t*1i`h*J35e">DLa>#):c4\DnYaB%O=hTZIL/aRZV)>rprUqf_q$KW&J*0^3Vf<-0E2"s%728uEBar#r[RkY)O/'X?P8a)PfM:N.O?c:e=mur%`p.;W.7"87EV/YO,fcB5';Z*Xq;-LM@2[l9J1j,SB*hb,;3\66`?rIFNiu3hB-i.SHNcL5oUm4J#Z(UcjrQo7(G"i.u>o:?,-&I3;bM@`/nL%;(IPC%-&:$[\sWJl@9D:c4\DnYaB%O=hTZIL/aRZV)>rprUqf_q$KW&JWKf3QM."MQ^0DM+gp<:Vu#g,/%rYQnBg61#Od!)_A'6UFN6`<)SFL6+.Uq.s:"cJqP:-WCf:gITp5jFtM)qHHD\fWln7;'<8r%NFs;T7jK5aj\h=.*dtXVN[L]m`I>J^-K7D0B&f90>dV)oY0@ifS0/!dZjQ6Y64T%"!S=c1l\Gc_9nf-)N04ja4P9++t_.faREV`nLIck'K&Rs`$f_'&na';3*1D2jS@8I_flqOh@'h;3DXoo5Jrr<)ZVXmNu0S/X=$R$UgXY51p2g'T42#bk-'g'.#5*hG`3QcEf!!BM_NjL]bQI8)qROfbirr5Rl#eOod;Yat#/S*/Yk8Db[!UdCpOkV-_iPA>I,[<3/r&7OmPO\tdKR>8/3t`#enCVoT*G-W\%9P7,rd)F24@Y;VoDJn/fq9H#u1]29-,qbajL@1eh=iO(sFAd:O`s_\3hNnUUU`kmuN.6p=8Je>,.Xl9UU7i1o'k4@;nDo\'p]+3O`h,rH^VkbB'^tGUo^SX;][e%>(kH=Hq]djBP1Cl1q74)cU1=(WtMG@?JngVP%^-T5Ac9/L<[,^o"o2L.T[jJ87k-`=TPVAcY8!jDj,GR=Bf)%=/^A>M):_r=G%8rWl*XW`q$HRMBo!@pU?%\HfQFfIXGW+(Eg9*uo4s.Sp&e@QmBQ)c('(-mPTAn_(f/RDt"`R&BuhP0:]BqRO&]#KPGLl34$)Y2Bs:/Sa4c56;O&Zkm-CWf[aI_m`unl0P#V:?Gqr,A@[b`0M-4f#p3FLFQ2V'h!5.[fHmo3:`$mZmDm8'r"]sZmADT7%+M\0+EOj\,jS8"@2bG&qS%Ye^>7rebRWTZg,m;COW;PCsN^nD"412PuPJ,\QDNo0:QRL*6QRmk;f`;O=f[rF4q0/48XB]m`R]PTBlcr4"c**4@8NVGBK:#,<$h1=^a%Mt(V6K9edA:++X-KQ+&"P4%Xi4flrQWFhB-sugdkN5FeY93-%\`2dY6\5uY#N:sAfM`:G94)g&pFid"kT'+^18VVP>o(_<40lE.to&\iUb^l4JP*sWZV_V#q@mK"M-.1m1'$6?2Wcc?rf0l*_Fju//'/6+4iXhX&MGsq(;Mn$G%8e.`DG"S"k+ideLKKUC92bN"bZH\mYZO7tf@\r6Pp"[NeY(YkU+a5oduok.%`1#W,sCbPb8.I?7)^o]n".s'jVNaU1$=BsUla8CS]79+qEVO$`J>g")U/r*e)9+S(ACq9"K)Ap#.$rD2#,2@"iJnE_(!1NBk,/T)*1$mHH#Y',DV&k*W'UE`N<.#*gne0c=oZ:MoS?)*;aLD_h%rQ;F\MYK#3.fHkkCK'(1$Z=in30e]C]A+V#q'-WZS\8DU[+&gOUW**A+oV9`H>C;iKG)3ZXVCb8d=@HLIC#j9,F5HhpLr%3AT`:`Hd+8*R`)0S>i_Z;$='i;a;X:J5%:2sa2^/EnT2Mh'B&2;c'@fP+n::kA/Sn'k)KVP*_41m*g_1\9]@&9jbnoe7j[PJG82bq;O:]_W2pu(0.rstmu_JsrWq39F"=`ud8PH3WL)2X/[U2;Xf;T@O;(B6AA9p#R;E4?%=tAnBg(_pnkb"#oOE"$-3;oSc#`mQ:j?,XI&hh0h.#ViW4>g_;!TbR/.6(C_G.&)gdT4>l94h(.;4uW@g37W*hFT_j:=;]]11=Td'\^&mC<9ZQ]e,($Bf:TX9535.[s97]8NTKhSB6OqVCGbO:MEV\2bdUb8leNK3469/]YG!;PE5c],_,nB-Q%:S%h=:ce_A4=@(pC#)4kb(cBsV+AU1?q%Dp"]rj3WdidT"gh^IRQZ"Z,e<91XQC@;.GTe*FFPFjaKQiMDm1iZ!F<+kK`UMI*O$?8jHPjM;0R3@ipoq*p2@$o1&#E%&jWlQo&J=&uhq\*Af+1--NXpS[m@RWH!XQ3J4lF9])XJp=;RFlgFW/K:d^<@le=C,0KlSUl!C679\W"Hp4t9tMf4/+8O]8^,53`I.l/>1]6i@Y$*_HW*`sBi>ZcV,]e:Wa8:*0B>;qM*^4Hmu8XlLYcjl\L0URhNX@']hM#\C77Ef!37`K,ssfgNL==)OVEKW'Z&Yd$6aD=Cr(]R`qs34FlkIO8,\CL)-7[J?\*/!4Bo(+JfH4-\1sPrR\)JE)ab6h5[Q(hAJimZ*T_&XR]s^a(*qaikOMp93]-b,JL%QK(-U1m/I&4r6-"tAgl*7o!7HV2T!YGqn-(*d:HB:E(mAd345Ehh'ob%bfn2b_I]-&7-c8g3<9c5JQPc8_-7OAeY9LRg.&Eo\?0BbF[oSP/R5;RM,?CuAj[^YS2eAZ4hs-m;m#>#9I)$to?'p7O#hY9**T[He9P#f:;Adh)2-uVWc"+NoXX5:o1R9/cVTHV)29pXA^+P(5!uST=gL$1k)#Y'QrN!0"J"phX9+fXajZ4pG_n!!?ZbG9QoK`;&?2I4^O1JM:p[c#`[C!JTHEOFV3X"j-D[a_Zsb3FOMIur5FI%uHRj6V<>fW1X^4=-r44*@T,RHfZMELKZH8p?!'3OYah_T\!A,%kEg:)2F*:#RuKLf[u1;*VeAMUOKJi>lhSXcWMf%t4\e!Y2dQWtefoBm1(%BX$9'GO,2&EAQhbUULlh:HIKEsettl'-k(@\ZYr]!Neoi9FL;R7#:[Vnlmb%p@D]%CX\aZ71$&:@QFh)R:h?FAtnNA`,*75hu7#[&lF5hGms[&1T7F@o0"=CF\#6>P)&MIb(DpjI;C!@pNhQobqWm$.`;0UQF3+&pBHAendstream +endobj +5 0 obj +<< /Contents 15 0 R /MediaBox [ 0 0 595.2756 841.8898 ] /Parent 14 0 R /Resources << /Font 1 0 R /ProcSet [ /PDF /Text /ImageB /ImageC /ImageI ] /XObject << /FormXob.a8ed09f747eb75e6355b954751a5e4bf 4 0 R >> >> /Rotate 0 /Trans << >> + /Type /Page >> +endobj +6 0 obj +<< /Outlines 8 0 R /PageLabels 16 0 R /PageMode /UseNone /Pages 14 0 R /Type /Catalog >> +endobj +7 0 obj +<< /Author () /CreationDate (D:20151215093942-01'00') /Creator (\(unspecified\)) /Keywords () /Producer (ReportLab PDF Library - www.reportlab.com) /Subject (\(unspecified\)) + /Title () >> +endobj +8 0 obj +<< /Count 6 /First 9 0 R /Last 13 0 R /Type /Outlines >> +endobj +9 0 obj +<< /Dest [ 5 0 R /XYZ 62.69291 765.0236 0 ] /Next 10 0 R /Parent 8 0 R /Title (Introduction) >> +endobj +10 0 obj +<< /Count 1 /Dest [ 5 0 R /XYZ 62.69291 732.0236 0 ] /First 11 0 R /Last 11 0 R /Next 12 0 R /Parent 8 0 R + /Prev 9 0 R /Title (Data) >> +endobj +11 0 obj +<< /Dest [ 5 0 R /XYZ 62.69291 699.0236 0 ] /Parent 10 0 R /Title (LOAEL Values) >> +endobj +12 0 obj +<< /Dest [ 5 0 R /XYZ 62.69291 243.0236 0 ] /Next 13 0 R /Parent 8 0 R /Prev 10 0 R /Title (Models) >> +endobj +13 0 obj +<< /Dest [ 5 0 R /XYZ 62.69291 210.0236 0 ] /Parent 8 0 R /Prev 12 0 R /Title (Validation) >> +endobj +14 0 obj +<< /Count 1 /Kids [ 5 0 R ] /Type /Pages >> +endobj +15 0 obj +<< /Length 2020 >> +stream +1 0 0 1 0 0 cm BT /F1 12 Tf 14.4 TL ET +q +1 0 0 1 62.69291 744.0236 cm +q +BT 1 0 0 1 0 3.5 Tm 21 TL /F2 17.5 Tf 0 0 0 rg (Introduction) Tj T* ET +Q +Q +q +1 0 0 1 62.69291 711.0236 cm +q +BT 1 0 0 1 0 3.5 Tm 21 TL /F2 17.5 Tf 0 0 0 rg (Data) Tj T* ET +Q +Q +q +1 0 0 1 62.69291 681.0236 cm +q +BT 1 0 0 1 0 3 Tm 18 TL /F2 15 Tf 0 0 0 rg (LOAEL Values) Tj T* ET +Q +Q +q +1 0 0 1 62.69291 663.0236 cm +q +0 0 0 rg +BT 1 0 0 1 0 2 Tm /F1 10 Tf 12 TL (#### Comparison of variances in datasets) Tj T* ET +Q +Q +q +1 0 0 1 62.69291 645.0236 cm +q +0 0 0 rg +BT 1 0 0 1 0 2 Tm /F1 10 Tf 12 TL (p-value: 0.4750771581019402) Tj T* ET +Q +Q +q +1 0 0 1 247.6378 539.0236 cm +q +100 0 0 100 0 0 cm +/FormXob.a8ed09f747eb75e6355b954751a5e4bf Do +Q +Q +q +1 0 0 1 62.69291 521.0236 cm +q +0 0 0 rg +BT 1 0 0 1 0 2 Tm /F1 10 Tf 12 TL (#### Comparison of compounds in both datasets) Tj T* ET +Q +Q +q +1 0 0 1 247.6378 415.0236 cm +q +100 0 0 100 0 0 cm +/FormXob.a8ed09f747eb75e6355b954751a5e4bf Do +Q +Q +q +1 0 0 1 62.69291 397.0236 cm +q +0 0 0 rg +BT 1 0 0 1 0 2 Tm /F1 10 Tf 12 TL (#### Correlation between datasets) Tj T* ET +Q +Q +q +1 0 0 1 247.6378 291.0236 cm +q +100 0 0 100 0 0 cm +/FormXob.a8ed09f747eb75e6355b954751a5e4bf Do +Q +Q +q +1 0 0 1 62.69291 273.0236 cm +q +0 0 0 rg +BT 1 0 0 1 0 2 Tm /F1 10 Tf 12 TL (with "identical" values) Tj T* ET +Q +Q +q +1 0 0 1 62.69291 267.0236 cm +Q +q +1 0 0 1 62.69291 255.0236 cm +0 0 0 rg +BT /F1 10 Tf 12 TL ET +BT 1 0 0 1 0 2 Tm T* ET +q +1 0 0 1 20 0 cm +q +0 0 0 rg +BT 1 0 0 1 0 2 Tm /F1 10 Tf 12 TL (r^2: 0.6106457754533314 RMSE: 1.2228212261024438 MAE: 0.801626064534318) Tj T* ET +Q +Q +q +Q +Q +q +1 0 0 1 62.69291 255.0236 cm +Q +q +1 0 0 1 62.69291 222.0236 cm +q +BT 1 0 0 1 0 3.5 Tm 21 TL /F2 17.5 Tf 0 0 0 rg (Models) Tj T* ET +Q +Q +q +1 0 0 1 62.69291 189.0236 cm +q +BT 1 0 0 1 0 3.5 Tm 21 TL /F2 17.5 Tf 0 0 0 rg (Validation) Tj T* ET +Q +Q +q +1 0 0 1 62.69291 171.0236 cm +q +0 0 0 rg +BT 1 0 0 1 0 2 Tm /F1 10 Tf 12 TL (Discussion) Tj T* ET +Q +Q + +endstream +endobj +16 0 obj +<< /Nums [ 0 17 0 R ] >> +endobj +17 0 obj +<< /S /D /St 1 >> +endobj +xref +0 18 +0000000000 65535 f +0000000075 00000 n +0000000119 00000 n +0000000229 00000 n +0000000344 00000 n +0000006902 00000 n +0000007174 00000 n +0000007281 00000 n +0000007491 00000 n +0000007566 00000 n +0000007680 00000 n +0000007839 00000 n +0000007942 00000 n +0000008064 00000 n +0000008177 00000 n +0000008240 00000 n +0000010317 00000 n +0000010361 00000 n +trailer +<< /ID + % ReportLab generated PDF document -- digest (http://www.reportlab.com) + [(C=h\326\032\301S\300\353\374b$\322H\311t) (C=h\326\032\301S\300\353\374b$\322H\311t)] + /Info 7 0 R /Root 6 0 R /Size 18 >> +startxref +10398 +%%EOF diff --git a/paper/loael.rst b/paper/loael.rst index 2a5bbea..50b7a6a 100644 --- a/paper/loael.rst +++ b/paper/loael.rst @@ -1,9 +1,34 @@ Introduction +------------ Data +---- -Models +LOAEL Values +............ -Validation +Comparison of variances in datasets +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ -Discussion +p-value: 0.4750771581019402 + +.. image:: loael-variance.svg + + +Comparison of compounds in both datasets +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +.. image:: loael-dataset-comparison-mmol_kg_day.svg + +Correlation between datasets +~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +using means + +.. image:: loael-dataset-correlation.svg + +with "identical" values + + r^2: 0.6106457754533314 + RMSE: 1.2228212261024438 + MAE: 0.801626064534318 diff --git a/regression/LOAEL_mg_corrected_smiles.csv b/regression/LOAEL_mg_corrected_smiles.csv new file mode 100644 index 0000000..b71129c --- /dev/null +++ b/regression/LOAEL_mg_corrected_smiles.csv @@ -0,0 +1,568 @@ +SMILES,LOAEL_mg_kg_bw_day +C1=C(C(=CC(=C1NN=C3C2=C(C=C([S]([O-])(=O)=O)C=C2)C=CC3=O)OC)[S]([O-])(=O)=O)C.[Na+].[Na+],3739 +O1C(=O)C(O)=C(O)C1C(O)CO,3051 +C1(C)=C(C=CC(C)=CC=CC(C)=CC=CC=C(C)C=CC=C(C)C(=O)OC)C(C)(C)CCC1,500 +c(cccc1)(c1)C(C)C,462 +O=C(OCCCC)c(c(ccc1)C(=O)OCCCC)c1,600 +O=C(OCC)c(c(ccc1)C(=O)OCC)c1,4435 +O=C(OC(OC(OC1C)C)C1)C,125 +Oc(c(ccc1)C)c1C,6 +Oc(ccc(c1C)C)c1,14 +O=C(OCC)C=C,248 +c(cccc1)(c1)CC,408 +OCCO,250 +c(ccc1C(=O)OCC(=O)OCC)cc1C(=O)OCC,2500 +O=C,82 +O=C(O)C=CC(=O)O,1081 +OCC(O)CO,6883 +O=C(OC)c(ccc(O)c1)c1,1500 +O=C(OCCC)c(ccc(O)c1)c1,1500 +CC(CCC(=O)(O))C3CCC4C2CCC1CC(O)CCC1(C)C2CCC34C,500 +OC(C(CCC1C)C(C)C)C1,593 +O=C(O)C(=C)C,248 +O=C(OC)c(c(O)ccc1)c1,360 +Oc(cccc1)c1,344 +O=C(OCCC)c(cc(O)c(O)c1O)c1,864 +OCC(O)C1C(O)=C(O)C(=O)O1,1554 +c(cccc1)(c1)C=C,21 +O=Cc(occ1)c1,60 +NCCNc1cccc2ccccc12,79 +CN(C)(C)CCCl,275 +O=C(Nc(ccc(c1)C(=O)CCl)c1)C,1580 +c(ccc(c1)Cl)(c1)C(c(ccc(c2)Cl)c2)C(Cl)(Cl)Cl,32 +CC(Oc1cc(Cl)c(Cl)cc1Cl)C(=O)(O),8.7 +O=N(=O)C(=CC=C1OC)C=C1N=NC(C(O)=C2C(=O)NC(=CC=C4)C=C4N(=O)=O)=C(C=C3)C(=C2)C=C3,2100 +O=N(=O)C(C=C1)=CC(OCCO)=C1NCCO,229 +Cc1cccc(CC)c1N(C(=O)CCl)COCC,50 +C1=C(C(=CC=C1OC2=CC=C(C=C2Cl)C(F)(F)F)[N+](=O)[O-])C(=O)[O-].[Na+],180 +CCc1cccc(CC)c1N(COC)C(=O)CCl,15 +O=C(Nc(ccc(OCC)c1N)c1)C,1185 +Oc(ccc(N)c1)c1,686 +CC(N)CC(=CC=C1)C=C1,5 +O(c(ccc(c1)C=CC)c1)C,344 +COc1ccc(N)cc1,474 +O=C(O)c(c(N)ccc1)c1,2751 +Clc2cccc(c2)c1ccccc1,4 +O=C(NC(C(=O)OC)Cc(cccc1)c1)C(N)CC(=O)O,147 +n1c2ccc(Cl)cc2ncc1Oc3ccc(OC(C)C(=O)OCC)cc3,3.7 +COC(=O)NS(=O)(=O)c1ccc(N)cc1,180 +S=P(OC)(OC)SCN1N=Nc2ccccc2C1(=O),0.36 +CNC(=O)Oc1ccccc1OC(C)C,50 +CC(C)(C)C(=O)C(Oc1ccc(Cl)cc1)n2cncn2,25 +O=S(O)(=O)C(=CC=C1)C=C1CN(CC)=C(C=C2)C=CC2=C(C(C=C3)=CC=C3N(C)C)C(C=C4)=CC=C4N(CC)CC(C=C5)=CC(=C5)S(=O)(=O)O,720 +c(c(cccc1)c1)(cccc2)c2,250 +BrC(Cl)Cl,130 +ClC(Cl)C(Cl)(Cl)SN2C(=O)C1CC=CCC1C2(=O),12 +O=C(Oc(c(c(ccc1)cc2)c1)c2)NC,15.6 +CC1=C(SCCO1)C(=O)Nc2ccccc2,30 +ClC1CC2C(C1Cl)C3(Cl)C(=C(Cl)C2(Cl)C3(Cl)Cl)Cl,0.27 +O=C(O)CCl,30 +ClC(=CC=C1N)C=C1,6 +CC(C)OC(=O)C(O)(c1ccc(Cl)cc1)c2ccc(Cl)cc2,9 +n1c(OC)nc(C)nc1NC(=O)NS(=O)(=O)c2ccccc2Cl,25 +OS(=O)(=O)C(C(=CC=C2)C1=C2)=CC=C1N=NC(C(O)=C3N=NC(C(C=C5)=C4C=C5)=CC=C4S(O)(=O)=O)=CC(=C3O)CO,736 +S=P(OCC)(OCC)Oc1ccc2C(C)=C(Cl)C(=O)Oc2c1,0.8 +CNP(=O)(OC)Oc1ccc(cc1Cl)C(C)(C)C,4 +C(C1C2C(C(O)C(O1)OC8C(OC(OC7C(OC(OC6C(OC(OC5C(C(C(OC4C(C(C(OC3C(C(C(O2)OC3CO)O)O)OC4CO)O)O)OC5CO)O)O)C(C6O)O)CO)C(C7O)O)CO)C(C8O)O)CO)O)O,1600 +n1c(N)nc(N)nc1NC2CC2,15 +COC(=O)c1c(Cl)c(Cl)c(C(=O)OC)c(Cl)c1Cl,500 +O=C(O)C(Cl)(Cl)C,28.17 +Nc1cc(N)c(O)cc1,25 +FC(F)(Cl)Cl,150 +ClCCl,50 +O=P(OC)(OC)OC=C(Cl)Cl,2.3 +OC(c1ccc(Cl)cc1)(c2ccc(Cl)cc2)C(Cl)(Cl)Cl,20 +ClC4=C(Cl)C5(Cl)C3C1CC(C2OC12)C3C4(Cl)C5(Cl)Cl,0.05 +CN(=C1C(C=C2)=CC=C2)N(C)C(=C1)C(C=C3)=CC=C3,125 +O=C(NC(=O)c(c(F)ccc1)c1F)Nc(ccc(c2)Cl)c2,8 +CC1=C(C)S(=O)(=O)CCS1(=O)=O,10 +O=C(NC)CSP(OC)(OC)=S,0.25 +COc1ccc(N)c(OC)c1,276 +COP(=O)OC,100 +CC(=C(N(=O)=O)C=C1N(=O)=O)C=C1,34 +CN(C)C(=O)C(c1ccccc1)c2ccccc2,30 +N(c(cccc1)c1)c(cccc2)c2,31 +C(C=C1)(=N(C=C1)CC2)C(N2=C3)=CC=C3,0.58 +CCOP(=S)(OCC)SCCSCC,0.1 +NC(=S)NNC(N)=S,947 +O=C(N(C)C)Nc(ccc(c1Cl)Cl)c1,6 +O=P(O)(O)CCCl,150 +O=C(OCC)C(O1)C1(c(cccc2)c2)C,175 +COC(=O)NC(=NC1=C2)NC1=CC(=C2)SC(C=C3)=CC=C3,15 +CN1C=C(c2ccccc2)C(=O)C(c3cc(C(F)(F)F)ccc3)=C1,25 +c1cc(C(F)(F)F)cc(Cl)c1NC(C(C)C)C(=O)OC(C(#N))c2cccc(Oc3ccccc3)c2,2.5 +S=P(OCC)(Sc1ccccc1)CC,1.58 +n1c(C)nc(OC)nc1NC(=O)NS(=O)(=O)c2ccsc2C(=O)OC,25 +C(C(C(C(C1Cl)Cl)Cl)Cl)(C1Cl)Cl,5 +O=N(=O)N(CN1N(=O)=O)CN(C1)N(=O)=O,1.5 +O=C(N=C(N(C1(=O))C)N(C)C)N1C(CCCC2)C2,50 +n(c(c(ccc1)cc2)c1O)c2,143 +c1cc(Cl)cc(Cl)c1C(OCC=C)Cn2cncc2,40 +COc1cccc(OC)c1C(=O)Nc2onc(C(C)(CC)CC)c2,50.7 +n1c(OC)cc(OC)nc1NC(=O)NS(=O)(=O)Cc2ccccc2C(=O)OC,309 +CCOC(=O)CC(SP(=S)(OC)OC)C(=O)OCC,50 +CN(C)(CCC1)CC1,150 +O=P(SCCCC)(SCCCC)SCCCC,1.25 +COCC(=O)N(C(C)C(=O)OC)c1c(C)cccc1C,62.5 +S=P(OC)(OC)SCN1C(=O)SC(OC)=N1,2 +CNC(=O)ON=C(C)SC,10 +COP(=S)(OC)Oc1ccc(cc1)N(=O)(=O),0.25 +O=C1N(N)C(SC)=NN=C1C(C)(C)C,15 +COP(=O)(OC)OC(Br)C(Cl)(Cl)Br,2 +OC(C(N)C1O)C(C)OC1(C)OC(CC(C)(C(C2O)C(O)=O)OC(O)(C2)CC(O)CC(C)(O3)C3C=C4)C=CC=CC=CC=CCC(C)OC4=O,72 +O=N(=O)c(ccc(c1N)C)c1,8 +O=N(=O)c(c(N)ccc1N)c1,87 +O=C(O)C(=C(N)C=C1N(=O)=O)C=C1,1185 +O=N(=O)c(c(c(ccc1)cc2)c1)c2,165 +c12c(N=Nc3ccccc3)c(O)ccc1cc(S(=O)(=O)O)cc2,180 +CC(C)Oc1cc(c(Cl)cc1Cl)N2N=C(OC2(=O))C(C)(C)C,5 +CNC(=O)ON=C(SC)C(=O)N(C)C,5 +CCOP(=S)(OCC)Oc1ccc(cc1)N(=O)=O,3.5 +Oc(c(c(c(c1Cl)Cl)Cl)Cl)c1Cl,10 +NC(=N)NC(=N)NCCc1ccccc1,73 +COP(=S)(OC)SCN2C(=O)c1ccccc1C2(=O),20 +CCN(CC)C(=O)C(Cl)=C(C)OP(=O)(OC)OC,12.3 +ClC3C6(Cl)C4C2C1OC1C5C2C3(Cl)C(Cl)(C45)C6(Cl)Cl,0.7 +O=C(OC(=O)c1cccc2)c12,1185 +Nc1c(Cl)c(Cl)nc(C(=O)(O))c1Cl,60 +CCN(CC)c1nc(C)cc(OP(=S)(OC)OC)n1,2.5 +Nc3ccc2cc1ccc(N)cc1nc2c3,47 +CCC(=O)Nc1ccc(Cl)c(Cl)c1,20 +Clc1cc(Cl)ccc1C2(Cn3ncnc3)OC(CCC)CO2,25 +O=C(N)c(nccn1)c1,789 +Oc1cc(O)c2C(=O)C(O)=C(c3cc(O)c(O)cc3)Oc2c1,2034 +CCC(O)(C)C#C,46 +CC(C(NCC)=C1)=CC(C1=O2)=C(C(C2=C3)=CC(C)=C3NCC)C(=CC=C4)C(=C4)C(=O)OCC,12 +O=C(NS(=O)(=O)c1cccc2)c12,3602 +c1cc(Cl)ccc1C2SC(=O)N(C(=O)NC3CCCCC3)C2C,160 +n(c(nc(n1)NCC)NCC)c1Cl,5 +O=[S](NC1CCCCC1)(=O)[O-].[Na+],3602 +O=C(OCC(C1OCC(C1O)O)O)CCCCCCCCCCC,6883 +O(CC1O)C(C1O)C(O)COC(=O)CCCCCCCCCCCCCCCCC,7203 +O=S(=O)(Nc(nc(cc1C)C)n1)c(ccc(N)c2)c2,33 +CCNc1nc(NC(C)(C)C)nc(SC)n1,15 +Oc(c(cc(c1)C(C)(C)C)Cl)c1,216 +C(C(Cl)Cl)(Cl)Cl,108 +COP(=O)(OC)OC(=CCl)c1cc(Cl)c(Cl)cc1Cl,100 +CCN(CC)C(=O)SCc1ccc(Cl)cc1,5 +COC(=O)NC(=S)Nc1ccccc1NC(=S)NC(=O)OC,32 +N(C(=S)SSC(N(C)C)=S)(C)C,15 +c12OC(CCCC(C)CCCC(C)CCCC(C)C)(C)CCc1c(C)c(OC(=O)C)c(C)c2C,2000 +Cc1cc(N)ccc1NOS(O)(=O)=O,184 +C(Br)(C(Br)(Br)Br)C1C(C)(C)C1C(=O)OC(C(#N))c2cccc(Oc3ccccc3)c2,3 +O=C(O)COc(c(cc(c1Cl)Cl)Cl)c1,10 +FC(F)(F)C(=CC(N(=O)=O)=C1N(C(C)C)C(C)C)C=C1N(=O)=O,40 +Cc1cc(C)c(N)cc1C,63 +CC(O)(C(O)C(O1)C)CC1(C)OC(C(C)O2)C(C(O)C2(C)OC(C(C)C(O)CC(=O)OC(CC)C3COC(C(OC)C4OC)OC(C)C4O)C(CC=O)CC(C)C(=O)C=CC(=C3)C)N(C)C,500 +c1c(Cl)cc(Cl)cc1N2C(=O)C(C)(C=C)OC2(=O),72.9 +O=C(OC(CCCC(O)CCCCCc1cc(O)cc2O)C)c12,0.2 +COC(=O)C1(C2=CC=CC=C2C3=C1C=C(C=C3)Cl)O,150 +CC(C(=O)O)OC1=CC(=CC=C1)Cl,100 +P12P3P1P23,1472 +C(CO)O,400 +CCCCOCC(C)OCC(C)O,128 +C(CO)O,2000 +C(CO)O,920 +[O-][As](=O)([O-])[O-],6.25 +[Si](CN1C=NC=N1)(C2=CC=C(C=C2)F)C3=CC=C(C=C3)F,2.3 +N(C(=S)SSC(N(C)C)=S)(C)C,11.5 +COP(=O)(N)SC,0.9 +N(C(=S)SSC(N(C)C)=S)(C)C,5.47 +COP(=O)(NC(=O)(C))SC,35 +C1=CC=C(C=C1)NC(=O)NC2=CN=NS2,30 +CCOP(=S)(NC(C)C)OC1=CC=CC=C1C(=O)OC(C)C,0.5 +CC(=NOC(=O)N(C)SN(C)C(=O)ON=C(C)SC)SC,10 +CCOP(=S)(OCC)OC1=NC(=NC(=C1)C)C(C)C,1.5 +NC(CCCC1)C1,58.5 +CN1C=C(c2ccccc2)C(=O)C(c3cc(C(F)(F)F)ccc3)=C1,32.5 +ClC1CC2C(C1Cl)C3(Cl)C(=C(Cl)C2(Cl)C3(Cl)Cl)Cl,0.5 +CCCCC(CC)COC(=O)C1=CC=CC=C1C(=O)OCC(CC)CCCC,200 +OC(=O)CNCP(O)(O)=O,1000 +C1CNC(=S)N1,0.23 +O=C(N(OC)C)Nc(ccc(c1Cl)Cl)c1,6.25 +C1=CC=C2C(=C1)NC(=S)S2,750 +CCOP(=S)(OCC)OC1=NC(=C(C=C1Cl)Cl)Cl,10 +c(c(c(c(c1Cl)Cl)Cl)Cl)(c1Cl)Cl,0.29 +COc1ccc(cc1)C(c2ccc(OC)cc2)C(Cl)(Cl)Cl,125 +C1=CC(=CC=C1Cl)Cl,300 +CC(C)OC(=O)NC1=CC(=CC=C1)Cl,500 +COP(=O)(OC)OC=C(Cl)Cl,2.15 +CCOP(=S)(OCC)Oc1ccc(cc1)N(=O)=O,0.42 +CNC(=O)N(C)c1nnc(s1)C(C)(C)C,40 +CCCCOCCOCCOCC1=CC2=C(C=C1CCC)OCO2,250 +CC(C(=O)O)OC1=C(C=C(C=C1)Cl)Cl,9 +CC1(C(C1C(=O)OC(C#N)C2=CC(=C(C=C2)F)OC3=CC=CC=C3)C=C(Cl)Cl)C,12.5 +C(#N)c(c(c(c(c1C(#N))Cl)Cl)Cl)c1Cl,4 +O=C(OCC)C(O)(c(ccc(c1)Cl)c1)c(ccc(c2)Cl)c2,18.4 +O=C(N(C)C)Nc(ccc(c1)Cl)c1,125 +O=C(N(SC(Cl)(Cl)Cl)C(=O)C1CC=CC2)C12,100 +CCc1cccc(C)c1N(C(C)COC)C(=O)CCl,150 +C1=CC(=C(C=C1Cl)Cl)OCC(=O)O,5 +CCNC1=NC(=NC(=N1)Cl)NC(C)(C)C#N,1.25 +C(C(C(C(C1Cl)Cl)Cl)Cl)(C1Cl)Cl,4.6 +COP(=S)(OC)OC1=CC(=C(C=C1Cl)Cl)Cl,50 +C1C2C=CC1C3C2C4(C(=C(C3(C4(Cl)Cl)Cl)Cl)Cl)Cl,0.01 +CC1(C(C1C(=O)OCC2=CC(=CC=C2)OC3=CC=CC=C3)C=C(Cl)Cl)C,25 +CCN(CC)C(=O)C(C)OC1=CC=CC2=CC=CC=C21,100 +ClC1C=CC2C1C3(Cl)C(=C(Cl)C2(Cl)C3(Cl)Cl)Cl,0.25 +CC(=CC(=O)NC)OP(=O)(OC)OC,0.45 +CC(C)C1(C)N=C(NC1(=O))c3nc2ccccc2cc3C(=O)(O),20 +CC(C)Nc1nc(Cl)nc(NC(C)C)n1,50 +CC(C(=O)O)(Cl)Cl,50 +CC1(C(C1C(=O)OC(C#N)C2=CC(=C(C=C2)F)OC3=CC=CC=C3)C=C(Cl)Cl)C,7.5 +O=C(NC)CSP(OC)(OC)=S,5 +C12C3(C4(C5(C3(C(C1(C5(C2(C4(Cl)Cl)Cl)Cl)Cl)(Cl)Cl)Cl)Cl)Cl)Cl,0.01 +COC(=O)C1=CC=CC=C1C(=O)OC,2000 +CCOP(=S)(OCC)SCSC(C)(C)C,0.05 +CCC(C)SP(=O)(OCC)SC(C)CC,0.25 +CCOP(=S)(OCC)SCSC(C)(C)C,2 +C1C(C(C(=O)N1C2=CC=CC(=C2)C(F)(F)F)Cl)CCl,5 +O=C(O)C(C(C(=O)O)C(O1)CC2)C12,115 +O=C(Oc(c(OC(C1)(C)C)c1cc2)c2)NC,5 +Oc(c(c(c(c1)Cl)Cl)Cc(c(c(cc2Cl)Cl)Cl)c2O)c1Cl,5 +CC1(CON(C1=O)CC2=CC=CC=C2Cl)C,21.5 +CCC(C)N1C(=O)C(=C(NC1=O)C)Br,62.5 +CC1=CC(=CC(=C1N(C)C)C)OC(=O)NC,1.5 +CNC(=O)OC1=CC=CC(=C1)N=CN(C)C,12.5 +CC1=NN(C(=O)N1C(F)F)C2=CC(=C(C=C2Cl)Cl)NS(=O)(=O)C,67 +CCOP(=S)(CC)SC1=CC=CC=C1,5 +CCOP(=S)(OCC)SC(CCl)N1C(=O)C2=CC=CC=C2C1=O,2.5 +N1CC(C)(C)CNC1=NN=C(C=Cc2ccc(C(F)(F)F)cc2)C=Cc3ccc(C(F)(F)F)cc3,5 +CC1=C(C(=C(C(=C1F)F)COC(=O)C2C(C2(C)C)C=C(C(F)(F)F)Cl)F)F,4.6 +CC1=CC(=C(C=C1)N=CN(C)C=NC2=C(C=C(C=C2)C)C)C,10.2 +S=P(OC)(OC)SCN1C(=O)SC(OC)=N1,0.8 +CC(C)N(C(C)C)C(=O)SCC(Cl)=C(Cl)Cl,12.5 +S=P(OC)(OC)SCN1N=Nc2ccccc2C1(=O),2.25 +CC1=NC(=NC(=N1)OC)NC(=O)NS(=O)(=O)C2=CC=CC=C2CCC(F)(F)F,79.9 +O=C(N(S(=O)(=O)Nc1cccc2)C(C)C)c12,40 +CCN(CC)c1nc(C)cc(OP(=S)(OC)OC)n1,13.8 +O=C(ON=CC(SC)(C)C)NC,0.1 +ClC(Cl)(Cl)CC1(OC1)c2cc(Cl)cc(Cl)c2,30 +CCC1CCCC(C(C(=O)C2CC3C(C2CC(=O)O1)CCC4C3CC(C4)OC5CC(C(C(C5OC)OC)OC)C)C)OC6CCC(C(O6)C)N(C)C,24 +CC(C)(C)C(=NOC(=O)NC)CSC,6 +CON=C(CC1=CN=CC=C1)C2=C(C=C(C=C2)Cl)Cl,45 +CC(=CC1C(C1(C)C)C(=O)OCN2C(=O)C3=C(C2=O)CCCC3)C,250 +C1COC(O1)(CN2C=NC=N2)C3=C(C=C(C=C3)Cl)Cl,10 +CCCOC(=O)C1=CN=C(C=C1)C(=O)OCCC,250 +CC1=CC(=NC(=N1)NC(=O)NS(=O)(=O)C2=CC=CC=C2C(=O)OC3COC3)C,83 +C1=C(C(=NC(=C1Cl)Cl)OCC(=O)O)Cl,36 +CCOCN1C(=C(C(=C1C(F)(F)F)Br)C#N)C2=CC=C(C=C2)Cl,13.6 +CC(C)CC1=C(C(=NC(=C1C(=O)SC)C(F)(F)F)C(F)F)C(=O)SC,3.63 +CC12CC1(C(=O)N(C2=O)C3=CC(=CC(=C3)Cl)Cl)C,15 +CC1=CC(=C(C=C1)C(=O)OC)C2=NC(C(=O)N2)(C)C(C)C,50 +COP(=S)(OC)OC1=NC(=C(C=C1Cl)Cl)Cl,3 +CC(C)CC1=C(C(=NC(=C1C(=O)OC)C(F)F)C(F)(F)F)C2=NCCS2,44.2 +CCOC(=O)C(CC1=CC(=C(C=C1Cl)F)N2C(=O)N(C(=N2)C)C(F)F)Cl,12 +CC(C)=CC3C(C(=O)OCc2coc(Cc1ccccc1)c2)C3(C)C,125 +CCCSP(=S)(OCC)OC1=CC=C(C=C1)SC,11.5 +CC1=CC(=C(C(=C1)OC(=O)NC)C)C,59.2 +CC1=CC=CC=C1COC2CC3(CCC2(O3)C)C(C)C,150 +CC1=C2C(=CC=C1)SC3=NN=CN23,31 +CCC(=C1C(=O)CC(CC1=O)CC(C)SCC)NOCC=CCl,100 +CCCN(CCC)C(=O)SCC,9 +CC(C)OC(=O)C=C(C)C=CCC(C)CCCC(C)(C)OC,46 +COP(=S)(OC)Oc1ccc(SC)c(C)c1,3.75 +COC1=C(C=C(C=C1)C(=CC(=O)N2CCOCC2)C3=CC=C(C=C3)Cl)OC,46.3 +CCSC(=O)N(CC(C)C)CC(C)C,100 +CC(C)OP(=S)(OC(C)C)SCCNS(=O)(=O)C1=CC=CC=C1,15 +CC(=CC1C(C1(C)C)C(=O)OCC2=CC(=CC=C2)OC3=CC=CC=C3)C,150 +CC1=CC(=CC(=C1C)C)OC(=O)NC,10 +CCOP(=S)(OCC)SCSC1=CC=C(C=C1)Cl,1 +C1CN(CCN1C(C(Cl)(Cl)Cl)NC=O)C(C(Cl)(Cl)Cl)NC=O,100 +C(=CC=C1)(C2=C1)NC(=N2)C(=CS3)N=C3,2 +C1(=C(C(=C(C(=C1Cl)Cl)Cl)Cl)Cl)[N+](=O)[O-],125 +CCCC(=NOCC)C1C(=O)CC(CC1=O)CC(C)SCC,16.56 +ClC2(Cl)C4(Cl)C1(Cl)C5(Cl)C(Cl)(Cl)C3(Cl)C1(Cl)C2(Cl)C3(Cl)C45Cl,0.7 +CCN(C1CCCCC1)C(=O)SCC,3 +CC1=NC(=NC(=N1)OC)NC(=O)NS(=O)(=O)C2=CC=CC=C2OCCCl,220.8 +C(C(=O)O)OC1=NC(=C(C(=C1Cl)N)Cl)F,500 +CC1=C(C(=O)CC1OC(=O)C2C(C2(C)C)C=C(C)C)CC#C,95 +C1C(COC1(CN2C=NC=N2)C3=C(C=C(C=C3)Cl)Cl)Br,6.48 +C1=NNC(=N1)N,2.5 +C1=CC(=C(C(=C1)F)C(=O)NC(=O)NC2=CC(=C(C(=C2F)Cl)F)Cl)F,26 +C1=CC(=CC=C1OS(=O)(=O)C2=CC=C(C=C2)Cl)Cl,2.5 +FC(F)(F)C(=CC(N(=O)=O)=C1N(C(C)C)C(C)C)C=C1N(=O)=O,1000 +CC1=C(C(=O)CC1OC(=O)C2C(C2(C)C)C=C(C)C)CC=C,75 +C1=CC(=C(C(=C1)Cl)C#N)Cl,2.5 +C1C(O1)COC2=CC=CC=C2C3=CC=CC=C3,500 +CC1=CC=CC=C1OCC2=CC=CC=C2C(=NOC)C(=O)OC,375 +O=N(=O)C(C(=C1N(=O)=O)N(C(C)C)C(C)C)=CC(=C1)S(=O)(=O)N,36.86 +C1=CC(=C(C2=NC=C(C=C21)Cl)C(=O)O)Cl,757 +CC(C)NC(=O)N1CC(=O)N(C1=O)C2=CC(=CC(=C2)Cl)Cl,46 +CCCN(CCCl)C1=C(C=C(C=C1[N+](=O)[O-])C(F)(F)F)[N+](=O)[O-],202.4 +C1=CC=C(C=C1)C2=CC=CC=C2O,1000 +O=C(N(C)C)Nc(cccc1C(F)(F)F)c1,15 +C1=CC(=NC(=C1)Cl)C(Cl)(Cl)Cl,1 +Clc1cc(Cl)cc(Cl)c1OCCN(CCC)C(=O)n2cncc2,7.5 +CC1=CC(=C(C=C1NC(=O)C)NS(=O)(=O)C(F)(F)F)C,27.6 +C(=C(I)I)(I)I,50 +C1=C(C=C(C(=C1Cl)N2C(=C(C(=N2)C#N)S(=O)C(F)(F)F)N)Cl)C(F)(F)F,0.06 +O=C(N(C)C)Nc(ccc(c1Cl)Cl)c1,6.25 +CC1=C(C(=O)CC1OC(=O)C2C(C2(C)C)C=C(C)C)CC=C,24.5 +CC1=CC2=C(C=C1)N=C3C(=N2)SC(=O)S3,7.5 +CC(C)N(C(=O)CCl)c1ccccc1,23 +CC(C)C1(C(=O)NC(=N1)C2=C(C=CC=N2)C(=O)O)C,500 +CC1(C(C1(C)C)C(=O)OC(C#N)C2=CC(=CC=C2)OC3=CC=CC=C3)C,19.45 +CN1CN(C(=S)SC1)C,30 +ClC(Cl)=CC1C(C)(C)C1C(=O)OC(C(#N))c2cccc(Oc3ccccc3)c2,75 +ClC2C1OC1C3C2C4(Cl)C(=C(Cl)C3(Cl)C4(Cl)Cl)Cl,0.2 +CCOC(=O)CN1C2=C(C=CC=C2Cl)SC1=O,12.5 +CCCN(CCC)C1=C(C=C(C(=C1[N+](=O)[O-])N)C(F)(F)F)[N+](=O)[O-],29.4 +C1=CC=C(C=C1)C(CCC2=CC=C(C=C2)Cl)(CN3C=NC=N3)C#N,40 +CC(C)(C)C(CCC1=CC=C(C=C1)Cl)(CN2C=NC=N2)O,15.9 +CC1=C(C=CC=C1COC(=O)C2C(C2(C)C)C=C(C(F)(F)F)Cl)C3=CC=CC=C3,5 +C(=CC=C1)(C2=C1)NC(=N2)C(=CS3)N=C3,40 +C1=C(C=C(C(=C1Cl)N)Cl)[N+](=O)[O-],150 +CC1=C(C=C(C=C1C(=O)N)[N+](=O)[O-])[N+](=O)[O-],6.25 +CC(C)OC1=CC=CC(=C1)NC(=O)C2=CC=CC=C2C(F)(F)F,500 +OC(c1ccc(Cl)cc1)(c2ccc(Cl)cc2)C(Cl)(Cl)Cl,2.5 +O=P(O)(O)CCCl,446 +CN(C(=O)NC1=CC=C(C=C1)Br)OC,12.5 +CC1=CC(=CC=C1)NC(=O)OC2=CC=CC(=C2)NC(=O)OC,25 +CC(C)(C)C1=NN=C(S1)N2C(CN(C2=O)C)O,50 +S=P(OCC)(OCC)Oc1ccc2C(C)=C(Cl)C(=O)Oc2c1,1.7 +COC(=O)c1ccccc1S(=O)(=O)NC(=O)N(C)c2nc(OC)nc(C)n2,12.5 +C1=CC=C(C(=C1)NC2=NC(=NC(=N2)Cl)Cl)Cl,1.15 +CC1=C(C=CC(=C1)OP(=S)(OC)OC)[N+](=O)[O-],0.46 +COc1c(Cl)ccc(Cl)c1C(=O)(O),115 +CC1(C(C1C(=O)OC(C#N)C2=CC(=CC=C2)OC3=CC=CC=C3)C=C(Br)Br)C,2.5 +C1=CC=C(C(=C1)C(C2=CC=C(C=C2)F)(C3=CN=CN=C3)O)Cl,2.5 +c1ccc2nc(NC(=O)OC)n(C(=O)NCCCC)c2c1,115 +CCOC(=O)COC(=O)C1=C(C=CC(=C1)OC2=C(C=C(C=C2)C(F)(F)F)Cl)[N+](=O)[O-],25 +CC(C)(C)C(C(N1C=NC=N1)OC2=CC=C(C=C2)C3=CC=CC=C3)O,25 +CCNC(=O)NC(=O)C(=NOC)C#N,30.3 +CCOC1=C(C=CC(=C1)OC2=C(C=C(C=C2)C(F)(F)F)Cl)[N+](=O)[O-],40 +CC1=NC=C(N1CCO)[N+](=O)[O-],150 +O=C(N(SC(Cl)(Cl)Cl)C(=O)c1cccc2)c12,500 +CC(C)(C)c2ccc(OC1CCCCC1OS(=O)OCC#C)cc2,100 +CCCCC(CN1C=NC=N1)(C2=C(C=C(C=C2)Cl)Cl)O,4.7 +CC(C)(C)C(C(=CC1=C(C=C(C=C1)Cl)Cl)N2C=NC=N2)O,50 +C1=CC(C2C1C3(C(=C(C2(C3(Cl)Cl)Cl)Cl)Cl)Cl)Cl,0.38 +C1=CC=C2C(=C1)C(=O)C3=C(C2=O)SC(=C(S3)C#N)C#N,10 +CC1=NN(C(=C1C=NOCC2=CC=C(C=C2)C(=O)OC(C)(C)C)OC3=CC=CC=C3)C,3.08 +CS(=O)(=O)C1=C(C=CC(=C1)C(F)(F)F)C(=O)C2=C(ON=C2)C3CC3,20 +CC1=C(N=C(N=C1OC(=O)N(C)C)N(C)C)C,12.5 +CCN(CC)C(=O)C(Cl)=C(C)OP(=O)(OC)OC,1.5 +C1=CC(=CC=C1C(CN)O)O,250 +CC1=C(C(=CC=C1)C)N(C(=O)COC)N2CCOC2=O,50 +c1c(C(F)(F)F)cccc1N2C(=O)C(Cl)=C(NC)C=N2,18.75 +CCC(C)NC1=C(C=C(C=C1[N+](=O)[O-])C(C)(C)C)[N+](=O)[O-],50 +C1=CC(=CC=C1S(=O)(=O)C2=CC(=C(C=C2Cl)Cl)Cl)Cl,230 +CCCCC1=C(NC(=NC1=O)NCC)C,25 +n(c(nc(n1)NCC)NCC)c1Cl,5.3 +FC(F)(F)C(C=C1N(=O)=O)=CC(N(=O)=O)=C1N(CC)CC(C)=C,12.5 +C1CCC(C1)N(CC2=CC=C(C=C2)Cl)C(=O)NC3=CC=CC=C3,25 +CS(=O)(=O)NC(=O)C1=C(C=CC(=C1)OC2=C(C=C(C=C2)C(F)(F)F)Cl)[N+](=O)[O-],50 +CCOC(=O)C(C)OC1=CC=C(C=C1)OC2=NC3=C(O2)C=C(C=C3)Cl,9 +CCC1=C(C(=CC=C1)CC)N(CNC(=O)C)C(=O)CCl,62.5 +NC(=N)NCCCCCCCCCCCC(OC(=O)C),29 +C1=CC(=CC(=C1)Cl)NC(=O)OCC#CCCl,450 +CC(C)C(C(=O)OC(C(#N))c2cccc(Oc1ccccc1)c2)c3ccc(Cl)cc3,25 +CC(C)C1=C(C=CC(=C1)C(C)(C)C2=CC(=C(C=C2)O)C(C)C)O,25 +CCN(CC1=C(C=CC=C1Cl)F)C2=C(C=C(C=C2[N+](=O)[O-])C(F)(F)F)[N+](=O)[O-],50 +CCCCCCCCSC(=O)OC1=CC(=NN=C1C2=CC=CC=C2)Cl,67.5 +CC1=C(C(=O)CC1OC(=O)C2C(C2(C)C)C=C(C)C)CC=C,13.8 +CCCCNC(=O)N1C2=CC=CC=C2N=C1NC(=O)OC,250 +CC1=C(C(=CC=C1)C)N(C(C)C(=O)OC)C(=O)CC2=CC=CC=C2,46 +CC(C)C(C1=CC=C(C=C1)OC(F)F)C(=O)OC(C#N)C2=CC(=CC=C2)OC3=CC=CC=C3,6 +Clc1ccccc1c2nnc(c3ccccc3Cl)nn2,20 +CCOC(=O)NCCOC1=CC=C(C=C1)OC2=CC=CC=C2,10 +CCC1=C(C(=CC=C1)CC)N(CC(=O)OCC)C(=O)CCl,50 +c1(O2)c(CC2(C)C)cccc1OC(=O)N(C)SN(CCCC)CCCC,25 +CCCCOC(=O)C(C)OC1=CC=C(C=C1)OC2=NC=C(C=C2)C(F)(F)F,3 +COC1=CC(=C(C=C1Cl)OC)Cl,125 +CCOP(=S)(OCC)OC1=NN(C(=N1)Cl)C(C)C,12.5 +n(c(nc(n1)NC(C)C)NCC)c1Cl,25 +CC(C)(C)C(C(=CC1=CC=C(C=C1)Cl)N2C=NC=N2)O,39.41 +CCCCCCCCc1cc(N(=O)(=O))c(OC(=O)C=CC)c(c1)N(=O)(=O),50 +c1cc(OC(F)(F)F)ccc1C(O)(C(C)C)c2cncnc2,12.1 +COP(=O)(C(C(Cl)(Cl)Cl)O)OC,20 +C1=CC(=C(C=C1C(F)(F)F)Cl)OC2=CC(=C(C=C2)[N+](=O)[O-])C(=O)O,125 +CCCN(CC1CC1)C2=C(C=C(C=C2[N+](=O)[O-])C(F)(F)F)[N+](=O)[O-],5 +CCOC(=O)C(C)OC(=O)C1=C(C=CC(=C1)OC2=C(C=C(C=C2)C(F)(F)F)Cl)[N+](=O)[O-],50 +CCSC(=O)N1CCCCCC1,14.81 +CCC1=CC=C(C=C1)C(=O)NN(C(=O)C2=CC(=CC(=C2)C)C)C(C)(C)C,48 +ClC(Cl)C(Cl)(Cl)SN2C(=O)C1CC=CCC1C2(=O),15 +COC(=O)C1=CC=CC=C1S(=O)(=O)NC(=O)NC2=NC(=CC(=N2)OC(F)F)OC(F)F,140 +CC(C)(C)C(C(N1C=NC=N1)OC2=CC=C(C=C2)Cl)O,25 +CC1=C(C=CC(=C1)Cl)OCC(=O)O,4 +COC=C(C1=CC=CC=C1OC2=NC=NC(=C2)OC3=CC=CC=C3C#N)C(=O)OC,62.25 +C1=CC=C(C(=C1)C(C2=CC=C(C=C2)Cl)(C3=CN=CN=C3)O)Cl,2.3 +[O-]Br(=O)=O,6.1 +OP(=O)OCC,400 +COP(N)(=O)SC,0.1 +CCOP(=O)(NC(C)C)Oc1ccc(SC)c(C)c1,1.5 +CCOP(=S)(OCC)SCCSCC,0.04 +CCOP(=S)(OCC)SCSP(=S)(OCC)OCC,2 +O=C(OCC(CCCC)CC)CCCCC(=O)OCC(CCCC)CC,1500 +CN(C=Nc1ccc(C)cc1C)C=Nc2ccc(C)cc2C,10 +[C@@]14([C@@H]5OCC1=CC=C[C@@H]([C@H](O[C@H]2C[C@@H]([C@H]([C@@H](O2)C)O[C@H]3C[C@@H]([C@H]([C@@H](O3)C)O)OC)OC)C(=CC[C@@H]6C[C@H](OC([C@@H]4C=C([C@H]5O)C)=O)C[C@]7(O6)O[C@@H]([C@H](C=C7)C)[C@H](CC)C)C)C)O,2 +O=C(N(S(=O)(=O)Nc1cccc2)C(C)C)c12,35 +S=P(OC)(OC)SCN1C(=O)SC(OC)=N1,1.25 +C(#N)Cl,70 +C(#N)Br,122 +C1=CC(=CC=C1C(C2=CC=C(C=C2)Cl)C(Cl)(Cl)Cl)Cl,0.25 +c(cccc1)(c1)C(C)C,331 +CCCN(CCC)C(=O)SCC,25 +NC(CCCC1)C1,60 +ClC1CC2C(C1Cl)C3(Cl)C(=C(Cl)C2(Cl)C3(Cl)Cl)Cl,6 +CC(C)OC(=O)NC1=CC(=CC=C1)Cl,1000 +COC(=O)c1c(Cl)c(Cl)c(C(=O)OC)c(Cl)c1Cl,10 +COC(=O)C1=CC=C(C=C1)C(=O)OC,125 +N(C(=S)NC1)C1,0.25 +O=C(N(OC)C)Nc(ccc(c1Cl)Cl)c1,2.5 +c(cccc1)(c1)C=C,285 +COC(=O)c1ccccc1S(=O)(=O)NC(=O)Nc2nc(OC)nc(C)n2,250 +C1=CC(=CC=C1N)Cl,12.5 +FC(F)(F)C(Cl)=CC1C(C)(C)C1C(=O)OC(C(#N))c2cc(Oc3ccccc3)ccc2,12.5 +C(Cl)(Br)Br,28.5 +C=C(Cl)Cl,14 +C(C=CCl)Cl,5.1 +COP(=O)(OC)OC(=CCl)c1cc(Cl)c(Cl)cc1Cl,50 +Oc(ccc(c1)C(c(ccc(O)c2)c2)(C)C)c1,50 +O=C(OCc(cccc1)c1)c(c(ccc2)C(=O)OCCCC)c2,470 +O=C(NCCCC1)C1,125 +c(cccc1)(c1)Cl,120 +C(Cl)(Cl)Cl,60 +ClCCl,52.58 +C1C2C3C(C1C4C2O4)C5(C(=C(C3(C5(Cl)Cl)Cl)Cl)Cl)Cl,0.125 +OCCO,1000 +O=C(C=C(CC1(C)C)C)C1,179 +C(F)(Cl)(Cl)Cl,349 +CCc1cccc(CC)c1N(COC)C(=O)CCl,14 +c1ccccc1c2c(C)c(COC(=O)C3C(C)(C)C3C=C(Cl)C(F)(F)F)ccc2,5 +n1c(Cl)cc(OC)nc1NC(=O)NS(=O)(=O)c2ccccc2C(=O)OCC,125 +O=C(NC(=O)c(c(F)ccc1)c1F)Nc(ccc(c2)Cl)c2,7.8 +c(cccc1)(c1)CC,291 +O=C(N(SC(Cl)(Cl)Cl)C(=O)c1cccc2)c12,40 +Clc1cc(C(F)(F)F)cnc1Oc2ccc(OC(C)C(=O)OC)cc2,1 +C#N,31 +ClC(C(OC(C=C2C(=O)OC(C)C(=O)OCC)=CC=C2N(=O)=O)=C1)=CC=C1C(F)(F)F,50 +c1c(C(F)(F)F)cccc1N2C(=O)C(Cl)=C(NC)C=N2,51.25 +O=N(=O)C(C(=C1N(=O)=O)N(C(C)C)C(C)C)=CC(=C1)S(=O)(=O)N,45 +CN(=CC=C1C(C=C2)=CC=N2C)C=C1,3.75 +C1=C(C=C(C=C1[N+](=O)[O-])[N+](=O)[O-])[N+](=O)[O-],13.31 +C(=C)Cl,1.3 +C1CCC(=O)CC1,910 +CC1(C(C1(C)C)C(=O)OC(C#N)C2=CC(=CC=C2)OC3=CC=CC=C3)C,25 +C1=CC(=O)NNC1(=O),500 +CCSC(=O)N1CCCCCC1,2 +C(C(Cl)(Cl)Cl)(O)O,135 +ClC2C1OC1C3C2C4(Cl)C(=C(Cl)C3(Cl)C4(Cl)Cl)Cl,0.025 +Clc1cc(C(F)(F)F)ccc1Oc2cc(OCC)c(N(=O)(=O))cc2,10 +c1cc(Cl)ccc1C(C(#N))(CCCC)Cn2ncnc2,9.84 +CC1=C(C=C(C=C1[N+](=O)[O-])[N+](=O)[O-])[N+](=O)[O-],2 +CC(C)OC(=O)C(C1=CC=C(C=C1)Br)(C2=CC=C(C=C2)Br)O,26 +C[N+](C)(C)CCCl,130 +CCC(=C1C(=O)CC(CC1=O)CC(C)SCC)NOCC=CCl,86 +CC1=NC(=NC(=C1)C2CC2)NC3=CC=CC=C3,35.6 +N(c(cccc1)c1)c(cccc2)c2,25 +CC1(C(=O)N(C(=O)O1)NC2=CC=CC=C2)C3=CC=C(C=C3)OC4=CC=CC=C4,16.8 +CC1(CCCCC1)C(=O)NC2=C(C(=C(C=C2)O)Cl)Cl,292 +C1=CC(=C2C(=C1)OC(O2)(F)F)C3=CNC=C3C#N,110 +C(F)(F)(F)c1ccccc1C(=O)Nc2cccc(OC(C)C)c2,87 +C(CCCCN=C(N)N)CCCNCCCCCCCCN=C(N)N,19 +C1CN(C(=N1)N[N+](=O)[O-])CC2=CN=C(C=C2)Cl,17 +COC(=O)C12CC3=C(C1=NN(CO2)C(=O)N(C4=CC=C(C=C4)OC(F)(F)F)C(=O)OC)C=CC(=C3)Cl,3.6 +CC1=CC=CC=C1OCC2=CC=CC=C2C(=NOC)C(=O)OC,370 +CC1=CC(=CC(=C1)C(=O)N(C(C)(C)C)NC(=O)C2=C(C(=CC=C2)OC)C)C,411 +C1=CC(=C(C(=C1)F)C(=O)NC(=O)NC2=CC(=C(C=C2)OC(C(OC(F)(F)F)F)(F)F)Cl)F,36 +CC1=CC=C(C=C1)N(SC(F)(Cl)Cl)S(=O)(=O)N(C)C,18 +CC(C)(C)C1=C(C=CC(=C1)O)O,225 +CC(=NOCC1=CC=CC=C1C(=NOC)C(=O)OC)C2=CC(=CC=C2)C(F)(F)F,60 +COC(=O)N(C1=CC=CC=C1COC2=NN(C=C2)C3=CC=C(C=C3)Cl)OC,9 +CC(C)N1C(=NC(C)(C)C)SCN(C1=O)C2=CC=CC=C2,8.7 +C1=CC=C(C(=C1)C2=NN=C(N=N2)C3=CC=CC=C3Cl)Cl,17.3 +CCCC(=C1C(=O)CC(CC1=O)C2CCCSC2)NOCC,28 +C1CC1NC2=NC(=C(C(=N2)N)C#N)N,22 +C(C=C1)(=N(C=C1)CC2)C(N2=C3)=CC=C3,0.57 +C1=CC=C2C(=C1)C(=O)C3=C(C2=O)SC(=C(S3)C#N)C#N,6 +CCOC1=CC2=C(C=C1)NC(C=C2C)(C)C,12 +C1=CC=C(C=C1)C(CCC2=CC=C(C=C2)Cl)(CN3C=NC=N3)C#N,30 +CC1CN(CC(O1)C)CC(C)CC2=CC=C(C=C2)C(C)(C)C,1.7 +C[Si](CN1C=NC=N1)(C2=CC=C(C=C2)F)C3=CC=C(C=C3)F,2 +c1cc(Cl)cc(Cl)c1C(OCC=C)Cn2cncc2,15 +CN(=CC=C1C(C=C2)=CC=N2C)C=C1,2.55 +CCCCOCCOCCOCC1=CC2=C(C=C1CCC)OCO2,100 +Clc1cc(Cl)ccc1C2(Cn3ncnc3)OC(CCC)CO2,96 +C(=CC=C1)(C2=C1)NC(=N2)C(=CS3)N=C3,30 +CCOC1=CC=C(C=C1)C(C)(C)COCC2=CC(=CC=C2)OC3=CC=CC=C3,26 +CC(C)(C)c2ccc(OC1CCCCC1OS(=O)OCC#C)cc2,19 +CC(COC1=CC=C(C=C1)OC2=CC=CC=C2)OC3=CC=CC=N3,140 +CC(C)(C)C(=O)C(N1C=NC=N1)OC2=CC=C(C=C2)Cl,114 +CC(C)(C)C(C(N1C=NC=N1)OC2=CC=C(C=C2)Cl)O,105 +c1ccccc1c2c(C)c(COC(=O)C3C(C)(C)C3C=C(Cl)C(F)(F)F)ccc2,8 +CC1(C(C1C(=O)OC(C#N)C2=CC(=C(C=C2)F)OC3=CC=CC=C3)C=C(Cl)Cl)C,6 +CC1(C(C1C(=O)OC(C#N)C2=CC(=C(C=C2)F)OC3=CC=CC=C3)C=C(Cl)Cl)C,12 +ClC(Cl)=CC1C(C)(C)C1C(=O)OC(C(#N))c2cccc(Oc3ccccc3)c2,50 +ClC1CC2C(C1Cl)C3(Cl)C(=C(Cl)C2(Cl)C3(Cl)Cl)Cl,0.25 +ClC4=C(Cl)C5(Cl)C3C1CC(C2OC12)C3C4(Cl)C5(Cl)Cl,0.1 +C1C2C3C(C1C4C2O4)C5(C(=C(C3(C5(Cl)Cl)Cl)Cl)Cl)Cl,0.25 +C1(C(C(C(C(C1Cl)Cl)Cl)Cl)Cl)Cl,4.7 +CCC(=O)Nc1ccc(Cl)c(Cl)c1,76 +C1(=C(C(=C(C(=C1Cl)Cl)Cl)Cl)Cl)[N+](=O)[O-],140 +C1C2C(COS(=O)O1)C3(C(=C(C2(C3(Cl)Cl)Cl)Cl)Cl)Cl,2.9 +O=C(N(SC(Cl)(Cl)Cl)C(=O)c1cccc2)c12,50 +CC(C(=O)O)OC1=CC=C(C=C1)OC2=C(C=C(C=N2)C(F)(F)F)Cl,0.1 +CCCCC(CN1C=NC=N1)(C#N)C2=CC=C(C=C2)Cl,9.8 +Clc1cc(Cl)cc(Cl)c1OCCN(CCC)C(=O)n2cncc2,5.1 +COP(=O)(NC(=O)(C))SC,2.5 +CCOP(=O)(OCC)OC(=CCl)C1=C(C=C(C=C1)Cl)Cl,1.5 +CCOP(=S)(OCC)SCCSCC,0.22 +O=P(O)(O)CCCl,12 +CCCSP(=O)(OCC)SCCC,2.7 +CCOP(=O)(NC(C)C)Oc1ccc(SC)c(C)c1,1.7 +COP(=S)(OC)Oc1ccc(SC)c(C)c1,0.72 +OC(=O)C(N)CCP(C)(=O)O,3.5 +OC(=O)CNCP(O)(O)=O,300 +CCOC(=O)CC(SP(=S)(OC)OC)C(=O)OCC,360 +COP(N)(=O)SC,0.29 +CC(=CC(=O)OC)OP(=O)(OC)OC,0.35 +CCOP(=S)(OCC)SCSCC,0.16 +CCOP(=S)(OCC)SCSC(C)(C)C,0.06 +S=P(OC)(OC)SCN1N=Nc2ccccc2C1(=O),2.58 +CCOP(=S)(OCC)OC1=NC(=C(C=C1Cl)Cl)Cl,1 +CCOP(=S)(OCC)OC1=NC(=NC(=C1)C)C(C)C,5.8 +CCC1=NC(=CC(=N1)OP(=S)(OC)OC)OCC,0.45 +S=P(OC)(OC)SCN1C(=O)SC(OC)=N1,1.6 +CCOP(=S)(OCC)SCN1C2=C(C=C(C=C2)Cl)OC1=O,2 +COP(=S)(OC)SCN2C(=O)c1ccccc1C2(=O),9 +CCOC(=O)C1=CN2C(=CC(=N2)OP(=S)(OCC)OCC)N=C1C,4 +CCOP(=S)(OCC)OC1=NN(C=N1)C2=CC=CC=C2,1.3 +O=C(Oc(c(c(ccc1)cc2)c1)c2)NC,60 +CC1=CC(=CC(=C1SC)C)OC(=O)NC,9.3 +CNC(=O)ON=C(C)SC,20 +CCCOC(=O)NCCCN(C)C,680 +COC(=O)NC1=NC2=CC=CC=C2N1,75 +CC1=C(N=C(N=C1OC(=O)N(C)C)N(C)C)C,12.3 +CNC(=O)CCSCCSP(=O)(OC)OC,0.54 +N(C(=S)SSC(N(C)C)=S)(C)C,12 +C1=NNC(=N1)N,5 +CCCCCCCCc1cc(N(=O)(=O))c(OC(=O)C=CC)c(c1)N(=O)(=O),64 +C1=CC=C(C=C1)[Sn](C2=CC=CC=C2)C3=CC=CC=C3,0.3 +O=C(NC(=O)c(c(F)ccc1)c1F)Nc(ccc(c2)Cl)c2,7 +N(C(=S)NC1)C1,1.25 +C1=CC(=C(C(=C1)F)C(=O)NC(=O)NC2=CC(=C(C(=C2F)Cl)F)Cl)F,25 +CCCSC1=CC2=C(C=C1)N=C(N2)NC(=O)OC,20 +C1CN(CCN1CCCC(=O)C2=CC=C(C=C2)F)C3=CC=CC=N3,115 +CC1(C2C(C3C(C(=O)C(=C(N)O)C(=O)C3(C(=O)C2=C(C4=C(C=CC(=C41)Cl)O)O)O)N(C)C)O)O,5200 +CC1=CC(=C(C=C1NC(=O)C2=CC(=CC(=C2O)I)I)Cl)C(C#N)C3=CC=C(C=C3)Cl,10 +CN1CC2CC1CN2C3=C(C=C4C(=C3)N(C=C(C4=O)C(=O)O)C5CC5)F,50 +C1=CC(=CC=C1C(C#N)C2=C(C=CC(=C2Cl)N3C(=O)NC(=O)C=N3)Cl)Cl,15 +CC1=NC=C(N1C)[N+](=O)[O-],15 +CCN1CCN(CC1)C2=C(C=C3C(=C2)N(C=C(C3=O)C(=O)O)C4CC4)F,26 +CC1C=CC=C2COC3C2(C(C=C(C3O)C)C(=O)OC4CC(CC=C(C1OC5CC(C(C(O5)C)OC6CC(C(C(O6)C)NC(=O)C)OC)OC)C)OC7(C4)C=CC(C(O7)C(C)C)C)O,1 +COCC(=O)NC1=C(C=CC(=C1)SC2=CC=CC=C2)NC(=NC(=O)OC)NC(=O)OC,40 +CC1CCC2=C3N1C=C(C(=O)C3=CC(=C2)F)C(=O)O,400 +COC(=O)NC1=NC2=C(N1)C=C(C=C2)S(=O)C3=CC=CC=C3,2 +CC1(C2CC3C(C(=O)C(=C(N)O)C(=O)C3(C(=O)C2=C(C4=C1C=CC=C4O)O)O)N(C)C)O,150 +C1CN(CCN1CCCC(=O)C2=CC=C(C=C2)F)C3=CC=CC=N3,30 +CC(C)NCC(COC1=CC=CC2=C1C3=CC=CC=C3N2)O,7 +C1=CC(=CC=C1C(C#N)C2=C(C=CC(=C2Cl)N3C(=O)NC(=O)C=N3)Cl)Cl,23 +CC1C=CC=C2COC3C2(C(C=C(C3O)C)C(=O)OC4CC(CC=C(C1OC5CC(C(C(O5)C)OC6CC(C(C(O6)C)NC(=O)C)OC)OC)C)OC7(C4)C=CC(C(O7)C(C)C)C)O,2.5 +COP(=S)(OC)Oc1ccc(SC)c(C)c1,0.45 +C(C(C(C(C1Cl)Cl)Cl)Cl)(C1Cl)Cl,8 +C(C(C(C(C1Cl)Cl)Cl)Cl)(C1Cl)Cl,4 +CC(N(C)C)CN(C(=CC=C3)C1=C3)C(=CC=C2)C(=C2)S1,16.6 +C1=C(C=C(C(=C1Cl)N)Cl)[N+](=O)[O-],240 +c(cccc1)(c1)C=C,400 diff --git a/regression/LOAEL_mg_corrected_smiles_mmol.csv b/regression/LOAEL_mg_corrected_smiles_mmol.csv new file mode 100644 index 0000000..921a53b --- /dev/null +++ b/regression/LOAEL_mg_corrected_smiles_mmol.csv @@ -0,0 +1,568 @@ +SMILES,LOAEL_mmol_kg_bw_day +C1=C(C(=CC(=C1NN=C3C2=C(C=C([S]([O-])(=O)=O)C=C2)C=CC3=O)OC)[S]([O-])(=O)=O)C.[Na+].[Na+],7.531899781214326 +O1C(=O)C(O)=C(O)C1C(O)CO,17.323010613197102 +C1(C)=C(C=CC(C)=CC=CC(C)=CC=CC=C(C)C=CC=C(C)C(=O)OC)C(C)(C)CCC1,1.119409718240544 +c(cccc1)(c1)C(C)C,3.8438632722857955 +O=C(OCCCC)c(c(ccc1)C(=O)OCCCC)c1,2.1556100397968727 +O=C(OCC)c(c(ccc1)C(=O)OCC)c1,19.95615854702247 +O=C(OC(OC(OC1C)C)C1)C,0.7175892491582392 +Oc(c(ccc1)C)c1C,0.04911414454620167 +Oc(ccc(c1C)C)c1,0.1145996706078039 +O=C(OCC)C=C,2.477130986890983 +c(cccc1)(c1)CC,3.843074459567654 +OCCO,4.027850816139244 +c(ccc1C(=O)OCC(=O)OCC)cc1C(=O)OCC,8.919866912731305 +O=C,2.73096831477274 +O=C(O)C=CC(=O)O,9.313172081918696 +OCC(O)CO,74.73899985905678 +O=C(OC)c(ccc(O)c1)c1,9.858865736182537 +O=C(OCCC)c(ccc(O)c1)c1,8.324062177858794 +CC(CCC(=O)(O))C3CCC4C2CCC1CC(O)CCC1(C)C2CCC34C,1.3277652171188237 +OC(C(CCC1C)C(C)C)C1,3.7948308388559964 +O=C(O)C(=C)C,2.8807316686731115 +O=C(OC)c(c(O)ccc1)c1,2.366127776683809 +Oc(cccc1)c1,3.655248831064175 +O=C(OCCC)c(cc(O)c(O)c1O)c1,4.071644352421931 +OCC(O)C1C(O)=C(O)C(=O)O1,8.82332300652517 +c(cccc1)(c1)C=C,0.20163396483810905 +O=Cc(occ1)c1,0.624453213155231 +NCCNc1cccc2ccccc12,0.4241543329029509 +CN(C)(C)CCCl,2.2427665071284903 +O=C(Nc(ccc(c1)C(=O)CCl)c1)C,7.465334624174738 +c(ccc(c1)Cl)(c1)C(c(ccc(c2)Cl)c2)C(Cl)(Cl)Cl,0.09027148189044054 +CC(Oc1cc(Cl)c(Cl)cc1Cl)C(=O)(O),0.03228091610123117 +O=N(=O)C(=CC=C1OC)C=C1N=NC(C(O)=C2C(=O)NC(=CC=C4)C=C4N(=O)=O)=C(C=C3)C(=C2)C=C3,4.308389780762046 +O=N(=O)C(C=C1)=CC(OCCO)=C1NCCO,0.9453881078267568 +Cc1cccc(CC)c1N(C(=O)CCl)COCC,0.18534506246313948 +C1=C(C(=CC=C1OC2=CC=C(C=C2Cl)C(F)(F)F)[N+](=O)[O-])C(=O)[O-].[Na+],0.46919094173712006 +CCc1cccc(CC)c1N(COC)C(=O)CCl,0.05560351873894184 +O=C(Nc(ccc(OCC)c1N)c1)C,6.1010029534002825 +Oc(ccc(N)c1)c1,6.286318149278613 +CC(N)CC(=CC=C1)C=C1,0.036980547196719206 +O(c(ccc(c1)C=CC)c1)C,2.3211612715861247 +COc1ccc(N)cc1,3.8488877932280037 +O=C(O)c(c(N)ccc1)c1,20.060380944519448 +Clc2cccc(c2)c1ccccc1,0.021202965065040626 +O=C(NC(C(=O)OC)Cc(cccc1)c1)C(N)CC(=O)O,0.4994850207500349 +n1c2ccc(Cl)cc2ncc1Oc3ccc(OC(C)C(=O)OCC)cc3,0.009924832004782804 +COC(=O)NS(=O)(=O)c1ccc(N)cc1,0.7817895162025876 +S=P(OC)(OC)SCN1N=Nc2ccccc2C1(=O),0.0011344859332252924 +CNC(=O)Oc1ccccc1OC(C)C,0.23895810443138246 +CC(C)(C)C(=O)C(Oc1ccc(Cl)cc1)n2cncn2,0.08510674803234901 +O=S(O)(=O)C(=CC=C1)C=C1CN(CC)=C(C=C2)C=CC2=C(C(C=C3)=CC=C3N(C)C)C(C=C4)=CC=C4N(CC)CC(C=C5)=CC(=C5)S(=O)(=O)O,1.009963174498295 +c(c(cccc1)c1)(cccc2)c2,1.6211890708511503 +BrC(Cl)Cl,0.7935120501519148 +ClC(Cl)C(Cl)(Cl)SN2C(=O)C1CC=CCC1C2(=O),0.034377949341570596 +O=C(Oc(c(c(ccc1)cc2)c1)c2)NC,0.07752660703214034 +CC1=C(SCCO1)C(=O)Nc2ccccc2,0.1274956638724717 +ClC1CC2C(C1Cl)C3(Cl)C(=C(Cl)C2(Cl)C3(Cl)Cl)Cl,0.0006588923229380624 +O=C(O)CCl,0.317470328693963 +ClC(=CC=C1N)C=C1,0.047032433723070206 +CC(C)OC(=O)C(O)(c1ccc(Cl)cc1)c2ccc(Cl)cc2,0.026531991066147967 +n1c(OC)nc(C)nc1NC(=O)NS(=O)(=O)c2ccccc2Cl,0.06987675250196507 +OS(=O)(=O)C(C(=CC=C2)C1=C2)=CC=C1N=NC(C(O)=C3N=NC(C(C=C5)=C4C=C5)=CC=C4S(O)(=O)=O)=CC(=C3O)CO,1.2093346835379808 +S=P(OCC)(OCC)Oc1ccc2C(C)=C(Cl)C(=O)Oc2c1,0.0022052807653206367 +CNP(=O)(OC)Oc1ccc(cc1Cl)C(C)(C)C,0.013712205220154254 +C(C1C2C(C(O)C(O1)OC8C(OC(OC7C(OC(OC6C(OC(OC5C(C(C(OC4C(C(C(OC3C(C(C(O2)OC3CO)O)O)OC4CO)O)O)OC5CO)O)O)C(C6O)O)CO)C(C7O)O)CO)C(C8O)O)CO)O)O,1.4097112541302337 +n1c(N)nc(N)nc1NC2CC2,0.09026150563412319 +COC(=O)c1c(Cl)c(Cl)c(C(=O)OC)c(Cl)c1Cl,1.5061863289853148 +O=C(O)C(Cl)(Cl)C,0.1970361896096669 +Nc1cc(N)c(O)cc1,0.2013846888993215 +FC(F)(Cl)Cl,1.2405561628307704 +ClCCl,0.5887022388817106 +O=P(OC)(OC)OC=C(Cl)Cl,0.010408382386229365 +OC(c1ccc(Cl)cc1)(c2ccc(Cl)cc2)C(Cl)(Cl)Cl,0.05398319600278186 +ClC4=C(Cl)C5(Cl)C3C1CC(C2OC12)C3C4(Cl)C5(Cl)Cl,0.0001312648375209092 +CN(=C1C(C=C2)=CC=C2)N(C)C(=C1)C(C=C3)=CC=C3,0.49533572071941767 +O=C(NC(=O)c(c(F)ccc1)c1F)Nc(ccc(c2)Cl)c2,0.025749696789273527 +CC1=C(C)S(=O)(=O)CCS1(=O)=O,0.047557630336441704 +O=C(NC)CSP(OC)(OC)=S,0.001090477150926923 +COc1ccc(N)c(OC)c1,1.8018201517132568 +COP(=O)OC,0.9086866261501474 +CC(=C(N(=O)=O)C=C1N(=O)=O)C=C1,0.1866762157041476 +CN(C)C(=O)C(c1ccccc1)c2ccccc2,0.1253592168358431 +N(c(cccc1)c1)c(cccc2)c2,0.1831908345016181 +C(C=C1)(=N(C=C1)CC2)C(N2=C3)=CC=C3,0.002984821462389602 +CCOP(=S)(OCC)SCCSCC,0.00036442614798427517 +NC(=S)NNC(N)=S,6.303842268414009 +O=C(N(C)C)Nc(ccc(c1Cl)Cl)c1,0.02574063309087087 +O=P(O)(O)CCCl,1.0381053884590363 +O=C(OCC)C(O1)C1(c(cccc2)c2)C,0.8485352051922984 +COC(=O)NC(=NC1=C2)NC1=CC(=C2)SC(C=C3)=CC=C3,0.050108966959550236 +CN1C=C(c2ccccc2)C(=O)C(c3cc(C(F)(F)F)ccc3)=C1,0.07591497971688389 +c1cc(C(F)(F)F)cc(Cl)c1NC(C(C)C)C(=O)OC(C(#N))c2cccc(Oc3ccccc3)c2,0.004971041792562443 +S=P(OCC)(Sc1ccccc1)CC,0.006414179135682054 +n1c(C)nc(OC)nc1NC(=O)NS(=O)(=O)c2ccsc2C(=O)OC,0.06453419527613821 +C(C(C(C(C1Cl)Cl)Cl)Cl)(C1Cl)Cl,0.017192183580611947 +O=N(=O)N(CN1N(=O)=O)CN(C1)N(=O)=O,0.006753217705640206 +O=C(N=C(N(C1(=O))C)N(C)C)N1C(CCCC2)C2,0.19816672003956992 +n(c(c(ccc1)cc2)c1O)c2,0.9851335765350275 +c1cc(Cl)cc(Cl)c1C(OCC=C)Cn2cncc2,0.13459866849613178 +COc1cccc(OC)c1C(=O)Nc2onc(C(C)(CC)CC)c2,0.15252975563710267 +n1c(OC)cc(OC)nc1NC(=O)NS(=O)(=O)Cc2ccccc2C(=O)OC,0.7529208210920754 +CCOC(=O)CC(SP(=S)(OC)OC)C(=O)OCC,0.1513509494941276 +CN(C)(CCC1)CC1,1.3133857473480115 +O=P(SCCCC)(SCCCC)SCCCC,0.003974424546249488 +COCC(=O)N(C(C)C(=O)OC)c1c(C)cccc1C,0.22374845318219344 +S=P(OC)(OC)SCN1C(=O)SC(OC)=N1,0.006615259485207122 +CNC(=O)ON=C(C)SC,0.061648442359631114 +COP(=S)(OC)Oc1ccc(cc1)N(=O)(=O),0.0009498211030948742 +O=C1N(N)C(SC)=NN=C1C(C)(C)C,0.06999926640768805 +COP(=O)(OC)OC(Br)C(Cl)(Cl)Br,0.005252325112411575 +OC(C(N)C1O)C(C)OC1(C)OC(CC(C)(C(C2O)C(O)=O)OC(O)(C2)CC(O)CC(C)(O3)C3C=C4)C=CC=CC=CC=CCC(C)OC4=O,0.10172294366080416 +O=N(=O)c(ccc(c1N)C)c1,0.05257947683683445 +O=N(=O)c(c(N)ccc1N)c1,0.5681125108300529 +O=C(O)C(=C(N)C=C1N(=O)=O)C=C1,6.506215164982792 +O=N(=O)c(c(c(ccc1)cc2)c1)c2,0.952831491808421 +c12c(N=Nc3ccccc3)c(O)ccc1cc(S(=O)(=O)O)cc2,0.5482080783455129 +CC(C)Oc1cc(c(Cl)cc1Cl)N2N=C(OC2(=O))C(C)(C)C,0.01448347496337274 +CNC(=O)ON=C(SC)C(=O)N(C)C,0.02280382932847922 +CCOP(=S)(OCC)Oc1ccc(cc1)N(=O)=O,0.012016729209736626 +Oc(c(c(c(c1Cl)Cl)Cl)Cl)c1Cl,0.037546481605565646 +NC(=N)NC(=N)NCCc1ccccc1,0.35564719019232227 +COP(=S)(OC)SCN2C(=O)c1ccccc1C2(=O),0.06302765174348351 +CCN(CC)C(=O)C(Cl)=C(C)OP(=O)(OC)OC,0.041042640567373466 +ClC3C6(Cl)C4C2C1OC1C5C2C3(Cl)C(Cl)(C45)C6(Cl)Cl,0.0018377077252927285 +O=C(OC(=O)c1cccc2)c12,8.000509872156579 +Nc1c(Cl)c(Cl)nc(C(=O)(O))c1Cl,0.24848916516834604 +CCN(CC)c1nc(C)cc(OP(=S)(OC)OC)n1,0.008187766847509327 +Nc3ccc2cc1ccc(N)cc1nc2c3,0.22461542255370148 +CCC(=O)Nc1ccc(Cl)c(Cl)c1,0.09170952329114665 +Clc1cc(Cl)ccc1C2(Cn3ncnc3)OC(CCC)CO2,0.07305234130123987 +O=C(N)c(nccn1)c1,6.408762052980724 +Oc1cc(O)c2C(=O)C(O)=C(c3cc(O)c(O)cc3)Oc2c1,6.729846937340625 +CCC(O)(C)C#C,0.4687038301254292 +CC(C(NCC)=C1)=CC(C1=O2)=C(C(C2=C3)=CC(C)=C3NCC)C(=CC=C4)C(=C4)C(=O)OCC,0.027053999376946393 +O=C(NS(=O)(=O)c1cccc2)c12,19.66323569952698 +c1cc(Cl)ccc1C2SC(=O)N(C(=O)NC3CCCCC3)C2C,0.4534134152107278 +n(c(nc(n1)NCC)NCC)c1Cl,0.024794616275543167 +O=[S](NC1CCCCC1)(=O)[O-].[Na+],17.900880706433757 +O=C(OCC(C1OCC(C1O)O)O)CCCCCCCCCCC,19.866710908558982 +O(CC1O)C(C1O)C(O)COC(=O)CCCCCCCCCCCCCCCCC,16.727105323218392 +O=S(=O)(Nc(nc(cc1C)C)n1)c(ccc(N)c2)c2,0.1185642260256668 +CCNc1nc(NC(C)(C)C)nc(SC)n1,0.06214876624755196 +Oc(c(cc(c1)C(C)(C)C)Cl)c1,1.1697007223226876 +C(C(Cl)Cl)(Cl)Cl,0.6434343954290421 +COP(=O)(OC)OC(=CCl)c1cc(Cl)c(Cl)cc1Cl,0.2732525485855328 +CCN(CC)C(=O)SCc1ccc(Cl)cc1,0.019396419126203733 +COC(=O)NC(=S)Nc1ccccc1NC(=S)NC(=O)OC,0.09345959256991566 +N(C(=S)SSC(N(C)C)=S)(C)C,0.06238747379310184 +c12OC(CCCC(C)CCCC(C)CCCC(C)C)(C)CCc1c(C)c(OC(=O)C)c(C)c2C,4.230630449818821 +Cc1cc(N)ccc1NOS(O)(=O)=O,0.8431459792705229 +C(Br)(C(Br)(Br)Br)C1C(C)(C)C1C(=O)OC(C(#N))c2cccc(Oc3ccccc3)c2,0.004511229623452476 +O=C(O)COc(c(cc(c1Cl)Cl)Cl)c1,0.03914162418169542 +FC(F)(F)C(=CC(N(=O)=O)=C1N(C(C)C)C(C)C)C=C1N(=O)=O,0.1193036069506878 +Cc1cc(C)c(N)cc1C,0.46595489467866197 +CC(O)(C(O)C(O1)C)CC1(C)OC(C(C)O2)C(C(O)C2(C)OC(C(C)C(O)CC(=O)OC(CC)C3COC(C(OC)C4OC)OC(C)C4O)C(CC=O)CC(C)C(=O)C=CC(=C3)C)N(C)C,0.5295750507618869 +c1c(Cl)cc(Cl)cc1N2C(=O)C(C)(C=C)OC2(=O),0.25479642918707424 +O=C(OC(CCCC(O)CCCCCc1cc(O)cc2O)C)c12,0.0006203550142861557 +COC(=O)C1(C2=CC=CC=C2C3=C1C=C(C=C3)Cl)O,0.546052144921948 +CC(C(=O)O)OC1=CC(=CC=C1)Cl,0.4984573741185779 +P12P3P1P23,11.881024454247726 +C(CO)O,6.44456130582279 +CCCCOCC(C)OCC(C)O,0.6726932978936081 +C(CO)O,32.22280652911395 +C(CO)O,14.822491003392418 +[O-][As](=O)([O-])[O-],0.044990181342823746 +[Si](CN1C=NC=N1)(C2=CC=C(C=C2)F)C3=CC=C(C=C3)F,0.007657523838454347 +N(C(=S)SSC(N(C)C)=S)(C)C,0.04783039657471141 +COP(=O)(N)SC,0.006377136181192296 +N(C(=S)SSC(N(C)C)=S)(C)C,0.02275063210988447 +COP(=O)(NC(=O)(C))SC,0.1910836440808347 +C1=CC=C(C=C1)NC(=O)NC2=CN=NS2,0.13620822278144273 +CCOP(=S)(NC(C)C)OC1=CC=CC=C1C(=O)OC(C)C,0.0014476216329334154 +CC(=NOC(=O)N(C)SN(C)C(=O)ON=C(C)SC)SC,0.02821118623185781 +CCOP(=S)(OCC)OC1=NC(=NC(=C1)C)C(C)C,0.004928609097226672 +NC(CCCC1)C1,0.5898716318329822 +CN1C=C(c2ccccc2)C(=O)C(c3cc(C(F)(F)F)ccc3)=C1,0.09868947363194906 +ClC1CC2C(C1Cl)C3(Cl)C(=C(Cl)C2(Cl)C3(Cl)Cl)Cl,0.0012201709684038192 +CCCCC(CC)COC(=O)C1=CC=CC=C1C(=O)OCC(CC)CCCC,0.5120902983161549 +OC(=O)CNCP(O)(O)=O,5.914602135360638 +C1CNC(=S)N1,0.0022514113902230405 +O=C(N(OC)C)Nc(ccc(c1Cl)Cl)c1,0.025090939601491648 +C1=CC=C2C(=C1)NC(=S)S2,4.484270077422418 +CCOP(=S)(OCC)OC1=NC(=C(C=C1Cl)Cl)Cl,0.028523647387248163 +c(c(c(c(c1Cl)Cl)Cl)Cl)(c1Cl)Cl,0.0010183220720957982 +COc1ccc(cc1)C(c2ccc(OC)cc2)C(Cl)(Cl)Cl,0.36163948246786254 +C1=CC(=CC=C1Cl)Cl,2.0407891160090657 +CC(C)OC(=O)NC1=CC(=CC=C1)Cl,2.340158076742021 +COP(=O)(OC)OC=C(Cl)Cl,0.009729574839301364 +CCOP(=S)(OCC)Oc1ccc(cc1)N(=O)=O,0.001442007505168395 +CNC(=O)N(C)c1nnc(s1)C(C)(C)C,0.1751969016077557 +CCCCOCCOCCOCC1=CC2=C(C=C1CCC)OCO2,0.7386866446932013 +CC(C(=O)O)OC1=C(C=C(C=C1)Cl)Cl,0.03828744186371015 +CC1(C(C1C(=O)OC(C#N)C2=CC(=C(C=C2)F)OC3=CC=CC=C3)C=C(Cl)Cl)C,0.028782768433509572 +C(#N)c(c(c(c(c1C(#N))Cl)Cl)Cl)c1Cl,0.015042627044387032 +O=C(OCC)C(O)(c(ccc(c1)Cl)c1)c(ccc(c2)Cl)c2,0.056582904287311254 +O=C(N(C)C)Nc(ccc(c1)Cl)c1,0.6292491939569526 +O=C(N(SC(Cl)(Cl)Cl)C(=O)C1CC=CC2)C12,0.3326798171006209 +CCc1cccc(C)c1N(C(C)COC)C(=O)CCl,0.5285529966699751 +C1=CC(=C(C=C1Cl)Cl)OCC(=O)O,0.022620602193004043 +CCNC1=NC(=NC(=N1)Cl)NC(C)(C)C#N,0.005193343612552968 +C(C(C(C(C1Cl)Cl)Cl)Cl)(C1Cl)Cl,0.015816808894162992 +COP(=S)(OC)OC1=CC(=C(C=C1Cl)Cl)Cl,0.15549919159080278 +C1C2C=CC1C3C2C4(C(=C(C3(C4(Cl)Cl)Cl)Cl)Cl)Cl,2.7404023436797774e-05 +CC1(C(C1C(=O)OCC2=CC(=CC=C2)OC3=CC=CC=C3)C=C(Cl)Cl)C,0.06389160712181856 +CCN(CC)C(=O)C(C)OC1=CC=CC2=CC=CC=C21,0.36852210915226874 +ClC1C=CC2C1C3(Cl)C(=C(Cl)C2(Cl)C3(Cl)Cl)Cl,0.0006696708996117783 +CC(=CC(=O)NC)OP(=O)(OC)OC,0.0020164586039868883 +CC(C)C1(C)N=C(NC1(=O))c3nc2ccccc2cc3C(=O)(O),0.06423944765895072 +CC(C)Nc1nc(Cl)nc(NC(C)C)n1,0.21766590408142725 +CC(C(=O)O)(Cl)Cl,0.3497269961122948 +CC1(C(C1C(=O)OC(C#N)C2=CC(=C(C=C2)F)OC3=CC=CC=C3)C=C(Cl)Cl)C,0.017269661060105742 +O=C(NC)CSP(OC)(OC)=S,0.02180954301853846 +C12C3(C4(C5(C3(C(C1(C5(C2(C4(Cl)Cl)Cl)Cl)Cl)(Cl)Cl)Cl)Cl)Cl)Cl,1.9565721591442926e-05 +COC(=O)C1=CC=CC=C1C(=O)OC,10.299509743336218 +CCOP(=S)(OCC)SCSC(C)(C)C,0.0001733519259052264 +CCC(C)SP(=O)(OCC)SC(C)CC,0.0009245829520661433 +CCOP(=S)(OCC)SCSC(C)(C)C,0.006934077036209056 +C1C(C(C(=O)N1C2=CC=CC(=C2)C(F)(F)F)Cl)CCl,0.016019730669239306 +O=C(O)C(C(C(=O)O)C(O1)CC2)C12,0.6177415369409439 +O=C(Oc(c(OC(C1)(C)C)c1cc2)c2)NC,0.022598624918870935 +Oc(c(c(c(c1)Cl)Cl)Cc(c(c(cc2Cl)Cl)Cl)c2O)c1Cl,0.012287924553322883 +CC1(CON(C1=O)CC2=CC=CC=C2Cl)C,0.08969617860069455 +CCC(C)N1C(=O)C(=C(NC1=O)C)Br,0.23935747721355113 +CC1=CC(=CC(=C1N(C)C)C)OC(=O)NC,0.0067481385934503825 +CNC(=O)OC1=CC=CC(=C1)N=CN(C)C,0.056495719658295813 +CC1=NN(C(=O)N1C(F)F)C2=CC(=C(C=C2Cl)Cl)NS(=O)(=O)C,0.1730416993562668 +CCOP(=S)(CC)SC1=CC=CC=C1,0.020298035239500172 +CCOP(=S)(OCC)SC(CCl)N1C(=O)C2=CC=CC=C2C1=O,0.006347661308292605 +N1CC(C)(C)CNC1=NN=C(C=Cc2ccc(C(F)(F)F)cc2)C=Cc3ccc(C(F)(F)F)cc3,0.010111728942243584 +CC1=C(C(=C(C(=C1F)F)COC(=O)C2C(C2(C)C)C=C(C(F)(F)F)Cl)F)F,0.010985502766340648 +CC1=CC(=C(C=C1)N=CN(C)C=NC2=C(C=C(C=C2)C)C)C,0.034764112883573416 +S=P(OC)(OC)SCN1C(=O)SC(OC)=N1,0.002646103794082849 +CC(C)N(C(C)C)C(=O)SCC(Cl)=C(Cl)Cl,0.04102878665011248 +S=P(OC)(OC)SCN1N=Nc2ccccc2C1(=O),0.0070905370826580775 +CC1=NC(=NC(=N1)OC)NC(=O)NS(=O)(=O)C2=CC=CC=C2CCC(F)(F)F,0.19051986050321804 +O=C(N(S(=O)(=O)Nc1cccc2)C(C)C)c12,0.16647322477947293 +CCN(CC)c1nc(C)cc(OP(=S)(OC)OC)n1,0.04519647299825149 +O=C(ON=CC(SC)(C)C)NC,0.0005255875464343458 +ClC(Cl)(Cl)CC1(OC1)c2cc(Cl)cc(Cl)c2,0.09362507489225783 +CCC1CCCC(C(C(=O)C2CC3C(C2CC(=O)O1)CCC4C3CC(C4)OC5CC(C(C(C5OC)OC)OC)C)C)OC6CCC(C(O6)C)N(C)C,0.03269690443692089 +CC(C)(C)C(=NOC(=O)NC)CSC,0.027483045022449526 +CON=C(CC1=CN=CC=C1)C2=C(C=C(C=C2)Cl)Cl,0.15245767876475944 +CC(=CC1C(C1(C)C)C(=O)OCN2C(=O)C3=C(C2=O)CCCC3)C,0.7543614918373561 +C1COC(O1)(CN2C=NC=N2)C3=C(C=C(C=C3)Cl)Cl,0.03331771398901528 +CCCOC(=O)C1=CN=C(C=C1)C(=O)OCCC,0.9949124950582696 +CC1=CC(=NC(=N1)NC(=O)NS(=O)(=O)C2=CC=CC=C2C(=O)OC3COC3)C,0.20422574060250331 +C1=C(C(=NC(=C1Cl)Cl)OCC(=O)O)Cl,0.1403669879303106 +CCOCN1C(=C(C(=C1C(F)(F)F)Br)C#N)C2=CC=C(C=C2)Cl,0.03336499327732185 +CC(C)CC1=C(C(=NC(=C1C(=O)SC)C(F)(F)F)C(F)F)C(=O)SC,0.00904300899921393 +CC12CC1(C(=O)N(C2=O)C3=CC(=CC(=C3)Cl)Cl)C,0.05279126047017867 +CC1=CC(=C(C=C1)C(=O)OC)C2=NC(C(=O)N2)(C)C(C)C,0.1734054330003024 +COP(=S)(OC)OC1=NC(=C(C=C1Cl)Cl)Cl,0.009301369775521361 +CC(C)CC1=C(C(=NC(=C1C(=O)OC)C(F)F)C(F)(F)F)C2=NCCS2,0.11151045196043953 +CCOC(=O)C(CC1=CC(=C(C=C1Cl)F)N2C(=O)N(C(=N2)C)C(F)F)Cl,0.029112705155716945 +CC(C)=CC3C(C(=O)OCc2coc(Cc1ccccc1)c2)C3(C)C,0.3693416417277341 +CCCSP(=S)(OCC)OC1=CC=C(C=C1)SC,0.03566479582586673 +CC1=CC(=C(C(=C1)OC(=O)NC)C)C,0.30635114568601185 +CC1=CC=CC=C1COC2CC3(CCC2(O3)C)C(C)C,0.5466515334085721 +CC1=C2C(=CC=C1)SC3=NN=CN23,0.16381576159162972 +CCC(=C1C(=O)CC(CC1=O)CC(C)SCC)NOCC=CCl,0.27784628232227476 +CCCN(CCC)C(=O)SCC,0.047538995974292175 +CC(C)OC(=O)C=C(C)C=CCC(C)CCCC(C)(C)OC,0.14816176662421726 +COP(=S)(OC)Oc1ccc(SC)c(C)c1,0.013473309158983109 +COC1=C(C=C(C=C1)C(=CC(=O)N2CCOCC2)C3=CC=C(C=C3)Cl)OC,0.11937399144446861 +CCSC(=O)N(CC(C)C)CC(C)C,0.4600420791288938 +CC(C)OP(=S)(OC(C)C)SCCNS(=O)(=O)C1=CC=CC=C1,0.03773457509937652 +CC(=CC1C(C1(C)C)C(=O)OCC2=CC(=CC=C2)OC3=CC=CC=C3)C,0.42802021191337764 +CC1=CC(=CC(=C1C)C)OC(=O)NC,0.05174850433885335 +CCOP(=S)(OCC)SCSC1=CC=C(C=C1)Cl,0.0029165972759564764 +C1CN(CCN1C(C(Cl)(Cl)Cl)NC=O)C(C(Cl)(Cl)Cl)NC=O,0.22990526799413355 +C(=CC=C1)(C2=C1)NC(=N2)C(=CS3)N=C3,0.009938002763559809 +C1(=C(C(=C(C(=C1Cl)Cl)Cl)Cl)Cl)[N+](=O)[O-],0.423248605734443 +CCCC(=NOCC)C1C(=O)CC(CC1=O)CC(C)SCC,0.05056765552287047 +ClC2(Cl)C4(Cl)C1(Cl)C5(Cl)C(Cl)(Cl)C3(Cl)C1(Cl)C2(Cl)C3(Cl)C45Cl,0.0012831252531881078 +CCN(C1CCCCC1)C(=O)SCC,0.013930451940080113 +CC1=NC(=NC(=N1)OC)NC(=O)NS(=O)(=O)C2=CC=CC=C2OCCCl,0.5494924735209582 +C(C(=O)O)OC1=NC(=C(C(=C1Cl)N)Cl)F,1.9605490478397496 +CC1=C(C(=O)CC1OC(=O)C2C(C2(C)C)C=C(C)C)CC#C,0.316253365684832 +C1C(COC1(CN2C=NC=N2)C3=C(C=C(C=C3)Cl)Cl)Br,0.017185416964361586 +C1=NNC(=N1)N,0.029733601205328832 +C1=CC(=C(C(=C1)F)C(=O)NC(=O)NC2=CC(=C(C(=C2F)Cl)F)Cl)F,0.06822190749765324 +C1=CC(=CC=C1OS(=O)(=O)C2=CC=C(C=C2)Cl)Cl,0.008246440044818412 +FC(F)(F)C(=CC(N(=O)=O)=C1N(C(C)C)C(C)C)C=C1N(=O)=O,2.982590173767195 +CC1=C(C(=O)CC1OC(=O)C2C(C2(C)C)C=C(C)C)CC=C,0.24800936112986982 +C1=CC(=C(C(=C1)Cl)C#N)Cl,0.014533918736325764 +C1C(O1)COC2=CC=CC=C2C3=CC=CC=C3,2.209744922072461 +CC1=CC=CC=C1OCC2=CC=CC=C2C(=NOC)C(=O)OC,1.1967534090558043 +O=N(=O)C(C(=C1N(=O)=O)N(C(C)C)C(C)C)=CC(=C1)S(=O)(=O)N,0.10642121227099519 +C1=CC(=C(C2=NC=C(C=C21)Cl)C(=O)O)Cl,3.127347059508829 +CC(C)NC(=O)N1CC(=O)N(C1=O)C2=CC(=CC(=C2)Cl)Cl,0.13932359364492994 +CCCN(CCCl)C1=C(C=C(C=C1[N+](=O)[O-])C(F)(F)F)[N+](=O)[O-],0.5690227874227859 +C1=CC=C(C=C1)C2=CC=CC=C2O,5.875192118782284 +O=C(N(C)C)Nc(cccc1C(F)(F)F)c1,0.06459882942614491 +C1=CC(=NC(=C1)Cl)C(Cl)(Cl)Cl,0.00433075312836283 +Clc1cc(Cl)cc(Cl)c1OCCN(CCC)C(=O)n2cncc2,0.01991156926953532 +CC1=CC(=C(C=C1NC(=O)C)NS(=O)(=O)C(F)(F)F)C,0.08894826507859208 +C(=C(I)I)(I)I,0.09404873168890004 +C1=C(C=C(C(=C1Cl)N2C(=C(C(=N2)C#N)S(=O)C(F)(F)F)N)Cl)C(F)(F)F,0.0001372533562906347 +O=C(N(C)C)Nc(ccc(c1Cl)Cl)c1,0.026813159469657157 +CC1=C(C(=O)CC1OC(=O)C2C(C2(C)C)C=C(C)C)CC=C,0.08101639130242413 +CC1=CC2=C(C=C1)N=C3C(=N2)SC(=O)S3,0.03201059303080734 +CC(C)N(C(=O)CCl)c1ccccc1,0.10865048725491992 +CC(C)C1(C(=O)NC(=N1)C2=C(C=CC=N2)C(=O)O)C,1.913681483026602 +CC1(C(C1(C)C)C(=O)OC(C#N)C2=CC(=CC=C2)OC3=CC=CC=C3)C,0.05566320606558952 +CN1CN(C(=S)SC1)C,0.18486987933542975 +ClC(Cl)=CC1C(C)(C)C1C(=O)OC(C(#N))c2cccc(Oc3ccccc3)c2,0.18015976856532 +ClC2C1OC1C3C2C4(Cl)C(=C(Cl)C3(Cl)C4(Cl)Cl)Cl,0.0005137200498000217 +CCOC(=O)CN1C2=C(C=CC=C2Cl)SC1=O,0.046003238627999404 +CCCN(CCC)C1=C(C=C(C(=C1[N+](=O)[O-])N)C(F)(F)F)[N+](=O)[O-],0.08392957349588569 +C1=CC=C(C=C1)C(CCC2=CC=C(C=C2)Cl)(CN3C=NC=N3)C#N,0.11875847044790469 +CC(C)(C)C(CCC1=CC=C(C=C1)Cl)(CN2C=NC=N2)O,0.05165383561566402 +CC1=C(C=CC=C1COC(=O)C2C(C2(C)C)C=C(C(F)(F)F)Cl)C3=CC=CC=C3,0.011824026606519262 +C(=CC=C1)(C2=C1)NC(=N2)C(=CS3)N=C3,0.19876005527119617 +C1=C(C=C(C(=C1Cl)N)Cl)[N+](=O)[O-],0.7245881151318344 +CC1=C(C=C(C=C1C(=O)N)[N+](=O)[O-])[N+](=O)[O-],0.027758250773633555 +CC(C)OC1=CC=CC(=C1)NC(=O)C2=CC=CC=C2C(F)(F)F,1.5465050300849357 +OC(c1ccc(Cl)cc1)(c2ccc(Cl)cc2)C(Cl)(Cl)Cl,0.006747899500347733 +O=P(O)(O)CCCl,3.0866333550182015 +CN(C(=O)NC1=CC=C(C=C1)Br)OC,0.048243951057630914 +CC1=CC(=CC=C1)NC(=O)OC2=CC=CC(=C2)NC(=O)OC,0.0832475217878744 +CC(C)(C)C1=NN=C(S1)N2C(CN(C2=O)C)O,0.19506513302817866 +S=P(OCC)(OCC)Oc1ccc2C(C)=C(Cl)C(=O)Oc2c1,0.004686221626306353 +COC(=O)c1ccccc1S(=O)(=O)NC(=O)N(C)c2nc(OC)nc(C)n2,0.031614325062739264 +C1=CC=C(C(=C1)NC2=NC(=NC(=N2)Cl)Cl)Cl,0.004173898399328111 +CC1=C(C=CC(=C1)OP(=S)(OC)OC)[N+](=O)[O-],0.001659247904766673 +COc1c(Cl)ccc(Cl)c1C(=O)(O),0.520273850439093 +CC1(C(C1C(=O)OC(C#N)C2=CC(=CC=C2)OC3=CC=CC=C3)C=C(Br)Br)C,0.004948543461552866 +C1=CC=C(C(=C1)C(C2=CC=C(C=C2)F)(C3=CN=CN=C3)O)Cl,0.007943029289634557 +c1ccc2nc(NC(=O)OC)n(C(=O)NCCCC)c2c1,0.3961177430023906 +CCOC(=O)COC(=O)C1=C(C=CC(=C1)OC2=C(C=C(C=C2)C(F)(F)F)Cl)[N+](=O)[O-],0.05583516191627437 +CC(C)(C)C(C(N1C=NC=N1)OC2=CC=C(C=C2)C3=CC=CC=C3)O,0.07409262028018154 +CCNC(=O)NC(=O)C(=NOC)C#N,0.15289185096526225 +CCOC1=C(C=CC(=C1)OC2=C(C=C(C=C2)C(F)(F)F)Cl)[N+](=O)[O-],0.11058877880543937 +CC1=NC=C(N1CCO)[N+](=O)[O-],0.8764039114257128 +O=C(N(SC(Cl)(Cl)Cl)C(=O)c1cccc2)c12,1.6860133324539086 +CC(C)(C)c2ccc(OC1CCCCC1OS(=O)OCC#C)cc2,0.2853292217012047 +CCCCC(CN1C=NC=N1)(C2=C(C=C(C=C2)Cl)Cl)O,0.014958135679074535 +CC(C)(C)C(C(=CC1=C(C=C(C=C1)Cl)Cl)N2C=NC=N2)O,0.15327033840680634 +C1=CC(C2C1C3(C(=C(C2(C3(Cl)Cl)Cl)Cl)Cl)Cl)Cl,0.001017899767409903 +C1=CC=C2C(=C1)C(=O)C3=C(C2=O)SC(=C(S3)C#N)C#N,0.03374687200243409 +CC1=NN(C(=C1C=NOCC2=CC=C(C=C2)C(=O)OC(C)(C)C)OC3=CC=CC=C3)C,0.0073074288460468996 +CS(=O)(=O)C1=C(C=CC(=C1)C(F)(F)F)C(=O)C2=C(ON=C2)C3CC3,0.05566064749641608 +CC1=C(N=C(N=C1OC(=O)N(C)C)N(C)C)C,0.0524579222415799 +CCN(CC)C(=O)C(Cl)=C(C)OP(=O)(OC)OC,0.005005200069191886 +C1=CC(=CC=C1C(CN)O)O,1.6320834707547616 +CC1=C(C(=CC=C1)C)N(C(=O)COC)N2CCOC2=O,0.17965983350851364 +c1c(C(F)(F)F)cccc1N2C(=O)C(Cl)=C(NC)C=N2,0.06174515112035177 +CCC(C)NC1=C(C=C(C=C1[N+](=O)[O-])C(C)(C)C)[N+](=O)[O-],0.16929970598735858 +C1=CC(=CC=C1S(=O)(=O)C2=CC(=C(C=C2Cl)Cl)Cl)Cl,0.6459733503975151 +CCCCC1=C(NC(=NC1=O)NCC)C,0.1194525860672606 +n(c(nc(n1)NCC)NCC)c1Cl,0.026282293252075754 +FC(F)(F)C(C=C1N(=O)=O)=CC(N(=O)=O)=C1N(CC)CC(C)=C,0.0375078950368263 +C1CCC(C1)N(CC2=CC=C(C=C2)Cl)C(=O)NC3=CC=CC=C3,0.0760257762657501 +CS(=O)(=O)NC(=O)C1=C(C=CC(=C1)OC2=C(C=C(C=C2)C(F)(F)F)Cl)[N+](=O)[O-],0.11395676083924232 +CCOC(=O)C(C)OC1=CC=C(C=C1)OC2=NC3=C(O2)C=C(C=C3)Cl,0.02487724874434851 +CCC1=C(C(=CC=C1)CC)N(CNC(=O)C)C(=O)CCl,0.21058487877925733 +NC(=N)NCCCCCCCCCCCC(OC(=O)C),0.10160268068512719 +C1=CC(=CC(=C1)Cl)NC(=O)OCC#CCCl,1.743505808935165 +CC(C)C(C(=O)OC(C(#N))c2cccc(Oc1ccccc1)c2)c3ccc(Cl)cc3,0.05953797389131243 +CC(C)C1=C(C=CC(=C1)C(C)(C)C2=CC(=C(C=C2)O)C(C)C)O,0.08001387248515598 +CCN(CC1=C(C=CC=C1Cl)F)C2=C(C=C(C=C2[N+](=O)[O-])C(F)(F)F)[N+](=O)[O-],0.1185590456888386 +CCCCCCCCSC(=O)OC1=CC(=NN=C1C2=CC=CC=C2)Cl,0.17813968959673715 +CC1=C(C(=O)CC1OC(=O)C2C(C2(C)C)C=C(C)C)CC=C,0.04563372244789605 +CCCCNC(=O)N1C2=CC=CC=C2N=C1NC(=O)OC,0.8611255282660666 +CC1=C(C(=CC=C1)C)N(C(C)C(=O)OC)C(=O)CC2=CC=CC=C2,0.14136381415796706 +CC(C)C(C1=CC=C(C=C1)OC(F)F)C(=O)OC(C#N)C2=CC(=CC=C2)OC3=CC=CC=C3,0.013290157156772887 +Clc1ccccc1c2nnc(c3ccccc3Cl)nn2,0.06597478470118634 +CCOC(=O)NCCOC1=CC=C(C=C1)OC2=CC=CC=C2,0.03318543029523152 +CCC1=C(C(=CC=C1)CC)N(CC(=O)OCC)C(=O)CCl,0.1603572605822803 +c1(O2)c(CC2(C)C)cccc1OC(=O)N(C)SN(CCCC)CCCC,0.06569530810416269 +CCCCOC(=O)C(C)OC1=CC=C(C=C1)OC2=NC=C(C=C2)C(F)(F)F,0.007825509706097071 +COC1=CC(=C(C=C1Cl)OC)Cl,0.6037074787089276 +CCOP(=S)(OCC)OC1=NN(C(=N1)Cl)C(C)C,0.039841737145637234 +n(c(nc(n1)NC(C)C)NCC)c1Cl,0.11591071091933607 +CC(C)(C)C(C(=CC1=CC=C(C=C1)Cl)N2C=NC=N2)O,0.13506940531624406 +CCCCCCCCc1cc(N(=O)(=O))c(OC(=O)C=CC)c(c1)N(=O)(=O),0.1372145060102149 +c1cc(OC(F)(F)F)ccc1C(O)(C(C)C)c2cncnc2,0.038746408312020406 +COP(=O)(C(C(Cl)(Cl)Cl)O)OC,0.07768900686568829 +C1=CC(=C(C=C1C(F)(F)F)Cl)OC2=CC(=C(C=C2)[N+](=O)[O-])C(=O)O,0.34563108073944815 +CCCN(CC1CC1)C2=C(C=C(C=C2[N+](=O)[O-])C(F)(F)F)[N+](=O)[O-],0.014397200032537671 +CCOC(=O)C(C)OC(=O)C1=C(C=CC(=C1)OC2=C(C=C(C=C2)C(F)(F)F)Cl)[N+](=O)[O-],0.10827828411229923 +CCSC(=O)N1CCCCCC1,0.07907000434271044 +CCC1=CC=C(C=C1)C(=O)NN(C(=O)C2=CC(=CC(=C2)C)C)C(C)(C)C,0.13618183361575933 +ClC(Cl)C(Cl)(Cl)SN2C(=O)C1CC=CCC1C2(=O),0.04297243667696324 +COC(=O)C1=CC=CC=C1S(=O)(=O)NC(=O)NC2=NC(=CC(=N2)OC(F)F)OC(F)F,0.2989300503468667 +CC(C)(C)C(C(N1C=NC=N1)OC2=CC=C(C=C2)Cl)O,0.08452667530010859 +CC1=C(C=CC(=C1)Cl)OCC(=O)O,0.019938294964743114 +COC=C(C1=CC=CC=C1OC2=NC=NC(=C2)OC3=CC=CC=C3C#N)C(=O)OC,0.15431812608561873 +C1=CC=C(C(=C1)C(C2=CC=C(C=C2)Cl)(C3=CN=CN=C3)O)Cl,0.00694452873492003 +[O-]Br(=O)=O,0.047692690196102956 +OP(=O)OCC,3.6347465046005896 +COP(N)(=O)SC,0.000708570686799144 +CCOP(=O)(NC(C)C)Oc1ccc(SC)c(C)c1,0.004944661980269876 +CCOP(=S)(OCC)SCCSCC,0.00014577045919371006 +CCOP(=S)(OCC)SCSP(=S)(OCC)OCC,0.005201883810203027 +O=C(OCC(CCCC)CC)CCCCC(=O)OCC(CCCC)CC,4.047856676081442 +CN(C=Nc1ccc(C)cc1C)C=Nc2ccc(C)cc2C,0.03408246361134649 +[C@@]14([C@@H]5OCC1=CC=C[C@@H]([C@H](O[C@H]2C[C@@H]([C@H]([C@@H](O2)C)O[C@H]3C[C@@H]([C@H]([C@@H](O3)C)O)OC)OC)C(=CC[C@@H]6C[C@H](OC([C@@H]4C=C([C@H]5O)C)=O)C[C@]7(O6)O[C@@H]([C@H](C=C7)C)[C@H](CC)C)C)C)O,0.002290749011702154 +O=C(N(S(=O)(=O)Nc1cccc2)C(C)C)c12,0.14566407168203882 +S=P(OC)(OC)SCN1C(=O)SC(OC)=N1,0.004134537178254452 +C(#N)Cl,1.1387594679715767 +C(#N)Br,1.1517974649126617 +C1=CC(=CC=C1C(C2=CC=C(C=C2)Cl)C(Cl)(Cl)Cl)Cl,0.0007052459522690667 +c(cccc1)(c1)C(C)C,2.7539366734341955 +CCCN(CCC)C(=O)SCC,0.13205276659525605 +NC(CCCC1)C1,0.6049965454697254 +ClC1CC2C(C1Cl)C3(Cl)C(=C(Cl)C2(Cl)C3(Cl)Cl)Cl,0.014642051620845831 +CC(C)OC(=O)NC1=CC(=CC=C1)Cl,4.680316153484042 +COC(=O)c1c(Cl)c(Cl)c(C(=O)OC)c(Cl)c1Cl,0.030123726579706293 +COC(=O)C1=CC=C(C=C1)C(=O)OC,0.6437193589585136 +N(C(=S)NC1)C1,0.0024471862937206963 +O=C(N(OC)C)Nc(ccc(c1Cl)Cl)c1,0.010036375840596658 +c(cccc1)(c1)C=C,2.736460951374337 +COC(=O)c1ccccc1S(=O)(=O)NC(=O)Nc2nc(OC)nc(C)n2,0.655542030995076 +C1=CC(=CC=C1N)Cl,0.09798423692306293 +FC(F)(F)C(Cl)=CC1C(C)(C)C1C(=O)OC(C(#N))c2cc(Oc3ccccc3)ccc2,0.02778703580061686 +C(Cl)(Br)Br,0.13683526627950768 +C=C(Cl)Cl,0.14441434207714035 +C(C=CCl)Cl,0.045958425107502164 +COP(=O)(OC)OC(=CCl)c1cc(Cl)c(Cl)cc1Cl,0.1366262742927664 +Oc(ccc(c1)C(c(ccc(O)c2)c2)(C)C)c1,0.21902317939829427 +O=C(OCc(cccc1)c1)c(c(ccc2)C(=O)OCCCC)c2,1.504675539130048 +O=C(NCCCC1)C1,1.10465364954589 +c(cccc1)(c1)Cl,1.0661274430976688 +C(Cl)(Cl)Cl,0.502606685808163 +ClCCl,0.6190792744080069 +C1C2C3C(C1C4C2O4)C5(C(=C(C3(C5(Cl)Cl)Cl)Cl)Cl)Cl,0.000328162093802273 +OCCO,16.111403264556976 +O=C(C=C(CC1(C)C)C)C1,1.295160023171064 +C(F)(Cl)(Cl)Cl,2.540618964665013 +CCc1cccc(CC)c1N(COC)C(=O)CCl,0.05189661748967905 +c1ccccc1c2c(C)c(COC(=O)C3C(C)(C)C3C=C(Cl)C(F)(F)F)ccc2,0.011824026606519262 +n1c(Cl)cc(OC)nc1NC(=O)NS(=O)(=O)c2ccccc2C(=O)OCC,0.30133493788161053 +O=C(NC(=O)c(c(F)ccc1)c1F)Nc(ccc(c2)Cl)c2,0.02510595436954169 +c(cccc1)(c1)CC,2.741016342485753 +O=C(N(SC(Cl)(Cl)Cl)C(=O)c1cccc2)c12,0.1348810665963127 +Clc1cc(C(F)(F)F)cnc1Oc2ccc(OC(C)C(=O)OC)cc2,0.0026615073878255148 +C#N,1.1470716002092851 +ClC(C(OC(C=C2C(=O)OC(C)C(=O)OCC)=CC=C2N(=O)=O)=C1)=CC=C1C(F)(F)F,0.10827828411229923 +c1c(C(F)(F)F)cccc1N2C(=O)C(Cl)=C(NC)C=N2,0.1687700797289615 +O=N(=O)C(C(=C1N(=O)=O)N(C(C)C)C(C)C)=CC(=C1)S(=O)(=O)N,0.12992280391195832 +CN(=CC=C1C(C=C2)=CC=N2C)C=C1,0.019100264469901956 +C1=C(C=C(C=C1[N+](=O)[O-])[N+](=O)[O-])[N+](=O)[O-],0.06245761469536169 +C(=C)Cl,0.020800592400871575 +C1CCC(=O)CC1,9.272184465524795 +CC1(C(C1(C)C)C(=O)OC(C#N)C2=CC(=CC=C2)OC3=CC=CC=C3)C,0.07154653735936956 +C1=CC(=O)NNC1(=O),4.460830164062196 +CCSC(=O)N1CCCCCC1,0.010677920910561842 +C(C(Cl)(Cl)Cl)(O)O,0.8161882413029702 +ClC2C1OC1C3C2C4(Cl)C(=C(Cl)C3(Cl)C4(Cl)Cl)Cl,6.421500622500271e-05 +Clc1cc(C(F)(F)F)ccc1Oc2cc(OCC)c(N(=O)(=O))cc2,0.02764719470135984 +c1cc(Cl)ccc1C(C(#N))(CCCC)Cn2ncnc2,0.03407493882440353 +CC1=C(C=C(C=C1[N+](=O)[O-])[N+](=O)[O-])[N+](=O)[O-],0.008805487227420639 +CC(C)OC(=O)C(C1=CC=C(C=C1)Br)(C2=CC=C(C=C2)Br)O,0.06073132568962639 +C[N+](C)(C)CCCl,1.0602168942789227 +CCC(=C1C(=O)CC(CC1=O)CC(C)SCC)NOCC=CCl,0.2389478027971563 +CC1=NC(=NC(=C1)C2CC2)NC3=CC=CC=C3,0.15801925526767843 +N(c(cccc1)c1)c(cccc2)c2,0.14773454395291782 +CC1(C(=O)N(C(=O)O1)NC2=CC=CC=C2)C3=CC=C(C=C3)OC4=CC=CC=C4,0.044873074905021335 +CC1(CCCCC1)C(=O)NC2=C(C(=C(C=C2)O)Cl)Cl,0.9662594125910484 +C1=CC(=C2C(=C1)OC(O2)(F)F)C3=CNC=C3C#N,0.443217671652664 +C(F)(F)(F)c1ccccc1C(=O)Nc2cccc(OC(C)C)c2,0.2690918752347788 +C(CCCCN=C(N)N)CCCNCCCCCCCCN=C(N)N,0.053436074592710235 +C1CN(C(=N1)N[N+](=O)[O-])CC2=CN=C(C=C2)Cl,0.0664943030028045 +COC(=O)C12CC3=C(C1=NN(CO2)C(=O)N(C4=CC=C(C=C4)OC(F)(F)F)C(=O)OC)C=CC(=C3)Cl,0.006820319755914397 +CC1=CC=CC=C1OCC2=CC=CC=C2C(=NOC)C(=O)OC,1.1807966969350603 +CC1=CC(=CC(=C1)C(=O)N(C(C)(C)C)NC(=O)C2=C(C(=CC=C2)OC)C)C,1.1154252951100516 +C1=CC(=C(C(=C1)F)C(=O)NC(=O)NC2=CC(=C(C=C2)OC(C(OC(F)(F)F)F)(F)F)Cl)F,0.07306609422899836 +CC1=CC=C(C=C1)N(SC(F)(Cl)Cl)S(=O)(=O)N(C)C,0.051834835094095484 +CC(C)(C)C1=C(C=CC(=C1)O)O,1.3536524792656537 +CC(=NOCC1=CC=CC=C1C(=NOC)C(=O)OC)C2=CC(=CC=C2)C(F)(F)F,0.14692519722320194 +COC(=O)N(C1=CC=CC=C1COC2=NN(C=C2)C3=CC=C(C=C3)Cl)OC,0.02320682656135787 +CC(C)N1C(=NC(C)(C)C)SCN(C1=O)C2=CC=CC=C2,0.02848365588181601 +C1=CC=C(C(=C1)C2=NN=C(N=N2)C3=CC=CC=C3Cl)Cl,0.05706818876652619 +CCCC(=C1C(=O)CC(CC1=O)C2CCCSC2)NOCC,0.08603044408485085 +C1CC1NC2=NC(=C(C(=N2)N)C#N)N,0.11566455596376966 +C(C=C1)(=N(C=C1)CC2)C(N2=C3)=CC=C3,0.002933359023382885 +C1=CC=C2C(=C1)C(=O)C3=C(C2=O)SC(=C(S3)C#N)C#N,0.020248123201460456 +CCOC1=CC2=C(C=C1)NC(C=C2C)(C)C,0.05522147585284508 +C1=CC=C(C=C1)C(CCC2=CC=C(C=C2)Cl)(CN3C=NC=N3)C#N,0.08906885283592852 +CC1CN(CC(O1)C)CC(C)CC2=CC=C(C=C2)C(C)(C)C,0.005601647965290344 +C[Si](CN1C=NC=N1)(C2=CC=C(C=C2)F)C3=CC=C(C=C3)F,0.006341300659739408 +c1cc(Cl)cc(Cl)c1C(OCC=C)Cn2cncc2,0.05047450068604942 +CN(=CC=C1C(C=C2)=CC=N2C)C=C1,0.012988179839533329 +CCCCOCCOCCOCC1=CC2=C(C=C1CCC)OCO2,0.29547465787728056 +Clc1cc(Cl)ccc1C2(Cn3ncnc3)OC(CCC)CO2,0.2805209905967611 +C(=CC=C1)(C2=C1)NC(=N2)C(=CS3)N=C3,0.1490700414533971 +CCOC1=CC=C(C=C1)C(C)(C)COCC2=CC(=CC=C2)OC3=CC=CC=C3,0.0690593023384914 +CC(C)(C)c2ccc(OC1CCCCC1OS(=O)OCC#C)cc2,0.0542125521232289 +CC(COC1=CC=C(C=C1)OC2=CC=CC=C2)OC3=CC=CC=N3,0.4356352632556343 +CC(C)(C)C(=O)C(N1C=NC=N1)OC2=CC=C(C=C2)Cl,0.3880867710275115 +CC(C)(C)C(C(N1C=NC=N1)OC2=CC=C(C=C2)Cl)O,0.3550120362604561 +c1ccccc1c2c(C)c(COC(=O)C3C(C)(C)C3C=C(Cl)C(F)(F)F)ccc2,0.018918442570430818 +CC1(C(C1C(=O)OC(C#N)C2=CC(=C(C=C2)F)OC3=CC=CC=C3)C=C(Cl)Cl)C,0.013815728848084595 +CC1(C(C1C(=O)OC(C#N)C2=CC(=C(C=C2)F)OC3=CC=CC=C3)C=C(Cl)Cl)C,0.02763145769616919 +ClC(Cl)=CC1C(C)(C)C1C(=O)OC(C(#N))c2cccc(Oc3ccccc3)c2,0.12010651237688001 +ClC1CC2C(C1Cl)C3(Cl)C(=C(Cl)C2(Cl)C3(Cl)Cl)Cl,0.0006100854842019096 +ClC4=C(Cl)C5(Cl)C3C1CC(C2OC12)C3C4(Cl)C5(Cl)Cl,0.0002625296750418184 +C1C2C3C(C1C4C2O4)C5(C(=C(C3(C5(Cl)Cl)Cl)Cl)Cl)Cl,0.000656324187604546 +C1(C(C(C(C(C1Cl)Cl)Cl)Cl)Cl)Cl,0.016160652565775233 +CCC(=O)Nc1ccc(Cl)c(Cl)c1,0.3484961885063573 +C1(=C(C(=C(C(=C1Cl)Cl)Cl)Cl)Cl)[N+](=O)[O-],0.47403843842257615 +C1C2C(COS(=O)O1)C3(C(=C(C2(C3(Cl)Cl)Cl)Cl)Cl)Cl,0.007126617932723449 +O=C(N(SC(Cl)(Cl)Cl)C(=O)c1cccc2)c12,0.16860133324539087 +CC(C(=O)O)OC1=CC=C(C=C1)OC2=C(C=C(C=N2)C(F)(F)F)Cl,0.00027647194701359843 +CCCCC(CN1C=NC=N1)(C#N)C2=CC=C(C=C2)Cl,0.033936422812922216 +Clc1cc(Cl)cc(Cl)c1OCCN(CCC)C(=O)n2cncc2,0.013539867103284017 +COP(=O)(NC(=O)(C))SC,0.013648831720059621 +CCOP(=O)(OCC)OC(=CCl)C1=C(C=C(C=C1)Cl)Cl,0.004171650398342553 +CCOP(=S)(OCC)SCCSCC,0.0008017375255654054 +O=P(O)(O)CCCl,0.08304843107672291 +CCCSP(=O)(OCC)SCCC,0.011141416681473747 +CCOP(=O)(NC(C)C)Oc1ccc(SC)c(C)c1,0.005603950244305859 +COP(=S)(OC)Oc1ccc(SC)c(C)c1,0.0025868753585247565 +OC(=O)C(N)CCP(C)(=O)O,0.019323475195614302 +OC(=O)CNCP(O)(O)=O,1.7743806406081915 +CCOC(=O)CC(SP(=S)(OC)OC)C(=O)OCC,1.0897268363577188 +COP(N)(=O)SC,0.002054854991717517 +CC(=CC(=O)OC)OP(=O)(OC)OC,0.001561466365033004 +CCOP(=S)(OCC)SCSCC,0.0006144925612602997 +CCOP(=S)(OCC)SCSC(C)(C)C,0.0002080223110862717 +S=P(OC)(OC)SCN1N=Nc2ccccc2C1(=O),0.00813048252144793 +CCOP(=S)(OCC)OC1=NC(=C(C=C1Cl)Cl)Cl,0.002852364738724816 +CCOP(=S)(OCC)OC1=NC(=NC(=C1)C)C(C)C,0.019057288509276463 +CCC1=NC(=CC(=N1)OP(=S)(OC)OC)OCC,0.0015395577035464635 +S=P(OC)(OC)SCN1C(=O)SC(OC)=N1,0.005292207588165698 +CCOP(=S)(OCC)SCN1C2=C(C=C(C=C2)Cl)OC1=O,0.0054376113486863924 +COP(=S)(OC)SCN2C(=O)c1ccccc1C2(=O),0.02836244328456758 +CCOC(=O)C1=CN2C(=CC(=N2)OP(=S)(OCC)OCC)N=C1C,0.010713392485187262 +CCOP(=S)(OCC)OC1=NN(C=N1)C2=CC=CC=C2,0.004149212048673449 +O=C(Oc(c(c(ccc1)cc2)c1)c2)NC,0.2981792578159244 +CC1=CC(=CC(=C1SC)C)OC(=O)NC,0.041276958181115306 +CNC(=O)ON=C(C)SC,0.12329688471926223 +CCCOC(=O)NCCCN(C)C,3.611885866531256 +COC(=O)NC1=NC2=CC=CC=C2N1,0.3922867840256219 +CC1=C(N=C(N=C1OC(=O)N(C)C)N(C)C)C,0.051618595485714625 +CNC(=O)CCSCCSP(=O)(OC)OC,0.001879329112916984 +N(C(=S)SSC(N(C)C)=S)(C)C,0.04990997903448147 +C1=NNC(=N1)N,0.059467202410657664 +CCCCCCCCc1cc(N(=O)(=O))c(OC(=O)C=CC)c(c1)N(=O)(=O),0.17563456769307506 +C1=CC=C(C=C1)[Sn](C2=CC=CC=C2)C3=CC=CC=C3,0.0008571117562305596 +O=C(NC(=O)c(c(F)ccc1)c1F)Nc(ccc(c2)Cl)c2,0.022530984690614337 +N(C(=S)NC1)C1,0.012235931468603481 +C1=CC(=C(C(=C1)F)C(=O)NC(=O)NC2=CC(=C(C(=C2F)Cl)F)Cl)F,0.06559798797851273 +CCCSC1=CC2=C(C=C1)N=C(N2)NC(=O)OC,0.07537743365466734 +C1CN(CCN1CCCC(=O)C2=CC=C(C=C2)F)C3=CC=CC=N3,0.35125671098854394 +CC1(C2C(C3C(C(=O)C(=C(N)O)C(=O)C3(C(=O)C2=C(C4=C(C=CC(=C41)Cl)O)O)O)N(C)C)O)O,10.50761860949369 +CC1=CC(=C(C=C1NC(=O)C2=CC(=CC(=C2O)I)I)Cl)C(C#N)C3=CC=C(C=C3)Cl,0.015081279803436631 +CN1CC2CC1CN2C3=C(C=C4C(=C3)N(C=C(C4=O)C(=O)O)C5CC5)F,0.13990757146198934 +C1=CC(=CC=C1C(C#N)C2=C(C=CC(=C2Cl)N3C(=O)NC(=O)C=N3)Cl)Cl,0.03679735812631385 +CC1=NC=C(N1C)[N+](=O)[O-],0.10628650675790867 +CCN1CCN(CC1)C2=C(C=C3C(=C2)N(C=C(C3=O)C(=O)O)C4CC4)F,0.07234386441112595 +CC1C=CC=C2COC3C2(C(C=C(C3O)C)C(=O)OC4CC(CC=C(C1OC5CC(C(C(O5)C)OC6CC(C(C(O6)C)NC(=O)C)OC)OC)C)OC7(C4)C=CC(C(O7)C(C)C)C)O,0.0011109849279118543 +COCC(=O)NC1=C(C=CC(=C1)SC2=CC=CC=C2)NC(=NC(=O)OC)NC(=O)OC,0.08959030532555236 +CC1CCC2=C3N1C=C(C(=O)C3=CC(=C2)F)C(=O)O,1.531109972815908 +COC(=O)NC1=NC2=C(N1)C=C(C=C2)S(=O)C3=CC=CC=C3,0.006342219438128827 +CC1(C2CC3C(C(=O)C(=C(N)O)C(=O)C3(C(=O)C2=C(C4=C1C=CC=C4O)O)O)N(C)C)O,0.33750750616693714 +C1CN(CCN1CCCC(=O)C2=CC=C(C=C2)F)C3=CC=CC=N3,0.09163218547527233 +CC(C)NCC(COC1=CC=CC2=C1C3=CC=CC=C3N2)O,0.023460058312320942 +C1=CC(=CC=C1C(C#N)C2=C(C=CC(=C2Cl)N3C(=O)NC(=O)C=N3)Cl)Cl,0.056422615793681234 +CC1C=CC=C2COC3C2(C(C=C(C3O)C)C(=O)OC4CC(CC=C(C1OC5CC(C(C(O5)C)OC6CC(C(C(O6)C)NC(=O)C)OC)OC)C)OC7(C4)C=CC(C(O7)C(C)C)C)O,0.0027774623197796356 +COP(=S)(OC)Oc1ccc(SC)c(C)c1,0.001616797099077973 +C(C(C(C(C1Cl)Cl)Cl)Cl)(C1Cl)Cl,0.027507493728979118 +C(C(C(C(C1Cl)Cl)Cl)Cl)(C1Cl)Cl,0.013753746864489559 +CC(N(C)C)CN(C(=CC=C3)C1=C3)C(=CC=C2)C(=C2)S1,0.058364575374860554 +C1=C(C=C(C(=C1Cl)N)Cl)[N+](=O)[O-],1.159340984210935 +c(cccc1)(c1)C=C,3.8406469492973154 diff --git a/regression/NOAEL-LOAEL_dv.xlsx b/regression/NOAEL-LOAEL_dv.xlsx deleted file mode 100644 index 34361cf..0000000 Binary files a/regression/NOAEL-LOAEL_dv.xlsx and /dev/null differ diff --git a/regression/NOAEL-LOAEL_elena_email_20150306.xlsx b/regression/NOAEL-LOAEL_elena_email_20150306.xlsx deleted file mode 100644 index be6065a..0000000 Binary files a/regression/NOAEL-LOAEL_elena_email_20150306.xlsx and /dev/null differ -- cgit v1.2.3