summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorChristoph Helma <helma@in-silico.ch>2016-03-02 11:20:26 +0100
committerChristoph Helma <helma@in-silico.ch>2016-03-02 11:20:26 +0100
commitd3071896a7116670756199f0df7c2a618de2aea3 (patch)
tree2cf71d47232c08da2973452950e1f969c733478a
parent7424234dbf1d7ebdb7a15adaec71c8b6fb53890f (diff)
repeated crossvalidations
-rw-r--r--Makefile42
-rw-r--r--TODO15
-rw-r--r--create-training.rb (renamed from create-combined.rb)2
-rw-r--r--crossvalidation-plots.R14
-rw-r--r--crossvalidation.rb4
-rw-r--r--data/combined-cv.csv637
-rw-r--r--data/combined-cv.id1
-rw-r--r--data/combined-test-predictions.csv151
-rw-r--r--data/combined-test-predictions.id1
-rw-r--r--data/training-cv-0.csv631
-rw-r--r--data/training-cv-0.id1
-rw-r--r--data/training-cv-1.csv632
-rw-r--r--data/training-cv-1.id1
-rw-r--r--data/training-cv-2.csv636
-rw-r--r--data/training-cv-2.id1
-rw-r--r--data/training-test-predictions.csv151
-rw-r--r--data/training-test-predictions.id1
-rw-r--r--data/training.csv (renamed from data/combined.csv)0
-rw-r--r--data/training.json (renamed from data/combined.json)0
-rw-r--r--figure/crossvalidation.pdfbin13667 -> 30511 bytes
-rw-r--r--figure/dataset-variability.pdfbin10357 -> 10357 bytes
-rw-r--r--figure/functional-groups.pdfbin6496 -> 6496 bytes
-rw-r--r--figure/matching-ClC(C)Cl.pngbin148825 -> 0 bytes
-rw-r--r--figure/test-correlation.pdfbin7618 -> 7533 bytes
-rw-r--r--figure/test-prediction.pdfbin10900 -> 10899 bytes
-rw-r--r--figure/unnamed-chunk-4-1.pngbin12939 -> 0 bytes
-rw-r--r--loael-variability.rb61
-rw-r--r--loael.Rmd80
-rw-r--r--loael.md64
-rw-r--r--loael.pdfbin755165 -> 653879 bytes
-rw-r--r--test-correlation-plot.R6
-rw-r--r--test-prediction-plot.R4
32 files changed, 2191 insertions, 945 deletions
diff --git a/Makefile b/Makefile
index 766518c..4fd750e 100644
--- a/Makefile
+++ b/Makefile
@@ -1,9 +1,16 @@
+# Variables
+
+datasets = data/median-correlation.csv data/test.csv data/training.csv data/mazzatorta.csv data/swiss.csv data/test.json data/training.json data/mazzatorta.json data/swiss.json
+crossvalidations = data/training-cv-0.csv data/training-cv-1.csv data/training-cv-2.csv
+validations = data/training-test-predictions.csv $(crossvalidations)
+figures = figure/functional-groups.pdf figure/test-prediction.pdf figure/test-correlation.pdf figure/crossvalidation.pdf figure/dataset-variability.pdf
+
# Paper
loael.pdf: loael.md references.bibtex
pandoc -r markdown+simple_tables+table_captions+yaml_metadata_block -s -S --bibliography=references.bibtex --latex-engine=pdflatex --filter pandoc-crossref --filter pandoc-citeproc -o loael.pdf loael.md
-loael.md: loael.Rmd figures # TODO: add further dependencies
+loael.md: loael.Rmd $(figures) $(datasets) $(validations)
Rscript --vanilla -e "library(knitr); knit('loael.Rmd');"
loael.docx: loael.md
@@ -11,36 +18,36 @@ loael.docx: loael.md
# Figures
-figures: datasets validations figure/functional-groups.pdf figure/test-prediction.pdf figure/test-correlation.pdf figure/crossvalidation.pdf figure/dataset-variability.pdf
-
figure/functional-groups.pdf: data/functional-groups-reduced4R.csv functional-groups.R
Rscript functional-groups.R
figure/dataset-variability.pdf: data/mazzatorta.csv data/swiss.csv dataset-variability.R
Rscript dataset-variability.R
-figure/crossvalidation.pdf: data/combined-cv.csv
+figure/crossvalidation.pdf: $(crossvalidations)
Rscript crossvalidation-plots.R
-figure/test-prediction.pdf: data/combined-test-predictions.csv data/median-correlation.csv test-prediction-plot.R
+figure/test-prediction.pdf: data/training-test-predictions.csv data/median-correlation.csv test-prediction-plot.R
Rscript test-prediction-plot.R
-figure/test-correlation.pdf: data/combined-test-predictions.csv data/median-correlation.csv test-correlation-plot.R
+figure/test-correlation.pdf: data/training-test-predictions.csv data/median-correlation.csv test-correlation-plot.R
Rscript test-correlation-plot.R
# Validations
-validations: data/combined-test-predictions.csv data/combined-cv.csv
+data/training-test-predictions.csv: test-validation.rb data/test.csv data/training.csv
+ ruby test-validation.rb training.csv
-data/combined-test-predictions.csv: test-validation.rb data/test.csv data/combined.csv
- ruby test-validation.rb combined.csv
+data/training-cv-0.csv: crossvalidation.rb data/training.csv
+ ruby crossvalidation.rb training.csv 0
-data/combined-cv.csv: crossvalidation.rb data/combined.csv
- ruby crossvalidation.rb combined.csv
+data/training-cv-1.csv: crossvalidation.rb data/training.csv
+ ruby crossvalidation.rb training.csv 1
-# Datasets
+data/training-cv-2.csv: crossvalidation.rb data/training.csv
+ ruby crossvalidation.rb training.csv 2
-datasets: data/median-correlation.csv data/test.csv data/combined.csv data/mazzatorta.csv data/swiss.csv data/test.json data/combined.json data/mazzatorta.json data/swiss.json
+# Datasets
data/functional-groups-reduced4R.csv: data/functional-groups-reduced.csv functional-groups4R.rb
ruby functional-groups4R.rb
@@ -57,11 +64,11 @@ data/test.json: data/mazzatorta.json
cp data/mazzatorta.json data/test.json
# Combined training set
-data/combined.csv: create-combined.rb data/mazzatorta.csv data/swiss.csv
- ruby create-combined.rb
+data/training.csv: create-training.rb data/mazzatorta.csv data/swiss.csv
+ ruby create-training.rb
-data/combined.json: data/mazzatorta.json
- cp data/mazzatorta.json data/combined.json
+data/training.json: data/mazzatorta.json
+ cp data/mazzatorta.json data/training.json
# Datasets with unique smiles
data/mazzatorta.csv: unique-smiles.rb data/LOAEL_mg_corrected_smiles_mmol.csv
@@ -77,4 +84,5 @@ data/swiss.json: data/swissRat_chron_LOAEL_mmol.json
cp data/swissRat_chron_LOAEL_mmol.json data/swiss.json
clean:
+ rm figure/*pdf
cd data && rm `ls -I "*LOAEL*" -I "*functional*" -I "*SMARTS*"`
diff --git a/TODO b/TODO
index c6f49b5..0e671e5 100644
--- a/TODO
+++ b/TODO
@@ -17,23 +17,22 @@ warning if query compound contains new functional groups
predictions fit experimental data
#only combined dataset (training)
-combined -> training dataset
+#combined -> training dataset
-functional groups: remove, minfreq
+#functional groups: remove, minfreq
smarts f functional groups
error band (expermental variability) for fig 7
# paper
-datasets:
- rat chronic column
- preprocessing remove first sentence
+#datasets:
+ #rat chronic column
+ #preprocessing remove first sentence
results:
- CheSMapper remove text, figures
- light colors at bottom of histograms
- fig 2 smiles -> smarts, leave out?
+ #CheSMapper remove text, figures
+ #fig 2 smiles -> smarts, leave out?
variability from paolos paper
https://en.wikipedia.org/wiki/Root_mean_square_deviation
diff --git a/create-combined.rb b/create-training.rb
index ef3c7a2..acba25b 100644
--- a/create-combined.rb
+++ b/create-training.rb
@@ -28,7 +28,7 @@ end
data.sort!{|a,b| a[1] <=> b[1]}
-CSV.open(File.join(DATA,"combined.csv"),"w+") do |csv|
+CSV.open(File.join(DATA,"training.csv"),"w+") do |csv|
csv << ["SMILES","LOAEL","Dataset"]
data.each{|r| csv << r}
end
diff --git a/crossvalidation-plots.R b/crossvalidation-plots.R
index 7b04984..2bc259f 100644
--- a/crossvalidation-plots.R
+++ b/crossvalidation-plots.R
@@ -1,7 +1,15 @@
library(ggplot2)
+library(grid)
+library(gridExtra)
-combined = read.csv("data/combined-cv.csv",header=T)
+t0 = read.csv("data/training-cv-0.csv",header=T)
+t1 = read.csv("data/training-cv-1.csv",header=T)
+t2 = read.csv("data/training-cv-2.csv",header=T)
-p = qplot(-log10(LOAEL_predicted),-log10(LOAEL_measured_median),data=combined,xlab="-log10(LOAEL predicted)",ylab="-log10(LOAEL measured median)",main="Combined") + geom_point() + geom_abline(intercept=0.0) + xlim(-2,4.5) + ylim(-2,4.5)
+p0 = qplot(-log10(LOAEL_predicted),-log10(LOAEL_measured_median),data=t0,xlab="-log10(LOAEL predicted)",ylab="-log10(LOAEL measured median)",main="Combined") + geom_point() + geom_abline(intercept=0.0) + xlim(-2,4.5) + ylim(-2,4.5)
+p1 = qplot(-log10(LOAEL_predicted),-log10(LOAEL_measured_median),data=t1,xlab="-log10(LOAEL predicted)",ylab="-log10(LOAEL measured median)",main="Combined") + geom_point() + geom_abline(intercept=0.0) + xlim(-2,4.5) + ylim(-2,4.5)
+p2 = qplot(-log10(LOAEL_predicted),-log10(LOAEL_measured_median),data=t2,xlab="-log10(LOAEL predicted)",ylab="-log10(LOAEL measured median)",main="Combined") + geom_point() + geom_abline(intercept=0.0) + xlim(-2,4.5) + ylim(-2,4.5)
-ggsave(file='figure/crossvalidation.pdf', plot=p)
+pdf('figure/crossvalidation.pdf')
+grid.arrange(p0,p1,p2,ncol=2)
+dev.off()
diff --git a/crossvalidation.rb b/crossvalidation.rb
index 00fab96..79aeb83 100644
--- a/crossvalidation.rb
+++ b/crossvalidation.rb
@@ -2,12 +2,12 @@ require_relative 'include.rb'
name = File.basename ARGV[0], ".csv"
file = File.join DATA,ARGV[0]
-csv_file = File.join(DATA,ARGV[0].sub(/.csv/,'-cv.csv'))
-id_file = File.join(DATA,ARGV[0].sub(/.csv/,'-cv.id'))
dataset = Dataset.from_csv_file file
model = Model::LazarRegression.create(dataset, :prediction_algorithm => "OpenTox::Algorithm::Regression.local_fingerprint_regression")
#model = Model::LazarRegression.create(dataset, :prediction_algorithm => "OpenTox::Algorithm::Regression.local_physchem_regression")
#model = Model::LazarRegression.create(dataset, :prediction_algorithm => "OpenTox::Algorithm::Regression.local_weighted_average")
+csv_file = File.join(DATA,ARGV[0].sub(/.csv/,"-cv-#{ARGV[1]}.csv"))
+id_file = File.join(DATA,ARGV[0].sub(/.csv/,"-cv-#{ARGV[1]}.id"))
cv = RegressionCrossValidation.create model
File.open(id_file,"w+"){|f| f.puts cv.id}
diff --git a/data/combined-cv.csv b/data/combined-cv.csv
deleted file mode 100644
index 853ea0c..0000000
--- a/data/combined-cv.csv
+++ /dev/null
@@ -1,637 +0,0 @@
-SMILES,LOAEL_measured_median,LOAEL_predicted,Confidence
-ClC12C3C4(C(C1(Cl)Cl)(C1(C2(C3(Cl)C(C41Cl)(Cl)Cl)Cl)Cl)Cl)Cl,1.9566e-05,0.0013256949622119727,1
-ClC1=C(Cl)C2(C(C1(Cl)C1C2C2CC1C=C2)(Cl)Cl)Cl,2.7404e-05,0.0016651169838136368,1
-N#Cc1nn(c(c1S(=O)C(F)(F)F)N)c1c(Cl)cc(cc1Cl)C(F)(F)F,0.00013611,0.011177655078409487,1
-Clc1ccc2c(c1)[n+]([O-])nc(n2)n1cncc1,0.00020191,0.048911153468458216,1
-OC(=O)C(Oc1ccc(cc1)Oc1ncc(cc1Cl)C(F)(F)F)C,0.00027647,0.015673431840531892,1
-CCOP(=S)(SCSC(C)(C)C)OCC,0.00027736000000000004,0.0024055968139354584,1
-ClC1C2OC2C2C1C1(Cl)C(=C(C2(C1(Cl)Cl)Cl)Cl)Cl,0.00028896749999999995,0.0003872005608077999,1
-ClC1=C(Cl)C2(C(C1(Cl)C1C2C2CC1C1C2O1)(Cl)Cl)Cl,0.000295345,0.0010281938554488118,1
-CCSCCSP(=S)(OCC)OCC,0.00036443,0.0031857123201829984,1
-CNC(=O)ON=CC(SC)(C)C,0.00052559,0.048676702040700716,1
-COC(=O)C(Oc1ccc(cc1)Oc1ccc(cc1Cl)Cl)C,0.00058619,0.19663123960711684,1
-CCSCSP(=S)(OCC)OCC,0.00061449,0.000833087380536691,1
-OC1CCCCCc2cc(O)cc(c2C(=O)OC(CCC1)C)O,0.00062036,1.3394560489313465,1
-ClC1C=CC2C1C1(Cl)C(=C(C2(C1(Cl)Cl)Cl)Cl)Cl,0.000843785,0.00023878471503217986,1
-c1ccc(cc1)[Sn](c1ccccc1)c1ccccc1,0.00085711,0.5915467780579419,1
-CCOP(=O)(SC(CC)C)SC(CC)C,0.000872805,0.006810211870769872,1
-CCS(=O)CCSP(=O)(OC)OC,0.00089328,0.0016027297178080409,1
-ClC1CC2C(C1Cl)C1(C(C2(Cl)C(=C1Cl)Cl)(Cl)Cl)Cl,0.000939545,0.000474144996915765,1
-COP(=S)(Oc1ccc(cc1)N(=O)=O)OC,0.00094982,0.007284727000192782,1
-Clc1c(Cl)c(Cl)c(c(c1Cl)Cl)Cl,0.0010183,0.10209707294282794,1
-CNC(=O)CSP(=S)(OC)OC,0.0010905,0.00950743899812471,1
-COP(=O)(SCCS(=O)(=O)CC)OC,0.0011438,0.0016027297178080409,1
-COC1CC(OC2C(C)C=CC=C3COC4C3(O)C(C=C(C4O)C)C(=O)OC3CC(CC=C2C)OC2(C3)C=CC(C(O2)C(CC)C)C)OC(C1OC1CC(OC)C(C(O1)C)O)C.COC1CC(OC(C1OC1CC(OC)C(C(O1)C)O)C)OC1C(C)C=CC=C2COC3C2(O)C(C=C(C3O)C)C(=O)OC2CC(CC=C1C)OC1(C2)C=CC(C(O1)C(C)C)C,0.0011546,0.004752783530343041,1
-ClC12C(Cl)(Cl)C3(C4(C1(Cl)C1(C2(Cl)C3(C4(C1(Cl)Cl)Cl)Cl)Cl)Cl)Cl,0.0012831,6.240058509303287e-05,0.625
-CCOP(=O)(N1CCSC1=O)SC(CC)C,0.0013411,0.004862125791750852,1
-O=C1CCCC(=O)C1C(=O)c1ccc(cc1[N+](=O)[O-])S(=O)(=O)C,0.0014146,0.01272848084265041,1
-CCOP(=S)(Oc1ccccc1C(=O)OC(C)C)NC(C)C,0.0014476,0.1436976283211822,1
-CCSCCSP(=O)(OC)OC,0.0015199,0.000843810750131057,1
-CCOc1cc(nc(n1)CC)OP(=S)(OC)OC,0.0015396,0.0074692781583135725,1
-COC(=O)C=C(OP(=O)(OC)OC)C,0.0015615,0.0023344044363854274,1
-COC(=O)/C=C(/OP(=O)(OC)OC)\C,0.0015615,0.00219330189291048,1
-OC(=O)c1ccccc1.CCC(C1OC2(C=CC1C)OC1CC=C(C)C(OC3CC(OC)C(C(O3)C)OC3CC(OC)C(C(O3)C)NC)C(C)C=CC=C3C4(C(C(=O)OC(C2)C1)C=C(C)C(C4OC3)O)O)C,0.001735715,0.0017196076009231797,1
-C1CCC(CC1)[Sn](n1ncnc1)(C1CCCCC1)C1CCCCC1,0.001811,0.008514092051115103,1
-ClC1C2(Cl)C3C4C5C1(Cl)C(C2(Cl)C5C3C1C4O1)(Cl)Cl,0.0018377,0.0002087548329594874,1
-CNC(=O)CCSCCSP(=O)(OC)OC,0.0018793,0.003299645431958148,1
-COC1CC(OC2C(C)C=CC=C3COC4C3(O)C(C=C(C4O)C)C(=O)OC3CC(CC=C2C)OC2(C3)C=CC(C(O2)C(C)C)C)OC(C1OC1CC(OC)C(C(O1)C)NC(=O)C)C,0.00194425,0.0020143710247334714,1
-N#CC(c1cccc(c1)Oc1ccccc1)OC(=O)[C@H](C(C)C)Nc1ccc(cc1Cl)C(F)(F)F,0.0019884,0.014130212225346979,1
-CNC(=O)C=C(OP(=O)(OC)OC)C,0.0020165,0.007421163190711053,1
-COP(=O)(SC)N,0.0020549,0.32686975597991175,1
-COP(=S)(Oc1ccc(cc1)[N+](=O)[O-])OC,0.0020896,0.008599103970165984,1
-CSc1ccc(cc1C)OP(=S)(OC)OC,0.00210185,0.006226953399598135,1
-CO[C@H]1C[C@H](O[C@H]2[C@@H](C)C=CC=C3CO[C@H]4[C@]3(O)[C@@H](C=C([C@H]4O)C)C(=O)O[C@H]3C[C@@H](CC=C2C)O[C@]2(C3)C=C[C@@H]([C@H](O2)[C@H](CC)C)C)O[C@H]([C@@H]1O[C@H]1C[C@H](OC)[C@H]([C@@H](O1)C)O)C,0.0022907,0.011736440632139812,1
-O=C1CCCC(=O)C1C(=O)c1ccc(c(c1Cl)COCC(F)(F)F)S(=O)(=O)C,0.0023819,0.0076397623343973636,1
-S=C1NCCN1,0.0024472,0.8700068298681244,1
-COC(=O)C(Oc1ccc(cc1)Oc1ncc(cc1Cl)C(F)(F)F)C,0.0026615,0.00040440532195588495,1
-CCOP(=S)(OCC)SCSc1ccc(cc1)Cl,0.0029166,0.004966131230882334,1
-C1CCN2C(C1)C1CCCCN1CC2,0.0029591,0.14662384480405752,1
-Fc1ccc(cc1)N(C(=O)COc1nnc(s1)C(F)(F)F)C(C)C,0.0033028,0.06691554271741995,1
-CCOP(=S)(Oc1ccc2c(c1)oc(=O)c(c2C)Cl)OCC,0.0033631,0.048408370628155103,1
-CNC(=O)Oc1cccc2c1OC(O2)(C)C,0.0035838,0.04605306530301147,1
-O[Sn](C1CCCCC1)(C1CCCCC1)C1CCCCC1,0.0036089,0.2530228410823333,1
-CCc1nn(c(c1Cl)C(=O)NCc1ccc(cc1)Oc1ccc(cc1)C)C,0.0039076,0.033024789752444356,1
-CCCCSP(=O)(SCCCC)SCCCC,0.0039744,0.1006183990667006,1
-CCOP(=S)(Oc1ncn(n1)c1ccccc1)OCC,0.0041492,0.02324835624859495,1
-CCOP(=O)(OC(=CCl)c1ccc(cc1Cl)Cl)OCC,0.0041717,0.013067571132986849,1
-CCOP(=O)(O/C(=C/Cl)/c1ccc(cc1Cl)Cl)OCC,0.0041717,0.01702737277422357,1
-Clc1nc(nc(n1)Cl)Nc1ccccc1Cl,0.0041739,0.1003905136708278,1
-Clc1cccc(n1)C(Cl)(Cl)Cl,0.0043308,0.11868912490120381,1
-N#CC(c1cccc(c1)Oc1ccccc1)OC(=O)C1C(C1(C)C)C(C(Br)(Br)Br)Br,0.0045112,0.04824745927102927,1
-COc1sc(=O)n(n1)CSP(=S)(OC)OC,0.00471335,0.00874579034717669,1
-N#CC(c1ccc(c(c1)Oc1ccccc1)F)OC(=O)C1C(C1(C)C)/C=C(/c1ccc(cc1)Cl)\Cl,0.0048983,0.026551476994806377,1
-CCOP(=S)(OCC)SCSP(=S)(OCC)OCC,0.0049418,0.002499790726477004,1
-CCOP(=O)(Oc1ccc(c(c1)C)SC)NC(C)C,0.0049447,0.0046994079738164616,1
-N#CC(c1cccc(c1)Oc1ccccc1)OC(=O)C(C(C)C)Nc1ccc(cc1Cl)C(F)(F)F,0.004971,0.014052887933215791,1
-CCNc1nc(nc(n1)Cl)NC(C#N)(C)C,0.0051933,0.019871878568418867,1
-CC(Cc1ccc(cc1)C(C)(C)C)CN1CC(C)OC(C1)C,0.0056016,0.05689806609873522,1
-COP(=S)(Oc1nc(Cl)c(cc1Cl)Cl)OC,0.00620095,0.008888961196783047,1
-COC(=O)Nc1nc2c([nH]1)cc(cc2)S(=O)c1ccccc1,0.0063422,0.4193655175382834,1
-ClCC(N1C(=O)c2c(C1=O)cccc2)SP(=S)(OCC)OCC,0.0063477,0.005535904142441076,1
-CCOP(=S)(Oc1ccc(cc1)N(=O)=O)OCC,0.0067295,0.00914730720067219,1
-OC(C(Cl)(Cl)Cl)(c1ccc(cc1)Cl)c1ccc(cc1)Cl,0.0067479,0.06080482197222799,1
-CNC(=O)Oc1cc(C)c(c(c1)C)N(C)C,0.0067481,0.07149526202720871,1
-COC(=O)N(C(=O)N1COC2(C(=N1)c1ccc(cc1C2)Cl)C(=O)OC)c1ccc(cc1)OC(F)(F)F,0.0068203,0.06940291643582872,1
-CCNc1nc(Cl)nc(n1)NC(C)(C)C,0.0069218,0.02110352327391748,1
-CCOP(=S)(Oc1ccc(cc1)[N+](=O)[O-])OCC,0.0070384,0.004920232148789232,1
-Cc1nn(c(c1/C=N/OCc1ccc(cc1)C(=O)OC(C)(C)C)Oc1ccccc1)C,0.0071176,0.0053531458724221555,1
-Cc1nn(c(c1C=NOCc1ccc(cc1)C(=O)OC(C)(C)C)Oc1ccccc1)C,0.0073074,0.004928836184751161,1
-Clc1ccc(cc1)C(c1ccccc1Cl)(c1cncnc1)O,0.0075484,0.0237544149065793,1
-COP(=S)(SCn1nnc2c(c1=O)cccc2)OC,0.0076105,0.019776424459769452,1
-Fc1ccc(cc1)[Si](c1ccc(cc1)F)Cn1cncn1,0.0076575,0.01656714837148342,1
-N#CC(c1cccc(c1)Oc1ccccc1)OC(=O)C1C(C1(C)C)C=C(Br)Br,0.00781875,0.0476361414541629,1
-Fc1ccc(cc1)C(c1ccccc1Cl)(c1cncnc1)O,0.007943,0.0037767398986128737,1
-N#Cc1nn(c(c1S(=O)CC)N)c1c(Cl)cc(cc1Cl)C(F)(F)F,0.0080563,0.00036850298033193655,1
-CCN(c1nc(cc(n1)C)OP(=S)(OC)OC)CC,0.0081878,0.018670394100004213,1
-Clc1ccc(cc1)OS(=O)(=O)c1ccc(cc1)Cl,0.0082464,0.06993971285350462,1
-Clc1cc(cnc1Nc1c(cc(c(c1[N+](=O)[O-])Cl)C(F)(F)F)[N+](=O)[O-])C(F)(F)F,0.008299399999999998,0.04959851365590442,1
-[O-][N+](=O)c1cc([N+](=O)[O-])c(c(c1)[N+](=O)[O-])C,0.0088055,0.08360420535197528,1
-CCCCOC(=O)C(Oc1ccc(cc1)Oc1ccc(cn1)C(F)(F)F)C,0.00885585,0.0053864179991845295,1
-CSC(=O)c1c(nc(c(c1CC(C)C)C(=O)SC)C(F)(F)F)C(F)F,0.009043,0.20483635152194707,1
-Clc1ccc(c(c1)Cl)C(Cn1cncn1)COC(C(F)F)(F)F,0.0091362,0.03630918352887816,1
-CCCN(C(=O)SCc1ccccc1)CCC,0.0091492,0.06345481449677945,1
-CON(C(=O)Nc1ccc(cc1)Cl)C,0.0093175,0.021314799504830784,1
-CCCCOC(=O)C(Oc1ccc(cc1)Oc1ccc(cc1F)C#N)C,0.0096257,0.06848237855881614,1
-N#C/N=C\1/SCCN1Cc1ccc(nc1)Cl,0.0098922,0.07580141426377905,1
-Cc1c(ccc(c1C1=NOCC1)S(=O)(=O)C)C(=O)c1cnn(c1O)C,0.0099068,0.018192563862906578,1
-CC1(C)CNC(=NC1)NN=C(C=Cc1ccc(cc1)C(F)(F)F)C=Cc1ccc(cc1)C(F)(F)F,0.0099095,0.030129053812819197,1
-COP(=O)(OC=C(Cl)Cl)OC,0.0100688,0.03740024117431609,1
-CCCSP(=O)(SCCC)OCC,0.010069,0.012239556496400182,1
-FC(c1ccc(cc1)C=CC(=NN=C1NCC(CN1)(C)C)C=Cc1ccc(cc1)C(F)(F)F)(F)F,0.010112,0.038274942065551015,1
-CCOC(=O)Nc1cccc(c1)OC(=O)Nc1ccccc1,0.010656,0.24114233756442657,1
-O=C(C1C(C1(C)C)C=C(C(F)(F)F)Cl)OCc1c(F)c(F)c(c(c1F)F)C,0.010986,0.016511847302981244,1
-O=C(C1C(C1(C)C)C=C(C(F)(F)F)Cl)OCc1cccc(c1C)c1ccccc1,0.011824,0.03482970362412285,1
-O=S1OCC2C(CO1)C1(C(C2(Cl)C(=C1Cl)Cl)(Cl)Cl)Cl,0.012287,0.0002292959719534936,1
-Clc1cc(Cl)c(c(c1O)Cc1c(O)c(Cl)cc(c1Cl)Cl)Cl,0.012288,0.12281327824391676,1
-CC(Oc1cc(c(cc1Cl)Cl)n1nc(oc1=O)C(C)(C)C)C,0.0124555,0.0648896491245731,1
-Clc1ccc(c(c1)Cl)n1c(nc2c(c1=O)cc(cc2)F)n1cncn1,0.01268,0.026819869452434184,1
-CCC1CCCC(OC2CCC(C(O2)C)N(C)C)C(C)C(=O)C2=CC3C(C2CC(=O)O1)C=C(C)C1C3CC(C1)OC1OC(C)C(C(C1OC)OC)OC,0.012735,0.039944372672364246,1
-CC1C=CC=C2COC3C2(O)C(C=C(C3O)C)C(=O)OC2CC(CC=C(C1)C)OC1(C2)CCC(C(O1)C)C,0.012862,0.004239636609434808,1
-COc1ccc(cc1NNC(=O)OC(C)C)c1ccccc1,0.012985,1.3103442276911403,1
-N#CC(c1cccc(c1)Oc1ccccc1)OC(=O)C(c1ccc(cc1)OC(F)F)C(C)C,0.01329,0.02515173772898091,1
-CCP(=S)(Sc1ccccc1)OCC,0.0133561,0.11337620636172581,1
-O=c1c(Cl)c(SCc2ccc(cc2)C(C)(C)C)cnn1C(C)(C)C,0.013701,0.07044883675706053,1
-CNP(=O)(Oc1ccc(cc1Cl)C(C)(C)C)OC,0.013712,0.09038896177801285,1
-NC1=C(Cl)C(=O)c2c(C1=O)cccc2,0.01392,1.4201104638681799,1
-CCN(C(=O)SCC)C1CCCCC1,0.01393,0.1637094971395815,1
-CNC(=O)Oc1cccc2c1OC(C2)(C)C,0.01394355,0.052364401039062904,1
-O=C(C1C(C1(C)C)/C=C(/C(F)(F)F)\Cl)OCc1c(F)c(F)c(c(c1F)F)C,0.01409,0.013695451802738396,1
-CC(c1ccccc1)(C[Sn](O[Sn](CC(c1ccccc1)(C)C)(CC(c1ccccc1)(C)C)CC(c1ccccc1)(C)C)(CC(c1ccccc1)(C)C)CC(c1ccccc1)(C)C)C,0.01425,0.12753835596438312,1
-CCCN(c1c(cc(cc1[N+](=O)[O-])C(F)(F)F)[N+](=O)[O-])CC1CC1,0.014397,0.12426923563661679,1
-CC(c1ccc(cc1)CCOc1ncnc2c1cccc2)(C)C,0.014687,0.06519419550170291,1
-CCCCC(c1ccc(cc1Cl)Cl)(Cn1cncn1)O,0.014958,0.06037968254378457,1
-N#CC(c1ccc(cc1)Oc1ccccc1)OC(=O)C1C(C1(C)C)/C=C\C(=O)OC(C(F)(F)F)C(F)(F)F,0.01496,0.05674473010193558,1
-N#Cc1c(Cl)c(C#N)c(c(c1Cl)Cl)Cl,0.015043,0.0030525301132065135,1
-N#CC(c1cc(C)c(cc1Cl)NC(=O)c1cc(I)cc(c1O)I)c1ccc(cc1)Cl,0.015081,0.07648672894220068,1
-Clc1cc(cnc1CCNC(=O)c1ccccc1C(F)(F)F)C(F)(F)F,0.015124,0.05299445071745992,1
-N#CN=S(=O)(C(c1ccc(nc1)C(F)(F)F)C)C,0.015292,0.05976038045583072,1
-CC(C1C2CCC1c1c2cccc1NC(=O)c1cn(nc1C(F)F)C)C,0.015303,0.1279473076510558,1
-Fc1ccc(cc1)[Si](c1ccc(cc1)F)(Cn1cncn1)C,0.015853,0.011266947490121013,1
-CN1CCC(CC1)C1CCN(CC1)C,0.016044,0.09456005347303233,1
-CCCCN(c1c(cc(cc1[N+](=O)[O-])C(F)(F)F)[N+](=O)[O-])CC,0.016106,0.0877536969078648,1
-CCOP(=S)(Oc1cc(C)nc(n1)C(C)C)OCC,0.016429,0.011133307740527188,1
-N#Cc1c(Cl)cccc1Cl,0.0165685,0.07835025199246949,1
-Fc1ccc(cc1)C1(Cn2cncn2)OC1c1ccccc1Cl,0.016679,0.028007952247435894,1
-CCOP(=S)(Oc1nc(Cl)c(cc1Cl)Cl)OCC,0.017114,0.002172216188722482,1
-BrC1COC(C1)(Cn1cncn1)c1ccc(cc1Cl)Cl,0.017185,0.032850559015257706,1
-CC(NC(=S)[S])CNC(=S)S[Zn],0.017255,0.07937722694698279,0.3076923076923077
-CCN(C(=O)SCc1ccc(cc1)Cl)CC,0.0180385,0.028540454851763406,1
-COCC(N(c1c(C)csc1C)C(=O)CCl)C,0.018129,0.2448121299470774,1
-c1cc[n+]2c(c1)c1cccc[n+]1CC2,0.018481499999999998,0.0944847039982625,1
-CCc1nn(c(c1Cl)C(=O)NCc1ccc(cc1)C(C)(C)C)C,0.019469,0.007130921476270174,1
-CCCN(C(=O)n1cncc1)CCOc1c(Cl)cc(cc1Cl)Cl,0.019912,0.026731194277271778,1
-CCOC(=O)c1cn2nc(cc2nc1C)OP(=S)(OCC)OCC,0.0200875,0.11278481360348319,1
-C[n+]1ccc(cc1)c1cc[n+](cc1)C,0.020134,0.17703724711923066,1
-COP(=S)(SCN1C(=O)c2c(C1=O)cccc2)OC,0.020484,0.03471919259139461,1
-ClC=C,0.020801,0.045958000000000006,0.14285714285714285
-Clc1cccc(c1)c1ccccc1,0.021203,0.23322591988057662,1
-CNC(=O)ON=C(C(=O)N(C)C)SC,0.022348,0.01673172895185738,1
-CSC1=NC(C(=O)N1Nc1ccccc1)(C)c1ccccc1,0.0228,0.2052533974522454,1
-CCN(C(=O)C(=C(OP(=O)(OC)OC)C)Cl)CC,0.023024100000000002,0.0047136458758295675,1
-COC(=O)N(c1ccccc1COc1ccn(n1)c1ccc(cc1)Cl)OC,0.023207,0.07698977613299948,1
-CCCCCCCCCCCCC1=C(OC(=O)C)C(=O)c2c(C1=O)cccc2,0.023407,0.3627977428877979,1
-OC(COc1cccc2c1c1ccccc1[nH]2)CNC(C)C,0.02346,0.6148326720757263,1
-O=C(NC(=O)c1ccccc1Cl)Nc1ccc(cc1)OC(F)(F)F,0.023557,0.11659835420727983,1
-CCOC(=O)C(Oc1ccc(cc1)Oc1nc2c(o1)cc(cc2)Cl)C,0.024877,0.0389848363641309,1
-CON(C(=O)Nc1ccc(c(c1)Cl)Cl)C,0.025091,0.012683003380057267,1
-CN(C(=S)S[Zn]SC(=S)N(C)C)C,0.02534245,0.10085113391523537,1
-O=C(NC(=O)c1c(F)cccc1F)Nc1ccc(cc1)Cl,0.025428,0.10576215176905492,1
-CCNc1nc(NCC)nc(n1)Cl,0.0255385,0.013287015321023797,1
-OC(=O)C(Oc1ccc(cc1C)Cl)C,0.025624,0.029473298093290683,1
-Clc1ccccc1CC(C1(Cl)CC1)(Cn1cncn1)O,0.025625,0.2214780319183428,1
-O=C(N(C)C)Nc1ccc(c(c1)Cl)Cl,0.025741,0.10638027419660342,1
-CCOC(=O)C(Oc1ccc(cc1)Oc1cnc2c(n1)ccc(c2)Cl)C,0.0257509,0.050316374651973673,1
-CC(OC(=O)C(c1ccc(cc1)Cl)(c1ccc(cc1)Cl)O)C,0.026532,0.0880353148754688,1
-N#CC(c1cccc(c1)Oc1ccccc1)OC(=O)C1C(C1(C)C)/C=C(/C(F)(F)F)\Cl,0.026676,0.007071037608874015,1
-O=C(C1C(C1(C)C)C=C(Cl)Cl)OCc1c(F)c(F)cc(c1F)F,0.026943,0.07150265077709765,1
-N#Cc1sc2=c(sc1C#N)c(=O)c1c(c2=O)cccc1,0.0269975,0.25137010092137463,1
-CCOC(=O)c1ccccc1C1=c2cc(C)c(cc2=[O]c2c1cc(C)c(c2)NCC)NCC,0.027054,1.7574175288355434,1
-CSCC(=NOC(=O)NC)C(C)(C)C,0.027483,0.008508266684841203,1
-Cc1nn(c(c1C(=O)c1ccc(cc1S(=O)(=O)C)C(F)(F)F)O)C,0.0276,0.0223121709933489,1
-CCOc1cc(ccc1N(=O)=O)Oc1ccc(cc1Cl)C(F)(F)F,0.027647,0.13616685989138735,1
-[O-][N+](=O)c1cc(C(=O)N)c(c(c1)[N+](=O)[O-])C,0.027758,0.0676663511476331,1
-N#CC(c1cccc(c1)Oc1ccccc1)OC(=O)C1C(C1(C)C)C=C(C(F)(F)F)Cl,0.027787,0.015947177847531368,1
-C=CC1(C)OC(=O)N(C1=O)c1cc(Cl)cc(c1)Cl,0.027961,0.1446766215634559,1
-OC(=O)C(Oc1ccc(cc1)Oc1nc2c(o1)cc(cc2)Cl)C,0.028167,0.017258929364652273,1
-N#CC(c1ccc(c(c1)Oc1ccccc1)F)OC(=O)C1C(C1(C)C)C=C(Cl)Cl,0.028207,0.038405800947860204,1
-CSC(=NOC(=O)N(SN(C(=O)ON=C(SC)C)C)C)C,0.028211,0.02379431320371135,1
-CS/C(=N/OC(=O)N(SN(C(=O)O/N=C(/SC)\C)C)C)/C,0.028211,0.028210999999999983,1
-CC(N1C(=NC(C)(C)C)SCN(C1=O)c1ccccc1)C,0.028484,0.04879363214984973,1
-CCO[C@H]1[C@@H](OC)[C@H](O[C@@H]2C[C@@H]3[C@@H](C2)[C@@H]2C=C4[C@H]([C@@H]2CC3)CC(=O)O[C@@H](CC)CCC[C@@H]([C@H](C4=O)C)O[C@H]2CC[C@@H]([C@H](O2)C)N(C)C)O[C@H]([C@@H]1OC)C,0.028877,0.0022907000000000005,0.20238095238095238
-N#Cc1cc(Br)c(c(c1)Br)O,0.02889,0.026140150366013495,1
-CCOC(=O)C(Cc1cc(c(cc1Cl)F)n1nc(n(c1=O)C(F)F)C)Cl,0.029113,0.14837646978213873,1
-C#CCOC(=O)C(Oc1ccc(cc1)Oc1ncc(cc1F)Cl)C,0.029164,0.010777716336569787,1
-CC(N1/C(=N/C(C)(C)C)/SCN(C1=O)c1ccccc1)C,0.029466,0.02958265326244864,1
-COc1nc(Oc2cccc(c2C(=O)[O-])Oc2nc(OC)cc(n2)OC)nc(c1)OC.[Na+],0.030507,0.7874696282154092,1
-CON(C(=O)Nc1ccc(cc1)Br)C,0.0313005,0.05513762602100957,1
-COc1nc(C)nc(n1)N(C(=O)NS(=O)(=O)c1ccccc1C(=O)OC)C,0.031614,0.40712286413682425,1
-Cc1ccc2c(c1)nc1c(n2)sc(=O)s1,0.032011,0.0763709804986192,1
-Fc1ccc(cc1)NC(=O)c1cccc(n1)Oc1cccc(c1)C(F)(F)F,0.032155,0.0847061467698462,1
-CCCn1c(OCCC)nc2c(c1=O)cc(cc2)I,0.032241,0.11240974023972475,0.10810810810810811
-CC(C(=O)O)Oc1cc(Cl)c(cc1Cl)Cl,0.032281,0.03743570267858144,1
-COc1cc(OC)nc(n1)NC(=O)NS(=O)(=O)c1ncccc1C(F)(F)F,0.032652,0.6981307592677698,1
-CN1CN(C)CSC1=S,0.03266,0.057561024688675286,1
-CCC1CCCC(OC2CCC(C(O2)C)N(C)C)C(C)C(=O)C2C(CC(=O)O1)C1CCC3C(C1C2)CC(C3)OC1CC(C)C(C(C1OC)OC)OC,0.032697,0.06647860336529689,1
-ClCC1CN(C(=O)C1Cl)c1cccc(c1)C(F)(F)F,0.033160999999999996,0.05319779479963586,1
-O=C(C(Oc1ccc(cc1)Oc1cnc2c(n1)ccc(c2)Cl)C)OCCON=C(C)C,0.033793,0.055796662316287195,1
-Fc1ccc(cc1)C(c1ccccc1F)(Cn1cncn1)O,0.033854,0.019969815313053807,1
-CN(/C=N/c1ccc(cc1C)C)/C=N/c1ccc(cc1C)C,0.034082,0.03318937625432382,1
-CCCCC(c1ccc(cc1)Cl)(Cn1cncn1)C#N,0.034179,0.09524732085940302,1
-CN(C=Nc1ccc(cc1C)C)C=Nc1ccc(cc1C)C,0.034423,0.04675133378507838,1
-CCOP(=S)(SCn1c(=O)oc2c1ccc(c2)Cl)OCC,0.0345288,0.003205443333311305,1
-ClC(=CCOc1cc(Cl)c(c(c1)Cl)OCCCOc1ccc(cn1)C(F)(F)F)Cl,0.034819,0.036101955216077876,1
-CCOCn1c(c2ccc(cc2)Cl)c(c(c1C(F)(F)F)Br)C#N,0.0350825,0.07257568036547735,1
-Fc1ccc(c(c1)c1ccc(c(c1)Cl)Cl)NC(=O)c1cn(nc1C(F)F)C,0.035609999999999996,0.04755116865693465,1
-CCCSP(=S)(Oc1ccc(cc1)SC)OCC,0.035665,0.0019317165946268113,1
-CCC(C(=O)OC1=C(C(=O)OC21CCCCC2)c1ccc(cc1Cl)Cl)(C)C,0.035787,0.03521871469117486,1
-C#CCOC(c1ccc(cc1)Cl)C(=O)NCCc1ccc(c(c1)OC)OCC#C,0.036904,0.14122820178110387,1
-CC(Cc1ccccc1)N,0.036981,0.2806768105575737,1
-OC(C(C)(C)C)C(n1ncnc1)Cc1ccc(cc1)Cl,0.037441,0.07049436282383191,1
-CCN(c1c(cc(cc1N(=O)=O)C(F)(F)F)N(=O)=O)CC(=C)C,0.037508,0.04933604886865032,1
-Clc1c(O)c(Cl)c(c(c1Cl)Cl)Cl,0.037546,0.05022719951399867,1
-CC(OP(=S)(OC(C)C)SCCNS(=O)(=O)c1ccccc1)C,0.037735,0.0034921174957338597,1
-Clc1ccc(cc1)c1ccccc1NC(=O)c1cccnc1Cl,0.037878,0.6096139704004845,1
-Clc1ccc(c(c1)Cl)C1(OCCO1)Cn1cncn1,0.0379825,0.06957440572418654,1
-CCOC(=O)CSc1nc(nn1C(=O)N(C)C)C(C)(C)C,0.038167,0.28041877908229246,1
-ClC(C(SN1C(=O)C2C(C1=O)CC=CC2)(Cl)Cl)Cl,0.038675,0.3298135504478184,0.42857142857142855
-CC(C(c1cncnc1)(c1ccc(cc1)OC(F)(F)F)O)C,0.038746,0.04709947199669047,1
-OC(=O)COc1cc(Cl)c(cc1Cl)Cl,0.039142,0.05728763095427253,1
-CCOP(=S)(Oc1nn(c(n1)Cl)C(C)C)OCC,0.039842,0.015613713394585008,1
-O=C(NC(=O)c1c(F)cccc1F)Nc1cc(Cl)c(cc1Cl)OC(C(C(F)(F)F)F)(F)F,0.03991,0.11533128322369293,1
-CNC(=S)S,0.040113,0.042124832750827935,1
-CCCOC/C(=N\c1ccc(cc1C(F)(F)F)Cl)/n1cncc1,0.040492,0.013820796487015764,1
-CC(N(C(=O)SCC(=C(Cl)Cl)Cl)C(C)C)C,0.041029,0.034659116233835524,1
-O=C(CC(C)(C)C)OC1=C(C(=O)OC21CCCC2)c1c(C)cc(cc1C)C,0.0414325,0.059414834718533226,1
-OC1(Cn2ncnc2)C(CCC1(C)C)Cc1ccc(cc1)Cl,0.0420535,0.04704002952159344,1
-COP(=S)(Oc1ccc(c(c1)C)[N+](=O)[O-])OC,0.0424911,0.0025680263440382533,1
-CCOC(=O)CCN(C(C)C)SN(C(=O)Oc1cccc2c1OC(C2)(C)C)C,0.042628,0.024668692486746004,1
-CC(Cc1ccc(cc1)C(C)(C)C)CN1CCCCC1,0.043261,0.0032046392460565298,1
-Nc1n[nH]cn1,0.0446005,0.04204987250872471,0.2727272727272727
-Nc1ncn[nH]1,0.0446005,0.04204987250872471,0.2727272727272727
-[S-]C(=S)NCCNC(=S)[S-].[Zn+2],0.044607,0.15072530935954748,1
-CCSC(=O)N1CCCCCC1,0.044874,0.12271869422025235,1
-O=C1OC(C(=O)N1Nc1ccccc1)(C)c1ccc(cc1)Oc1ccccc1,0.04514,0.04525651083360965,1
-ClC(C(c1ccc(cc1)Cl)c1ccc(cc1)Cl)(Cl)Cl,0.045488125000000004,0.07264637704327732,1
-S=C1NCCCN1,0.045617,6.3038,0.125
-ClCC=CCl,0.045958,0.07420608230927381,0.14285714285714285
-CCOC(=O)Cn1c(=O)sc2c1c(Cl)ccc2,0.046003,0.15639066792417952,1
-N#CC(c1c(Cl)ccc(c1Cl)n1ncc(=O)[nH]c1=O)c1ccc(cc1)Cl,0.04661,0.046883495038157925,1
-CN(C(=S)SSC(=S)N(C)C)C,0.04783,0.06344773604156866,1
-Cc1cccc(c1O)C,0.049114,0.2165295749354816,1
-CCC(C(=O)NCc1ccccc1)Oc1ccc(c(c1)C(F)(F)F)F,0.049813,0.056651772229788,1
-COC(=O)Nc1nc2c([nH]1)cc(cc2)Sc1ccccc1,0.050109,0.27381096381187453,1
-CCSC(CC1CC(=O)C(C(=O)C1)C(=NOCC)CCC)C,0.050568,0.12460566123801867,1
-C#CCN1C(=O)COc2c1cc(c(c2)F)N1C(=O)C2=C(C1=O)CCCC2,0.0508,0.0539418859421651,0.11764705882352941
-CNC(=O)Oc1cc(C)c(c(c1)C)C,0.051749,0.058368478174964565,1
-CNC(=O)Oc1cccc(c1)/N=C/N(C)C,0.051976,0.0451544459503357,1
-CN(C(=O)Oc1nc(nc(c1C)C)N(C)C)C,0.0520385,0.030679574124057456,1
-O=N(=O)c1ccc(c(c1)N)C,0.052579,0.2527905485909013,1
-CCO/N=C(\C1=C(O)CC(CC1=O)C1CCCSC1)/CCC,0.052847,0.07875278334485752,1
-CC(C(c1ccc(cc1)Cl)(Cn1ncnc1)O)C1CC1,0.05326,0.025056709910227338,1
-O=C(N/C(=N\OCC1CC1)/c1c(F)c(F)ccc1C(F)(F)F)Cc1ccccc1,0.053352,0.07264167394615283,1
-NC(=NCCCCCCCCNCCCCCCCCN=C(N)N)N,0.053436,0.06155286590252892,1
-C=CCOC(c1ccc(cc1Cl)Cl)Cn1cncc1,0.053503,0.02456177304979273,1
-COCN(c1c(CC)cccc1CC)C(=O)CCl,0.0537505,0.5776298808561321,1
-CNC1=C(c2cccc(c2)C(F)(F)F)C(=O)C(O1)c1ccccc1,0.055205,0.1272207635530908,1
-CCOc1ccc2c(c1)C(=CC(N2)(C)C)C,0.055221,0.33148221710055276,1
-O=C(c1ccc(cc1S(=O)(=O)C)C(F)(F)F)c1cnoc1C1CC1,0.055661,0.032367399052604835,1
-CCOC(=O)COC(=O)c1cc(ccc1[N+](=O)[O-])Oc1ccc(cc1Cl)C(F)(F)F,0.055835,0.7582894135175174,1
-COc1nc(nc(n1)C)NC(=O)[N-]S(=O)(=O)c1cc(I)ccc1C(=O)OC.[Na+],0.056118,0.1797579079237444,1
-CNC(=O)Oc1cccc(c1)N=CN(C)C,0.056496,0.027043374950702744,1
-CCOC(=O)C(c1ccc(cc1)Cl)(c1ccc(cc1)Cl)O,0.056583,0.0534905056365256,1
-OC(=O)COc1ccc(cc1C)Cl,0.0573225,0.1374858357573797,1
-CCOCCN(C(=C(C)C)c1ccccc1)C(=O)CCl,0.05747,0.5013448275944697,1
-CCOC(=O)NCCOc1ccc(cc1)Oc1ccccc1,0.0575765,0.2655583180670471,1
-CN(C(CN1c2ccccc2Sc2c1cccc2)C)C,0.058365,0.06956949821859792,1
-CC1COC(O1)(Cn1cncn1)c1ccc(cc1Cl)Oc1ccc(cc1)Cl,0.059321,0.11327120894691388,1
-N#CC(c1cccc(c1)Oc1ccccc1)OC(=O)C(c1ccc(cc1)Cl)C(C)C,0.059538,0.01010952465943001,1
-CCN(c1c(cc(cc1[N+](=O)[O-])C(F)(F)F)[N+](=O)[O-])CC(=C)C,0.0595625,0.03636221417956393,1
-N#CC(c1cccc(c1)Oc1ccccc1)OC(=O)C1C(C1(C)C)(C)C,0.060099,0.021044538880212044,1
-CC(OC(=O)C(c1ccc(cc1)Br)(c1ccc(cc1)Br)O)C,0.0606145,0.016991083513169893,1
-C=CC=CCC1=C(C)C(CC1=O)OC(=O)C1C(C1(C)C)C=C(C)C.C=CC=CCC1=C(C)C(CC1=O)OC(=O)C1C(C1(C)C)C=C(C(=O)OC)C,0.06135,0.24686576244361327,1
-Clc1ccccc1c1nnc(nn1)c1ccccc1Cl,0.06152150000000001,0.12518396447783367,1
-COC(=O)c1cccc(c1S(=O)(=O)NC(=O)Nc1nc(OCC(F)(F)F)nc(n1)N(C)C)C,0.062141,0.044532992248395256,1
-CCNc1nc(SC)nc(n1)NC(C)(C)C,0.062149,0.013562987100874077,1
-[O-][N+](=O)c1cc(cc(c1)[N+](=O)[O-])[N+](=O)[O-],0.062458,0.050968394283231515,1
-Clc1cc(ccc1Oc1ccc(c(c1)C(=O)NS(=O)(=O)C)[N+](=O)[O-])C(F)(F)F,0.062678,0.15065374027185452,1
-Clc1cc(F)c(cc1C(=O)NS(=O)(=O)N(C(C)C)C)n1c(=O)cc(n(c1=O)C)C(F)(F)F,0.062693,0.029112999999999997,0.10416666666666667
-COc1nc(nc(n1)C)NC(=O)NS(=O)(=O)c1ccccc1Cl,0.062889,0.08922291015617623,1
-O=C(NS(=O)(=O)c1c(C)cccc1C(=O)O)Nc1nc(OCC(F)(F)F)nc(n1)N(C)C,0.063963,0.11229542199312496,1
-COc1nc(nc(n1)C)NC(=O)NS(=O)(=O)c1ccsc1C(=O)OC,0.064534,0.12474889604443357,1
-O=C(N(C)C)Nc1ccc(c(c1)Cl)n1nc(oc1=O)C(C)(C)C,0.064937,0.010850071933786998,1
-CCCCN(SN(C(=O)Oc1cccc2c1OC(C2)(C)C)C)CCCC,0.065695,0.04311589274981677,1
-[O-][N+](=O)NC1=NCCN1Cc1ccc(nc1)Cl,0.066494,0.06983499732815486,1
-O=C(NC(=O)c1c(F)cccc1F)Nc1cc(Cl)c(c(c1F)Cl)F,0.06691,0.07794450362937026,1
-CSc1nnc(c(=O)n1N)C(C)(C)C,0.067199,0.013700999999999996,0.11538461538461539
-O=C(NC(=O)c1c(F)cccc1F)Nc1ccc(c(c1)Cl)OC(C(OC(F)(F)F)F)(F)F,0.06758600000000001,0.04990201341868817,1
-CCOc1ccc(cc1)C(COCc1cccc(c1)Oc1ccccc1)(C)C,0.068395,0.09666883573836946,1
-C#CCOS(=O)OC1CCCCC1Oc1ccc(cc1)C(C)(C)C,0.06905,0.11822577560262015,1
-CCO/N=C(/C1=C(O)CC(CC1=O)c1c(C)cc(cc1C)C)\CC,0.069817,0.15296827749856443,1
-CO/N=C(/c1ccccc1COc1cc(C)ccc1C)\C(=O)NC,0.070468,0.6592822660136698,1
-COc1cc(OC)n2c(n1)nc(n2)S(=O)(=O)Nc1c(Cl)ccc(c1Cl)C,0.071727,0.38440305457631463,1
-OC(=O)COc1nc(Cl)c(cc1Cl)Cl,0.07213454999999999,0.057476139233731106,1
-CCCN(c1c(cc(cc1[N+](=O)[O-])S(=O)(=O)N)[N+](=O)[O-])CCC,0.07218,0.1428533665730988,1
-CCN1CCN(CC1)c1cc2c(cc1F)c(=O)c(cn2C1CC1)C(=O)O,0.072344,0.14796068079487337,1
-Nc1ccc(cc1)Cl,0.072508,0.17494468126384538,1
-CO/N=C(\c1ccccc1CO/N=C(/c1cccc(c1)C(F)(F)F)\C)/C(=O)OC,0.072728,0.17258713194270128,1
-O=C(N(C)C)Nc1cccc(c1)C(F)(F)F,0.073957,0.028168866359541144,1
-OC(C(C)(C)C)C(n1cncn1)Oc1ccc(cc1)c1ccccc1,0.074093,0.20643434587608972,1
-CCCSc1ccc2c(c1)[nH]c(n2)NC(=O)OC,0.075377,0.23138893863325,1
-Cn1nc(c(c1)C(=O)Nc1cccc2c1C1CCC2C1=C(Cl)Cl)C(F)F,0.075835,0.07840740133487478,1
-CCNc1nc(NC(C)C)nc(n1)Cl,0.077892,0.09542622196726332,1
-N#C/N=C(/N(Cc1ccc(nc1)Cl)C)\C,0.07859,0.025211982621502822,1
-CC(c1cc(ccc1O)C(c1ccc(c(c1)C(C)C)O)(C)C)C,0.080014,0.4801984745947794,1
-C=CCC1=C(C)C(CC1=O)OC(=O)C1C(C1(C)C)C=C(C)C,0.081016,0.10212714039120113,1
-NC(=N)NCCCCCCCCNC(=N)N,0.08102,0.12282753342909995,1
-O=C(C1=C(C)OCCS1)Nc1ccccc1,0.0811745,0.1408897841601131,1
-Clc1cc(cnc1CNC(=O)c1c(Cl)cccc1Cl)C(F)(F)F,0.082121,0.023014861241390974,1
-CNC(=O)Oc1cc(C)c(c(c1)C)SC,0.0827735,0.019509342348745098,1
-O=C(c1cccc(c1C(=O)NC(CS(=O)(=O)C)(C)C)I)Nc1ccc(cc1C)C(C(F)(F)F)(C(F)(F)F)F,0.0827975,0.09120820541175852,1
-COC(=O)Nc1cccc(c1)OC(=O)Nc1cccc(c1)C,0.083248,0.04455499038648241,1
-CCCN(c1c(cc(c(c1[N+](=O)[O-])N)C(F)(F)F)[N+](=O)[O-])CCC,0.08393,0.12254117091989798,1
-OC(C(C)(C)C)C(n1ncnc1)Oc1ccc(cc1)Cl,0.084527,0.1148759132503888,1
-O=C(C(C)(C)C)C(n1ncnc1)Oc1ccc(cc1)Cl,0.085107,0.05767071605055378,1
-CCCC(=C1C(=O)CC(CC1=O)C1CCCSC1)NOCC,0.08603,0.02942797334316427,1
-Cn1cc(c2cccc(c2)C(F)(F)F)c(=O)c(c1)c1ccccc1,0.08730199999999999,0.07785085723179364,1
-CC(NC(=O)N1CC(=O)N(C1=O)c1cc(Cl)cc(c1)Cl)C,0.08783250000000001,0.06807351127420704,1
-CC(=O)Nc1cc(NS(=O)(=O)C(F)(F)F)c(cc1C)C,0.088948,0.6780233355694847,1
-COCC(=O)Nc1cc(ccc1NC(=NC(=O)OC)NC(=O)OC)Sc1ccccc1,0.08959,0.15847371102769114,1
-CCCN(C(=O)SCC)CCC,0.0897945,0.016283440985122764,1
-COc1cc(ccc1OC)/C(=C/C(=O)N1CCOCC1)/c1ccc(cc1)Cl,0.0902395,0.14393963791143458,1
-CCC(=O)Nc1ccc(c(c1)Cl)Cl,0.09171,0.333568365804758,1
-N#CC(c1ccccc1)(Cn1cncn1)CCc1ccc(cc1)Cl,0.092038,0.10513801664225397,1
-Clc1ccc2c(c1)ncc(n2)Oc1ccc(cc1)OC(C(=O)OCC1CCCO1)C,0.092103,0.039374926974406005,1
-CNC(=O)ON=C(SC)C,0.092474,0.04408248592060167,1
-NC(=O)c1c(Cl)cccc1Cl,0.092619,0.17677494087773862,1
-Clc1ccc(c(c1)Cl)NC(=O)C1(CC1)C(=O)O,0.093032,0.20540187587900968,1
-Clc1cc(Cl)cc(c1)C1(CO1)CC(Cl)(Cl)Cl,0.093625,0.08040969607549583,1
-ClC(=CC1C(C1(C)C)C(=O)OCc1cccc(c1)Oc1ccccc1)Cl,0.095836,0.15525761200750926,1
-OC(=O)C(Oc1ccc(cc1Cl)Cl)C,0.0967835,0.06520821629920553,1
-[O-][N+](=O)/N=C/1\NCCN1Cc1ccc(nc1)Cl,0.097395,0.0498238889526532,1
-NC(=N)NCCCCCCCCCCCCOC(=O)C,0.1016,0.07890791550233842,1
-OC1CC2(O)CC(O)C(C(O2)(C)CC(C=CC=CC=CC=CCC(OC(=O)C=CC2C(C1)(C)O2)C)OC1(C)OC(C)C(C(C1O)N)O)C(=O)O,0.10172,0.3454024852255698,0.11538461538461539
-COP(=O)(NC(=O)C)SC,0.1023645,0.002336517915881827,1
-COc1ncc(c2n1nc(n2)NS(=O)(=O)c1c(cccc1C(F)(F)F)OCC(F)F)OC,0.10344,0.5793947443673408,1
-COCc1c(F)c(F)c(c(c1F)F)COC(=O)C1C(C1(C)C)/C=C/C,0.10573,0.02826127404446732,1
-[O-][N+](=O)c1cnc(n1C)C,0.10629,0.4321727995049707,1
-CCOC(=O)C(OC(=O)c1cc(ccc1N(=O)=O)Oc1cc(ccc1Cl)C(F)(F)F)C,0.10828,0.11158496211838487,1
-CCOC(=O)C(OC(=O)c1cc(ccc1[N+](=O)[O-])Oc1ccc(cc1Cl)C(F)(F)F)C,0.10828,0.20315463110568607,1
-COc1c(OC)cc(c(c1OC)C(=O)c1c(OC)ncc(c1C)Cl)C,0.108388,0.47251185201133067,1
-S=C1NCCNC(=S)S[Mn+2]S1,0.10856,0.027076543319787847,1
-ClCC(=O)N(c1ccccc1)C(C)C,0.10865,0.04358738695355643,1
-O=C1CCCC(=O)C1C(=O)c1ccc(cc1Cl)S(=O)(=O)C,0.11010835,0.005221326635599275,1
-CCCN(CC1COC2(O1)CCC(CC2)C(C)(C)C)CC,0.11029,1.3278,0.1
-O=C1N(c2cc(Cl)cc(c2)Cl)C(=O)C2(C1(C)C2)C,0.1108605,0.09110908501858947,1
-COC(=O)c1c(nc(c(c1CC(C)C)C1=NCCS1)C(F)(F)F)C(F)F,0.11151,0.07000589236173488,1
-Oc1ccc(c(c1)C)C,0.1146,0.24597693213596078,1
-Clc1ccc(cc1)CCC(C(C)(C)C)(Cn1cncn1)O,0.115167,0.08421759441500878,1
-CNc1cnn(c(=O)c1Cl)c1cccc(c1)C(F)(F)F,0.1152575,0.08228631990037968,1
-N#Cc1c(N)nc(nc1N)NC1CC1,0.11566,0.10848236653429426,1
-CC(N(c1c(cc(cc1N(=O)=O)S(=O)(=O)N)N(=O)=O)C(C)C)C,0.11817,0.44536613196402264,1
-CNC(=O)O/N=C(\SC)/C,0.11837,0.06924562409892328,1
-CCN(c1c(cc(cc1[N+](=O)[O-])C(F)(F)F)[N+](=O)[O-])Cc1c(F)cccc1Cl,0.11856,0.059723353173232956,1
-Nc1ccc(cc1)S(=O)(=O)Nc1nc(C)cc(n1)C,0.11856,0.2114468941953269,1
-COc1cc(ccc1OC)C(=CC(=O)N1CCOCC1)c1ccc(cc1)Cl,0.11937,0.08493030834500154,1
-CCCCc1c(=O)nc([nH]c1C)NCC,0.11945,0.20321175404469666,1
-COC(=O)NC(=S)Nc1ccccc1NC(=S)NC(=O)OC,0.12412500000000001,0.29639107460573455,1
-c1coc(c1)c1nc2c([nH]1)cccc2,0.12487,0.16345305860877363,1
-CN(C(=O)C(c1ccccc1)c1ccccc1)C,0.12536,0.252017522892532,1
-CCOc1cc(ccc1[N+](=O)[O-])Oc1ccc(cc1Cl)C(F)(F)F,0.12856,0.11548226573327393,1
-[O-][N+](=O)/N=C(\NC)/NCc1cnc(s1)Cl,0.13017,1.4984994797645517,1
-Clc1c(ccc(c1N)[N+](=O)[O-])Oc1ccccc1,0.13224349999999999,0.44604309558497135,1
-OC(C(C)(C)C)C(=Cc1ccc(cc1)Cl)n1ncnc1,0.13507,0.2625802165125763,1
-CCNC(=O)NC(=O)/C(=N\OC)/C#N,0.135735,0.15289,1
-O=C(Nc1cnns1)Nc1ccccc1,0.13621,0.07091123061323612,1
-CCc1ccc(cc1)C(=O)NN(C(C)(C)C)C(=O)c1cc(C)cc(c1)C,0.13674999999999998,1.1141000224735962,1
-CN1CC2CC1CN2c1cc2c(cc1F)c(=O)c(cn2C1CC1)C(=O)O,0.13991,0.15516821975426845,1
-OCC(CCl)O,0.14067559999999998,14.49700149043021,1
-COC(=O)C(N(c1c(C)cccc1C)C(=O)Cc1ccccc1)C,0.14136,0.3389265622476747,1
-COc1nc(C)nc(n1)N(C(=O)NS(=O)(=O)c1ccccc1C(=O)O)C,0.14422,0.13660513530329318,1
-ClC(=C)Cl,0.14441,0.010111649638502713,0.1
-CC(=O)O.CCCCCCCCCCCCNC(=N)N,0.14612,0.052877720107918885,1
-CON=C(c1ccccc1CON=C(c1cccc(c1)C(F)(F)F)C)C(=O)OC,0.14693,0.10075330074887334,1
-COC(CCCC(CC=CC(=CC(=O)OC(C)C)C)C)(C)C,0.14816,0.7701876369159575,1
-c1scc(n1)c1nc2c([nH]1)cccc2,0.14907,0.07699993998855402,1
-CC(N1C(=O)c2ccccc2NS1(=O)=O)C,0.14983,0.8026729593409413,1
-N#CC(c1cccc(c1)Oc1ccccc1)OC(=O)C1C(C1(C)C)C=C(Cl)Cl,0.150135,0.027338877871913532,1
-Cc1cccc2c1n1cnnc1s2,0.150605,0.2583348711393936,1
-ClC(SN1C(=O)c2c(C1=O)cccc2)(Cl)Cl,0.15173999999999999,0.22399250093818054,1
-CON=C(c1ccc(cc1Cl)Cl)Cc1cccnc1,0.15246,0.055340269703244654,1
-CCNC(=O)NC(=O)C(=NOC)C#N,0.15289,0.13464656029769198,1
-Clc1ccc(c(c1)Cl)C=C(C(C(C)(C)C)O)n1cncn1,0.15327,0.11585082175588145,1
-CCC(Nc1c(cc(cc1[N+](=O)[O-])C(C)(C)C)[N+](=O)[O-])C,0.153385,0.050847810645436115,1
-COC=C(c1ccccc1Oc1ncnc(c1)Oc1ccccc1C#N)C(=O)OC,0.15432,0.21740569749799113,1
-COP(=S)(Oc1cc(Cl)c(cc1Cl)Cl)OC,0.1555,0.007465919889678132,1
-CCCCCCCCc1cc(N(=O)=O)c(c(c1)N(=O)=O)OC(=O)C=CC,0.15642,0.36458886480183417,1
-Cc1nc(Nc2ccccc2)nc(c1)C1CC1,0.15802,0.5049958406738252,1
-CCOC(=O)CN(c1c(CC)cccc1CC)C(=O)CCl,0.16036,0.15573428530224812,1
-CC(OC(=O)Nc1ccccc1)C,0.16182,1.2038794826813126,1
-c1ccc(cc1)Nc1ccccc1,0.16546,0.34214154497849186,1
-C#CC(NC(=O)c1cc(Cl)cc(c1)Cl)(C)C,0.16593,0.10495846539939853,1
-Cc1ccc(c2c1cccc2)C,0.17283,0.20065212533915003,1
-Clc1cc(Cl)c(cc1n1nc(n(c1=O)C(F)F)C)NS(=O)(=O)C,0.17304,0.02384153039577781,1
-COC(=O)c1ccc(cc1C1=NC(C(=O)N1)(C)C(C)C)C,0.17341,0.4191501641238604,1
-CNC(=O)N(c1nnc(s1)C(C)(C)C)C,0.1752,0.1495836088149363,1
-CCCCCCC(c1cc(cc(c1OC(=O)/C=C/C)[N+](=O)[O-])[N+](=O)[O-])C,0.17563,0.2545305073618732,1
-CCCCCCCCCC[N+](CCCCCCCCCC)(C)C.[Cl-],0.17676,1.1336101490021564,1
-CCCC1COC(O1)(Cn1cncn1)c1ccc(cc1Cl)Cl,0.176786,0.040032582610034013,1
-N#Cc1cc(C)c(c(c1)C(=O)NC)NC(=O)c1cc(nn1c1ncccc1Cl)Br,0.17901,0.01959582292450347,1
-COCC(=O)N(c1c(C)cccc1C)N1CCOC1=O,0.17966,0.1487457875748487,1
-CC1=NNC(=O)N(C1)/N=C/c1cccnc1,0.18092,0.6252990751401865,1
-C#CCC1=C(C)C(CC1=O)OC(=O)C1C(C1(C)C)C=C(C)C,0.18558899999999998,0.10642915416664439,1
-O=N(=O)c1ccc(c(c1)N(=O)=O)C,0.18668,0.08595887901173618,1
-ClCC(=O)N(c1c(C)cccc1C)Cn1cccn1,0.18829800000000002,0.15567835942186406,1
-N#CCNC(=O)c1cnccc1C(F)(F)F,0.19244,0.5427855256778984,1
-OC1CN(C(=O)N1c1nnc(s1)C(C)(C)C)C,0.19507,0.1752,0.4
-O=c1nc(N(C)C)n(c(=O)n1C1CCCCC1)C,0.19817,0.50364,0.16666666666666666
-COc1nc(nc(n1)C)NC(=O)NS(=O)(=O)c1ccccc1CCC(F)(F)F,0.200175,0.09707150588929125,1
-Nc1ccc(c(c1)N)O,0.20138,1.4562256171566648,1
-Cn1nc(c(c1)C(=O)Nc1ccccc1C1CC1C1CC1)C(F)F,0.2022,0.045280907807383065,1
-O=C(NS(=O)(=O)c1ccccc1C(=O)OC1COC1)Nc1nc(C)cc(n1)C,0.20423,0.13785207944512576,1
-CO/C=C(\c1ccccc1Oc1ncnc(c1)Oc1ccccc1C#N)/C(=O)OC,0.20427,0.16674362069652293,1
-ClC=C(c1cc(Cl)c(cc1Cl)Cl)OP(=O)(OC)OC,0.20494,0.004310893390577039,1
-CC(=CC1C(C1(C)C)C(=O)OCc1coc(c1)Cc1ccccc1)C,0.2068305,0.11584321939060163,1
-ClCC(=O)N(c1c(CC)cccc1CC)CNC(=O)C,0.21058,0.48432074444169504,1
-CCOCN(c1c(C)cccc1CC)C(=O)CCl,0.21666999999999997,0.11444463906789311,1
-CC(c1ccc(cc1)O)(c1ccc(cc1)O)C,0.21902,0.3679654268791726,1
-CC(Nc1nc(NC(C)C)nc(n1)Cl)C,0.219845,0.06340505986168649,1
-Fc1ccc(cc1)C(=O)CCCN1CCN(CC1)c1ccccn1,0.221446,0.26723279490757085,1
-COCC(=O)N(c1c(C)cccc1C)C(C(=O)OC)C,0.22375,0.1735868657144906,1
-Nc1ccc2c(c1)nc1c(c2)ccc(c1)N,0.22462,0.40061581692956755,1
-Cc1nnc(c(=O)n1N)c1ccccc1,0.2326765,0.2208383183584409,1
-CCNC(=O)C(OC(=O)Nc1ccccc1)C,0.23279,0.19887387104852916,1
-CNC(=O)Oc1ccccc1OC(C)C,0.23418,0.02804416739630823,1
-Cl/C=C/CO/N=C(\C1=C(O)CC(CC1=O)CC(SCC)C)/CC,0.23895,0.1494808047305403,1
-CCCCCCCCSC(=O)Oc1cc(Cl)nnc1c1ccccc1,0.24081999999999998,0.1756867983898355,1
-Nc1cnn(c(=O)c1Cl)c1ccccc1,0.24815,0.15325426728351224,1
-CCc1cc(C)cc(c1c1c(OC(=O)C(C)(C)C)n2n(c1=O)CCOCC2)CC,0.24968,0.10769710055647778,1
-CC1OC(C)OC(OC(O1)C)C,0.2497,0.71759,0.25
-[S]C(=S)NCCNC(=S)S[Mn],0.25254,0.06925561625351073,0.5555555555555556
-O=C1N(OCC1(C)C)Cc1ccccc1Cl,0.253443,0.07647837984785612,1
-CC(CC(c1sccc1NC(=O)c1cn(nc1C(F)(F)F)C)C)C,0.25458,0.09782662843119466,1
-CCSC(CC1CC(=O)C(=C(NOCC=CCl)CC)C(=O)C1)C,0.25839999999999996,0.18293674689934017,1
-Cc1ccc(cc1)N(S(=O)(=O)N(C)C)SC(Cl)(Cl)F,0.25917,0.07969043541391148,1
-CC1N(C(=O)NC2CCCCC2)C(=O)SC1c1ccc(cc1)Cl,0.259436,0.04005266390325064,1
-Fc1ccc(cc1)Oc1ccnc2c1c(Cl)cc(c2)Cl,0.25963,0.055779827077111925,1
-CCCCCCC(c1cc(cc(c1OC(=O)/C=C\C)[N+](=O)[O-])[N+](=O)[O-])C,0.26317500000000005,0.1182193925380227,1
-CCN(C(=O)C(Oc1cccc2c1cccc2)C)CC,0.271895,0.4023979292131557,1
-OC(=O)C(Cl)(Cl)C,0.273385,0.40748941215818874,1
-COc1cc(OC)nc(n1)NC(=O)NS(=O)(=O)c1ncccc1S(=O)(=O)CC,0.28045,0.6953814394904266,1
-OC(=O)COc1ccc(cc1Cl)Cl,0.2805,0.09927408401065535,1
-CO/C=C(\c1ccccc1COc1cccc(n1)C(F)(F)F)/C(=O)OC,0.28313,0.11494204535315701,1
-CCOC(=O)CC(C(=O)OCC)SP(=S)(OC)OC,0.292105,0.0224309463357269,1
-CNC(=O)Oc1cccc2c1cccc2,0.29818,0.10386523138524342,1
-COC(=O)c1ccccc1S(=O)(=O)NC(=O)Nc1nc(OC(F)F)cc(n1)OC(F)F,0.29893,0.5879373772903014,1
-CN(C(=S)[S-])C.CN(C(=S)[S-])C.CN(C(=S)[S-])C.[Fe+3],0.30012,0.03237758502851625,1
-CCOC(=O)c1ccccc1S(=O)(=O)NC(=O)Nc1nc(Cl)cc(n1)OC,0.30133,0.5387245381366738,1
-Fc1ccc(c(c1)F)NC(=O)c1cccnc1Oc1cccc(c1)C(F)(F)F,0.30333,0.05760403378897727,1
-NC1CC(N=C(C(=O)O)N)C(OC1OC1C(O)C(O)C(C(C1O)O)O)C,0.30578,2.574489036438502,1
-CNC(=O)Oc1cc(C)cc(c1C)C,0.30635,0.04696290381687956,1
-Clc1ccc(cc1)CN(C(=O)Nc1ccccc1)C1CCCC1,0.31170800000000004,0.06174119226311679,1
-ClCCOc1ccccc1S(=O)(=O)NC(=O)Nc1nc(C)nc(n1)OC,0.31207450000000003,0.31432215806248914,1
-CCC(n1c(=O)[nH]c(c(c1=O)Br)C)C,0.31690999999999997,0.11944999999999997,0.14814814814814814
-OC(=O)CCl,0.31747,0.16711518719423485,1
-ClC(SN1C(=O)C2C(C1=O)CC=CC2)(Cl)Cl,0.32935499999999995,0.07976078042600031,1
-CN(C1C(=O)C(=C(O)N)C(=O)C2(C1CC1C(=C(O)c3c(C1(C)O)cccc3O)C2=O)O)C,0.33751,7.451766115785945,1
-Clc1cc(ccc1Oc1ccc(c(c1)C(=O)O)[N+](=O)[O-])C(F)(F)F,0.34563,0.34874764544447434,1
-N=C(NC(=N)N)NCCc1ccccc1,0.35565,0.3556361221730666,1
-COc1ccc(cc1)C(C(Cl)(Cl)Cl)c1ccc(cc1)OC,0.36164,0.1265467049128216,1
-Cc1cc(C)cc(c1)C(=O)N(C(C)(C)C)NC(=O)c1ccc2c(c1C)CCCO2,0.3678,0.47314070100080247,1
-O=C(Nc1ccnc(c1)Cl)Nc1ccccc1,0.37548,0.04119061527401321,1
-CO/N=C(\c1ccccc1Oc1ncnc(c1F)Oc1ccccc1Cl)/C1=NOCCO1,0.39448,0.09031046696084999,1
-N#Cc1ccc(cc1)C/C(=N/NC(=O)Nc1ccc(cc1)OC(F)(F)F)/c1ccc(cc1)C(F)(F)F,0.39494,0.1289156533936465,1
-NCCNc1cccc2c1cccc2,0.42415,0.5041505717401247,1
-CC(=CC1C(C1(C)C)C(=O)OCc1cccc(c1)Oc1ccccc1)C,0.42802,0.05494724264264156,1
-CC(Oc1ccccn1)COc1ccc(cc1)Oc1ccccc1,0.433615,0.06255777987627306,1
-N#Cc1c[nH]cc1c1cccc2c1OC(O2)(F)F,0.449265,0.8015791740632473,1
-O=C(NC(=O)c1c(F)cccc1F)Nc1ccc(cc1F)Oc1ccc(cc1Cl)C(F)(F)F,0.458295,0.07689645205805669,1
-CCSC(=O)N(CC(C)C)CC(C)C,0.46004,0.021799212026929166,1
-CSC(=O)c1cccc2c1snn2,0.46082,0.2921698747527669,1
-ClCC(=O)N(c1c(C)cccc1CC)COC(C)C,0.463365,0.16882237548986226,1
-Cc1cc(N)c(cc1C)C,0.46595,0.10584602574432846,1
-Clc1cc(ccc1Oc1ccc(c(c1)C(=O)[O-])[N+](=O)[O-])C(F)(F)F.[Na+],0.46919,0.3098807099240806,1
-Clc1c(Cl)c([N+](=O)[O-])c(c(c1Cl)Cl)Cl,0.47404,0.03270697752233635,1
-CC1OC(C)CN(C1)C1CCCCCCCCCCC1,0.48317,0.02422606420968877,1
-COc1nc(nc(n1)C)NC(=O)NS(=O)(=O)c1ccccc1C(=O)OC,0.48379,0.08370885626026489,1
-CCCCc1c(C)nc(nc1OS(=O)(=O)N(C)C)NCC,0.49302,0.06088089285660283,1
-CN1N(C)C(CC1c1ccccc1)c1ccccc1,0.49534,0.2195420020229526,1
-OC(=O)C(Oc1cccc(c1)Cl)C,0.49846,0.02233156647755098,1
-COC(=O)C(NC(=O)C(CC(=O)O)N)Cc1ccccc1,0.49949,0.5850132465767467,1
-O=c1[nH]c2CCCc2c(=O)n1C1CCCCC1,0.50364,0.1579369235868818,1
-CCOC(=O)OC1=C(C(=O)NC21CCC(CC2)OC)c1cc(C)ccc1C,0.5061,0.08176658385983912,1
-N#Cc1c[nH]cc1c1cccc(c1Cl)Cl,0.50615,0.051215931949500394,1
-CCOc1nc(nc(n1)NC)NC(=O)NS(=O)(=O)c1ccccc1C(=O)OC,0.51169,0.17773381602953137,1
-CCCCC(COC(=O)c1ccccc1C(=O)OCC(CCCC)CC)CC,0.51209,3.346952927678189,1
-Nc1nc(NC2CC2)nc(n1)N,0.514491,0.1592850202388702,1
-CCCCOCCOCCOCc1cc2OCOc2cc1CCC,0.51708,0.3903993311226464,1
-COc1c(Cl)ccc(c1C(=O)O)Cl,0.52027,0.8384453203050886,1
-CCOc1cc(ccc1C1COC(=N1)c1c(F)cccc1F)C(C)(C)C,0.5203,0.044433715744366484,1
-COCC(N(c1c(C)cccc1CC)C(=O)CCl)C,0.52855,0.2017279252684121,1
-O=CCC1CC(C)C(=O)C=CC(=CC(C(OC(=O)CC(C(C1OC1(C)OC(C)C(C(C1O)N(C)C)OC1(C)OC(C)C(C(C1)(C)O)O)C)O)CC)COC1OC(C)C(C(C1OC)OC)O)C,0.52958,0.12358461251658102,1
-[O-][N+](=O)/N=C\1/N(Cc2cnc(s2)Cl)COCN1C,0.53134,0.13017,0.23076923076923078
-COC(=O)C1(O)c2cc(Cl)ccc2c2c1cccc2,0.54605,0.01802620124970752,1
-COC(=O)c1cc(ccc1[N+](=O)[O-])Oc1ccc(cc1Cl)Cl,0.54657,0.42237555685565,1
-CC(C12CCC(O2)(C(C1)OCc1ccccc1C)C)C,0.54665,0.3219772779610656,1
-Oc1ccc2c(c1N=Nc1ccccc1)ccc(c2)S(=O)(=O)O,0.54821,1.3886327455523073,1
-Nc1ccc(c(c1)N(=O)=O)N,0.56811,0.2804083362878233,1
-CCCN(c1c(cc(cc1[N+](=O)[O-])C(F)(F)F)[N+](=O)[O-])CCCl,0.56902,0.06494950861999851,1
-NC1CCCCC1,0.5974349999999999,0.21433100178807302,1
-COC(=O)c1csc(c1S(=O)(=O)NC(=O)n1nc(n(c1=O)C)OC)C,0.5994,0.5429608670889106,1
-COc1cc(Cl)c(cc1Cl)OC,0.60371,0.07919613263587906,1
-COCCN(c1c(C)cccc1C)C(=O)CCl,0.6139,0.07724717041159121,1
-OC(=O)C1C2CCC(C1C(=O)O)O2,0.61774,0.5699732483940234,1
-O=Cc1ccco1,0.62445,0.12487,0.1111111111111111
-CCCCNC(=O)n1c(NC(=O)OC)nc2c1cccc2,0.628625,0.2610710991106925,1
-CN(C(=O)Nc1ccc(cc1)Cl)C,0.62925,0.028774413345298757,1
-COc1c(OC)cc(c(c1OC)C(=O)c1c(OC)ccc(c1C)Br)C,0.63528,0.1577332179726726,1
-OC1(Cn2ncnc2)/C(=C/c2ccc(cc2)Cl)/CCC1(C)C,0.64063,0.07620497526521675,1
-COC(=O)c1ccc(cc1)C(=O)OC,0.64372,1.2884624080505191,1
-Clc1ccc(cc1)S(=O)(=O)c1cc(Cl)c(cc1Cl)Cl,0.64597,0.036861029336468266,1
-CC(OC(=O)NC(C(=O)NC(c1nc2c(s1)cc(cc2)F)C)C(C)C)C,0.65432,0.1635769833258675,1
-CCCOC(=O)NCCCN(C)C.Cl,0.66747,2.8880425961450746,1
-CCCCOCC(OCC(O)C)C,0.67269,0.6023016576472656,1
-CC1OC(C)OC(C1)OC(=O)C,0.71759,0.2085996500301516,1
-[O-][N+](=O)c1cc(Cl)c(c(c1)Cl)N,0.72459,0.06879792582835728,1
-COc1nc(nc(c1)OC)NC(=O)NS(=O)(=O)Cc1ccccc1C(=O)OC,0.75292,0.5903600808147756,1
-O=C(C1C(C1(C)C)C=C(C)C)OCN1C(=O)C2=C(C1=O)CCCC2,0.75436,0.10800361461285946,1
-CCOc1nc(F)cc2n1nc(n2)S(=O)(=O)Nc1c(Cl)cccc1C(=O)OC,0.75615,0.5850627837580527,1
-CCCN(c1c(cc(cc1[N+](=O)[O-])C(F)(F)F)[N+](=O)[O-])CCC,0.760539,0.03936403682289997,1
-COC(=O)c1c(Cl)c(Cl)c(c(c1Cl)Cl)C(=O)OC,0.768162,0.2997583332849286,1
-COc1cc(OC)nc(n1)NC(=O)NS(=O)(=O)Cc1ccccc1C(=O)O,0.77956,0.6395811977437235,1
-Clc1ccc(c(n1)C(=O)O)Cl,0.78125,0.2935631716850155,1
-COC(=O)NS(=O)(=O)c1ccc(cc1)N,0.78179,0.3130022353956828,1
-ClCC[N+](C)(C)C.[Cl-],0.79079,4.885143286777227,1
-COC(CCCC(C/C=C/C(=C/C(=O)OC(C)C)/C)C)(C)C,0.80523,0.1481599999999995,1
-CCOc1cc(ccc1OCC)NC(=O)OC(C)C,0.8241,0.24953968467889315,1
-OC(=O)c1nc(Cl)c(c(c1Cl)N)Cl,0.8283,1.5013335136864707,1
-CC(C1(C)N=C(NC1=O)c1nc2ccccc2cc1C(=O)O)C,0.8351195,0.5362888665627948,1
-Nc1ccc(c(c1)C)NOS(=O)(=O)O,0.84315,0.3801164314656728,1
-CCOC(=O)C1OC1(C)c1ccccc1,0.84854,0.1552558608623956,1
-COC(=O)Nc1nc2c([nH]1)cccc2,0.8499450000000001,0.03943710192365588,1
-OCCn1c(C)ncc1[N+](=O)[O-],0.8764,0.11232884148620186,1
-CC(Oc1cccc(c1)NC(=O)c1ccccc1C(F)(F)F)C,0.907795,0.219732563840245,1
-COP(=O)OC,0.90869,0.06922203786330303,1
-OCCNc1ccc(cc1OCCO)N(=O)=O,0.94539,0.1974258100920134,1
-O=N(=O)c1cccc2c1cccc2,0.95283,0.39440545036679536,1
-O=C(C1(C)CCCCC1)Nc1ccc(c(c1Cl)Cl)O,0.96626,0.26616781257634764,1
-ClCCP(=O)(O)O,0.9723550000000001,2.4009973601180943,1
-Oc1cccc2c1nccc2,0.98513,0.944144644167336,1
-CCCOC(=O)c1ccc(cn1)C(=O)OCCC,0.99491,2.1845204370536457,1
-Oc1noc(c1)C,0.99911,4.460800000000001,0.1
-CC[N](=C1C=CC(=C(c2ccc(cc2)N(Cc2cccc(c2)S(=O)(=O)O)CC)c2ccc(cc2)N(C)C)C=C1)Cc1cccc(c1)S(=O)(=O)O,1.01,0.18076645608408032,1
-ClCC[N+](C)(C)C,1.0602,2.278336097399379,1
-Clc1ccccc1,1.0661,0.07309524260747297,1
-O=C1CCCCCN1,1.1047,0.32229991005045816,1
-Cc1cc(C)nc(n1)Nc1ccccc1,1.1091,0.10185001505164672,1
-COc1cccc(c1C)C(=O)NN(C(C)(C)C)C(=O)c1cc(C)cc(c1)C,1.1154,0.7054494590371179,1
-COC(=O)C(=CC=CC(=CC=CC=C(C=CC=C(C=CC1=C(C)CCCC1(C)C)C)C)C)C,1.1194,0.016064956420567343,1
-Clc1ccccc1CC(C1(Cl)CC1)(Cn1nc[nH]c1=S)O,1.1619199999999998,0.03945721630080327,1
-Oc1ccc(cc1Cl)C(C)(C)C,1.1697,0.04838453786228862,1
-COc1cc(OC)nc(n1)NC(=O)NS(=O)(=O)Nc1ccccc1C(=O)N(C)C,1.178,0.558920251480791,1
-CON=C(c1ccccc1COc1ccccc1C)C(=O)OC,1.1888,1.0311764773695973,1
-CCCOc1nn(c(=O)n1C)C(=O)[N-]S(=O)(=O)c1ccccc1C(=O)OC.[Na+],1.1894,0.9517713195122869,1
-OC(=O)Cc1cccc2c1cccc2,1.2057,0.2898151330802695,1
-OCc1cc(N=Nc2ccc(c3c2cccc3)S(=O)(=O)O)c(c(c1O)N=Nc1ccc(c2c1cccc2)S(=O)(=O)O)O,1.2093,0.947536350287709,1
-CC1=CC(=O)CC(C1)(C)C,1.2952,0.1131559776714462,1
-C[N]1(C)CCCCC1,1.3134,1.2054882989184272,1
-OC1CCC2(C(C1)CCC1C2CCC2(C1CCC2C(CCC(=O)O)C)C)C,1.3278,1.1070929244515704,1
-COc1cc(OC)nc(n1)NC(=O)NS(=O)(=O)N(S(=O)(=O)C)C,1.3412,0.27596947611718897,1
-Oc1ccc(c(c1)C(C)(C)C)O,1.3537,0.3302011007099653,1
-COc1ncc(c2n1nc(n2)S(=O)(=O)Nc1c(F)cccc1F)F,1.3917,0.18269239456732794,1
-OCC1OC2OC3C(CO)OC(C(C3O)O)OC3C(CO)OC(C(C3O)O)OC3C(CO)OC(C(C3O)O)OC3C(OC(OC4C(OC(OC5C(OC(OC1C(C2O)O)C(O)C5O)CO)C(O)C4O)CO)C(O)C3O)CO,1.4097,4.66309574187792,1
-O=C(Nc1cc(F)cc(c1)F)N/N=C(/c1ncccc1C(=O)O)\C,1.412,0.5475053703148323,1
-CCCCOC(=O)c1ccccc1C(=O)OCc1ccccc1,1.5047,1.19078952928514,1
-Fc1cc2CCC(n3c2c(c1)c(=O)c(c3)C(=O)O)C,1.5311,0.2632953576124685,0.3125
-CC(N(c1c(cc(cc1N(=O)=O)C(F)(F)F)N(=O)=O)C(C)C)C,1.55095,0.06103298628515611,1
-CCC(c1noc(c1)NC(=O)c1c(OC)cccc1OC)(CC)C,1.5855,0.3364574595300736,1
-c1ccc(cc1)c1ccccc1,1.6212,0.17615942353720057,1
-NCC(c1ccc(cc1)O)O,1.6321,0.5923856917698849,1
-CCc1c(C(=O)O)c(=O)cnn1c1ccc(cc1)Cl,1.6865,0.1372023757478525,1
-ClCC#CCOC(=O)Nc1cccc(c1)Cl,1.7435,0.36928732827264665,1
-O/C(=C\1/C(=O)CC(CC1=O)C(=O)O)/C1CC1,1.7528,1.1164855772875812,1
-CO/N=C(\c1ccccc1COc1ccccc1C)/C(=O)OC,1.7985,0.8720996824403675,1
-COc1ccc(c(c1)OC)N,1.8018,1.7238078171346856,1
-CCC(=O)C1=C([O-])CC(CC1=O)C(=O)[O-].[Ca+2],1.874,0.7779135467595814,1
-CC(C1(C)N=C(NC1=O)c1ncccc1C(=O)O)C,1.9137,0.39774521824125936,1
-OC(=O)COc1nc(F)c(c(c1Cl)N)Cl,1.9605,0.08697616184469983,1
-Clc1ccc(cc1)Cl,2.0408,0.06374335438397329,1
-CCCCOC(=O)c1ccccc1C(=O)OCCCC,2.1556,3.47150991350572,1
-c1ccc(cc1)c1ccccc1OCC1CO1,2.2097,0.3675910983305166,1
-ClCC[N](C)(C)C,2.2428,0.7656044000783344,1
-COc1cc(OC)n2c(n1)nc(n2)NS(=O)(=O)c1c(OC)nccc1C(F)(F)F,2.3023,0.08509085671419739,1
-CC=Cc1ccc(cc1)OC,2.3212,0.9451726792585206,1
-CC(OC(=O)Nc1cccc(c1)Cl)C,2.3402,0.22033235150017733,1
-COC(=O)c1ccccc1O,2.3661,1.4771718460546608,1
-CCOC(=O)C=C,2.4771,0.183806556992341,1
-COC(=O)CC(c1ccc(cc1)Cl)NC(=O)C(C(C)C)NC(=O)OC(C)C,2.507,0.13815791804834107,1
-COc1nn(c(=O)n1C)C(=O)NS(=O)(=O)c1ccccc1OC(F)(F)F,2.5233,0.5971845115967703,1
-C=Cc1ccccc1,2.7365,0.37577606726866863,1
-COc1cc(OC)nc(n1)NC(=O)NS(=O)(=O)c1n2ccccc2nc1S(=O)(=O)CC,2.7557,0.3466419024720839,1
-CC(=C)C(=O)O,2.8807,9.313199999999998,0.14285714285714285
-CN(NC(=O)CCC(=O)O)C,3.0343,0.49949,0.13043478260869565
-Oc1ccccc1c1ccccc1,3.1197,0.6935630327006294,1
-Clc1cnc2c(c1)ccc(c2C(=O)O)Cl,3.1273,1.5398255822598488,1
-C[N+]1(C)CCCCC1.[Cl-],3.1805,0.42824624111805554,1
-CCc1ccccc1,3.29205,0.12214402534200347,1
-CC(c1ccccc1)C,3.2988999999999997,0.16350124244576295,1
-Cc1cnc2c(c1)ccc(c2C(=O)O)Cl,3.3388,1.3837642554197285,1
-CCCOC(=O)NCCCN(C)C,3.6119,0.7995598959039829,1
-CCOP(=O)O,3.6347,0.017372030330823008,1
-Oc1ccccc1,3.6552,0.7307613484688117,1
-[O-]P(=O)OCC.[O-]P(=O)OCC.[O-]P(=O)OCC.[Al+3],3.6854,0.0044552770310519515,1
-CC1CCC(C(C1)O)C(C)C,3.7948,8.900107006796395,1
-COc1ccc(cc1)N,3.8489,0.730848069456594,1
-CCCCC(COC(=O)CCCCC(=O)OCC(CCCC)CC)CC,4.0479,1.2122077026918385,1
-CCCOC(=O)c1cc(O)c(c(c1)O)O,4.0716,1.331860755078258,1
-CC(CCCC1(C)CCc2c(O1)c(C)c(c(c2C)OC(=O)C)C)CCCC(CCCC(C)C)C,4.2306,1.5880951010398416,1
-COc1ccc(cc1N=Nc1c(O)c(cc2c1cccc2)C(=O)Nc1cccc(c1)N(=O)=O)N(=O)=O,4.3084,0.2224070954460962,1
-Oc1ccc(nn1)O,4.4608,0.99911,0.1
-S=c1sc2c([nH]1)cccc2,4.4843,0.07222458435399681,1
-Clc1cc(N)c(c(n1)C(=O)O)Cl,4.8306,0.5924316874068799,1
-CNC(=N[N](=O)[O])NCC1COCC1,4.9008,0.13017,0.12
-COc1cc(OC)nc(n1)NC(=O)NS(=O)(=O)c1ncccc1C(=O)N(C)C,5.0877,0.2484449827798134,1
-OC(=O)CNCP(=O)(O)O,5.5597,0.7008374592406027,0.16666666666666666
-CCOc1ccc(cc1N)NC(=O)C,6.101,0.5180080318003157,1
-Nc1ccc(cc1)O,6.2863,0.9867697053880642,1
-NC(=S)NNC(=S)N,6.3038,0.009103354136383681,1
-NC(=O)c1cnccn1,6.4088,0.08617861868365057,1
-OC(=O)c1ccc(cc1N)N(=O)=O,6.5062,1.2330759884995215,1
-Oc1cc(O)c2c(c1)oc(c(c2=O)O)c1ccc(c(c1)O)O,6.7298,0.7698070145861168,1
-ClCC(=O)c1ccc(cc1)NC(=O)C,7.4653,0.49841116488313375,1
-O=C1OC(=O)c2c1cccc2,8.0005,0.9151765995105839,1
-CCCOC(=O)c1ccc(cc1)O,8.3241,2.95845847977303,1
-CCOC(=O)COC(=O)c1ccccc1C(=O)OCC,8.9199,0.7185658779034559,1
-O=C1CCCCC1,9.2722,0.2378628917431664,1
-OC(=O)C=CC(=O)O,9.3132,2.880700000000001,0.14285714285714285
-COC(=O)c1ccc(cc1)O,9.8589,1.1386534488588607,1
-COC(=O)c1ccccc1C(=O)OC,10.3,0.916674173950007,1
-OC1C2C(N(C)C)C(=O)C(=C(O)N)C(=O)C2(O)C(=O)C2=C(O)c3c(C(C12)(C)O)c(Cl)ccc3O,10.508,0.33751,0.6216216216216216
-OCC(C1OC(=O)C(=C1O)O)O,13.07315,9.165234699656954,1
-OCCO,14.822,12.136574449142156,1
-CCCCCCCCCCCCCCCCCC(=O)OCC(C1OCC(C1O)O)O,16.727,1.3648967676120518,1
-[O-]S(=O)(=O)NC1CCCCC1.[Na+],17.901,0.13111496023516397,1
-O=C1NS(=O)(=O)c2c1cccc2,19.663,0.2160942139151245,1
-CCCCCCCCCCCC(=O)OCC(C1OCC(C1O)O)O,19.867,1.3648967676120518,1
-CCOC(=O)c1ccccc1C(=O)OCC,19.956,0.9367228432191498,1
-OC(=O)c1ccccc1N,20.06,1.0639519022761117,1
-OCC(CO)O,74.739,1.1970876762413112,1
diff --git a/data/combined-cv.id b/data/combined-cv.id
deleted file mode 100644
index 19697a4..0000000
--- a/data/combined-cv.id
+++ /dev/null
@@ -1 +0,0 @@
-56d593572b72ed384a000001
diff --git a/data/combined-test-predictions.csv b/data/combined-test-predictions.csv
deleted file mode 100644
index 326c916..0000000
--- a/data/combined-test-predictions.csv
+++ /dev/null
@@ -1,151 +0,0 @@
-SMILES,LOAEL_measured_median,LOAEL_predicted,Confidence,Dataset
-N#Cc1nn(c(c1S(=O)C(F)(F)F)N)c1c(Cl)cc(cc1Cl)C(F)(F)F,0.00013611,0.012223549654189954,1,combined-prediction
-OC(=O)C(Oc1ccc(cc1)Oc1ncc(cc1Cl)C(F)(F)F)C,0.00027647,0.012363739179264848,1,combined-prediction
-CCOP(=S)(SCSC(C)(C)C)OCC,0.00027736000000000004,0.003234463493265512,1,combined-prediction
-CCSCSP(=S)(OCC)OCC,0.00061449,0.0007865744283201257,1,combined-prediction
-CCOP(=O)(SC(CC)C)SC(CC)C,0.000872805,0.005039445065903741,1,combined-prediction
-CNC(=O)CSP(=S)(OC)OC,0.0010905,0.00950743899812471,1,combined-prediction
-COP(=O)(SC)N,0.0020549,0.32686975597991175,1,combined-prediction
-CSc1ccc(cc1C)OP(=S)(OC)OC,0.00210185,0.00515916415689228,1,combined-prediction
-CCOP(=S)(Oc1ccc2c(c1)oc(=O)c(c2C)Cl)OCC,0.0033631,0.03604767643689561,1,combined-prediction
-CCOP(=S)(Oc1ncn(n1)c1ccccc1)OCC,0.0041492,0.021711294422324952,1,combined-prediction
-COc1sc(=O)n(n1)CSP(=S)(OC)OC,0.00471335,0.009823341977484811,1,combined-prediction
-CCOP(=S)(OCC)SCSP(=S)(OCC)OCC,0.0049418,0.002790446349330914,1,combined-prediction
-CCOP(=O)(Oc1ccc(c(c1)C)SC)NC(C)C,0.0049447,0.0046994079738164616,1,combined-prediction
-CC(Cc1ccc(cc1)C(C)(C)C)CN1CC(C)OC(C1)C,0.0056016,0.06748715670088713,1,combined-prediction
-COP(=S)(Oc1nc(Cl)c(cc1Cl)Cl)OC,0.00620095,0.009085825113386419,1,combined-prediction
-OC(C(Cl)(Cl)Cl)(c1ccc(cc1)Cl)c1ccc(cc1)Cl,0.0067479,0.06242817556011404,1,combined-prediction
-COC(=O)N(C(=O)N1COC2(C(=N1)c1ccc(cc1C2)Cl)C(=O)OC)c1ccc(cc1)OC(F)(F)F,0.0068203,0.03766454733832817,1,combined-prediction
-Clc1ccc(cc1)C(c1ccccc1Cl)(c1cncnc1)O,0.0075484,0.02648213936639114,1,combined-prediction
-COP(=S)(SCn1nnc2c(c1=O)cccc2)OC,0.0076105,0.0256192873852848,1,combined-prediction
-N#CC(c1cccc(c1)Oc1ccccc1)OC(=O)C1C(C1(C)C)C=C(Br)Br,0.00781875,0.04433313532487736,1,combined-prediction
-CCN(c1nc(cc(n1)C)OP(=S)(OC)OC)CC,0.0081878,0.016199432386363694,1,combined-prediction
-CCCCOC(=O)C(Oc1ccc(cc1)Oc1ccc(cn1)C(F)(F)F)C,0.00885585,0.006522109887884214,1,combined-prediction
-COP(=O)(OC=C(Cl)Cl)OC,0.0100688,0.03379255796926954,1,combined-prediction
-CCCSP(=O)(SCCC)OCC,0.010069,0.013404183743512306,1,combined-prediction
-O=S1OCC2C(CO1)C1(C(C2(Cl)C(=C1Cl)Cl)(Cl)Cl)Cl,0.012287,0.0002292959719534936,1,combined-prediction
-CC(Oc1cc(c(cc1Cl)Cl)n1nc(oc1=O)C(C)(C)C)C,0.0124555,0.06185932200974554,1,combined-prediction
-CNC(=O)Oc1cccc2c1OC(C2)(C)C,0.01394355,0.03840409396889159,1,combined-prediction
-N#Cc1c(Cl)c(C#N)c(c(c1Cl)Cl)Cl,0.015043,0.0045096410773658386,1,combined-prediction
-Fc1ccc(cc1)[Si](c1ccc(cc1)F)(Cn1cncn1)C,0.015853,0.01191187101473148,1,combined-prediction
-CCOP(=S)(Oc1cc(C)nc(n1)C(C)C)OCC,0.016429,0.01567055641265714,1,combined-prediction
-N#Cc1c(Cl)cccc1Cl,0.0165685,0.09205382040597357,1,combined-prediction
-CCOP(=S)(Oc1nc(Cl)c(cc1Cl)Cl)OCC,0.017114,0.002156167700318906,1,combined-prediction
-BrC1COC(C1)(Cn1cncn1)c1ccc(cc1Cl)Cl,0.017185,0.026572319241467978,1,combined-prediction
-CCN(C(=O)SCc1ccc(cc1)Cl)CC,0.0180385,0.022723781300182423,1,combined-prediction
-CCCN(C(=O)n1cncc1)CCOc1c(Cl)cc(cc1Cl)Cl,0.019912,0.026488774907181132,1,combined-prediction
-CCOC(=O)c1cn2nc(cc2nc1C)OP(=S)(OCC)OCC,0.0200875,0.11278481360348322,1,combined-prediction
-COP(=S)(SCN1C(=O)c2c(C1=O)cccc2)OC,0.020484,0.03832158653625922,1,combined-prediction
-CNC(=O)ON=C(C(=O)N(C)C)SC,0.022348,0.02446526703205196,1,combined-prediction
-COC(=O)N(c1ccccc1COc1ccn(n1)c1ccc(cc1)Cl)OC,0.023207,0.09370340804227252,1,combined-prediction
-CON(C(=O)Nc1ccc(c(c1)Cl)Cl)C,0.025091,0.013517640874997548,1,combined-prediction
-O=C(NC(=O)c1c(F)cccc1F)Nc1ccc(cc1)Cl,0.025428,0.13059896553323086,1,combined-prediction
-O=C(N(C)C)Nc1ccc(c(c1)Cl)Cl,0.025741,0.10976420937355227,1,combined-prediction
-CCOC(=O)C(Oc1ccc(cc1)Oc1cnc2c(n1)ccc(c2)Cl)C,0.0257509,0.055642540351215304,1,combined-prediction
-N#Cc1sc2=c(sc1C#N)c(=O)c1c(c2=O)cccc1,0.0269975,0.19771192535499266,1,combined-prediction
-C=CC1(C)OC(=O)N(C1=O)c1cc(Cl)cc(c1)Cl,0.027961,0.14931435109679134,1,combined-prediction
-N#CC(c1ccc(c(c1)Oc1ccccc1)F)OC(=O)C1C(C1(C)C)C=C(Cl)Cl,0.028207,0.04294738649097546,1,combined-prediction
-CCOC(=O)C(Cc1cc(c(cc1Cl)F)n1nc(n(c1=O)C(F)F)C)Cl,0.029113,0.16077273661454186,1,combined-prediction
-CON(C(=O)Nc1ccc(cc1)Br)C,0.0313005,0.04588226113305051,1,combined-prediction
-CN1CN(C)CSC1=S,0.03266,0.057561024688675286,1,combined-prediction
-ClCC1CN(C(=O)C1Cl)c1cccc(c1)C(F)(F)F,0.033160999999999996,0.04443788235729328,1,combined-prediction
-CCCCC(c1ccc(cc1)Cl)(Cn1cncn1)C#N,0.034179,0.1393370406646657,1,combined-prediction
-CCOP(=S)(SCn1c(=O)oc2c1ccc(c2)Cl)OCC,0.0345288,0.003431963174626776,1,combined-prediction
-CCOCn1c(c2ccc(cc2)Cl)c(c(c1C(F)(F)F)Br)C#N,0.0350825,0.05876685361804707,1,combined-prediction
-Clc1ccc(c(c1)Cl)C1(OCCO1)Cn1cncn1,0.0379825,0.0695739469692122,1,combined-prediction
-CC(C(c1cncnc1)(c1ccc(cc1)OC(F)(F)F)O)C,0.038746,0.05959349856848933,1,combined-prediction
-CC(N(C(=O)SCC(=C(Cl)Cl)Cl)C(C)C)C,0.041029,0.03290179250585915,1,combined-prediction
-COP(=S)(Oc1ccc(c(c1)C)[N+](=O)[O-])OC,0.0424911,0.0026857015728372815,1,combined-prediction
-O=C1OC(C(=O)N1Nc1ccccc1)(C)c1ccc(cc1)Oc1ccccc1,0.04514,0.04648962078753177,1,combined-prediction
-CN(C(=S)SSC(=S)N(C)C)C,0.04783,0.06887194446611773,1,combined-prediction
-CN(C(=O)Oc1nc(nc(c1C)C)N(C)C)C,0.0520385,0.030679574124057456,1,combined-prediction
-C=CCOC(c1ccc(cc1Cl)Cl)Cn1cncc1,0.053503,0.01220166683832079,1,combined-prediction
-COCN(c1c(CC)cccc1CC)C(=O)CCl,0.0537505,0.5492287026006372,1,combined-prediction
-CCOc1ccc2c(c1)C(=CC(N2)(C)C)C,0.055221,0.38446688839029125,1,combined-prediction
-O=C(c1ccc(cc1S(=O)(=O)C)C(F)(F)F)c1cnoc1C1CC1,0.055661,0.02979380878867247,1,combined-prediction
-OC(=O)COc1ccc(cc1C)Cl,0.0573225,0.12358841791299814,1,combined-prediction
-CCOC(=O)NCCOc1ccc(cc1)Oc1ccccc1,0.0575765,0.21490884902162277,1,combined-prediction
-N#CC(c1cccc(c1)Oc1ccccc1)OC(=O)C(c1ccc(cc1)Cl)C(C)C,0.059538,0.008917492959978625,1,combined-prediction
-N#CC(c1cccc(c1)Oc1ccccc1)OC(=O)C1C(C1(C)C)(C)C,0.060099,0.02799624502205084,1,combined-prediction
-CC(OC(=O)C(c1ccc(cc1)Br)(c1ccc(cc1)Br)O)C,0.0606145,0.020876712373277328,1,combined-prediction
-Clc1ccccc1c1nnc(nn1)c1ccccc1Cl,0.06152150000000001,0.13676230027805866,1,combined-prediction
-Clc1cc(ccc1Oc1ccc(c(c1)C(=O)NS(=O)(=O)C)[N+](=O)[O-])C(F)(F)F,0.062678,0.1593365592289975,1,combined-prediction
-COc1nc(nc(n1)C)NC(=O)NS(=O)(=O)c1ccccc1Cl,0.062889,0.08917429877460775,1,combined-prediction
-CCCCN(SN(C(=O)Oc1cccc2c1OC(C2)(C)C)C)CCCC,0.065695,0.042879232776977826,1,combined-prediction
-O=C(NC(=O)c1c(F)cccc1F)Nc1cc(Cl)c(c(c1F)Cl)F,0.06691,0.07460254987161218,1,combined-prediction
-CSc1nnc(c(=O)n1N)C(C)(C)C,0.067199,0.013700999999999996,0.11538461538461539,combined-prediction
-O=C(NC(=O)c1c(F)cccc1F)Nc1ccc(c(c1)Cl)OC(C(OC(F)(F)F)F)(F)F,0.06758600000000001,0.05063196441044935,1,combined-prediction
-CCOc1ccc(cc1)C(COCc1cccc(c1)Oc1ccccc1)(C)C,0.068395,0.11539248656999716,1,combined-prediction
-C#CCOS(=O)OC1CCCCC1Oc1ccc(cc1)C(C)(C)C,0.06905,0.11208703427638497,1,combined-prediction
-OC(=O)COc1nc(Cl)c(cc1Cl)Cl,0.07213454999999999,0.058440427687189135,1,combined-prediction
-O=C(N(C)C)Nc1cccc(c1)C(F)(F)F,0.073957,0.03806261592334438,1,combined-prediction
-OC(C(C)(C)C)C(n1cncn1)Oc1ccc(cc1)c1ccccc1,0.074093,0.20973249001111333,1,combined-prediction
-CCNc1nc(NC(C)C)nc(n1)Cl,0.077892,0.09542622196726332,1,combined-prediction
-O=C(C1=C(C)OCCS1)Nc1ccccc1,0.0811745,0.1516243942725363,1,combined-prediction
-CNC(=O)Oc1cc(C)c(c(c1)C)SC,0.0827735,0.018221311036309484,1,combined-prediction
-OC(C(C)(C)C)C(n1ncnc1)Oc1ccc(cc1)Cl,0.084527,0.09646473813841924,1,combined-prediction
-O=C(C(C)(C)C)C(n1ncnc1)Oc1ccc(cc1)Cl,0.085107,0.06024507371941071,1,combined-prediction
-CC(NC(=O)N1CC(=O)N(C1=O)c1cc(Cl)cc(c1)Cl)C,0.08783250000000001,0.07219303112178485,1,combined-prediction
-CCC(=O)Nc1ccc(c(c1)Cl)Cl,0.09171,0.28670416643325786,1,combined-prediction
-N#CC(c1ccccc1)(Cn1cncn1)CCc1ccc(cc1)Cl,0.092038,0.09042035954229727,1,combined-prediction
-ClC(=CC1C(C1(C)C)C(=O)OCc1cccc(c1)Oc1ccccc1)Cl,0.095836,0.1332061462012948,1,combined-prediction
-OC(=O)C(Oc1ccc(cc1Cl)Cl)C,0.0967835,0.032049112648988555,1,combined-prediction
-COP(=O)(NC(=O)C)SC,0.1023645,0.020044612459808032,1,combined-prediction
-O=C1N(c2cc(Cl)cc(c2)Cl)C(=O)C2(C1(C)C2)C,0.1108605,0.11530582189962267,1,combined-prediction
-COC(=O)c1c(nc(c(c1CC(C)C)C1=NCCS1)C(F)(F)F)C(F)F,0.11151,0.06082857653650607,1,combined-prediction
-Clc1ccc(cc1)CCC(C(C)(C)C)(Cn1cncn1)O,0.115167,0.059464868761800495,1,combined-prediction
-COC(=O)NC(=S)Nc1ccccc1NC(=S)NC(=O)OC,0.12412500000000001,0.2343134557391411,1,combined-prediction
-CCOc1cc(ccc1[N+](=O)[O-])Oc1ccc(cc1Cl)C(F)(F)F,0.12856,0.1019674562628807,1,combined-prediction
-CCc1ccc(cc1)C(=O)NN(C(C)(C)C)C(=O)c1cc(C)cc(c1)C,0.13674999999999998,0.9924390725585213,1,combined-prediction
-c1scc(n1)c1nc2c([nH]1)cccc2,0.14907,0.11397814782194533,1,combined-prediction
-CC(N1C(=O)c2ccccc2NS1(=O)=O)C,0.14983,0.724485848042646,1,combined-prediction
-N#CC(c1cccc(c1)Oc1ccccc1)OC(=O)C1C(C1(C)C)C=C(Cl)Cl,0.150135,0.029306511257410083,1,combined-prediction
-Cc1cccc2c1n1cnnc1s2,0.150605,0.3273764631299369,1,combined-prediction
-ClC(SN1C(=O)c2c(C1=O)cccc2)(Cl)Cl,0.15173999999999999,0.1990986315906923,1,combined-prediction
-CCC(Nc1c(cc(cc1[N+](=O)[O-])C(C)(C)C)[N+](=O)[O-])C,0.153385,0.049911304976084696,1,combined-prediction
-Cc1nc(Nc2ccccc2)nc(c1)C1CC1,0.15802,0.5049958406738252,1,combined-prediction
-c1ccc(cc1)Nc1ccccc1,0.16546,0.376281025030794,1,combined-prediction
-Clc1cc(Cl)c(cc1n1nc(n(c1=O)C(F)F)C)NS(=O)(=O)C,0.17304,0.02384153039577781,1,combined-prediction
-CCCC1COC(O1)(Cn1cncn1)c1ccc(cc1Cl)Cl,0.176786,0.04142332630393303,1,combined-prediction
-C#CCC1=C(C)C(CC1=O)OC(=O)C1C(C1(C)C)C=C(C)C,0.18558899999999998,0.10462262901548752,1,combined-prediction
-COc1nc(nc(n1)C)NC(=O)NS(=O)(=O)c1ccccc1CCC(F)(F)F,0.200175,0.0812430402043688,1,combined-prediction
-CC(=CC1C(C1(C)C)C(=O)OCc1coc(c1)Cc1ccccc1)C,0.2068305,0.23587481170699223,1,combined-prediction
-CCOCN(c1c(C)cccc1CC)C(=O)CCl,0.21666999999999997,0.13964694567855077,1,combined-prediction
-CC(Nc1nc(NC(C)C)nc(n1)Cl)C,0.219845,0.06340505986168649,1,combined-prediction
-CNC(=O)Oc1ccccc1OC(C)C,0.23418,0.014174463921646627,1,combined-prediction
-CCCCCCCCSC(=O)Oc1cc(Cl)nnc1c1ccccc1,0.24081999999999998,0.13659751142830953,1,combined-prediction
-O=C1N(OCC1(C)C)Cc1ccccc1Cl,0.253443,0.06471680728508057,1,combined-prediction
-Cc1ccc(cc1)N(S(=O)(=O)N(C)C)SC(Cl)(Cl)F,0.25917,0.07250548946753735,1,combined-prediction
-CC1N(C(=O)NC2CCCCC2)C(=O)SC1c1ccc(cc1)Cl,0.259436,0.036135896771232294,1,combined-prediction
-CCN(C(=O)C(Oc1cccc2c1cccc2)C)CC,0.271895,0.8705324664135307,1,combined-prediction
-OC(=O)COc1ccc(cc1Cl)Cl,0.2805,0.09638291063682661,1,combined-prediction
-CCOC(=O)CC(C(=O)OCC)SP(=S)(OC)OC,0.292105,0.027748303472073976,1,combined-prediction
-CNC(=O)Oc1cccc2c1cccc2,0.29818,0.2121515649550718,1,combined-prediction
-Clc1ccc(cc1)CN(C(=O)Nc1ccccc1)C1CCCC1,0.31170800000000004,0.06823627555192432,1,combined-prediction
-ClCCOc1ccccc1S(=O)(=O)NC(=O)Nc1nc(C)nc(n1)OC,0.31207450000000003,0.19321858483679857,1,combined-prediction
-CCC(n1c(=O)[nH]c(c(c1=O)Br)C)C,0.31690999999999997,0.2868010916268421,1,combined-prediction
-ClC(SN1C(=O)C2C(C1=O)CC=CC2)(Cl)Cl,0.32935499999999995,0.07976078042600027,1,combined-prediction
-CC(=CC1C(C1(C)C)C(=O)OCc1cccc(c1)Oc1ccccc1)C,0.42802,0.05916637749066978,1,combined-prediction
-CC(Oc1ccccn1)COc1ccc(cc1)Oc1ccccc1,0.433615,0.0683405586517136,1,combined-prediction
-N#Cc1c[nH]cc1c1cccc2c1OC(O2)(F)F,0.449265,0.7584096769789066,1,combined-prediction
-Clc1c(Cl)c([N+](=O)[O-])c(c(c1Cl)Cl)Cl,0.47404,0.05334808800865584,1,combined-prediction
-COc1nc(nc(n1)C)NC(=O)NS(=O)(=O)c1ccccc1C(=O)OC,0.48379,0.08627382168635772,1,combined-prediction
-Nc1nc(NC2CC2)nc(n1)N,0.514491,0.1646588145839564,1,combined-prediction
-CCCCOCCOCCOCc1cc2OCOc2cc1CCC,0.51708,0.3372417142709603,1,combined-prediction
-COCC(N(c1c(C)cccc1CC)C(=O)CCl)C,0.52855,0.19631971323678116,1,combined-prediction
-O=Cc1ccco1,0.62445,0.12487,0.1111111111111111,combined-prediction
-[O-][N+](=O)c1cc(Cl)c(c(c1)Cl)N,0.72459,0.10147624629271434,1,combined-prediction
-COC(=O)c1c(Cl)c(Cl)c(c(c1Cl)Cl)C(=O)OC,0.768162,0.2955184678677059,1,combined-prediction
-COC(=O)NS(=O)(=O)c1ccc(cc1)N,0.78179,0.3130022353956828,1,combined-prediction
-OC(=O)c1nc(Cl)c(c(c1Cl)N)Cl,0.8283,1.5484096804871008,1,combined-prediction
-CC(C1(C)N=C(NC1=O)c1nc2ccccc2cc1C(=O)O)C,0.8351195,0.5362888665627948,1,combined-prediction
-COC(=O)Nc1nc2c([nH]1)cccc2,0.8499450000000001,0.03767007785899512,1,combined-prediction
-CC(Oc1cccc(c1)NC(=O)c1ccccc1C(F)(F)F)C,0.907795,0.16829179729827692,1,combined-prediction
-O=C(C1(C)CCCCC1)Nc1ccc(c(c1Cl)Cl)O,0.96626,0.3904998254580453,1,combined-prediction
-ClCCP(=O)(O)O,0.9723550000000001,2.4009973601180943,1,combined-prediction
-COc1cccc(c1C)C(=O)NN(C(C)(C)C)C(=O)c1cc(C)cc(c1)C,1.1154,0.7796764143585404,1,combined-prediction
-CCC(c1noc(c1)NC(=O)c1c(OC)cccc1OC)(CC)C,1.5855,0.4879331636731657,1,combined-prediction
-OC(=O)COc1nc(F)c(c(c1Cl)N)Cl,1.9605,0.07884649342822374,1,combined-prediction
-CC(OC(=O)Nc1cccc(c1)Cl)C,2.3402,0.23602292201205227,1,combined-prediction
-Oc1ccccc1c1ccccc1,3.1197,0.8192745419841765,1,combined-prediction
-OC(=O)CNCP(=O)(O)O,5.5597,0.7008374592406027,0.16666666666666666,combined-prediction
diff --git a/data/combined-test-predictions.id b/data/combined-test-predictions.id
deleted file mode 100644
index ab6c881..0000000
--- a/data/combined-test-predictions.id
+++ /dev/null
@@ -1 +0,0 @@
-56d593502b72ed3787000004
diff --git a/data/training-cv-0.csv b/data/training-cv-0.csv
new file mode 100644
index 0000000..da27aae
--- /dev/null
+++ b/data/training-cv-0.csv
@@ -0,0 +1,631 @@
+SMILES,LOAEL_measured_median,LOAEL_predicted,Confidence
+ClC12C3C4(C(C1(Cl)Cl)(C1(C2(C3(Cl)C(C41Cl)(Cl)Cl)Cl)Cl)Cl)Cl,1.9566e-05,0.0014217916687719956,0.625
+ClC1=C(Cl)C2(C(C1(Cl)C1C2C2CC1C=C2)(Cl)Cl)Cl,2.7404e-05,0.0013706062569694513,1
+N#Cc1nn(c(c1S(=O)C(F)(F)F)N)c1c(Cl)cc(cc1Cl)C(F)(F)F,0.00013611,0.012636565759511635,1
+Clc1ccc2c(c1)[n+]([O-])nc(n2)n1cncc1,0.00020191,0.06134084368719656,1
+OC(=O)C(Oc1ccc(cc1)Oc1ncc(cc1Cl)C(F)(F)F)C,0.00027647,0.010309205899374637,1
+CCOP(=S)(SCSC(C)(C)C)OCC,0.00027736000000000004,0.003281002651967321,1
+ClC1C2OC2C2C1C1(Cl)C(=C(C2(C1(Cl)Cl)Cl)Cl)Cl,0.00028896749999999995,0.0007308189563592216,1
+ClC1=C(Cl)C2(C(C1(Cl)C1C2C2CC1C1C2O1)(Cl)Cl)Cl,0.000295345,0.00038858131599372076,1
+CCSCCSP(=S)(OCC)OCC,0.00036443,0.002479025960626162,1
+CNC(=O)ON=CC(SC)(C)C,0.00052559,0.049415575509958495,1
+COC(=O)C(Oc1ccc(cc1)Oc1ccc(cc1Cl)Cl)C,0.00058619,0.17281993122474898,1
+CCSCSP(=S)(OCC)OCC,0.00061449,0.0007932432885978219,1
+OC1CCCCCc2cc(O)cc(c2C(=O)OC(CCC1)C)O,0.00062036,0.46407564001892226,1
+ClC1C=CC2C1C1(Cl)C(=C(C2(C1(Cl)Cl)Cl)Cl)Cl,0.000843785,0.00023424144160233445,1
+c1ccc(cc1)[Sn](c1ccccc1)c1ccccc1,0.00085711,0.6089345620132928,1
+CCOP(=O)(SC(CC)C)SC(CC)C,0.000872805,0.00431082033723489,1
+CCS(=O)CCSP(=O)(OC)OC,0.00089328,0.0013951101578154512,1
+ClC1CC2C(C1Cl)C1(C(C2(Cl)C(=C1Cl)Cl)(Cl)Cl)Cl,0.000939545,0.0003282100247208412,1
+COP(=S)(Oc1ccc(cc1)N(=O)=O)OC,0.00094982,0.00808983327405174,1
+Clc1c(Cl)c(Cl)c(c(c1Cl)Cl)Cl,0.0010183,0.1496193233273976,1
+CNC(=O)CSP(=S)(OC)OC,0.0010905,0.009515127939063844,1
+COP(=O)(SCCS(=O)(=O)CC)OC,0.0011438,0.0012475492886251487,1
+COC1CC(OC2C(C)C=CC=C3COC4C3(O)C(C=C(C4O)C)C(=O)OC3CC(CC=C2C)OC2(C3)C=CC(C(O2)C(CC)C)C)OC(C1OC1CC(OC)C(C(O1)C)O)C.COC1CC(OC(C1OC1CC(OC)C(C(O1)C)O)C)OC1C(C)C=CC=C2COC3C2(O)C(C=C(C3O)C)C(=O)OC2CC(CC=C1C)OC1(C2)C=CC(C(O1)C(C)C)C,0.0011546,0.004752783530343022,1
+ClC12C(Cl)(Cl)C3(C4(C1(Cl)C1(C2(Cl)C3(C4(C1(Cl)Cl)Cl)Cl)Cl)Cl)Cl,0.0012831,6.240058509303313e-05,0.625
+CCOP(=O)(N1CCSC1=O)SC(CC)C,0.0013411,0.014243323330903914,1
+O=C1CCCC(=O)C1C(=O)c1ccc(cc1[N+](=O)[O-])S(=O)(=O)C,0.0014146,0.013126761603553482,1
+CCOP(=S)(Oc1ccccc1C(=O)OC(C)C)NC(C)C,0.0014476,0.1593163042859205,1
+CCSCCSP(=O)(OC)OC,0.0015199,0.000892447632027103,1
+CCOc1cc(nc(n1)CC)OP(=S)(OC)OC,0.0015396,0.008735989693461715,1
+COC(=O)C=C(OP(=O)(OC)OC)C,0.0015615,0.0023812687906506857,1
+COC(=O)/C=C(/OP(=O)(OC)OC)\C,0.0015615,0.0023812687906506857,1
+OC(=O)c1ccccc1.CCC(C1OC2(C=CC1C)OC1CC=C(C)C(OC3CC(OC)C(C(O3)C)OC3CC(OC)C(C(O3)C)NC)C(C)C=CC=C3C4(C(C(=O)OC(C2)C1)C=C(C)C(C4OC3)O)O)C,0.001735715,0.001650952778414861,1
+C1CCC(CC1)[Sn](n1ncnc1)(C1CCCCC1)C1CCCCC1,0.001811,0.01739584228447045,1
+ClC1C2(Cl)C3C4C5C1(Cl)C(C2(Cl)C5C3C1C4O1)(Cl)Cl,0.0018377,0.00017075213457395932,1
+CNC(=O)CCSCCSP(=O)(OC)OC,0.0018793,0.0033386848364462857,1
+COC1CC(OC2C(C)C=CC=C3COC4C3(O)C(C=C(C4O)C)C(=O)OC3CC(CC=C2C)OC2(C3)C=CC(C(O2)C(C)C)C)OC(C1OC1CC(OC)C(C(O1)C)NC(=O)C)C,0.00194425,0.0019671733161550544,1
+N#CC(c1cccc(c1)Oc1ccccc1)OC(=O)[C@H](C(C)C)Nc1ccc(cc1Cl)C(F)(F)F,0.0019884,0.007439697832488631,1
+CNC(=O)C=C(OP(=O)(OC)OC)C,0.0020165,0.006177137380174914,1
+COP(=O)(SC)N,0.0020549,0.33146588454802073,1
+COP(=S)(Oc1ccc(cc1)[N+](=O)[O-])OC,0.0020896,0.009162643797104183,1
+CSc1ccc(cc1C)OP(=S)(OC)OC,0.00210185,0.014159970849698342,1
+CO[C@H]1C[C@H](O[C@H]2[C@@H](C)C=CC=C3CO[C@H]4[C@]3(O)[C@@H](C=C([C@H]4O)C)C(=O)O[C@H]3C[C@@H](CC=C2C)O[C@]2(C3)C=C[C@@H]([C@H](O2)[C@H](CC)C)C)O[C@H]([C@@H]1O[C@H]1C[C@H](OC)[C@H]([C@@H](O1)C)O)C,0.0022907,0.004991833997616914,1
+O=C1CCCC(=O)C1C(=O)c1ccc(c(c1Cl)COCC(F)(F)F)S(=O)(=O)C,0.0023819,0.01161082890621692,1
+S=C1NCCN1,0.0024472,0.09978718938005215,1
+COC(=O)C(Oc1ccc(cc1)Oc1ncc(cc1Cl)C(F)(F)F)C,0.0026615,0.00019853097292179823,1
+CCOP(=S)(OCC)SCSc1ccc(cc1)Cl,0.0029166,0.004191025366902165,1
+C1CCN2C(C1)C1CCCCN1CC2,0.0029591,0.13745344572368123,1
+Fc1ccc(cc1)N(C(=O)COc1nnc(s1)C(F)(F)F)C(C)C,0.0033028,0.06770307506528785,1
+CCOP(=S)(Oc1ccc2c(c1)oc(=O)c(c2C)Cl)OCC,0.0033631,0.06434003756258823,1
+CNC(=O)Oc1cccc2c1OC(O2)(C)C,0.0035838,0.10712411334963678,1
+O[Sn](C1CCCCC1)(C1CCCCC1)C1CCCCC1,0.0036089,0.9532888823413931,1
+CCc1nn(c(c1Cl)C(=O)NCc1ccc(cc1)Oc1ccc(cc1)C)C,0.0039076,0.02663272998837942,1
+CCCCSP(=O)(SCCCC)SCCCC,0.0039744,0.10718532348415942,1
+CCOP(=S)(Oc1ncn(n1)c1ccccc1)OCC,0.0041492,0.02694672880225483,1
+CCOP(=O)(O/C(=C/Cl)/c1ccc(cc1Cl)Cl)OCC,0.0041717,0.017216889092144964,1
+CCOP(=O)(OC(=CCl)c1ccc(cc1Cl)Cl)OCC,0.0041717,0.01194803303416274,1
+Clc1nc(nc(n1)Cl)Nc1ccccc1Cl,0.0041739,0.12034422929443074,1
+Clc1cccc(n1)C(Cl)(Cl)Cl,0.0043308,0.2937201288867553,1
+N#CC(c1cccc(c1)Oc1ccccc1)OC(=O)C1C(C1(C)C)C(C(Br)(Br)Br)Br,0.0045112,0.04567800663110234,1
+COc1sc(=O)n(n1)CSP(=S)(OC)OC,0.00471335,0.006481826771352025,1
+N#CC(c1ccc(c(c1)Oc1ccccc1)F)OC(=O)C1C(C1(C)C)/C=C(/c1ccc(cc1)Cl)\Cl,0.0048983,0.029845437855186795,1
+CCOP(=S)(OCC)SCSP(=S)(OCC)OCC,0.0049418,0.002528952560387183,1
+CCOP(=O)(Oc1ccc(c(c1)C)SC)NC(C)C,0.0049447,0.018551553823283395,1
+N#CC(c1cccc(c1)Oc1ccccc1)OC(=O)C(C(C)C)Nc1ccc(cc1Cl)C(F)(F)F,0.004971,0.006946895656622712,1
+CCNc1nc(nc(n1)Cl)NC(C#N)(C)C,0.0051933,0.019902544410799968,1
+CC(Cc1ccc(cc1)C(C)(C)C)CN1CC(C)OC(C1)C,0.0056016,0.0706862013575946,1
+COP(=S)(Oc1nc(Cl)c(cc1Cl)Cl)OC,0.00620095,0.0087766409206098,1
+COC(=O)Nc1nc2c([nH]1)cc(cc2)S(=O)c1ccccc1,0.0063422,0.3997822088869809,1
+ClCC(N1C(=O)c2c(C1=O)cccc2)SP(=S)(OCC)OCC,0.0063477,0.005038791017128024,1
+CCOP(=S)(Oc1ccc(cc1)N(=O)=O)OCC,0.0067295,0.006852001949249623,1
+OC(C(Cl)(Cl)Cl)(c1ccc(cc1)Cl)c1ccc(cc1)Cl,0.0067479,0.04867006598925414,1
+CNC(=O)Oc1cc(C)c(c(c1)C)N(C)C,0.0067481,0.06376522503737679,1
+COC(=O)N(C(=O)N1COC2(C(=N1)c1ccc(cc1C2)Cl)C(=O)OC)c1ccc(cc1)OC(F)(F)F,0.0068203,0.025134069126390886,1
+CCNc1nc(Cl)nc(n1)NC(C)(C)C,0.0069218,0.027979558935434277,1
+CCOP(=S)(Oc1ccc(cc1)[N+](=O)[O-])OCC,0.0070384,0.005420164676136777,1
+Cc1nn(c(c1/C=N/OCc1ccc(cc1)C(=O)OC(C)(C)C)Oc1ccccc1)C,0.0071176,0.005221730118229197,1
+Cc1nn(c(c1C=NOCc1ccc(cc1)C(=O)OC(C)(C)C)Oc1ccccc1)C,0.0073074,0.004993710375105845,1
+Clc1ccc(cc1)C(c1ccccc1Cl)(c1cncnc1)O,0.0075484,0.01816556808488827,1
+COP(=S)(SCn1nnc2c(c1=O)cccc2)OC,0.0076105,0.028026523430560644,1
+Fc1ccc(cc1)[Si](c1ccc(cc1)F)Cn1cncn1,0.0076575,0.015838544032731786,1
+N#CC(c1cccc(c1)Oc1ccccc1)OC(=O)C1C(C1(C)C)C=C(Br)Br,0.00781875,0.04027081027639703,1
+Fc1ccc(cc1)C(c1ccccc1Cl)(c1cncnc1)O,0.007943,0.0026614630199184846,1
+N#Cc1nn(c(c1S(=O)CC)N)c1c(Cl)cc(cc1Cl)C(F)(F)F,0.0080563,0.00037800167177383604,1
+CCN(c1nc(cc(n1)C)OP(=S)(OC)OC)CC,0.0081878,0.01987889026734089,1
+Clc1ccc(cc1)OS(=O)(=O)c1ccc(cc1)Cl,0.0082464,0.09954101211178366,1
+Clc1cc(cnc1Nc1c(cc(c(c1[N+](=O)[O-])Cl)C(F)(F)F)[N+](=O)[O-])C(F)(F)F,0.008299399999999998,0.06443603956019302,1
+[O-][N+](=O)c1cc([N+](=O)[O-])c(c(c1)[N+](=O)[O-])C,0.0088055,0.07875259863085814,1
+CCCCOC(=O)C(Oc1ccc(cc1)Oc1ccc(cn1)C(F)(F)F)C,0.00885585,0.00634131904484888,1
+CSC(=O)c1c(nc(c(c1CC(C)C)C(=O)SC)C(F)(F)F)C(F)F,0.009043,0.204836351521947,1
+Clc1ccc(c(c1)Cl)C(Cn1cncn1)COC(C(F)F)(F)F,0.0091362,0.03561549247110582,1
+CCCN(C(=O)SCc1ccccc1)CCC,0.0091492,0.09176053975898289,1
+CON(C(=O)Nc1ccc(cc1)Cl)C,0.0093175,0.02373775075444103,1
+CCCCOC(=O)C(Oc1ccc(cc1)Oc1ccc(cc1F)C#N)C,0.0096257,0.022697507512597942,1
+N#C/N=C\1/SCCN1Cc1ccc(nc1)Cl,0.0098922,0.08211542249954593,1
+Cc1c(ccc(c1C1=NOCC1)S(=O)(=O)C)C(=O)c1cnn(c1O)C,0.0099068,0.014734981060753658,1
+CC1(C)CNC(=NC1)NN=C(C=Cc1ccc(cc1)C(F)(F)F)C=Cc1ccc(cc1)C(F)(F)F,0.0099095,0.023429047658751763,1
+COP(=O)(OC=C(Cl)Cl)OC,0.0100688,0.03379255796926954,1
+CCCSP(=O)(SCCC)OCC,0.010069,0.012657180818924377,1
+FC(c1ccc(cc1)C=CC(=NN=C1NCC(CN1)(C)C)C=Cc1ccc(cc1)C(F)(F)F)(F)F,0.010112,0.036370558779348826,1
+CCOC(=O)Nc1cccc(c1)OC(=O)Nc1ccccc1,0.010656,0.17813891300624735,1
+O=C(C1C(C1(C)C)C=C(C(F)(F)F)Cl)OCc1c(F)c(F)c(c(c1F)F)C,0.010986,0.015513380963953891,1
+O=C(C1C(C1(C)C)C=C(C(F)(F)F)Cl)OCc1cccc(c1C)c1ccccc1,0.011824,0.038530366603758304,1
+O=S1OCC2C(CO1)C1(C(C2(Cl)C(=C1Cl)Cl)(Cl)Cl)Cl,0.012287,0.00022929597195349384,1
+Clc1cc(Cl)c(c(c1O)Cc1c(O)c(Cl)cc(c1Cl)Cl)Cl,0.012288,0.13448008863034894,1
+CC(Oc1cc(c(cc1Cl)Cl)n1nc(oc1=O)C(C)(C)C)C,0.0124555,0.0639086556427057,1
+Clc1ccc(c(c1)Cl)n1c(nc2c(c1=O)cc(cc2)F)n1cncn1,0.01268,0.04948226359599296,1
+CCC1CCCC(OC2CCC(C(O2)C)N(C)C)C(C)C(=O)C2=CC3C(C2CC(=O)O1)C=C(C)C1C3CC(C1)OC1OC(C)C(C(C1OC)OC)OC,0.012735,0.04122544888624932,1
+CC1C=CC=C2COC3C2(O)C(C=C(C3O)C)C(=O)OC2CC(CC=C(C1)C)OC1(C2)CCC(C(O1)C)C,0.012862,0.004239636609434808,1
+COc1ccc(cc1NNC(=O)OC(C)C)c1ccccc1,0.012985,1.1504508786009586,1
+N#CC(c1cccc(c1)Oc1ccccc1)OC(=O)C(c1ccc(cc1)OC(F)F)C(C)C,0.01329,0.029141936055180628,1
+CCP(=S)(Sc1ccccc1)OCC,0.0133561,0.180552509557717,1
+O=c1c(Cl)c(SCc2ccc(cc2)C(C)(C)C)cnn1C(C)(C)C,0.013701,0.07015650259648021,1
+CNP(=O)(Oc1ccc(cc1Cl)C(C)(C)C)OC,0.013712,0.10042068758188868,1
+NC1=C(Cl)C(=O)c2c(C1=O)cccc2,0.01392,1.2007205519265012,1
+CCN(C(=O)SCC)C1CCCCC1,0.01393,0.1768421335505478,1
+CNC(=O)Oc1cccc2c1OC(C2)(C)C,0.01394355,0.04199253503546284,1
+O=C(C1C(C1(C)C)/C=C(/C(F)(F)F)\Cl)OCc1c(F)c(F)c(c(c1F)F)C,0.01409,0.015432269420149127,1
+CC(c1ccccc1)(C[Sn](O[Sn](CC(c1ccccc1)(C)C)(CC(c1ccccc1)(C)C)CC(c1ccccc1)(C)C)(CC(c1ccccc1)(C)C)CC(c1ccccc1)(C)C)C,0.01425,0.1596660262709614,1
+CCCN(c1c(cc(cc1[N+](=O)[O-])C(F)(F)F)[N+](=O)[O-])CC1CC1,0.014397,0.17932714736827124,1
+CC(c1ccc(cc1)CCOc1ncnc2c1cccc2)(C)C,0.014687,0.06839002460448418,1
+CCCCC(c1ccc(cc1Cl)Cl)(Cn1cncn1)O,0.014958,0.03781713765732192,1
+N#CC(c1ccc(cc1)Oc1ccccc1)OC(=O)C1C(C1(C)C)/C=C\C(=O)OC(C(F)(F)F)C(F)(F)F,0.01496,0.03380219195325788,1
+N#Cc1c(Cl)c(C#N)c(c(c1Cl)Cl)Cl,0.015043,0.003102278786944784,1
+N#CC(c1cc(C)c(cc1Cl)NC(=O)c1cc(I)cc(c1O)I)c1ccc(cc1)Cl,0.015081,0.05806458024227402,1
+Clc1cc(cnc1CCNC(=O)c1ccccc1C(F)(F)F)C(F)(F)F,0.015124,0.07248777526000999,1
+N#CN=S(=O)(C(c1ccc(nc1)C(F)(F)F)C)C,0.015292,0.06883732609589185,1
+CC(C1C2CCC1c1c2cccc1NC(=O)c1cn(nc1C(F)F)C)C,0.015303,0.08218113939863288,1
+Fc1ccc(cc1)[Si](c1ccc(cc1)F)(Cn1cncn1)C,0.015853,0.01236601227587634,1
+CN1CCC(CC1)C1CCN(CC1)C,0.016044,0.08536100236003388,1
+CCCCN(c1c(cc(cc1[N+](=O)[O-])C(F)(F)F)[N+](=O)[O-])CC,0.016106,0.0830407836081033,1
+CCOP(=S)(Oc1cc(C)nc(n1)C(C)C)OCC,0.016429,0.011333492736012427,1
+N#Cc1c(Cl)cccc1Cl,0.0165685,0.08861346523698686,1
+Fc1ccc(cc1)C1(Cn2cncn2)OC1c1ccccc1Cl,0.016679,0.02683258169097081,1
+CCOP(=S)(Oc1nc(Cl)c(cc1Cl)Cl)OCC,0.017114,0.0021312647369153594,1
+BrC1COC(C1)(Cn1cncn1)c1ccc(cc1Cl)Cl,0.017185,0.0331672514896163,1
+CC(NC(=S)[S])CNC(=S)S[Zn],0.017255,0.055649620961502506,1
+CCN(C(=O)SCc1ccc(cc1)Cl)CC,0.0180385,0.020921315761282585,1
+COCC(N(c1c(C)csc1C)C(=O)CCl)C,0.018129,0.31466838335607944,1
+c1cc[n+]2c(c1)c1cccc[n+]1CC2,0.018481499999999998,0.07013406488036791,1
+CCc1nn(c(c1Cl)C(=O)NCc1ccc(cc1)C(C)(C)C)C,0.019469,0.007208504322428422,1
+CCCN(C(=O)n1cncc1)CCOc1c(Cl)cc(cc1Cl)Cl,0.019912,0.032617145173988164,1
+CCOC(=O)c1cn2nc(cc2nc1C)OP(=S)(OCC)OCC,0.0200875,0.11290862495631,1
+C[n+]1ccc(cc1)c1cc[n+](cc1)C,0.020134,0.17703724711923066,1
+COP(=S)(SCN1C(=O)c2c(C1=O)cccc2)OC,0.020484,0.03640627043753581,1
+Clc1cccc(c1)c1ccccc1,0.021203,0.2129407876803702,1
+CNC(=O)ON=C(C(=O)N(C)C)SC,0.022348,0.023724837234317484,1
+CSC1=NC(C(=O)N1Nc1ccccc1)(C)c1ccccc1,0.0228,0.10984557403049432,1
+CCN(C(=O)C(=C(OP(=O)(OC)OC)C)Cl)CC,0.023024100000000002,0.004600027916953598,1
+COC(=O)N(c1ccccc1COc1ccn(n1)c1ccc(cc1)Cl)OC,0.023207,0.09809137897658023,1
+CCCCCCCCCCCCC1=C(OC(=O)C)C(=O)c2c(C1=O)cccc2,0.023407,0.3978357015149616,1
+OC(COc1cccc2c1c1ccccc1[nH]2)CNC(C)C,0.02346,0.6438307981194183,1
+O=C(NC(=O)c1ccccc1Cl)Nc1ccc(cc1)OC(F)(F)F,0.023557,0.13358291661989544,1
+CCOC(=O)C(Oc1ccc(cc1)Oc1nc2c(o1)cc(cc2)Cl)C,0.024877,0.026475924769929923,1
+CON(C(=O)Nc1ccc(c(c1)Cl)Cl)C,0.025091,0.016650533715012246,1
+CN(C(=S)S[Zn]SC(=S)N(C)C)C,0.02534245,0.07523627134138902,1
+O=C(NC(=O)c1c(F)cccc1F)Nc1ccc(cc1)Cl,0.025428,0.0984709984094233,1
+CCNc1nc(NCC)nc(n1)Cl,0.0255385,0.01990254441079999,1
+OC(=O)C(Oc1ccc(cc1C)Cl)C,0.025624,0.032502135480438434,1
+Clc1ccccc1CC(C1(Cl)CC1)(Cn1cncn1)O,0.025625,0.20951297500074023,1
+O=C(N(C)C)Nc1ccc(c(c1)Cl)Cl,0.025741,0.08293596235384967,1
+CCOC(=O)C(Oc1ccc(cc1)Oc1cnc2c(n1)ccc(c2)Cl)C,0.0257509,0.08148548004151869,1
+CC(OC(=O)C(c1ccc(cc1)Cl)(c1ccc(cc1)Cl)O)C,0.026532,0.10218745390088035,1
+N#CC(c1cccc(c1)Oc1ccccc1)OC(=O)C1C(C1(C)C)/C=C(/C(F)(F)F)\Cl,0.026676,0.011677048407392303,1
+O=C(C1C(C1(C)C)C=C(Cl)Cl)OCc1c(F)c(F)cc(c1F)F,0.026943,0.06344054151894221,1
+N#Cc1sc2=c(sc1C#N)c(=O)c1c(c2=O)cccc1,0.0269975,0.15530666985465563,1
+CCOC(=O)c1ccccc1C1=c2cc(C)c(cc2=[O]c2c1cc(C)c(c2)NCC)NCC,0.027054,1.660584417238517,1
+CSCC(=NOC(=O)NC)C(C)(C)C,0.027483,0.00789274785250164,1
+Cc1nn(c(c1C(=O)c1ccc(cc1S(=O)(=O)C)C(F)(F)F)O)C,0.0276,0.026923343331066146,1
+CCOc1cc(ccc1N(=O)=O)Oc1ccc(cc1Cl)C(F)(F)F,0.027647,0.14765165288122328,1
+[O-][N+](=O)c1cc(C(=O)N)c(c(c1)[N+](=O)[O-])C,0.027758,0.04915460020833467,1
+N#CC(c1cccc(c1)Oc1ccccc1)OC(=O)C1C(C1(C)C)C=C(C(F)(F)F)Cl,0.027787,0.00909812820067356,1
+C=CC1(C)OC(=O)N(C1=O)c1cc(Cl)cc(c1)Cl,0.027961,0.14266612867789524,1
+OC(=O)C(Oc1ccc(cc1)Oc1nc2c(o1)cc(cc2)Cl)C,0.028167,0.01711250324602175,1
+N#CC(c1ccc(c(c1)Oc1ccccc1)F)OC(=O)C1C(C1(C)C)C=C(Cl)Cl,0.028207,0.0426574152094694,1
+CS/C(=N/OC(=O)N(SN(C(=O)O/N=C(/SC)\C)C)C)/C,0.028211,0.028210999999999983,1
+CSC(=NOC(=O)N(SN(C(=O)ON=C(SC)C)C)C)C,0.028211,0.02379431320371135,1
+CC(N1C(=NC(C)(C)C)SCN(C1=O)c1ccccc1)C,0.028484,0.029904067056948657,1
+N#Cc1cc(Br)c(c(c1)Br)O,0.02889,0.039616506440811085,1
+CCOC(=O)C(Cc1cc(c(cc1Cl)F)n1nc(n(c1=O)C(F)F)C)Cl,0.029113,0.1703418373948284,1
+C#CCOC(=O)C(Oc1ccc(cc1)Oc1ncc(cc1F)Cl)C,0.029164,0.01495050998848888,1
+CC(N1/C(=N/C(C)(C)C)/SCN(C1=O)c1ccccc1)C,0.029466,0.031298297859973165,1
+COc1nc(Oc2cccc(c2C(=O)[O-])Oc2nc(OC)cc(n2)OC)nc(c1)OC.[Na+],0.030507,0.8857069796462624,1
+CON(C(=O)Nc1ccc(cc1)Br)C,0.0313005,0.02353550999851074,1
+COc1nc(C)nc(n1)N(C(=O)NS(=O)(=O)c1ccccc1C(=O)OC)C,0.031614,0.47676626552153417,1
+Cc1ccc2c(c1)nc1c(n2)sc(=O)s1,0.032011,0.0914876846785335,1
+Fc1ccc(cc1)NC(=O)c1cccc(n1)Oc1cccc(c1)C(F)(F)F,0.032155,0.05977601983840624,1
+CCCn1c(OCCC)nc2c(c1=O)cc(cc2)I,0.032241,0.11240974023972475,0.10810810810810811
+CC(C(=O)O)Oc1cc(Cl)c(cc1Cl)Cl,0.032281,0.03257838303008498,1
+COc1cc(OC)nc(n1)NC(=O)NS(=O)(=O)c1ncccc1C(F)(F)F,0.032652,0.7136401490254,1
+CN1CN(C)CSC1=S,0.03266,0.05748016757235302,1
+CCC1CCCC(OC2CCC(C(O2)C)N(C)C)C(C)C(=O)C2C(CC(=O)O1)C1CCC3C(C1C2)CC(C3)OC1CC(C)C(C(C1OC)OC)OC,0.032697,0.07537393885801477,1
+ClCC1CN(C(=O)C1Cl)c1cccc(c1)C(F)(F)F,0.033160999999999996,0.04474739523765091,1
+O=C(C(Oc1ccc(cc1)Oc1cnc2c(n1)ccc(c2)Cl)C)OCCON=C(C)C,0.033793,0.03948643902176639,1
+Fc1ccc(cc1)C(c1ccccc1F)(Cn1cncn1)O,0.033854,0.024061122566030407,1
+CN(/C=N/c1ccc(cc1C)C)/C=N/c1ccc(cc1C)C,0.034082,0.10334041996542481,1
+CCCCC(c1ccc(cc1)Cl)(Cn1cncn1)C#N,0.034179,0.13570461889549004,1
+CN(C=Nc1ccc(cc1C)C)C=Nc1ccc(cc1C)C,0.034423,0.10334041996542481,1
+CCOP(=S)(SCn1c(=O)oc2c1ccc(c2)Cl)OCC,0.0345288,0.0033780120065874876,1
+ClC(=CCOc1cc(Cl)c(c(c1)Cl)OCCCOc1ccc(cn1)C(F)(F)F)Cl,0.034819,0.029461037155614538,1
+CCOCn1c(c2ccc(cc2)Cl)c(c(c1C(F)(F)F)Br)C#N,0.0350825,0.06402302685939379,1
+Fc1ccc(c(c1)c1ccc(c(c1)Cl)Cl)NC(=O)c1cn(nc1C(F)F)C,0.035609999999999996,0.03045142490176041,1
+CCCSP(=S)(Oc1ccc(cc1)SC)OCC,0.035665,0.004647020354732256,1
+CCC(C(=O)OC1=C(C(=O)OC21CCCCC2)c1ccc(cc1Cl)Cl)(C)C,0.035787,0.0676076219102873,1
+C#CCOC(c1ccc(cc1)Cl)C(=O)NCCc1ccc(c(c1)OC)OCC#C,0.036904,0.12880612497460633,1
+CC(Cc1ccccc1)N,0.036981,0.37241504916097706,1
+OC(C(C)(C)C)C(n1ncnc1)Cc1ccc(cc1)Cl,0.037441,0.08324058003320423,1
+CCN(c1c(cc(cc1N(=O)=O)C(F)(F)F)N(=O)=O)CC(=C)C,0.037508,0.20384580236005995,1
+Clc1c(O)c(Cl)c(c(c1Cl)Cl)Cl,0.037546,0.03735555848053126,1
+CC(OP(=S)(OC(C)C)SCCNS(=O)(=O)c1ccccc1)C,0.037735,0.002507186081424219,1
+Clc1ccc(cc1)c1ccccc1NC(=O)c1cccnc1Cl,0.037878,0.35775569216900976,1
+Clc1ccc(c(c1)Cl)C1(OCCO1)Cn1cncn1,0.0379825,0.05925854846782829,1
+CCOC(=O)CSc1nc(nn1C(=O)N(C)C)C(C)(C)C,0.038167,0.27161496739438523,1
+ClC(C(SN1C(=O)C2C(C1=O)CC=CC2)(Cl)Cl)Cl,0.038675,0.3297078612771189,0.42857142857142855
+CC(C(c1cncnc1)(c1ccc(cc1)OC(F)(F)F)O)C,0.038746,0.04367441887753131,1
+OC(=O)COc1cc(Cl)c(cc1Cl)Cl,0.039142,0.07307066178054096,1
+CCOP(=S)(Oc1nn(c(n1)Cl)C(C)C)OCC,0.039842,0.012976866662781082,1
+O=C(NC(=O)c1c(F)cccc1F)Nc1cc(Cl)c(cc1Cl)OC(C(C(F)(F)F)F)(F)F,0.03991,0.11093187543369389,1
+CNC(=S)S,0.040113,0.04526482606586425,1
+CCCOC/C(=N\c1ccc(cc1C(F)(F)F)Cl)/n1cncc1,0.040492,0.012164183574922672,1
+CC(N(C(=O)SCC(=C(Cl)Cl)Cl)C(C)C)C,0.041029,0.03687618046077712,1
+O=C(CC(C)(C)C)OC1=C(C(=O)OC21CCCC2)c1c(C)cc(cc1C)C,0.0414325,0.09612584285128209,1
+OC1(Cn2ncnc2)C(CCC1(C)C)Cc1ccc(cc1)Cl,0.0420535,0.053376610054185716,1
+COP(=S)(Oc1ccc(c(c1)C)[N+](=O)[O-])OC,0.0424911,0.002384016951572669,1
+CCOC(=O)CCN(C(C)C)SN(C(=O)Oc1cccc2c1OC(C2)(C)C)C,0.042628,0.026514948775914114,1
+CC(Cc1ccc(cc1)C(C)(C)C)CN1CCCCC1,0.043261,0.0027903587131728642,1
+Nc1n[nH]cn1,0.0446005,0.04204987250872469,0.2727272727272727
+Nc1ncn[nH]1,0.0446005,0.04204987250872469,0.2727272727272727
+[S-]C(=S)NCCNC(=S)[S-].[Zn+2],0.044607,0.1694797471947793,1
+CCSC(=O)N1CCCCCC1,0.044874,0.1222518161386908,1
+O=C1OC(C(=O)N1Nc1ccccc1)(C)c1ccc(cc1)Oc1ccccc1,0.04514,0.045730864312893,1
+ClC(C(c1ccc(cc1)Cl)c1ccc(cc1)Cl)(Cl)Cl,0.045488125000000004,0.06288262653490974,1
+S=C1NCCCN1,0.045617,0.01384383462435663,1
+ClCC=CCl,0.045958,0.31747,0.125
+CCOC(=O)Cn1c(=O)sc2c1c(Cl)ccc2,0.046003,0.1687181994278459,1
+N#CC(c1c(Cl)ccc(c1Cl)n1ncc(=O)[nH]c1=O)c1ccc(cc1)Cl,0.04661,0.050771212356166946,1
+CN(C(=S)SSC(=S)N(C)C)C,0.04783,0.06926194842492117,1
+Cc1cccc(c1O)C,0.049114,0.20058564161827389,1
+CCC(C(=O)NCc1ccccc1)Oc1ccc(c(c1)C(F)(F)F)F,0.049813,0.04437595699860732,1
+COC(=O)Nc1nc2c([nH]1)cc(cc2)Sc1ccccc1,0.050109,0.14986556789217165,1
+CCSC(CC1CC(=O)C(C(=O)C1)C(=NOCC)CCC)C,0.050568,0.12460566123801867,1
+C#CCN1C(=O)COc2c1cc(c(c2)F)N1C(=O)C2=C(C1=O)CCCC2,0.0508,0.053941885942165126,0.11764705882352941
+CNC(=O)Oc1cc(C)c(c(c1)C)C,0.051749,0.060398815269606866,1
+CNC(=O)Oc1cccc(c1)/N=C/N(C)C,0.051976,0.049959813676698134,1
+CN(C(=O)Oc1nc(nc(c1C)C)N(C)C)C,0.0520385,0.030679541298093704,1
+O=N(=O)c1ccc(c(c1)N)C,0.052579,0.21665325505383387,1
+CCO/N=C(\C1=C(O)CC(CC1=O)C1CCCSC1)/CCC,0.052847,0.07543495983019052,1
+CC(C(c1ccc(cc1)Cl)(Cn1ncnc1)O)C1CC1,0.05326,0.02502998066492108,1
+O=C(N/C(=N\OCC1CC1)/c1c(F)c(F)ccc1C(F)(F)F)Cc1ccccc1,0.053352,0.051964159537253175,1
+NC(=NCCCCCCCCNCCCCCCCCN=C(N)N)N,0.053436,0.06155286590252889,1
+C=CCOC(c1ccc(cc1Cl)Cl)Cn1cncc1,0.053503,0.01374144736573495,1
+COCN(c1c(CC)cccc1CC)C(=O)CCl,0.0537505,0.5872703265474054,1
+CNC1=C(c2cccc(c2)C(F)(F)F)C(=O)C(O1)c1ccccc1,0.055205,0.12096920476570115,1
+CCOc1ccc2c(c1)C(=CC(N2)(C)C)C,0.055221,0.3806288619670738,1
+O=C(c1ccc(cc1S(=O)(=O)C)C(F)(F)F)c1cnoc1C1CC1,0.055661,0.027171174867194094,1
+CCOC(=O)COC(=O)c1cc(ccc1[N+](=O)[O-])Oc1ccc(cc1Cl)C(F)(F)F,0.055835,0.24838169603066493,1
+COc1nc(nc(n1)C)NC(=O)[N-]S(=O)(=O)c1cc(I)ccc1C(=O)OC.[Na+],0.056118,0.22973691335919075,1
+CNC(=O)Oc1cccc(c1)N=CN(C)C,0.056496,0.0330473860931032,1
+CCOC(=O)C(c1ccc(cc1)Cl)(c1ccc(cc1)Cl)O,0.056583,0.029595337714367734,1
+OC(=O)COc1ccc(cc1C)Cl,0.0573225,0.1332435185684817,1
+CCOCCN(C(=C(C)C)c1ccccc1)C(=O)CCl,0.05747,0.37429577400621544,1
+CCOC(=O)NCCOc1ccc(cc1)Oc1ccccc1,0.0575765,0.22612517895268872,1
+CN(C(CN1c2ccccc2Sc2c1cccc2)C)C,0.058365,0.0955384340999688,1
+CC1COC(O1)(Cn1cncn1)c1ccc(cc1Cl)Oc1ccc(cc1)Cl,0.059321,0.11089254590582763,1
+N#CC(c1cccc(c1)Oc1ccccc1)OC(=O)C(c1ccc(cc1)Cl)C(C)C,0.059538,0.011966342190996581,1
+CCN(c1c(cc(cc1[N+](=O)[O-])C(F)(F)F)[N+](=O)[O-])CC(=C)C,0.0595625,0.03294158607883975,1
+N#CC(c1cccc(c1)Oc1ccccc1)OC(=O)C1C(C1(C)C)(C)C,0.060099,0.02763144960652484,1
+CC(OC(=O)C(c1ccc(cc1)Br)(c1ccc(cc1)Br)O)C,0.0606145,0.020841190814278196,1
+C=CC=CCC1=C(C)C(CC1=O)OC(=O)C1C(C1(C)C)C=C(C)C.C=CC=CCC1=C(C)C(CC1=O)OC(=O)C1C(C1(C)C)C=C(C(=O)OC)C,0.06135,0.15780818899648733,1
+Clc1ccccc1c1nnc(nn1)c1ccccc1Cl,0.06152150000000001,0.13308775089910072,1
+COC(=O)c1cccc(c1S(=O)(=O)NC(=O)Nc1nc(OCC(F)(F)F)nc(n1)N(C)C)C,0.062141,0.16138405979142514,1
+CCNc1nc(SC)nc(n1)NC(C)(C)C,0.062149,0.013482271036981958,1
+[O-][N+](=O)c1cc(cc(c1)[N+](=O)[O-])[N+](=O)[O-],0.062458,0.08677605592325374,1
+Clc1cc(ccc1Oc1ccc(c(c1)C(=O)NS(=O)(=O)C)[N+](=O)[O-])C(F)(F)F,0.062678,0.1528433955174944,1
+Clc1cc(F)c(cc1C(=O)NS(=O)(=O)N(C(C)C)C)n1c(=O)cc(n(c1=O)C)C(F)(F)F,0.062693,0.029112999999999997,0.10416666666666667
+COc1nc(nc(n1)C)NC(=O)NS(=O)(=O)c1ccccc1Cl,0.062889,0.0890875062280205,1
+O=C(NS(=O)(=O)c1c(C)cccc1C(=O)O)Nc1nc(OCC(F)(F)F)nc(n1)N(C)C,0.063963,0.42512361325325054,1
+COc1nc(nc(n1)C)NC(=O)NS(=O)(=O)c1ccsc1C(=O)OC,0.064534,0.11435332900490963,1
+O=C(N(C)C)Nc1ccc(c(c1)Cl)n1nc(oc1=O)C(C)(C)C,0.064937,0.01117665376540355,1
+CCCCN(SN(C(=O)Oc1cccc2c1OC(C2)(C)C)C)CCCC,0.065695,0.028393651001017862,1
+[O-][N+](=O)NC1=NCCN1Cc1ccc(nc1)Cl,0.066494,0.06983499732815489,1
+O=C(NC(=O)c1c(F)cccc1F)Nc1cc(Cl)c(c(c1F)Cl)F,0.06691,0.10975123036700667,1
+CSc1nnc(c(=O)n1N)C(C)(C)C,0.067199,0.01370099999999999,0.11538461538461539
+O=C(NC(=O)c1c(F)cccc1F)Nc1ccc(c(c1)Cl)OC(C(OC(F)(F)F)F)(F)F,0.06758600000000001,0.054818728149877004,1
+CCOc1ccc(cc1)C(COCc1cccc(c1)Oc1ccccc1)(C)C,0.068395,0.09820443732276256,1
+C#CCOS(=O)OC1CCCCC1Oc1ccc(cc1)C(C)(C)C,0.06905,0.13896995963026978,1
+CCO/N=C(/C1=C(O)CC(CC1=O)c1c(C)cc(cc1C)C)\CC,0.069817,0.14919497287286787,1
+CO/N=C(/c1ccccc1COc1cc(C)ccc1C)\C(=O)NC,0.070468,0.4749292233768437,1
+COc1cc(OC)n2c(n1)nc(n2)S(=O)(=O)Nc1c(Cl)ccc(c1Cl)C,0.071727,0.3911131219885315,1
+OC(=O)COc1nc(Cl)c(cc1Cl)Cl,0.07213454999999999,0.05684508706325722,1
+CCCN(c1c(cc(cc1[N+](=O)[O-])S(=O)(=O)N)[N+](=O)[O-])CCC,0.07218,0.1928126729158588,1
+CCN1CCN(CC1)c1cc2c(cc1F)c(=O)c(cn2C1CC1)C(=O)O,0.072344,0.13991,0.5862068965517241
+Nc1ccc(cc1)Cl,0.072508,0.21450594943480125,1
+CO/N=C(\c1ccccc1CO/N=C(/c1cccc(c1)C(F)(F)F)\C)/C(=O)OC,0.072728,0.16104296340673316,1
+O=C(N(C)C)Nc1cccc(c1)C(F)(F)F,0.073957,0.028219619566234058,1
+OC(C(C)(C)C)C(n1cncn1)Oc1ccc(cc1)c1ccccc1,0.074093,0.15044751241915677,1
+CCCSc1ccc2c(c1)[nH]c(n2)NC(=O)OC,0.075377,0.029694598836754082,1
+Cn1nc(c(c1)C(=O)Nc1cccc2c1C1CCC2C1=C(Cl)Cl)C(F)F,0.075835,0.05526839542853898,1
+CCNc1nc(NC(C)C)nc(n1)Cl,0.077892,0.09557547621401412,1
+N#C/N=C(/N(Cc1ccc(nc1)Cl)C)\C,0.07859,0.026400030134249707,1
+CC(c1cc(ccc1O)C(c1ccc(c(c1)C(C)C)O)(C)C)C,0.080014,0.4395099232948336,1
+C=CCC1=C(C)C(CC1=O)OC(=O)C1C(C1(C)C)C=C(C)C,0.081016,0.09473524972813754,1
+NC(=N)NCCCCCCCCNC(=N)N,0.08102,0.12282753342910002,1
+O=C(C1=C(C)OCCS1)Nc1ccccc1,0.0811745,0.15573428524718813,1
+Clc1cc(cnc1CNC(=O)c1c(Cl)cccc1Cl)C(F)(F)F,0.082121,0.01718770407505741,1
+CNC(=O)Oc1cc(C)c(c(c1)C)SC,0.0827735,0.017398102764576116,1
+O=C(c1cccc(c1C(=O)NC(CS(=O)(=O)C)(C)C)I)Nc1ccc(cc1C)C(C(F)(F)F)(C(F)(F)F)F,0.0827975,0.08998272006962794,1
+COC(=O)Nc1cccc(c1)OC(=O)Nc1cccc(c1)C,0.083248,0.029088943915557667,1
+CCCN(c1c(cc(c(c1[N+](=O)[O-])N)C(F)(F)F)[N+](=O)[O-])CCC,0.08393,0.13322462877430882,1
+OC(C(C)(C)C)C(n1ncnc1)Oc1ccc(cc1)Cl,0.084527,0.09452757279585151,1
+O=C(C(C)(C)C)C(n1ncnc1)Oc1ccc(cc1)Cl,0.085107,0.06018850451817422,1
+CCCC(=C1C(=O)CC(CC1=O)C1CCCSC1)NOCC,0.08603,0.029427973343164302,1
+Cn1cc(c2cccc(c2)C(F)(F)F)c(=O)c(c1)c1ccccc1,0.08730199999999999,0.07214443659877276,1
+CC(NC(=O)N1CC(=O)N(C1=O)c1cc(Cl)cc(c1)Cl)C,0.08783250000000001,0.07311274839022557,1
+CC(=O)Nc1cc(NS(=O)(=O)C(F)(F)F)c(cc1C)C,0.088948,0.8840250837103576,1
+COCC(=O)Nc1cc(ccc1NC(=NC(=O)OC)NC(=O)OC)Sc1ccccc1,0.08959,0.14538565337728704,1
+CCCN(C(=O)SCC)CCC,0.0897945,0.03300624320502932,1
+COc1cc(ccc1OC)/C(=C/C(=O)N1CCOCC1)/c1ccc(cc1)Cl,0.0902395,0.1409651153114008,1
+CCC(=O)Nc1ccc(c(c1)Cl)Cl,0.09171,0.24431318312583458,1
+N#CC(c1ccccc1)(Cn1cncn1)CCc1ccc(cc1)Cl,0.092038,0.07234937880705852,1
+Clc1ccc2c(c1)ncc(n2)Oc1ccc(cc1)OC(C(=O)OCC1CCCO1)C,0.092103,0.04640546757315488,1
+CNC(=O)ON=C(SC)C,0.092474,0.04066921692596899,1
+NC(=O)c1c(Cl)cccc1Cl,0.092619,0.22037811393558152,1
+Clc1ccc(c(c1)Cl)NC(=O)C1(CC1)C(=O)O,0.093032,0.22385031294889093,1
+Clc1cc(Cl)cc(c1)C1(CO1)CC(Cl)(Cl)Cl,0.093625,0.06738779377643565,1
+ClC(=CC1C(C1(C)C)C(=O)OCc1cccc(c1)Oc1ccccc1)Cl,0.095836,0.13585880635599093,1
+OC(=O)C(Oc1ccc(cc1Cl)Cl)C,0.0967835,0.03672512677859495,1
+[O-][N+](=O)/N=C/1\NCCN1Cc1ccc(nc1)Cl,0.097395,0.09059586582208207,1
+NC(=N)NCCCCCCCCCCCCOC(=O)C,0.1016,0.09232709423649268,1
+OC1CC2(O)CC(O)C(C(O2)(C)CC(C=CC=CC=CC=CCC(OC(=O)C=CC2C(C1)(C)O2)C)OC1(C)OC(C)C(C(C1O)N)O)C(=O)O,0.10172,0.80523,0.11538461538461539
+COP(=O)(NC(=O)C)SC,0.1023645,0.020049393739713695,1
+COc1ncc(c2n1nc(n2)NS(=O)(=O)c1c(cccc1C(F)(F)F)OCC(F)F)OC,0.10344,0.529012881332425,1
+COCc1c(F)c(F)c(c(c1F)F)COC(=O)C1C(C1(C)C)/C=C/C,0.10573,0.029546606216402968,1
+[O-][N+](=O)c1cnc(n1C)C,0.10629,0.08158352045907184,1
+CCOC(=O)C(OC(=O)c1cc(ccc1N(=O)=O)Oc1cc(ccc1Cl)C(F)(F)F)C,0.10828,0.05034984560496159,1
+CCOC(=O)C(OC(=O)c1cc(ccc1[N+](=O)[O-])Oc1ccc(cc1Cl)C(F)(F)F)C,0.10828,0.2305030993484664,1
+COc1c(OC)cc(c(c1OC)C(=O)c1c(OC)ncc(c1C)Cl)C,0.108388,0.442824415382828,1
+S=C1NCCNC(=S)S[Mn+2]S1,0.10856,0.044545364034366486,1
+ClCC(=O)N(c1ccccc1)C(C)C,0.10865,0.04026148385573769,1
+O=C1CCCC(=O)C1C(=O)c1ccc(cc1Cl)S(=O)(=O)C,0.11010835,0.0048166108976690275,1
+CCCN(CC1COC2(O1)CCC(CC2)C(C)(C)C)CC,0.11029,1.3278,0.1
+O=C1N(c2cc(Cl)cc(c2)Cl)C(=O)C2(C1(C)C2)C,0.1108605,0.13106762525413437,1
+COC(=O)c1c(nc(c(c1CC(C)C)C1=NCCS1)C(F)(F)F)C(F)F,0.11151,0.06043692115939837,1
+Oc1ccc(c(c1)C)C,0.1146,0.3479628565636459,1
+Clc1ccc(cc1)CCC(C(C)(C)C)(Cn1cncn1)O,0.115167,0.056288884169246704,1
+CNc1cnn(c(=O)c1Cl)c1cccc(c1)C(F)(F)F,0.1152575,0.03111103885603756,1
+N#Cc1c(N)nc(nc1N)NC1CC1,0.11566,0.11056446731723946,1
+CC(N(c1c(cc(cc1N(=O)=O)S(=O)(=O)N)N(=O)=O)C(C)C)C,0.11817,0.41913381480648365,1
+CNC(=O)O/N=C(\SC)/C,0.11837,0.06400325897362466,1
+Nc1ccc(cc1)S(=O)(=O)Nc1nc(C)cc(n1)C,0.11856,0.2186156235995446,1
+CCN(c1c(cc(cc1[N+](=O)[O-])C(F)(F)F)[N+](=O)[O-])Cc1c(F)cccc1Cl,0.11856,0.058778302601955115,1
+COc1cc(ccc1OC)C(=CC(=O)N1CCOCC1)c1ccc(cc1)Cl,0.11937,0.08489169150210692,1
+CCCCc1c(=O)nc([nH]c1C)NCC,0.11945,0.15982622066467786,1
+COC(=O)NC(=S)Nc1ccccc1NC(=S)NC(=O)OC,0.12412500000000001,0.3115690461921685,1
+c1coc(c1)c1nc2c([nH]1)cccc2,0.12487,0.10928852708217107,1
+CN(C(=O)C(c1ccccc1)c1ccccc1)C,0.12536,0.21305160036338935,1
+CCOc1cc(ccc1[N+](=O)[O-])Oc1ccc(cc1Cl)C(F)(F)F,0.12856,0.12964803508283673,1
+[O-][N+](=O)/N=C(\NC)/NCc1cnc(s1)Cl,0.13017,0.53134,0.23076923076923078
+Clc1c(ccc(c1N)[N+](=O)[O-])Oc1ccccc1,0.13224349999999999,0.4526201811157268,1
+OC(C(C)(C)C)C(=Cc1ccc(cc1)Cl)n1ncnc1,0.13507,0.24955229911836616,1
+CCNC(=O)NC(=O)/C(=N\OC)/C#N,0.135735,0.15289,1
+O=C(Nc1cnns1)Nc1ccccc1,0.13621,0.07758581528990915,1
+CCc1ccc(cc1)C(=O)NN(C(C)(C)C)C(=O)c1cc(C)cc(c1)C,0.13674999999999998,0.36885598794348823,1
+CN1CC2CC1CN2c1cc2c(cc1F)c(=O)c(cn2C1CC1)C(=O)O,0.13991,0.2090946529245896,0.5862068965517241
+OCC(CCl)O,0.14067559999999998,14.497001490430202,1
+COC(=O)C(N(c1c(C)cccc1C)C(=O)Cc1ccccc1)C,0.14136,0.26940692371366265,1
+COc1nc(C)nc(n1)N(C(=O)NS(=O)(=O)c1ccccc1C(=O)O)C,0.14422,0.1474928503094857,1
+ClC(=C)Cl,0.14441,0.010100837249467656,0.1
+CC(=O)O.CCCCCCCCCCCCNC(=N)N,0.14612,0.07624062130924328,1
+CON=C(c1ccccc1CON=C(c1cccc(c1)C(F)(F)F)C)C(=O)OC,0.14693,0.08314064599352722,1
+COC(CCCC(CC=CC(=CC(=O)OC(C)C)C)C)(C)C,0.14816,0.8052299999999997,1
+c1scc(n1)c1nc2c([nH]1)cccc2,0.14907,0.10738182341473035,1
+CC(N1C(=O)c2ccccc2NS1(=O)=O)C,0.14983,0.567304025971418,1
+N#CC(c1cccc(c1)Oc1ccccc1)OC(=O)C1C(C1(C)C)C=C(Cl)Cl,0.150135,0.030804750827027095,1
+Cc1cccc2c1n1cnnc1s2,0.150605,0.3607837978275225,1
+ClC(SN1C(=O)c2c(C1=O)cccc2)(Cl)Cl,0.15173999999999999,0.21986859881425846,1
+CON=C(c1ccc(cc1Cl)Cl)Cc1cccnc1,0.15246,0.03739430341466496,1
+CCNC(=O)NC(=O)C(=NOC)C#N,0.15289,0.13464656029769195,1
+Clc1ccc(c(c1)Cl)C=C(C(C(C)(C)C)O)n1cncn1,0.15327,0.10677135158310637,1
+CCC(Nc1c(cc(cc1[N+](=O)[O-])C(C)(C)C)[N+](=O)[O-])C,0.153385,0.05644136089279899,1
+COC=C(c1ccccc1Oc1ncnc(c1)Oc1ccccc1C#N)C(=O)OC,0.15432,0.21627993526671827,1
+COP(=S)(Oc1cc(Cl)c(cc1Cl)Cl)OC,0.1555,0.009166929225323212,1
+CCCCCCCCc1cc(N(=O)=O)c(c(c1)N(=O)=O)OC(=O)C=CC,0.15642,0.35884113310639476,1
+Cc1nc(Nc2ccccc2)nc(c1)C1CC1,0.15802,0.6089638229229073,1
+CCOC(=O)CN(c1c(CC)cccc1CC)C(=O)CCl,0.16036,0.24863228224734207,1
+CC(OC(=O)Nc1ccccc1)C,0.16182,1.1708873702537812,1
+c1ccc(cc1)Nc1ccccc1,0.16546,0.38230959751715715,1
+C#CC(NC(=O)c1cc(Cl)cc(c1)Cl)(C)C,0.16593,0.13167988211278275,1
+Cc1ccc(c2c1cccc2)C,0.17283,0.16120910099868146,1
+Clc1cc(Cl)c(cc1n1nc(n(c1=O)C(F)F)C)NS(=O)(=O)C,0.17304,0.02384153039577781,1
+COC(=O)c1ccc(cc1C1=NC(C(=O)N1)(C)C(C)C)C,0.17341,0.31007186013262555,1
+CNC(=O)N(c1nnc(s1)C(C)(C)C)C,0.1752,0.15654919233821035,0.4
+CCCCCCC(c1cc(cc(c1OC(=O)/C=C/C)[N+](=O)[O-])[N+](=O)[O-])C,0.17563,0.2855294643082782,1
+CCCCCCCCCC[N+](CCCCCCCCCC)(C)C.[Cl-],0.17676,1.1643137822479213,1
+CCCC1COC(O1)(Cn1cncn1)c1ccc(cc1Cl)Cl,0.176786,0.041282688264930485,1
+N#Cc1cc(C)c(c(c1)C(=O)NC)NC(=O)c1cc(nn1c1ncccc1Cl)Br,0.17901,0.01959582292450347,1
+COCC(=O)N(c1c(C)cccc1C)N1CCOC1=O,0.17966,0.14796616786876735,1
+CC1=NNC(=O)N(C1)/N=C/c1cccnc1,0.18092,0.6252990751401866,1
+C#CCC1=C(C)C(CC1=O)OC(=O)C1C(C1(C)C)C=C(C)C,0.18558899999999998,0.10990739666701174,1
+O=N(=O)c1ccc(c(c1)N(=O)=O)C,0.18668,0.07014234537110925,1
+ClCC(=O)N(c1c(C)cccc1C)Cn1cccn1,0.18829800000000002,0.16535427022646612,1
+N#CCNC(=O)c1cnccc1C(F)(F)F,0.19244,0.2303129862357631,1
+OC1CN(C(=O)N1c1nnc(s1)C(C)(C)C)C,0.19507,0.17520000000000005,0.4
+O=c1nc(N(C)C)n(c(=O)n1C1CCCCC1)C,0.19817,0.5036400000000001,0.16666666666666666
+COc1nc(nc(n1)C)NC(=O)NS(=O)(=O)c1ccccc1CCC(F)(F)F,0.200175,0.08609366768940808,1
+Nc1ccc(c(c1)N)O,0.20138,2.3270767492496245,1
+Cn1nc(c(c1)C(=O)Nc1ccccc1C1CC1C1CC1)C(F)F,0.2022,0.08530560389864407,1
+O=C(NS(=O)(=O)c1ccccc1C(=O)OC1COC1)Nc1nc(C)cc(n1)C,0.20423,0.2457556305108701,1
+CO/C=C(\c1ccccc1Oc1ncnc(c1)Oc1ccccc1C#N)/C(=O)OC,0.20427,0.15276161737193344,1
+ClC=C(c1cc(Cl)c(cc1Cl)Cl)OP(=O)(OC)OC,0.20494,0.005545057436381607,1
+CC(=CC1C(C1(C)C)C(=O)OCc1coc(c1)Cc1ccccc1)C,0.2068305,0.11195103584278988,1
+ClCC(=O)N(c1c(CC)cccc1CC)CNC(=O)C,0.21058,0.3924849952918688,1
+CCOCN(c1c(C)cccc1CC)C(=O)CCl,0.21666999999999997,0.07675200321461363,1
+CC(c1ccc(cc1)O)(c1ccc(cc1)O)C,0.21902,0.4212603683317479,1
+CC(Nc1nc(NC(C)C)nc(n1)Cl)C,0.219845,0.06430354395190928,1
+Fc1ccc(cc1)C(=O)CCCN1CCN(CC1)c1ccccn1,0.221446,0.2913921284521735,1
+COCC(=O)N(c1c(C)cccc1C)C(C(=O)OC)C,0.22375,0.13496328422109782,1
+Nc1ccc2c(c1)nc1c(c2)ccc(c1)N,0.22462,0.687683681392934,1
+Cc1nnc(c(=O)n1N)c1ccccc1,0.2326765,0.22870570020497283,1
+CCNC(=O)C(OC(=O)Nc1ccccc1)C,0.23279,0.3030365914767059,1
+CNC(=O)Oc1ccccc1OC(C)C,0.23418,0.013151553815225373,1
+Cl/C=C/CO/N=C(\C1=C(O)CC(CC1=O)CC(SCC)C)/CC,0.23895,0.15737026431213788,1
+CCCCCCCCSC(=O)Oc1cc(Cl)nnc1c1ccccc1,0.24081999999999998,0.13659751142830953,1
+Nc1cnn(c(=O)c1Cl)c1ccccc1,0.24815,0.0990886943710885,1
+CCc1cc(C)cc(c1c1c(OC(=O)C(C)(C)C)n2n(c1=O)CCOCC2)CC,0.24968,0.10769710055647776,1
+CC1OC(C)OC(OC(O1)C)C,0.2497,0.71759,0.25
+[S]C(=S)NCCNC(=S)S[Mn],0.25254,0.04688388228967474,1
+O=C1N(OCC1(C)C)Cc1ccccc1Cl,0.253443,0.05966229922143249,1
+CC(CC(c1sccc1NC(=O)c1cn(nc1C(F)(F)F)C)C)C,0.25458,0.12140293055430215,1
+CCSC(CC1CC(=O)C(=C(NOCC=CCl)CC)C(=O)C1)C,0.25839999999999996,0.18080210641569622,1
+Cc1ccc(cc1)N(S(=O)(=O)N(C)C)SC(Cl)(Cl)F,0.25917,0.06963376614355403,1
+CC1N(C(=O)NC2CCCCC2)C(=O)SC1c1ccc(cc1)Cl,0.259436,0.04351436613794085,1
+Fc1ccc(cc1)Oc1ccnc2c1c(Cl)cc(c2)Cl,0.25963,0.05346729270334559,1
+CCCCCCC(c1cc(cc(c1OC(=O)/C=C\C)[N+](=O)[O-])[N+](=O)[O-])C,0.26317500000000005,0.1154974400434934,1
+CCN(C(=O)C(Oc1cccc2c1cccc2)C)CC,0.271895,0.7627118418342616,1
+OC(=O)C(Cl)(Cl)C,0.273385,0.31747,0.125
+COc1cc(OC)nc(n1)NC(=O)NS(=O)(=O)c1ncccc1S(=O)(=O)CC,0.28045,0.6596025887989719,1
+OC(=O)COc1ccc(cc1Cl)Cl,0.2805,0.1207143956787754,1
+CO/C=C(\c1ccccc1COc1cccc(n1)C(F)(F)F)/C(=O)OC,0.28313,0.10934310268327334,1
+CCOC(=O)CC(C(=O)OCC)SP(=S)(OC)OC,0.292105,0.026854285769707928,1
+CNC(=O)Oc1cccc2c1cccc2,0.29818,0.2381224485079104,1
+COC(=O)c1ccccc1S(=O)(=O)NC(=O)Nc1nc(OC(F)F)cc(n1)OC(F)F,0.29893,1.1476156139346487,1
+CN(C(=S)[S-])C.CN(C(=S)[S-])C.CN(C(=S)[S-])C.[Fe+3],0.30012,0.033370225153194974,1
+CCOC(=O)c1ccccc1S(=O)(=O)NC(=O)Nc1nc(Cl)cc(n1)OC,0.30133,0.9373184759167799,1
+Fc1ccc(c(c1)F)NC(=O)c1cccnc1Oc1cccc(c1)C(F)(F)F,0.30333,0.05755462424551961,1
+NC1CC(N=C(C(=O)O)N)C(OC1OC1C(O)C(O)C(C(C1O)O)O)C,0.30578,2.5744890364385027,1
+CNC(=O)Oc1cc(C)cc(c1C)C,0.30635,0.0435085474327715,1
+Clc1ccc(cc1)CN(C(=O)Nc1ccccc1)C1CCCC1,0.31170800000000004,0.0654317460884942,1
+ClCCOc1ccccc1S(=O)(=O)NC(=O)Nc1nc(C)nc(n1)OC,0.31207450000000003,0.20041529457543128,1
+CCC(n1c(=O)[nH]c(c(c1=O)Br)C)C,0.31690999999999997,0.2868010916268421,1
+OC(=O)CCl,0.31747,0.1671151871942349,1
+ClC(SN1C(=O)C2C(C1=O)CC=CC2)(Cl)Cl,0.32935499999999995,0.07976078042600035,1
+CN(C1C(=O)C(=C(O)N)C(=O)C2(C1CC1C(=C(O)c3c(C1(C)O)cccc3O)C2=O)O)C,0.33751,7.451766115785945,1
+Clc1cc(ccc1Oc1ccc(c(c1)C(=O)O)[N+](=O)[O-])C(F)(F)F,0.34563,0.32446996355831736,1
+N=C(NC(=N)N)NCCc1ccccc1,0.35565,0.3059173490559243,1
+COc1ccc(cc1)C(C(Cl)(Cl)Cl)c1ccc(cc1)OC,0.36164,0.1221573228329189,1
+Cc1cc(C)cc(c1)C(=O)N(C(C)(C)C)NC(=O)c1ccc2c(c1C)CCCO2,0.3678,0.4358481045223442,1
+O=C(Nc1ccnc(c1)Cl)Nc1ccccc1,0.37548,0.03484318520034047,1
+CO/N=C(\c1ccccc1Oc1ncnc(c1F)Oc1ccccc1Cl)/C1=NOCCO1,0.39448,0.07850055307387023,1
+N#Cc1ccc(cc1)C/C(=N/NC(=O)Nc1ccc(cc1)OC(F)(F)F)/c1ccc(cc1)C(F)(F)F,0.39494,0.12983229034890975,1
+NCCNc1cccc2c1cccc2,0.42415,0.37905161649260066,1
+CC(=CC1C(C1(C)C)C(=O)OCc1cccc(c1)Oc1ccccc1)C,0.42802,0.05216940193626031,1
+CC(Oc1ccccn1)COc1ccc(cc1)Oc1ccccc1,0.433615,0.05658470066534964,1
+N#Cc1c[nH]cc1c1cccc2c1OC(O2)(F)F,0.449265,0.7723832498999122,1
+O=C(NC(=O)c1c(F)cccc1F)Nc1ccc(cc1F)Oc1ccc(cc1Cl)C(F)(F)F,0.458295,0.04066763532873794,1
+CCSC(=O)N(CC(C)C)CC(C)C,0.46004,0.048828992889441855,1
+CSC(=O)c1cccc2c1snn2,0.46082,0.2808007644496951,1
+ClCC(=O)N(c1c(C)cccc1CC)COC(C)C,0.463365,0.10286925442445778,1
+Cc1cc(N)c(cc1C)C,0.46595,0.10039385481688198,1
+Clc1cc(ccc1Oc1ccc(c(c1)C(=O)[O-])[N+](=O)[O-])C(F)(F)F.[Na+],0.46919,0.2703943597238443,1
+Clc1c(Cl)c([N+](=O)[O-])c(c(c1Cl)Cl)Cl,0.47404,0.051127054646843625,1
+CC1OC(C)CN(C1)C1CCCCCCCCCCC1,0.48317,0.24662505674890514,1
+COc1nc(nc(n1)C)NC(=O)NS(=O)(=O)c1ccccc1C(=O)OC,0.48379,0.08332865278307376,1
+CCCCc1c(C)nc(nc1OS(=O)(=O)N(C)C)NCC,0.49302,0.06170339457236688,1
+CN1N(C)C(CC1c1ccccc1)c1ccccc1,0.49534,0.23644849196465795,1
+OC(=O)C(Oc1cccc(c1)Cl)C,0.49846,0.02886727189175808,1
+COC(=O)C(NC(=O)C(CC(=O)O)N)Cc1ccccc1,0.49949,0.5185137420900692,1
+O=c1[nH]c2CCCc2c(=O)n1C1CCCCC1,0.50364,0.2509626579462685,1
+CCOC(=O)OC1=C(C(=O)NC21CCC(CC2)OC)c1cc(C)ccc1C,0.5061,0.08169257692890085,1
+N#Cc1c[nH]cc1c1cccc(c1Cl)Cl,0.50615,0.049253025635166925,1
+CCOc1nc(nc(n1)NC)NC(=O)NS(=O)(=O)c1ccccc1C(=O)OC,0.51169,0.21727682147646538,1
+CCCCC(COC(=O)c1ccccc1C(=O)OCC(CCCC)CC)CC,0.51209,2.3074089813456724,1
+Nc1nc(NC2CC2)nc(n1)N,0.514491,0.1473261240842984,1
+CCCCOCCOCCOCc1cc2OCOc2cc1CCC,0.51708,0.39049133868029323,1
+COc1c(Cl)ccc(c1C(=O)O)Cl,0.52027,0.7919287856233722,1
+CCOc1cc(ccc1C1COC(=N1)c1c(F)cccc1F)C(C)(C)C,0.5203,0.0627459635658777,1
+COCC(N(c1c(C)cccc1CC)C(=O)CCl)C,0.52855,0.20161523210741691,1
+O=CCC1CC(C)C(=O)C=CC(=CC(C(OC(=O)CC(C(C1OC1(C)OC(C)C(C(C1O)N(C)C)OC1(C)OC(C)C(C(C1)(C)O)O)C)O)CC)COC1OC(C)C(C(C1OC)OC)O)C,0.52958,0.1235846125165807,1
+[O-][N+](=O)/N=C\1/N(Cc2cnc(s2)Cl)COCN1C,0.53134,0.1157001357916454,1
+COC(=O)C1(O)c2cc(Cl)ccc2c2c1cccc2,0.54605,0.020133159529269997,1
+COC(=O)c1cc(ccc1[N+](=O)[O-])Oc1ccc(cc1Cl)Cl,0.54657,0.48109285382726574,1
+CC(C12CCC(O2)(C(C1)OCc1ccccc1C)C)C,0.54665,0.19916614842025832,1
+Oc1ccc2c(c1N=Nc1ccccc1)ccc(c2)S(=O)(=O)O,0.54821,1.2808366624250582,1
+Nc1ccc(c(c1)N(=O)=O)N,0.56811,0.42167630838934106,1
+CCCN(c1c(cc(cc1[N+](=O)[O-])C(F)(F)F)[N+](=O)[O-])CCCl,0.56902,0.07265854131324372,1
+NC1CCCCC1,0.5974349999999999,0.16869122618294258,1
+COC(=O)c1csc(c1S(=O)(=O)NC(=O)n1nc(n(c1=O)C)OC)C,0.5994,0.4521540321445514,1
+COc1cc(Cl)c(cc1Cl)OC,0.60371,0.08485374483857483,1
+COCCN(c1c(C)cccc1C)C(=O)CCl,0.6139,0.07679393873425915,1
+OC(=O)C1C2CCC(C1C(=O)O)O2,0.61774,0.6212199885761438,1
+O=Cc1ccco1,0.62445,0.12487,0.1111111111111111
+CCCCNC(=O)n1c(NC(=O)OC)nc2c1cccc2,0.628625,0.33238030711110755,1
+CN(C(=O)Nc1ccc(cc1)Cl)C,0.62925,0.05986301870762587,1
+COc1c(OC)cc(c(c1OC)C(=O)c1c(OC)ccc(c1C)Br)C,0.63528,0.13989748490623555,1
+OC1(Cn2ncnc2)/C(=C/c2ccc(cc2)Cl)/CCC1(C)C,0.64063,0.08048240143429203,1
+COC(=O)c1ccc(cc1)C(=O)OC,0.64372,1.5127462916286585,1
+Clc1ccc(cc1)S(=O)(=O)c1cc(Cl)c(cc1Cl)Cl,0.64597,0.03298325187627329,1
+CC(OC(=O)NC(C(=O)NC(c1nc2c(s1)cc(cc2)F)C)C(C)C)C,0.65432,0.22600178609579571,1
+CCCOC(=O)NCCCN(C)C.Cl,0.66747,3.0584798918838514,1
+CCCCOCC(OCC(O)C)C,0.67269,0.6435158090039054,1
+CC1OC(C)OC(C1)OC(=O)C,0.71759,0.1800567934233961,0.25
+[O-][N+](=O)c1cc(Cl)c(c(c1)Cl)N,0.72459,0.11432259330046882,1
+COc1nc(nc(c1)OC)NC(=O)NS(=O)(=O)Cc1ccccc1C(=O)OC,0.75292,0.6669606330058914,1
+O=C(C1C(C1(C)C)C=C(C)C)OCN1C(=O)C2=C(C1=O)CCCC2,0.75436,0.08351584029706628,1
+CCOc1nc(F)cc2n1nc(n2)S(=O)(=O)Nc1c(Cl)cccc1C(=O)OC,0.75615,0.6080549298886078,1
+CCCN(c1c(cc(cc1[N+](=O)[O-])C(F)(F)F)[N+](=O)[O-])CCC,0.760539,0.0520811349082886,1
+COC(=O)c1c(Cl)c(Cl)c(c(c1Cl)Cl)C(=O)OC,0.768162,0.2311336293540029,1
+COc1cc(OC)nc(n1)NC(=O)NS(=O)(=O)Cc1ccccc1C(=O)O,0.77956,0.5799830012080455,1
+Clc1ccc(c(n1)C(=O)O)Cl,0.78125,0.4206441427308671,1
+COC(=O)NS(=O)(=O)c1ccc(cc1)N,0.78179,0.284608896430702,1
+ClCC[N+](C)(C)C.[Cl-],0.79079,3.3587364920090987,1
+COC(CCCC(C/C=C/C(=C/C(=O)OC(C)C)/C)C)(C)C,0.80523,0.13732812785699586,1
+CCOc1cc(ccc1OCC)NC(=O)OC(C)C,0.8241,0.18345599077084476,1
+OC(=O)c1nc(Cl)c(c(c1Cl)N)Cl,0.8283,1.5783612475338262,1
+CC(C1(C)N=C(NC1=O)c1nc2ccccc2cc1C(=O)O)C,0.8351195,0.46856151866597084,1
+Nc1ccc(c(c1)C)NOS(=O)(=O)O,0.84315,1.1493442892403127,1
+CCOC(=O)C1OC1(C)c1ccccc1,0.84854,0.1522850003589944,1
+COC(=O)Nc1nc2c([nH]1)cccc2,0.8499450000000001,0.032903800706747484,1
+OCCn1c(C)ncc1[N+](=O)[O-],0.8764,0.11132431495031211,1
+CC(Oc1cccc(c1)NC(=O)c1ccccc1C(F)(F)F)C,0.907795,0.16217893899872973,1
+COP(=O)OC,0.90869,0.1163372948750952,1
+OCCNc1ccc(cc1OCCO)N(=O)=O,0.94539,1.048318798934636,1
+O=N(=O)c1cccc2c1cccc2,0.95283,0.3859224139193975,1
+O=C(C1(C)CCCCC1)Nc1ccc(c(c1Cl)Cl)O,0.96626,0.38098624299804507,1
+ClCCP(=O)(O)O,0.9723550000000001,1.5420170427073756,0.1
+Oc1cccc2c1nccc2,0.98513,0.7327093511236694,1
+CCCOC(=O)c1ccc(cn1)C(=O)OCCC,0.99491,2.2864828696048862,1
+CC[N](=C1C=CC(=C(c2ccc(cc2)N(Cc2cccc(c2)S(=O)(=O)O)CC)c2ccc(cc2)N(C)C)C=C1)Cc1cccc(c1)S(=O)(=O)O,1.01,0.18076645608408035,1
+ClCC[N+](C)(C)C,1.0602,0.769322382021074,1
+Clc1ccccc1,1.0661,0.11002978958001745,1
+O=C1CCCCCN1,1.1047,0.38321359858083043,1
+Cc1cc(C)nc(n1)Nc1ccccc1,1.1091,0.0737976978862917,1
+COc1cccc(c1C)C(=O)NN(C(C)(C)C)C(=O)c1cc(C)cc(c1)C,1.1154,0.6179914694943823,1
+COC(=O)C(=CC=CC(=CC=CC=C(C=CC=C(C=CC1=C(C)CCCC1(C)C)C)C)C)C,1.1194,0.026610657692314046,1
+Clc1ccccc1CC(C1(Cl)CC1)(Cn1nc[nH]c1=S)O,1.1619199999999998,0.04080742433855793,1
+Oc1ccc(cc1Cl)C(C)(C)C,1.1697,0.05414658121041314,1
+COc1cc(OC)nc(n1)NC(=O)NS(=O)(=O)Nc1ccccc1C(=O)N(C)C,1.178,2.2108585215201204,1
+CON=C(c1ccccc1COc1ccccc1C)C(=O)OC,1.1888,1.0692542662549145,1
+CCCOc1nn(c(=O)n1C)C(=O)[N-]S(=O)(=O)c1ccccc1C(=O)OC.[Na+],1.1894,1.1132038468325207,1
+OC(=O)Cc1cccc2c1cccc2,1.2057,0.25631264534831816,1
+OCc1cc(N=Nc2ccc(c3c2cccc3)S(=O)(=O)O)c(c(c1O)N=Nc1ccc(c2c1cccc2)S(=O)(=O)O)O,1.2093,0.9453956798919527,1
+CC1=CC(=O)CC(C1)(C)C,1.2952,0.1131559776714462,1
+C[N]1(C)CCCCC1,1.3134,1.0402900161039697,1
+OC1CCC2(C(C1)CCC1C2CCC2(C1CCC2C(CCC(=O)O)C)C)C,1.3278,1.14292772924409,1
+COc1cc(OC)nc(n1)NC(=O)NS(=O)(=O)N(S(=O)(=O)C)C,1.3412,0.2450842983329933,1
+Oc1ccc(c(c1)C(C)(C)C)O,1.3537,0.2841660766112939,1
+COc1ncc(c2n1nc(n2)S(=O)(=O)Nc1c(F)cccc1F)F,1.3917,0.182692394567328,1
+OCC1OC2OC3C(CO)OC(C(C3O)O)OC3C(CO)OC(C(C3O)O)OC3C(CO)OC(C(C3O)O)OC3C(OC(OC4C(OC(OC5C(OC(OC1C(C2O)O)C(O)C5O)CO)C(O)C4O)CO)C(O)C3O)CO,1.4097,2.86894354722703,1
+O=C(Nc1cc(F)cc(c1)F)N/N=C(/c1ncccc1C(=O)O)\C,1.412,0.5195206113164795,1
+CCCCOC(=O)c1ccccc1C(=O)OCc1ccccc1,1.5047,0.9205578802078176,1
+Fc1cc2CCC(n3c2c(c1)c(=O)c(c3)C(=O)O)C,1.5311,0.3484648653987975,1
+CC(N(c1c(cc(cc1N(=O)=O)C(F)(F)F)N(=O)=O)C(C)C)C,1.55095,0.060310916930519404,1
+CCC(c1noc(c1)NC(=O)c1c(OC)cccc1OC)(CC)C,1.5855,0.4718129550181333,1
+c1ccc(cc1)c1ccccc1,1.6212,0.17085222084726095,1
+NCC(c1ccc(cc1)O)O,1.6321,0.5444682693336544,1
+CCc1c(C(=O)O)c(=O)cnn1c1ccc(cc1)Cl,1.6865,0.12416495842018065,1
+ClCC#CCOC(=O)Nc1cccc(c1)Cl,1.7435,0.36665007965054974,1
+O/C(=C\1/C(=O)CC(CC1=O)C(=O)O)/C1CC1,1.7528,1.874,0.35294117647058826
+CO/N=C(\c1ccccc1COc1ccccc1C)/C(=O)OC,1.7985,0.7855418402497004,1
+COc1ccc(c(c1)OC)N,1.8018,1.1178937253738959,1
+CCC(=O)C1=C([O-])CC(CC1=O)C(=O)[O-].[Ca+2],1.874,0.7779135467595814,1
+CC(C1(C)N=C(NC1=O)c1ncccc1C(=O)O)C,1.9137,0.3915316820059443,1
+OC(=O)COc1nc(F)c(c(c1Cl)N)Cl,1.9605,0.08780454163311108,1
+Clc1ccc(cc1)Cl,2.0408,0.06725795962874732,1
+CCCCOC(=O)c1ccccc1C(=O)OCCCC,2.1556,3.628316332763503,1
+c1ccc(cc1)c1ccccc1OCC1CO1,2.2097,0.33405950069544427,1
+ClCC[N](C)(C)C,2.2428,0.6513227853708423,1
+COc1cc(OC)n2c(n1)nc(n2)NS(=O)(=O)c1c(OC)nccc1C(F)(F)F,2.3023,0.12641472227999387,1
+CC=Cc1ccc(cc1)OC,2.3212,0.9724358881625295,1
+CC(OC(=O)Nc1cccc(c1)Cl)C,2.3402,0.25076367166153085,1
+COC(=O)c1ccccc1O,2.3661,0.5849515398302718,1
+CCOC(=O)C=C,2.4771,0.09022650313479785,1
+COC(=O)CC(c1ccc(cc1)Cl)NC(=O)C(C(C)C)NC(=O)OC(C)C,2.507,0.1334911782991685,1
+COc1nn(c(=O)n1C)C(=O)NS(=O)(=O)c1ccccc1OC(F)(F)F,2.5233,1.038609503259571,1
+C=Cc1ccccc1,2.7365,0.4050462138675692,1
+COc1cc(OC)nc(n1)NC(=O)NS(=O)(=O)c1n2ccccc2nc1S(=O)(=O)CC,2.7557,0.21895634937682856,1
+CC(=C)C(=O)O,2.8807,9.313199999999998,0.14285714285714285
+CN(NC(=O)CCC(=O)O)C,3.0343,0.49949,0.13043478260869565
+Oc1ccccc1c1ccccc1,3.1197,0.7350707232243242,1
+Clc1cnc2c(c1)ccc(c2C(=O)O)Cl,3.1273,1.3338616611292693,1
+C[N+]1(C)CCCCC1.[Cl-],3.1805,0.5213335768409364,1
+CCc1ccccc1,3.29205,0.11479120197816142,1
+CC(c1ccccc1)C,3.2988999999999997,0.16099422775504726,1
+Cc1cnc2c(c1)ccc(c2C(=O)O)Cl,3.3388,1.3141332642872232,1
+CCCOC(=O)NCCCN(C)C,3.6119,0.8238875458367859,1
+CCOP(=O)O,3.6347,0.05315766581705339,1
+Oc1ccccc1,3.6552,0.5646334588832973,1
+[O-]P(=O)OCC.[O-]P(=O)OCC.[O-]P(=O)OCC.[Al+3],3.6854,0.01992736351280432,1
+CC1CCC(C(C1)O)C(C)C,3.7948,1.370100620510844,1
+COc1ccc(cc1)N,3.8489,0.901262178442535,1
+CCCCC(COC(=O)CCCCC(=O)OCC(CCCC)CC)CC,4.0479,1.1943279195985483,1
+CCCOC(=O)c1cc(O)c(c(c1)O)O,4.0716,1.4754838301646152,1
+CC(CCCC1(C)CCc2c(O1)c(C)c(c(c2C)OC(=O)C)C)CCCC(CCCC(C)C)C,4.2306,0.9982324982068119,1
+COc1ccc(cc1N=Nc1c(O)c(cc2c1cccc2)C(=O)Nc1cccc(c1)N(=O)=O)N(=O)=O,4.3084,0.2220491146216253,1
+S=c1sc2c([nH]1)cccc2,4.4843,0.11452172958366895,1
+Clc1cc(N)c(c(n1)C(=O)O)Cl,4.8306,0.6541806042925804,1
+COc1cc(OC)nc(n1)NC(=O)NS(=O)(=O)c1ncccc1C(=O)N(C)C,5.0877,0.24014279270227162,1
+CCOc1ccc(cc1N)NC(=O)C,6.101,0.4797687217616524,1
+Nc1ccc(cc1)O,6.2863,0.9015646839383878,1
+NC(=S)NNC(=S)N,6.3038,0.009103354136383681,1
+NC(=O)c1cnccn1,6.4088,0.09261900000000002,0.14285714285714285
+OC(=O)c1ccc(cc1N)N(=O)=O,6.5062,1.447418039307372,1
+Oc1cc(O)c2c(c1)oc(c(c2=O)O)c1ccc(c(c1)O)O,6.7298,0.7655804043523278,1
+ClCC(=O)c1ccc(cc1)NC(=O)C,7.4653,0.39098146781323945,1
+O=C1OC(=O)c2c1cccc2,8.0005,0.7745765770438742,1
+CCCOC(=O)c1ccc(cc1)O,8.3241,3.118233416093697,1
+CCOC(=O)COC(=O)c1ccccc1C(=O)OCC,8.9199,0.6760144100991292,1
+O=C1CCCCC1,9.2722,0.24400021704754923,1
+OC(=O)C=CC(=O)O,9.3132,2.8807000000000005,0.14285714285714285
+COC(=O)c1ccc(cc1)O,9.8589,1.1933281681716323,1
+COC(=O)c1ccccc1C(=O)OC,10.3,1.3596984772454652,1
+OC1C2C(N(C)C)C(=O)C(=C(O)N)C(=O)C2(O)C(=O)C2=C(O)c3c(C(C12)(C)O)c(Cl)ccc3O,10.508,0.33751000000000003,0.6216216216216216
+OCC(C1OC(=O)C(=C1O)O)O,13.07315,0.17916850424182862,1
+OCCO,14.822,3.4872299765323835,1
+CCCCCCCCCCCCCCCCCC(=O)OCC(C1OCC(C1O)O)O,16.727,20.71040537593191,1
+[O-]S(=O)(=O)NC1CCCCC1.[Na+],17.901,0.18626027910642426,1
+O=C1NS(=O)(=O)c2c1cccc2,19.663,0.1426084275745469,1
+CCCCCCCCCCCC(=O)OCC(C1OCC(C1O)O)O,19.867,25.10005600485723,1
+CCOC(=O)c1ccccc1C(=O)OCC,19.956,0.8636538519958127,1
+OC(=O)c1ccccc1N,20.06,1.0606380596495208,1
+OCC(CO)O,74.739,0.8875588822522977,1
diff --git a/data/training-cv-0.id b/data/training-cv-0.id
new file mode 100644
index 0000000..8a2a7c7
--- /dev/null
+++ b/data/training-cv-0.id
@@ -0,0 +1 @@
+56d5de852b72ed1a5c000001
diff --git a/data/training-cv-1.csv b/data/training-cv-1.csv
new file mode 100644
index 0000000..2625aed
--- /dev/null
+++ b/data/training-cv-1.csv
@@ -0,0 +1,632 @@
+SMILES,LOAEL_measured_median,LOAEL_predicted,Confidence
+ClC12C3C4(C(C1(Cl)Cl)(C1(C2(C3(Cl)C(C41Cl)(Cl)Cl)Cl)Cl)Cl)Cl,1.9566e-05,0.0018377000000000018,0.25
+ClC1=C(Cl)C2(C(C1(Cl)C1C2C2CC1C=C2)(Cl)Cl)Cl,2.7404e-05,0.001291721255127229,1
+N#Cc1nn(c(c1S(=O)C(F)(F)F)N)c1c(Cl)cc(cc1Cl)C(F)(F)F,0.00013611,0.01266290172948335,1
+Clc1ccc2c(c1)[n+]([O-])nc(n2)n1cncc1,0.00020191,0.04452057535910419,1
+OC(=O)C(Oc1ccc(cc1)Oc1ncc(cc1Cl)C(F)(F)F)C,0.00027647,0.012353952024790952,1
+CCOP(=S)(SCSC(C)(C)C)OCC,0.00027736000000000004,0.003912319652872025,1
+ClC1C2OC2C2C1C1(Cl)C(=C(C2(C1(Cl)Cl)Cl)Cl)Cl,0.00028896749999999995,0.0007124710122354402,1
+ClC1=C(Cl)C2(C(C1(Cl)C1C2C2CC1C1C2O1)(Cl)Cl)Cl,0.000295345,0.00020148548332822786,1
+CCSCCSP(=S)(OCC)OCC,0.00036443,0.002479025960626162,1
+CNC(=O)ON=CC(SC)(C)C,0.00052559,0.05719488141259865,1
+COC(=O)C(Oc1ccc(cc1)Oc1ccc(cc1Cl)Cl)C,0.00058619,0.11670708140762617,1
+CCSCSP(=S)(OCC)OCC,0.00061449,0.0008962496537916937,1
+OC1CCCCCc2cc(O)cc(c2C(=O)OC(CCC1)C)O,0.00062036,0.46407564001892226,1
+ClC1C=CC2C1C1(Cl)C(=C(C2(C1(Cl)Cl)Cl)Cl)Cl,0.000843785,0.0002446319009718216,1
+c1ccc(cc1)[Sn](c1ccccc1)c1ccccc1,0.00085711,0.4582721595810513,1
+CCOP(=O)(SC(CC)C)SC(CC)C,0.000872805,0.01247660917708954,1
+CCS(=O)CCSP(=O)(OC)OC,0.00089328,0.0016027297178080409,1
+ClC1CC2C(C1Cl)C1(C(C2(Cl)C(=C1Cl)Cl)(Cl)Cl)Cl,0.000939545,0.0003282100247208412,1
+COP(=S)(Oc1ccc(cc1)N(=O)=O)OC,0.00094982,0.02595721700355286,1
+Clc1c(Cl)c(Cl)c(c(c1Cl)Cl)Cl,0.0010183,0.08780541800732805,1
+CNC(=O)CSP(=S)(OC)OC,0.0010905,0.009515127939063844,1
+COP(=O)(SCCS(=O)(=O)CC)OC,0.0011438,0.0016027297178080409,1
+COC1CC(OC2C(C)C=CC=C3COC4C3(O)C(C=C(C4O)C)C(=O)OC3CC(CC=C2C)OC2(C3)C=CC(C(O2)C(CC)C)C)OC(C1OC1CC(OC)C(C(O1)C)O)C.COC1CC(OC(C1OC1CC(OC)C(C(O1)C)O)C)OC1C(C)C=CC=C2COC3C2(O)C(C=C(C3O)C)C(=O)OC2CC(CC=C1C)OC1(C2)C=CC(C(O1)C(C)C)C,0.0011546,0.004452708028277983,1
+ClC12C(Cl)(Cl)C3(C4(C1(Cl)C1(C2(Cl)C3(C4(C1(Cl)Cl)Cl)Cl)Cl)Cl)Cl,0.0012831,0.0018376999999999998,0.21428571428571427
+CCOP(=O)(N1CCSC1=O)SC(CC)C,0.0013411,0.13650963743101127,1
+O=C1CCCC(=O)C1C(=O)c1ccc(cc1[N+](=O)[O-])S(=O)(=O)C,0.0014146,0.015088846606844258,1
+CCOP(=S)(Oc1ccccc1C(=O)OC(C)C)NC(C)C,0.0014476,0.15170104041664476,1
+CCSCCSP(=O)(OC)OC,0.0015199,0.0008432099438716096,1
+CCOc1cc(nc(n1)CC)OP(=S)(OC)OC,0.0015396,0.023660512174966182,1
+COC(=O)C=C(OP(=O)(OC)OC)C,0.0015615,0.0023812687906506857,1
+COC(=O)/C=C(/OP(=O)(OC)OC)\C,0.0015615,0.002081528804995513,1
+OC(=O)c1ccccc1.CCC(C1OC2(C=CC1C)OC1CC=C(C)C(OC3CC(OC)C(C(O3)C)OC3CC(OC)C(C(O3)C)NC)C(C)C=CC=C3C4(C(C(=O)OC(C2)C1)C=C(C)C(C4OC3)O)O)C,0.001735715,0.0017196076009231745,1
+C1CCC(CC1)[Sn](n1ncnc1)(C1CCCCC1)C1CCCCC1,0.001811,0.007147190221049201,1
+ClC1C2(Cl)C3C4C5C1(Cl)C(C2(Cl)C5C3C1C4O1)(Cl)Cl,0.0018377,0.00017075213457395932,1
+CNC(=O)CCSCCSP(=O)(OC)OC,0.0018793,0.0033386848364462857,1
+COC1CC(OC2C(C)C=CC=C3COC4C3(O)C(C=C(C4O)C)C(=O)OC3CC(CC=C2C)OC2(C3)C=CC(C(O2)C(C)C)C)OC(C1OC1CC(OC)C(C(O1)C)NC(=O)C)C,0.00194425,0.001646537166266416,1
+N#CC(c1cccc(c1)Oc1ccccc1)OC(=O)[C@H](C(C)C)Nc1ccc(cc1Cl)C(F)(F)F,0.0019884,0.00633638005051865,1
+CNC(=O)C=C(OP(=O)(OC)OC)C,0.0020165,0.007274526885190497,1
+COP(=O)(SC)N,0.0020549,0.33146588454802073,1
+COP(=S)(Oc1ccc(cc1)[N+](=O)[O-])OC,0.0020896,0.020207547632267724,1
+CSc1ccc(cc1C)OP(=S)(OC)OC,0.00210185,0.015315732687291136,1
+CO[C@H]1C[C@H](O[C@H]2[C@@H](C)C=CC=C3CO[C@H]4[C@]3(O)[C@@H](C=C([C@H]4O)C)C(=O)O[C@H]3C[C@@H](CC=C2C)O[C@]2(C3)C=C[C@@H]([C@H](O2)[C@H](CC)C)C)O[C@H]([C@@H]1O[C@H]1C[C@H](OC)[C@H]([C@@H](O1)C)O)C,0.0022907,0.011583598135897934,1
+O=C1CCCC(=O)C1C(=O)c1ccc(c(c1Cl)COCC(F)(F)F)S(=O)(=O)C,0.0023819,0.01161082890621692,1
+S=C1NCCN1,0.0024472,0.12298076673290073,1
+COC(=O)C(Oc1ccc(cc1)Oc1ncc(cc1Cl)C(F)(F)F)C,0.0026615,0.0001899031773236392,1
+CCOP(=S)(OCC)SCSc1ccc(cc1)Cl,0.0029166,0.007040322537353415,1
+C1CCN2C(C1)C1CCCCN1CC2,0.0029591,0.14662384480405752,1
+Fc1ccc(cc1)N(C(=O)COc1nnc(s1)C(F)(F)F)C(C)C,0.0033028,0.06386465246867795,1
+CCOP(=S)(Oc1ccc2c(c1)oc(=O)c(c2C)Cl)OCC,0.0033631,0.021460885004789175,1
+CNC(=O)Oc1cccc2c1OC(O2)(C)C,0.0035838,0.11368917232194076,1
+O[Sn](C1CCCCC1)(C1CCCCC1)C1CCCCC1,0.0036089,0.2530228410823332,1
+CCc1nn(c(c1Cl)C(=O)NCc1ccc(cc1)Oc1ccc(cc1)C)C,0.0039076,0.026303374046670085,1
+CCCCSP(=O)(SCCCC)SCCCC,0.0039744,0.12041582513564118,1
+CCOP(=S)(Oc1ncn(n1)c1ccccc1)OCC,0.0041492,0.01847095454548987,1
+CCOP(=O)(OC(=CCl)c1ccc(cc1Cl)Cl)OCC,0.0041717,0.018461477952369756,1
+CCOP(=O)(O/C(=C/Cl)/c1ccc(cc1Cl)Cl)OCC,0.0041717,0.009379841017851992,1
+Clc1nc(nc(n1)Cl)Nc1ccccc1Cl,0.0041739,0.08123357705211397,1
+Clc1cccc(n1)C(Cl)(Cl)Cl,0.0043308,0.2937201288867553,1
+N#CC(c1cccc(c1)Oc1ccccc1)OC(=O)C1C(C1(C)C)C(C(Br)(Br)Br)Br,0.0045112,0.050781170812224614,1
+COc1sc(=O)n(n1)CSP(=S)(OC)OC,0.00471335,0.0098233419774848,1
+N#CC(c1ccc(c(c1)Oc1ccccc1)F)OC(=O)C1C(C1(C)C)/C=C(/c1ccc(cc1)Cl)\Cl,0.0048983,0.02367392641287567,1
+CCOP(=S)(OCC)SCSP(=S)(OCC)OCC,0.0049418,0.002892472589687803,1
+CCOP(=O)(Oc1ccc(c(c1)C)SC)NC(C)C,0.0049447,0.0045306929228430695,1
+N#CC(c1cccc(c1)Oc1ccccc1)OC(=O)C(C(C)C)Nc1ccc(cc1Cl)C(F)(F)F,0.004971,0.005120902843232485,1
+CCNc1nc(nc(n1)Cl)NC(C#N)(C)C,0.0051933,0.023073414392932562,1
+CC(Cc1ccc(cc1)C(C)(C)C)CN1CC(C)OC(C1)C,0.0056016,0.05599458944129579,1
+COP(=S)(Oc1nc(Cl)c(cc1Cl)Cl)OC,0.00620095,0.02532208390194291,1
+COC(=O)Nc1nc2c([nH]1)cc(cc2)S(=O)c1ccccc1,0.0063422,0.3723218145294313,1
+ClCC(N1C(=O)c2c(C1=O)cccc2)SP(=S)(OCC)OCC,0.0063477,0.0038299744725306816,1
+CCOP(=S)(Oc1ccc(cc1)N(=O)=O)OCC,0.0067295,0.00746717705567433,1
+OC(C(Cl)(Cl)Cl)(c1ccc(cc1)Cl)c1ccc(cc1)Cl,0.0067479,0.05970613966526424,1
+CNC(=O)Oc1cc(C)c(c(c1)C)N(C)C,0.0067481,0.08045423503172283,1
+COC(=O)N(C(=O)N1COC2(C(=N1)c1ccc(cc1C2)Cl)C(=O)OC)c1ccc(cc1)OC(F)(F)F,0.0068203,0.039132335471712874,1
+CCNc1nc(Cl)nc(n1)NC(C)(C)C,0.0069218,0.02126556527201187,1
+CCOP(=S)(Oc1ccc(cc1)[N+](=O)[O-])OCC,0.0070384,0.006517282995153355,1
+Cc1nn(c(c1/C=N/OCc1ccc(cc1)C(=O)OC(C)(C)C)Oc1ccccc1)C,0.0071176,0.005027849264876859,1
+Cc1nn(c(c1C=NOCc1ccc(cc1)C(=O)OC(C)(C)C)Oc1ccccc1)C,0.0073074,0.004854783124674696,1
+Clc1ccc(cc1)C(c1ccccc1Cl)(c1cncnc1)O,0.0075484,0.06514279997015786,1
+COP(=S)(SCn1nnc2c(c1=O)cccc2)OC,0.0076105,0.026458465110469828,1
+Fc1ccc(cc1)[Si](c1ccc(cc1)F)Cn1cncn1,0.0076575,0.01681187235360046,1
+N#CC(c1cccc(c1)Oc1ccccc1)OC(=O)C1C(C1(C)C)C=C(Br)Br,0.00781875,0.04645324040056576,1
+Fc1ccc(cc1)C(c1ccccc1Cl)(c1cncnc1)O,0.007943,0.04460455505375353,1
+N#Cc1nn(c(c1S(=O)CC)N)c1c(Cl)cc(cc1Cl)C(F)(F)F,0.0080563,0.00036975923331507304,1
+CCN(c1nc(cc(n1)C)OP(=S)(OC)OC)CC,0.0081878,0.014190198691473107,1
+Clc1ccc(cc1)OS(=O)(=O)c1ccc(cc1)Cl,0.0082464,0.08087932294789864,1
+Clc1cc(cnc1Nc1c(cc(c(c1[N+](=O)[O-])Cl)C(F)(F)F)[N+](=O)[O-])C(F)(F)F,0.008299399999999998,0.06491000024254719,1
+[O-][N+](=O)c1cc([N+](=O)[O-])c(c(c1)[N+](=O)[O-])C,0.0088055,0.07592898184353129,1
+CCCCOC(=O)C(Oc1ccc(cc1)Oc1ccc(cn1)C(F)(F)F)C,0.00885585,0.004671164935002904,1
+CSC(=O)c1c(nc(c(c1CC(C)C)C(=O)SC)C(F)(F)F)C(F)F,0.009043,0.204836351521947,1
+Clc1ccc(c(c1)Cl)C(Cn1cncn1)COC(C(F)F)(F)F,0.0091362,0.039017228447202096,1
+CCCN(C(=O)SCc1ccccc1)CCC,0.0091492,0.07029896680313592,1
+CON(C(=O)Nc1ccc(cc1)Cl)C,0.0093175,0.017711986455279917,1
+CCCCOC(=O)C(Oc1ccc(cc1)Oc1ccc(cc1F)C#N)C,0.0096257,0.044718200311922994,1
+N#C/N=C\1/SCCN1Cc1ccc(nc1)Cl,0.0098922,0.08211542249954593,1
+Cc1c(ccc(c1C1=NOCC1)S(=O)(=O)C)C(=O)c1cnn(c1O)C,0.0099068,0.010814638210970872,1
+CC1(C)CNC(=NC1)NN=C(C=Cc1ccc(cc1)C(F)(F)F)C=Cc1ccc(cc1)C(F)(F)F,0.0099095,0.0224283649565607,1
+COP(=O)(OC=C(Cl)Cl)OC,0.0100688,0.03288850803762549,1
+CCCSP(=O)(SCCC)OCC,0.010069,0.014370465150356471,1
+FC(c1ccc(cc1)C=CC(=NN=C1NCC(CN1)(C)C)C=Cc1ccc(cc1)C(F)(F)F)(F)F,0.010112,0.040992157055566934,1
+CCOC(=O)Nc1cccc(c1)OC(=O)Nc1ccccc1,0.010656,0.25222249073722786,1
+O=C(C1C(C1(C)C)C=C(C(F)(F)F)Cl)OCc1c(F)c(F)c(c(c1F)F)C,0.010986,0.014032643067128155,1
+O=C(C1C(C1(C)C)C=C(C(F)(F)F)Cl)OCc1cccc(c1C)c1ccccc1,0.011824,0.030373251871906218,1
+O=S1OCC2C(CO1)C1(C(C2(Cl)C(=C1Cl)Cl)(Cl)Cl)Cl,0.012287,0.00019389348590569905,1
+Clc1cc(Cl)c(c(c1O)Cc1c(O)c(Cl)cc(c1Cl)Cl)Cl,0.012288,0.11639872034879696,1
+CC(Oc1cc(c(cc1Cl)Cl)n1nc(oc1=O)C(C)(C)C)C,0.0124555,0.0639086556427057,1
+Clc1ccc(c(c1)Cl)n1c(nc2c(c1=O)cc(cc2)F)n1cncn1,0.01268,0.02638548889580358,1
+CCC1CCCC(OC2CCC(C(O2)C)N(C)C)C(C)C(=O)C2=CC3C(C2CC(=O)O1)C=C(C)C1C3CC(C1)OC1OC(C)C(C(C1OC)OC)OC,0.012735,0.039944372672364246,1
+CC1C=CC=C2COC3C2(O)C(C=C(C3O)C)C(=O)OC2CC(CC=C(C1)C)OC1(C2)CCC(C(O1)C)C,0.012862,0.004168990496430349,1
+COc1ccc(cc1NNC(=O)OC(C)C)c1ccccc1,0.012985,1.5449834159532374,1
+N#CC(c1cccc(c1)Oc1ccccc1)OC(=O)C(c1ccc(cc1)OC(F)F)C(C)C,0.01329,0.024675382901419764,1
+CCP(=S)(Sc1ccccc1)OCC,0.0133561,0.163234418596232,1
+O=c1c(Cl)c(SCc2ccc(cc2)C(C)(C)C)cnn1C(C)(C)C,0.013701,0.05461043265554864,1
+CNP(=O)(Oc1ccc(cc1Cl)C(C)(C)C)OC,0.013712,0.10391299239645767,1
+NC1=C(Cl)C(=O)c2c(C1=O)cccc2,0.01392,1.232699956972765,1
+CCN(C(=O)SCC)C1CCCCC1,0.01393,0.15937767340165446,1
+CNC(=O)Oc1cccc2c1OC(C2)(C)C,0.01394355,0.03912717913635733,1
+O=C(C1C(C1(C)C)/C=C(/C(F)(F)F)\Cl)OCc1c(F)c(F)c(c(c1F)F)C,0.01409,0.014826989448103378,1
+CC(c1ccccc1)(C[Sn](O[Sn](CC(c1ccccc1)(C)C)(CC(c1ccccc1)(C)C)CC(c1ccccc1)(C)C)(CC(c1ccccc1)(C)C)CC(c1ccccc1)(C)C)C,0.01425,0.1381772370584208,1
+CCCN(c1c(cc(cc1[N+](=O)[O-])C(F)(F)F)[N+](=O)[O-])CC1CC1,0.014397,0.14525145741874465,1
+CC(c1ccc(cc1)CCOc1ncnc2c1cccc2)(C)C,0.014687,0.06988972215238497,1
+CCCCC(c1ccc(cc1Cl)Cl)(Cn1cncn1)O,0.014958,0.06300267135260926,1
+N#CC(c1ccc(cc1)Oc1ccccc1)OC(=O)C1C(C1(C)C)/C=C\C(=O)OC(C(F)(F)F)C(F)(F)F,0.01496,0.03303530569688321,1
+N#Cc1c(Cl)c(C#N)c(c(c1Cl)Cl)Cl,0.015043,0.0038259351864843435,1
+N#CC(c1cc(C)c(cc1Cl)NC(=O)c1cc(I)cc(c1O)I)c1ccc(cc1)Cl,0.015081,0.05656535948903225,1
+Clc1cc(cnc1CCNC(=O)c1ccccc1C(F)(F)F)C(F)(F)F,0.015124,0.05806052469182294,1
+N#CN=S(=O)(C(c1ccc(nc1)C(F)(F)F)C)C,0.015292,0.08837960136607742,1
+CC(C1C2CCC1c1c2cccc1NC(=O)c1cn(nc1C(F)F)C)C,0.015303,0.10997211098678802,1
+Fc1ccc(cc1)[Si](c1ccc(cc1)F)(Cn1cncn1)C,0.015853,0.01575950727809121,1
+CN1CCC(CC1)C1CCN(CC1)C,0.016044,0.08536100236003388,1
+CCCCN(c1c(cc(cc1[N+](=O)[O-])C(F)(F)F)[N+](=O)[O-])CC,0.016106,0.12481997229313714,1
+CCOP(=S)(Oc1cc(C)nc(n1)C(C)C)OCC,0.016429,0.016348830968791805,1
+N#Cc1c(Cl)cccc1Cl,0.0165685,0.08752217356029626,1
+Fc1ccc(cc1)C1(Cn2cncn2)OC1c1ccccc1Cl,0.016679,0.028907029866608463,1
+CCOP(=S)(Oc1nc(Cl)c(cc1Cl)Cl)OCC,0.017114,0.0028622597917380035,1
+BrC1COC(C1)(Cn1cncn1)c1ccc(cc1Cl)Cl,0.017185,0.02422024179199092,1
+CC(NC(=S)[S])CNC(=S)S[Zn],0.017255,0.21764908996860194,1
+CCN(C(=O)SCc1ccc(cc1)Cl)CC,0.0180385,0.023348617608924552,1
+COCC(N(c1c(C)csc1C)C(=O)CCl)C,0.018129,0.339078236799798,1
+c1cc[n+]2c(c1)c1cccc[n+]1CC2,0.018481499999999998,0.0573536502666472,1
+CCc1nn(c(c1Cl)C(=O)NCc1ccc(cc1)C(C)(C)C)C,0.019469,0.005727025058264749,1
+CCCN(C(=O)n1cncc1)CCOc1c(Cl)cc(cc1Cl)Cl,0.019912,0.031861923875190136,1
+CCOC(=O)c1cn2nc(cc2nc1C)OP(=S)(OCC)OCC,0.0200875,0.08192307928628871,1
+C[n+]1ccc(cc1)c1cc[n+](cc1)C,0.020134,0.17703724711923066,1
+COP(=S)(SCN1C(=O)c2c(C1=O)cccc2)OC,0.020484,0.03889508961033929,1
+ClC=C,0.020801,0.045958000000000006,0.14285714285714285
+Clc1cccc(c1)c1ccccc1,0.021203,0.2364441075109156,1
+CNC(=O)ON=C(C(=O)N(C)C)SC,0.022348,0.07265961613327457,1
+CSC1=NC(C(=O)N1Nc1ccccc1)(C)c1ccccc1,0.0228,0.14176283327034858,1
+CCN(C(=O)C(=C(OP(=O)(OC)OC)C)Cl)CC,0.023024100000000002,0.004600027916953598,1
+COC(=O)N(c1ccccc1COc1ccn(n1)c1ccc(cc1)Cl)OC,0.023207,0.09375400983009505,1
+CCCCCCCCCCCCC1=C(OC(=O)C)C(=O)c2c(C1=O)cccc2,0.023407,0.34838048088413476,1
+OC(COc1cccc2c1c1ccccc1[nH]2)CNC(C)C,0.02346,0.6162139789626989,1
+O=C(NC(=O)c1ccccc1Cl)Nc1ccc(cc1)OC(F)(F)F,0.023557,0.12109409529168039,1
+CCOC(=O)C(Oc1ccc(cc1)Oc1nc2c(o1)cc(cc2)Cl)C,0.024877,0.02473243117023472,1
+CON(C(=O)Nc1ccc(c(c1)Cl)Cl)C,0.025091,0.014856283660298345,1
+CN(C(=S)S[Zn]SC(=S)N(C)C)C,0.02534245,0.1008090248545193,1
+O=C(NC(=O)c1c(F)cccc1F)Nc1ccc(cc1)Cl,0.025428,0.11123172997577015,1
+CCNc1nc(NCC)nc(n1)Cl,0.0255385,0.017686115479739323,1
+OC(=O)C(Oc1ccc(cc1C)Cl)C,0.025624,0.03294368514486615,1
+Clc1ccccc1CC(C1(Cl)CC1)(Cn1cncn1)O,0.025625,0.21829023265614486,1
+O=C(N(C)C)Nc1ccc(c(c1)Cl)Cl,0.025741,0.11364647525923395,1
+CCOC(=O)C(Oc1ccc(cc1)Oc1cnc2c(n1)ccc(c2)Cl)C,0.0257509,0.06346458956465112,1
+CC(OC(=O)C(c1ccc(cc1)Cl)(c1ccc(cc1)Cl)O)C,0.026532,0.09991566555257765,1
+N#CC(c1cccc(c1)Oc1ccccc1)OC(=O)C1C(C1(C)C)/C=C(/C(F)(F)F)\Cl,0.026676,0.006826191880629708,1
+O=C(C1C(C1(C)C)C=C(Cl)Cl)OCc1c(F)c(F)cc(c1F)F,0.026943,0.1057474476760432,1
+N#Cc1sc2=c(sc1C#N)c(=O)c1c(c2=O)cccc1,0.0269975,0.2211063750937945,1
+CCOC(=O)c1ccccc1C1=c2cc(C)c(cc2=[O]c2c1cc(C)c(c2)NCC)NCC,0.027054,1.8361979449677917,1
+CSCC(=NOC(=O)NC)C(C)(C)C,0.027483,0.00785717268166877,1
+Cc1nn(c(c1C(=O)c1ccc(cc1S(=O)(=O)C)C(F)(F)F)O)C,0.0276,0.026435917018637907,1
+CCOc1cc(ccc1N(=O)=O)Oc1ccc(cc1Cl)C(F)(F)F,0.027647,0.1156132981375311,1
+[O-][N+](=O)c1cc(C(=O)N)c(c(c1)[N+](=O)[O-])C,0.027758,0.06918939035121353,1
+N#CC(c1cccc(c1)Oc1ccccc1)OC(=O)C1C(C1(C)C)C=C(C(F)(F)F)Cl,0.027787,0.009150598211001433,1
+C=CC1(C)OC(=O)N(C1=O)c1cc(Cl)cc(c1)Cl,0.027961,0.15906283270679236,1
+OC(=O)C(Oc1ccc(cc1)Oc1nc2c(o1)cc(cc2)Cl)C,0.028167,0.03979620248347257,1
+N#CC(c1ccc(c(c1)Oc1ccccc1)F)OC(=O)C1C(C1(C)C)C=C(Cl)Cl,0.028207,0.04079779337482198,1
+CSC(=NOC(=O)N(SN(C(=O)ON=C(SC)C)C)C)C,0.028211,0.02379431320371135,1
+CS/C(=N/OC(=O)N(SN(C(=O)O/N=C(/SC)\C)C)C)/C,0.028211,0.02821100000000001,1
+CC(N1C(=NC(C)(C)C)SCN(C1=O)c1ccccc1)C,0.028484,0.10937338988822155,1
+CCO[C@H]1[C@@H](OC)[C@H](O[C@@H]2C[C@@H]3[C@@H](C2)[C@@H]2C=C4[C@H]([C@@H]2CC3)CC(=O)O[C@@H](CC)CCC[C@@H]([C@H](C4=O)C)O[C@H]2CC[C@@H]([C@H](O2)C)N(C)C)O[C@H]([C@@H]1OC)C,0.028877,0.0022907000000000005,0.20238095238095238
+N#Cc1cc(Br)c(c(c1)Br)O,0.02889,0.04055141873065782,1
+CCOC(=O)C(Cc1cc(c(cc1Cl)F)n1nc(n(c1=O)C(F)F)C)Cl,0.029113,0.1703418373948284,1
+C#CCOC(=O)C(Oc1ccc(cc1)Oc1ncc(cc1F)Cl)C,0.029164,0.00597827513272657,1
+CC(N1/C(=N/C(C)(C)C)/SCN(C1=O)c1ccccc1)C,0.029466,0.11809888768043729,1
+COc1nc(Oc2cccc(c2C(=O)[O-])Oc2nc(OC)cc(n2)OC)nc(c1)OC.[Na+],0.030507,0.6654783138947025,1
+CON(C(=O)Nc1ccc(cc1)Br)C,0.0313005,0.04742742201582306,1
+COc1nc(C)nc(n1)N(C(=O)NS(=O)(=O)c1ccccc1C(=O)OC)C,0.031614,0.4660661889892665,1
+Cc1ccc2c(c1)nc1c(n2)sc(=O)s1,0.032011,0.07663848154823513,1
+Fc1ccc(cc1)NC(=O)c1cccc(n1)Oc1cccc(c1)C(F)(F)F,0.032155,0.09839567726217836,1
+CCCn1c(OCCC)nc2c(c1=O)cc(cc2)I,0.032241,0.11240974023972475,0.10810810810810811
+CC(C(=O)O)Oc1cc(Cl)c(cc1Cl)Cl,0.032281,0.029593959969870794,1
+COc1cc(OC)nc(n1)NC(=O)NS(=O)(=O)c1ncccc1C(F)(F)F,0.032652,0.8236061451454418,1
+CN1CN(C)CSC1=S,0.03266,0.07479815014588137,1
+CCC1CCCC(OC2CCC(C(O2)C)N(C)C)C(C)C(=O)C2C(CC(=O)O1)C1CCC3C(C1C2)CC(C3)OC1CC(C)C(C(C1OC)OC)OC,0.032697,0.033969472022277895,1
+ClCC1CN(C(=O)C1Cl)c1cccc(c1)C(F)(F)F,0.033160999999999996,0.06069712737749953,1
+O=C(C(Oc1ccc(cc1)Oc1cnc2c(n1)ccc(c2)Cl)C)OCCON=C(C)C,0.033793,0.041066234999117913,1
+Fc1ccc(cc1)C(c1ccccc1F)(Cn1cncn1)O,0.033854,0.01726665471631053,1
+CN(/C=N/c1ccc(cc1C)C)/C=N/c1ccc(cc1C)C,0.034082,0.02662544913342841,1
+CCCCC(c1ccc(cc1)Cl)(Cn1cncn1)C#N,0.034179,0.12033690374067868,1
+CN(C=Nc1ccc(cc1C)C)C=Nc1ccc(cc1C)C,0.034423,0.042488565764564425,1
+CCOP(=S)(SCn1c(=O)oc2c1ccc(c2)Cl)OCC,0.0345288,0.003244287693660079,1
+ClC(=CCOc1cc(Cl)c(c(c1)Cl)OCCCOc1ccc(cn1)C(F)(F)F)Cl,0.034819,0.02931446924453367,1
+CCOCn1c(c2ccc(cc2)Cl)c(c(c1C(F)(F)F)Br)C#N,0.0350825,0.05625728978408869,1
+Fc1ccc(c(c1)c1ccc(c(c1)Cl)Cl)NC(=O)c1cn(nc1C(F)F)C,0.035609999999999996,0.03932567030945589,1
+CCCSP(=S)(Oc1ccc(cc1)SC)OCC,0.035665,0.004711340468310734,1
+CCC(C(=O)OC1=C(C(=O)OC21CCCCC2)c1ccc(cc1Cl)Cl)(C)C,0.035787,0.03198882233811575,1
+C#CCOC(c1ccc(cc1)Cl)C(=O)NCCc1ccc(c(c1)OC)OCC#C,0.036904,0.13401482275993515,1
+CC(Cc1ccccc1)N,0.036981,0.36111864011024203,1
+OC(C(C)(C)C)C(n1ncnc1)Cc1ccc(cc1)Cl,0.037441,0.10667091962813896,1
+CCN(c1c(cc(cc1N(=O)=O)C(F)(F)F)N(=O)=O)CC(=C)C,0.037508,0.1431542602879971,1
+Clc1c(O)c(Cl)c(c(c1Cl)Cl)Cl,0.037546,0.0373555584805313,1
+CC(OP(=S)(OC(C)C)SCCNS(=O)(=O)c1ccccc1)C,0.037735,0.003483461373934047,1
+Clc1ccc(cc1)c1ccccc1NC(=O)c1cccnc1Cl,0.037878,0.7322171046306378,1
+Clc1ccc(c(c1)Cl)C1(OCCO1)Cn1cncn1,0.0379825,0.08193239851033172,1
+CCOC(=O)CSc1nc(nn1C(=O)N(C)C)C(C)(C)C,0.038167,0.22389128716309517,1
+CC(C(c1cncnc1)(c1ccc(cc1)OC(F)(F)F)O)C,0.038746,0.04877699653482289,1
+OC(=O)COc1cc(Cl)c(cc1Cl)Cl,0.039142,0.0762510675404676,1
+CCOP(=S)(Oc1nn(c(n1)Cl)C(C)C)OCC,0.039842,0.01364895381111031,1
+O=C(NC(=O)c1c(F)cccc1F)Nc1cc(Cl)c(cc1Cl)OC(C(C(F)(F)F)F)(F)F,0.03991,0.11291803798049704,1
+CNC(=S)S,0.040113,0.04526482606586425,1
+CCCOC/C(=N\c1ccc(cc1C(F)(F)F)Cl)/n1cncc1,0.040492,0.010829244497822825,1
+CC(N(C(=O)SCC(=C(Cl)Cl)Cl)C(C)C)C,0.041029,0.034659116233835524,1
+O=C(CC(C)(C)C)OC1=C(C(=O)OC21CCCC2)c1c(C)cc(cc1C)C,0.0414325,0.06716323023627085,1
+OC1(Cn2ncnc2)C(CCC1(C)C)Cc1ccc(cc1)Cl,0.0420535,0.045733295416611315,1
+COP(=S)(Oc1ccc(c(c1)C)[N+](=O)[O-])OC,0.0424911,0.011196757318467296,1
+CCOC(=O)CCN(C(C)C)SN(C(=O)Oc1cccc2c1OC(C2)(C)C)C,0.042628,0.03698852803092934,1
+CC(Cc1ccc(cc1)C(C)(C)C)CN1CCCCC1,0.043261,0.004406553082131647,1
+Nc1ncn[nH]1,0.0446005,0.04204987250872469,0.2727272727272727
+Nc1n[nH]cn1,0.0446005,0.04204987250872469,0.2727272727272727
+[S-]C(=S)NCCNC(=S)[S-].[Zn+2],0.044607,0.19790248567357543,1
+CCSC(=O)N1CCCCCC1,0.044874,0.07642422021606303,1
+O=C1OC(C(=O)N1Nc1ccccc1)(C)c1ccc(cc1)Oc1ccccc1,0.04514,0.04532867511572046,1
+ClC(C(c1ccc(cc1)Cl)c1ccc(cc1)Cl)(Cl)Cl,0.045488125000000004,0.07554077067349983,1
+S=C1NCCCN1,0.045617,0.01384383462435663,1
+ClCC=CCl,0.045958,0.07420608230927385,0.14285714285714285
+CCOC(=O)Cn1c(=O)sc2c1c(Cl)ccc2,0.046003,0.15796626344328552,1
+N#CC(c1c(Cl)ccc(c1Cl)n1ncc(=O)[nH]c1=O)c1ccc(cc1)Cl,0.04661,0.045269921234742785,1
+CN(C(=S)SSC(=S)N(C)C)C,0.04783,0.06877566406998858,1
+Cc1cccc(c1O)C,0.049114,0.2414252457840195,1
+CCC(C(=O)NCc1ccccc1)Oc1ccc(c(c1)C(F)(F)F)F,0.049813,0.05195765769812722,1
+COC(=O)Nc1nc2c([nH]1)cc(cc2)Sc1ccccc1,0.050109,0.1435937337887938,1
+CCSC(CC1CC(=O)C(C(=O)C1)C(=NOCC)CCC)C,0.050568,0.12460566123801867,1
+C#CCN1C(=O)COc2c1cc(c(c2)F)N1C(=O)C2=C(C1=O)CCCC2,0.0508,0.053941885942165126,0.11764705882352941
+CNC(=O)Oc1cc(C)c(c(c1)C)C,0.051749,0.10673357885388511,1
+CNC(=O)Oc1cccc(c1)/N=C/N(C)C,0.051976,0.03762575471585514,1
+CN(C(=O)Oc1nc(nc(c1C)C)N(C)C)C,0.0520385,0.04932686575335115,1
+O=N(=O)c1ccc(c(c1)N)C,0.052579,0.18412041944535595,1
+CCO/N=C(\C1=C(O)CC(CC1=O)C1CCCSC1)/CCC,0.052847,0.07824045781528054,1
+CC(C(c1ccc(cc1)Cl)(Cn1ncnc1)O)C1CC1,0.05326,0.03268723660002496,1
+O=C(N/C(=N\OCC1CC1)/c1c(F)c(F)ccc1C(F)(F)F)Cc1ccccc1,0.053352,0.06857503872045755,1
+NC(=NCCCCCCCCNCCCCCCCCN=C(N)N)N,0.053436,0.059840855763556515,1
+C=CCOC(c1ccc(cc1Cl)Cl)Cn1cncc1,0.053503,0.013364919753585823,1
+COCN(c1c(CC)cccc1CC)C(=O)CCl,0.0537505,0.5689762657666069,1
+CNC1=C(c2cccc(c2)C(F)(F)F)C(=O)C(O1)c1ccccc1,0.055205,0.12096558058466282,1
+CCOc1ccc2c(c1)C(=CC(N2)(C)C)C,0.055221,0.3899071218471605,1
+O=C(c1ccc(cc1S(=O)(=O)C)C(F)(F)F)c1cnoc1C1CC1,0.055661,0.031413620867328615,1
+CCOC(=O)COC(=O)c1cc(ccc1[N+](=O)[O-])Oc1ccc(cc1Cl)C(F)(F)F,0.055835,0.2928139774036721,1
+COc1nc(nc(n1)C)NC(=O)[N-]S(=O)(=O)c1cc(I)ccc1C(=O)OC.[Na+],0.056118,0.05404414990115363,1
+CNC(=O)Oc1cccc(c1)N=CN(C)C,0.056496,0.03682120125010236,1
+CCOC(=O)C(c1ccc(cc1)Cl)(c1ccc(cc1)Cl)O,0.056583,0.03293127933501043,1
+OC(=O)COc1ccc(cc1C)Cl,0.0573225,0.11122941902910707,1
+CCOCCN(C(=C(C)C)c1ccccc1)C(=O)CCl,0.05747,0.3610868942231481,1
+CCOC(=O)NCCOc1ccc(cc1)Oc1ccccc1,0.0575765,0.20626740154765416,1
+CN(C(CN1c2ccccc2Sc2c1cccc2)C)C,0.058365,0.11756462218095892,1
+CC1COC(O1)(Cn1cncn1)c1ccc(cc1Cl)Oc1ccc(cc1)Cl,0.059321,0.10433637078167099,1
+N#CC(c1cccc(c1)Oc1ccccc1)OC(=O)C(c1ccc(cc1)Cl)C(C)C,0.059538,0.007586643948243213,1
+CCN(c1c(cc(cc1[N+](=O)[O-])C(F)(F)F)[N+](=O)[O-])CC(=C)C,0.0595625,0.05855836191865126,1
+N#CC(c1cccc(c1)Oc1ccccc1)OC(=O)C1C(C1(C)C)(C)C,0.060099,0.025857629111763467,1
+CC(OC(=O)C(c1ccc(cc1)Br)(c1ccc(cc1)Br)O)C,0.0606145,0.01861658055281908,1
+C=CC=CCC1=C(C)C(CC1=O)OC(=O)C1C(C1(C)C)C=C(C)C.C=CC=CCC1=C(C)C(CC1=O)OC(=O)C1C(C1(C)C)C=C(C(=O)OC)C,0.06135,0.1674015669247459,1
+Clc1ccccc1c1nnc(nn1)c1ccccc1Cl,0.06152150000000001,0.17457800452365999,1
+COC(=O)c1cccc(c1S(=O)(=O)NC(=O)Nc1nc(OCC(F)(F)F)nc(n1)N(C)C)C,0.062141,0.028650452770180745,1
+CCNc1nc(SC)nc(n1)NC(C)(C)C,0.062149,0.013482271036981958,1
+[O-][N+](=O)c1cc(cc(c1)[N+](=O)[O-])[N+](=O)[O-],0.062458,0.06275942720161548,1
+Clc1cc(ccc1Oc1ccc(c(c1)C(=O)NS(=O)(=O)C)[N+](=O)[O-])C(F)(F)F,0.062678,0.182234765828178,1
+Clc1cc(F)c(cc1C(=O)NS(=O)(=O)N(C(C)C)C)n1c(=O)cc(n(c1=O)C)C(F)(F)F,0.062693,0.029112999999999997,0.10416666666666667
+COc1nc(nc(n1)C)NC(=O)NS(=O)(=O)c1ccccc1Cl,0.062889,0.09421850511311705,1
+O=C(NS(=O)(=O)c1c(C)cccc1C(=O)O)Nc1nc(OCC(F)(F)F)nc(n1)N(C)C,0.063963,0.1394148565121269,1
+COc1nc(nc(n1)C)NC(=O)NS(=O)(=O)c1ccsc1C(=O)OC,0.064534,0.11308795186678679,1
+O=C(N(C)C)Nc1ccc(c(c1)Cl)n1nc(oc1=O)C(C)(C)C,0.064937,0.013577057957631705,1
+CCCCN(SN(C(=O)Oc1cccc2c1OC(C2)(C)C)C)CCCC,0.065695,0.034686887309826164,1
+[O-][N+](=O)NC1=NCCN1Cc1ccc(nc1)Cl,0.066494,0.07858478548601301,1
+O=C(NC(=O)c1c(F)cccc1F)Nc1cc(Cl)c(c(c1F)Cl)F,0.06691,0.06672646208100211,1
+CSc1nnc(c(=O)n1N)C(C)(C)C,0.067199,0.01370099999999999,0.11538461538461539
+O=C(NC(=O)c1c(F)cccc1F)Nc1ccc(c(c1)Cl)OC(C(OC(F)(F)F)F)(F)F,0.06758600000000001,0.10260672054349806,1
+CCOc1ccc(cc1)C(COCc1cccc(c1)Oc1ccccc1)(C)C,0.068395,0.11446126899334733,1
+C#CCOS(=O)OC1CCCCC1Oc1ccc(cc1)C(C)(C)C,0.06905,0.10684727593488692,1
+CCO/N=C(/C1=C(O)CC(CC1=O)c1c(C)cc(cc1C)C)\CC,0.069817,0.15230798085384742,1
+CO/N=C(/c1ccccc1COc1cc(C)ccc1C)\C(=O)NC,0.070468,0.6220505471560788,1
+COc1cc(OC)n2c(n1)nc(n2)S(=O)(=O)Nc1c(Cl)ccc(c1Cl)C,0.071727,0.40993866398627304,1
+OC(=O)COc1nc(Cl)c(cc1Cl)Cl,0.07213454999999999,0.07269541806149572,1
+CCCN(c1c(cc(cc1[N+](=O)[O-])S(=O)(=O)N)[N+](=O)[O-])CCC,0.07218,0.17868551302319066,1
+CCN1CCN(CC1)c1cc2c(cc1F)c(=O)c(cn2C1CC1)C(=O)O,0.072344,0.24865568952630662,1
+Nc1ccc(cc1)Cl,0.072508,0.21337307508691025,1
+CO/N=C(\c1ccccc1CO/N=C(/c1cccc(c1)C(F)(F)F)\C)/C(=O)OC,0.072728,0.13830233131650127,1
+O=C(N(C)C)Nc1cccc(c1)C(F)(F)F,0.073957,0.026815528437119592,1
+OC(C(C)(C)C)C(n1cncn1)Oc1ccc(cc1)c1ccccc1,0.074093,0.1903742967163982,1
+CCCSc1ccc2c(c1)[nH]c(n2)NC(=O)OC,0.075377,0.028512765674156317,1
+Cn1nc(c(c1)C(=O)Nc1cccc2c1C1CCC2C1=C(Cl)Cl)C(F)F,0.075835,0.036895155541294765,1
+CCNc1nc(NC(C)C)nc(n1)Cl,0.077892,0.10522175259985397,1
+N#C/N=C(/N(Cc1ccc(nc1)Cl)C)\C,0.07859,0.026400030134249707,1
+CC(c1cc(ccc1O)C(c1ccc(c(c1)C(C)C)O)(C)C)C,0.080014,0.6398700944627715,1
+C=CCC1=C(C)C(CC1=O)OC(=O)C1C(C1(C)C)C=C(C)C,0.081016,0.1015069968804333,1
+NC(=N)NCCCCCCCCNC(=N)N,0.08102,0.19314970975159368,1
+O=C(C1=C(C)OCCS1)Nc1ccccc1,0.0811745,0.13891336071324945,1
+Clc1cc(cnc1CNC(=O)c1c(Cl)cccc1Cl)C(F)(F)F,0.082121,0.018460817122028766,1
+CNC(=O)Oc1cc(C)c(c(c1)C)SC,0.0827735,0.01741923082610049,1
+O=C(c1cccc(c1C(=O)NC(CS(=O)(=O)C)(C)C)I)Nc1ccc(cc1C)C(C(F)(F)F)(C(F)(F)F)F,0.0827975,0.07944646574020595,1
+COC(=O)Nc1cccc(c1)OC(=O)Nc1cccc(c1)C,0.083248,0.04240128957444986,1
+CCCN(c1c(cc(c(c1[N+](=O)[O-])N)C(F)(F)F)[N+](=O)[O-])CCC,0.08393,0.07717181445849283,1
+OC(C(C)(C)C)C(n1ncnc1)Oc1ccc(cc1)Cl,0.084527,0.0708471105605172,1
+O=C(C(C)(C)C)C(n1ncnc1)Oc1ccc(cc1)Cl,0.085107,0.05419733120295796,1
+CCCC(=C1C(=O)CC(CC1=O)C1CCCSC1)NOCC,0.08603,0.029427973343164302,1
+Cn1cc(c2cccc(c2)C(F)(F)F)c(=O)c(c1)c1ccccc1,0.08730199999999999,0.05629475116022586,1
+CC(NC(=O)N1CC(=O)N(C1=O)c1cc(Cl)cc(c1)Cl)C,0.08783250000000001,0.0787926300099515,1
+CC(=O)Nc1cc(NS(=O)(=O)C(F)(F)F)c(cc1C)C,0.088948,0.8470175048555991,1
+COCC(=O)Nc1cc(ccc1NC(=NC(=O)OC)NC(=O)OC)Sc1ccccc1,0.08959,0.0928601351535762,1
+CCCN(C(=O)SCC)CCC,0.0897945,0.0385202690181602,1
+COc1cc(ccc1OC)/C(=C/C(=O)N1CCOCC1)/c1ccc(cc1)Cl,0.0902395,0.13842611680362346,1
+CCC(=O)Nc1ccc(c(c1)Cl)Cl,0.09171,0.2861199303524308,1
+N#CC(c1ccccc1)(Cn1cncn1)CCc1ccc(cc1)Cl,0.092038,0.10411365095113242,1
+Clc1ccc2c(c1)ncc(n2)Oc1ccc(cc1)OC(C(=O)OCC1CCCO1)C,0.092103,0.044295365301475084,1
+CNC(=O)ON=C(SC)C,0.092474,0.058812875836751474,1
+NC(=O)c1c(Cl)cccc1Cl,0.092619,0.1889659806940431,1
+Clc1ccc(c(c1)Cl)NC(=O)C1(CC1)C(=O)O,0.093032,0.23340355300882404,1
+Clc1cc(Cl)cc(c1)C1(CO1)CC(Cl)(Cl)Cl,0.093625,0.05408377453081826,1
+ClC(=CC1C(C1(C)C)C(=O)OCc1cccc(c1)Oc1ccccc1)Cl,0.095836,0.11785556782611674,1
+OC(=O)C(Oc1ccc(cc1Cl)Cl)C,0.0967835,0.028654663804704807,1
+[O-][N+](=O)/N=C/1\NCCN1Cc1ccc(nc1)Cl,0.097395,0.05857715290899933,1
+NC(=N)NCCCCCCCCCCCCOC(=O)C,0.1016,0.09232709423649274,1
+OC1CC2(O)CC(O)C(C(O2)(C)CC(C=CC=CC=CC=CCC(OC(=O)C=CC2C(C1)(C)O2)C)OC1(C)OC(C)C(C(C1O)N)O)C(=O)O,0.10172,0.39458193614551607,1
+COP(=O)(NC(=O)C)SC,0.1023645,0.020049393739713695,1
+COc1ncc(c2n1nc(n2)NS(=O)(=O)c1c(cccc1C(F)(F)F)OCC(F)F)OC,0.10344,0.5775171729482689,1
+COCc1c(F)c(F)c(c(c1F)F)COC(=O)C1C(C1(C)C)/C=C/C,0.10573,0.027432945347156186,1
+[O-][N+](=O)c1cnc(n1C)C,0.10629,0.4244751165005822,1
+CCOC(=O)C(OC(=O)c1cc(ccc1[N+](=O)[O-])Oc1ccc(cc1Cl)C(F)(F)F)C,0.10828,0.20973070990352538,1
+CCOC(=O)C(OC(=O)c1cc(ccc1N(=O)=O)Oc1cc(ccc1Cl)C(F)(F)F)C,0.10828,0.06982995210089786,1
+COc1c(OC)cc(c(c1OC)C(=O)c1c(OC)ncc(c1C)Cl)C,0.108388,0.442824415382828,1
+S=C1NCCNC(=S)S[Mn+2]S1,0.10856,0.03112795546667836,1
+ClCC(=O)N(c1ccccc1)C(C)C,0.10865,0.039800196201902616,1
+O=C1CCCC(=O)C1C(=O)c1ccc(cc1Cl)S(=O)(=O)C,0.11010835,0.003777275512082462,1
+O=C1N(c2cc(Cl)cc(c2)Cl)C(=O)C2(C1(C)C2)C,0.1108605,0.10136461108030684,1
+COC(=O)c1c(nc(c(c1CC(C)C)C1=NCCS1)C(F)(F)F)C(F)F,0.11151,0.0662884473428508,1
+Oc1ccc(c(c1)C)C,0.1146,0.26536776349523966,1
+Clc1ccc(cc1)CCC(C(C)(C)C)(Cn1cncn1)O,0.115167,0.05930283852644727,1
+CNc1cnn(c(=O)c1Cl)c1cccc(c1)C(F)(F)F,0.1152575,0.08731175498612348,1
+N#Cc1c(N)nc(nc1N)NC1CC1,0.11566,0.05280926072342975,1
+CC(N(c1c(cc(cc1N(=O)=O)S(=O)(=O)N)N(=O)=O)C(C)C)C,0.11817,0.2777632424133651,1
+CNC(=O)O/N=C(\SC)/C,0.11837,0.058793334381417275,1
+Nc1ccc(cc1)S(=O)(=O)Nc1nc(C)cc(n1)C,0.11856,0.2378427297754382,1
+CCN(c1c(cc(cc1[N+](=O)[O-])C(F)(F)F)[N+](=O)[O-])Cc1c(F)cccc1Cl,0.11856,0.07762896013966018,1
+COc1cc(ccc1OC)C(=CC(=O)N1CCOCC1)c1ccc(cc1)Cl,0.11937,0.08117798587530316,1
+CCCCc1c(=O)nc([nH]c1C)NCC,0.11945,0.10686864997979274,1
+COC(=O)NC(=S)Nc1ccccc1NC(=S)NC(=O)OC,0.12412500000000001,0.15478950911292666,1
+c1coc(c1)c1nc2c([nH]1)cccc2,0.12487,0.16183727218960647,1
+CN(C(=O)C(c1ccccc1)c1ccccc1)C,0.12536,0.19544609225520085,1
+CCOc1cc(ccc1[N+](=O)[O-])Oc1ccc(cc1Cl)C(F)(F)F,0.12856,0.15587702082687252,1
+[O-][N+](=O)/N=C(\NC)/NCc1cnc(s1)Cl,0.13017,0.6528339562976342,1
+Clc1c(ccc(c1N)[N+](=O)[O-])Oc1ccccc1,0.13224349999999999,0.5152638423941532,1
+OC(C(C)(C)C)C(=Cc1ccc(cc1)Cl)n1ncnc1,0.13507,0.46450126673863174,1
+CCNC(=O)NC(=O)/C(=N\OC)/C#N,0.135735,0.15289,1
+O=C(Nc1cnns1)Nc1ccccc1,0.13621,0.07649670799599474,1
+CCc1ccc(cc1)C(=O)NN(C(C)(C)C)C(=O)c1cc(C)cc(c1)C,0.13674999999999998,1.2027870812869572,1
+CN1CC2CC1CN2c1cc2c(cc1F)c(=O)c(cn2C1CC1)C(=O)O,0.13991,0.2090946529245896,0.5862068965517241
+OCC(CCl)O,0.14067559999999998,29.5829657649106,1
+COC(=O)C(N(c1c(C)cccc1C)C(=O)Cc1ccccc1)C,0.14136,0.28123787582917653,1
+COc1nc(C)nc(n1)N(C(=O)NS(=O)(=O)c1ccccc1C(=O)O)C,0.14422,0.1466226684428757,1
+ClC(=C)Cl,0.14441,0.010100837249467656,0.1
+CC(=O)O.CCCCCCCCCCCCNC(=N)N,0.14612,0.07726031960810226,1
+CON=C(c1ccccc1CON=C(c1cccc(c1)C(F)(F)F)C)C(=O)OC,0.14693,0.07879158625494943,1
+COC(CCCC(CC=CC(=CC(=O)OC(C)C)C)C)(C)C,0.14816,0.7701876369159573,1
+c1scc(n1)c1nc2c([nH]1)cccc2,0.14907,0.08330318481895425,1
+CC(N1C(=O)c2ccccc2NS1(=O)=O)C,0.14983,0.6805437100363501,1
+N#CC(c1cccc(c1)Oc1ccccc1)OC(=O)C1C(C1(C)C)C=C(Cl)Cl,0.150135,0.034357755122311796,1
+Cc1cccc2c1n1cnnc1s2,0.150605,0.3288254723492316,1
+ClC(SN1C(=O)c2c(C1=O)cccc2)(Cl)Cl,0.15173999999999999,0.19868816260628974,1
+CON=C(c1ccc(cc1Cl)Cl)Cc1cccnc1,0.15246,0.03586423281596468,1
+CCNC(=O)NC(=O)C(=NOC)C#N,0.15289,0.13464656029769195,1
+Clc1ccc(c(c1)Cl)C=C(C(C(C)(C)C)O)n1cncn1,0.15327,0.1442160520052237,1
+CCC(Nc1c(cc(cc1[N+](=O)[O-])C(C)(C)C)[N+](=O)[O-])C,0.153385,0.04677148915962652,1
+COC=C(c1ccccc1Oc1ncnc(c1)Oc1ccccc1C#N)C(=O)OC,0.15432,0.21541160679804994,1
+COP(=S)(Oc1cc(Cl)c(cc1Cl)Cl)OC,0.1555,0.00951413645493796,1
+CCCCCCCCc1cc(N(=O)=O)c(c(c1)N(=O)=O)OC(=O)C=CC,0.15642,0.4256932568967014,1
+Cc1nc(Nc2ccccc2)nc(c1)C1CC1,0.15802,0.042364590523769674,1
+CCOC(=O)CN(c1c(CC)cccc1CC)C(=O)CCl,0.16036,0.3274260465988832,1
+CC(OC(=O)Nc1ccccc1)C,0.16182,1.0468050257363828,1
+c1ccc(cc1)Nc1ccccc1,0.16546,0.39957687799119046,1
+C#CC(NC(=O)c1cc(Cl)cc(c1)Cl)(C)C,0.16593,0.15088138979068927,1
+Cc1ccc(c2c1cccc2)C,0.17283,0.14368749917136306,1
+Clc1cc(Cl)c(cc1n1nc(n(c1=O)C(F)F)C)NS(=O)(=O)C,0.17304,0.020268939200598496,1
+COC(=O)c1ccc(cc1C1=NC(C(=O)N1)(C)C(C)C)C,0.17341,0.4632575521540832,1
+CNC(=O)N(c1nnc(s1)C(C)(C)C)C,0.1752,0.15654919233821035,0.4
+CCCCCCC(c1cc(cc(c1OC(=O)/C=C/C)[N+](=O)[O-])[N+](=O)[O-])C,0.17563,0.26307095482632786,1
+CCCCCCCCCC[N+](CCCCCCCCCC)(C)C.[Cl-],0.17676,1.4242396853844175,1
+CCCC1COC(O1)(Cn1cncn1)c1ccc(cc1Cl)Cl,0.176786,0.031616115175867994,1
+N#Cc1cc(C)c(c(c1)C(=O)NC)NC(=O)c1cc(nn1c1ncccc1Cl)Br,0.17901,0.08118529460943061,1
+COCC(=O)N(c1c(C)cccc1C)N1CCOC1=O,0.17966,0.16910207634610167,1
+CC1=NNC(=O)N(C1)/N=C/c1cccnc1,0.18092,0.5923344240176047,1
+C#CCC1=C(C)C(CC1=O)OC(=O)C1C(C1(C)C)C=C(C)C,0.18558899999999998,0.1171259150385069,1
+O=N(=O)c1ccc(c(c1)N(=O)=O)C,0.18668,0.08157821699215927,1
+ClCC(=O)N(c1c(C)cccc1C)Cn1cccn1,0.18829800000000002,0.16889835619314295,1
+N#CCNC(=O)c1cnccc1C(F)(F)F,0.19244,0.5428266925258607,1
+OC1CN(C(=O)N1c1nnc(s1)C(C)(C)C)C,0.19507,0.17520000000000005,0.4
+O=c1nc(N(C)C)n(c(=O)n1C1CCCCC1)C,0.19817,0.5036400000000001,0.16666666666666666
+COc1nc(nc(n1)C)NC(=O)NS(=O)(=O)c1ccccc1CCC(F)(F)F,0.200175,0.0780132802865645,1
+Nc1ccc(c(c1)N)O,0.20138,1.9760672030218895,1
+Cn1nc(c(c1)C(=O)Nc1ccccc1C1CC1C1CC1)C(F)F,0.2022,0.036791889297855665,1
+O=C(NS(=O)(=O)c1ccccc1C(=O)OC1COC1)Nc1nc(C)cc(n1)C,0.20423,0.17247354062790787,1
+CO/C=C(\c1ccccc1Oc1ncnc(c1)Oc1ccccc1C#N)/C(=O)OC,0.20427,0.17279764194135627,1
+ClC=C(c1cc(Cl)c(cc1Cl)Cl)OP(=O)(OC)OC,0.20494,0.0051523323240041516,1
+CC(=CC1C(C1(C)C)C(=O)OCc1coc(c1)Cc1ccccc1)C,0.2068305,0.2266649040812373,1
+ClCC(=O)N(c1c(CC)cccc1CC)CNC(=O)C,0.21058,0.3889237596843575,1
+CCOCN(c1c(C)cccc1CC)C(=O)CCl,0.21666999999999997,0.14118934221000953,1
+CC(c1ccc(cc1)O)(c1ccc(cc1)O)C,0.21902,0.8642094522619983,1
+CC(Nc1nc(NC(C)C)nc(n1)Cl)C,0.219845,0.06430354395190928,1
+Fc1ccc(cc1)C(=O)CCCN1CCN(CC1)c1ccccn1,0.221446,0.2460138158494776,1
+COCC(=O)N(c1c(C)cccc1C)C(C(=O)OC)C,0.22375,0.23004424615920194,1
+Nc1ccc2c(c1)nc1c(c2)ccc(c1)N,0.22462,0.31183121631075367,1
+Cc1nnc(c(=O)n1N)c1ccccc1,0.2326765,0.17804621363074108,1
+CCNC(=O)C(OC(=O)Nc1ccccc1)C,0.23279,0.332030179459587,1
+CNC(=O)Oc1ccccc1OC(C)C,0.23418,0.015136840603514414,1
+Cl/C=C/CO/N=C(\C1=C(O)CC(CC1=O)CC(SCC)C)/CC,0.23895,0.17623271825645226,1
+CCCCCCCCSC(=O)Oc1cc(Cl)nnc1c1ccccc1,0.24081999999999998,0.17568679838983547,1
+Nc1cnn(c(=O)c1Cl)c1ccccc1,0.24815,0.15209240263006019,1
+CCc1cc(C)cc(c1c1c(OC(=O)C(C)(C)C)n2n(c1=O)CCOCC2)CC,0.24968,0.08859444244722274,1
+CC1OC(C)OC(OC(O1)C)C,0.2497,0.71759,0.25
+[S]C(=S)NCCNC(=S)S[Mn],0.25254,0.029230690430281737,1
+O=C1N(OCC1(C)C)Cc1ccccc1Cl,0.253443,0.06489437227107174,1
+CC(CC(c1sccc1NC(=O)c1cn(nc1C(F)(F)F)C)C)C,0.25458,0.05435038080668476,1
+CCSC(CC1CC(=O)C(=C(NOCC=CCl)CC)C(=O)C1)C,0.25839999999999996,0.18080210641569622,1
+Cc1ccc(cc1)N(S(=O)(=O)N(C)C)SC(Cl)(Cl)F,0.25917,0.07289219748870154,1
+CC1N(C(=O)NC2CCCCC2)C(=O)SC1c1ccc(cc1)Cl,0.259436,0.045228630751251844,1
+Fc1ccc(cc1)Oc1ccnc2c1c(Cl)cc(c2)Cl,0.25963,0.04429643068450033,1
+CCCCCCC(c1cc(cc(c1OC(=O)/C=C\C)[N+](=O)[O-])[N+](=O)[O-])C,0.26317500000000005,0.11063436333535125,1
+CCN(C(=O)C(Oc1cccc2c1cccc2)C)CC,0.271895,0.864195109372932,1
+OC(=O)C(Cl)(Cl)C,0.273385,0.42676906198092396,0.125
+COc1cc(OC)nc(n1)NC(=O)NS(=O)(=O)c1ncccc1S(=O)(=O)CC,0.28045,0.326984742341746,1
+OC(=O)COc1ccc(cc1Cl)Cl,0.2805,0.07090654737788459,1
+CO/C=C(\c1ccccc1COc1cccc(n1)C(F)(F)F)/C(=O)OC,0.28313,0.10998721204910458,1
+CCOC(=O)CC(C(=O)OCC)SP(=S)(OC)OC,0.292105,0.027360274484330736,1
+CNC(=O)Oc1cccc2c1cccc2,0.29818,0.06924709306744524,1
+COC(=O)c1ccccc1S(=O)(=O)NC(=O)Nc1nc(OC(F)F)cc(n1)OC(F)F,0.29893,0.8950685424697046,1
+CN(C(=S)[S-])C.CN(C(=S)[S-])C.CN(C(=S)[S-])C.[Fe+3],0.30012,0.033370225153194974,1
+CCOC(=O)c1ccccc1S(=O)(=O)NC(=O)Nc1nc(Cl)cc(n1)OC,0.30133,0.2501804647195122,1
+Fc1ccc(c(c1)F)NC(=O)c1cccnc1Oc1cccc(c1)C(F)(F)F,0.30333,0.043526987502530146,1
+NC1CC(N=C(C(=O)O)N)C(OC1OC1C(O)C(O)C(C(C1O)O)O)C,0.30578,2.5744890364385022,1
+CNC(=O)Oc1cc(C)cc(c1C)C,0.30635,0.048125076360843136,1
+Clc1ccc(cc1)CN(C(=O)Nc1ccccc1)C1CCCC1,0.31170800000000004,0.05235632970904802,1
+ClCCOc1ccccc1S(=O)(=O)NC(=O)Nc1nc(C)nc(n1)OC,0.31207450000000003,0.16009310690897538,1
+CCC(n1c(=O)[nH]c(c(c1=O)Br)C)C,0.31690999999999997,0.11945,0.14814814814814814
+OC(=O)CCl,0.31747,0.1671151871942349,1
+CN(C1C(=O)C(=C(O)N)C(=O)C2(C1CC1C(=C(O)c3c(C1(C)O)cccc3O)C2=O)O)C,0.33751,7.451766115785945,1
+Clc1cc(ccc1Oc1ccc(c(c1)C(=O)O)[N+](=O)[O-])C(F)(F)F,0.34563,0.19270607583833513,1
+N=C(NC(=N)N)NCCc1ccccc1,0.35565,0.26993051712987703,1
+COc1ccc(cc1)C(C(Cl)(Cl)Cl)c1ccc(cc1)OC,0.36164,0.10499077478025709,1
+Cc1cc(C)cc(c1)C(=O)N(C(C)(C)C)NC(=O)c1ccc2c(c1C)CCCO2,0.3678,0.48224036732567843,1
+O=C(Nc1ccnc(c1)Cl)Nc1ccccc1,0.37548,0.04012190755928847,1
+CO/N=C(\c1ccccc1Oc1ncnc(c1F)Oc1ccccc1Cl)/C1=NOCCO1,0.39448,0.08196210659292386,1
+N#Cc1ccc(cc1)C/C(=N/NC(=O)Nc1ccc(cc1)OC(F)(F)F)/c1ccc(cc1)C(F)(F)F,0.39494,0.051118203192945126,1
+NCCNc1cccc2c1cccc2,0.42415,0.48062761831185635,1
+CC(=CC1C(C1(C)C)C(=O)OCc1cccc(c1)Oc1ccccc1)C,0.42802,0.05819218797884211,1
+CC(Oc1ccccn1)COc1ccc(cc1)Oc1ccccc1,0.433615,0.07205856883688595,1
+N#Cc1c[nH]cc1c1cccc2c1OC(O2)(F)F,0.449265,0.6923188317779512,1
+O=C(NC(=O)c1c(F)cccc1F)Nc1ccc(cc1F)Oc1ccc(cc1Cl)C(F)(F)F,0.458295,0.04852253482722704,1
+CCSC(=O)N(CC(C)C)CC(C)C,0.46004,0.061611392287918516,1
+CSC(=O)c1cccc2c1snn2,0.46082,0.6841455305610391,1
+ClCC(=O)N(c1c(C)cccc1CC)COC(C)C,0.463365,0.13550848235759821,1
+Cc1cc(N)c(cc1C)C,0.46595,0.13860612331714822,1
+Clc1cc(ccc1Oc1ccc(c(c1)C(=O)[O-])[N+](=O)[O-])C(F)(F)F.[Na+],0.46919,0.15261865086149698,1
+Clc1c(Cl)c([N+](=O)[O-])c(c(c1Cl)Cl)Cl,0.47404,0.052471899619992095,1
+CC1OC(C)CN(C1)C1CCCCCCCCCCC1,0.48317,0.040365094277215886,1
+COc1nc(nc(n1)C)NC(=O)NS(=O)(=O)c1ccccc1C(=O)OC,0.48379,0.09678356438189871,1
+CCCCc1c(C)nc(nc1OS(=O)(=O)N(C)C)NCC,0.49302,0.04087513302969224,1
+CN1N(C)C(CC1c1ccccc1)c1ccccc1,0.49534,0.2573977051460968,1
+OC(=O)C(Oc1cccc(c1)Cl)C,0.49846,0.013941374646101169,1
+COC(=O)C(NC(=O)C(CC(=O)O)N)Cc1ccccc1,0.49949,0.5075472835013551,1
+O=c1[nH]c2CCCc2c(=O)n1C1CCCCC1,0.50364,0.1579369235868818,1
+CCOC(=O)OC1=C(C(=O)NC21CCC(CC2)OC)c1cc(C)ccc1C,0.5061,0.08169257692890085,1
+N#Cc1c[nH]cc1c1cccc(c1Cl)Cl,0.50615,0.057904757941349944,1
+CCOc1nc(nc(n1)NC)NC(=O)NS(=O)(=O)c1ccccc1C(=O)OC,0.51169,0.2508956878129736,1
+CCCCC(COC(=O)c1ccccc1C(=O)OCC(CCCC)CC)CC,0.51209,2.7378333403755764,1
+Nc1nc(NC2CC2)nc(n1)N,0.514491,0.32292487000815034,1
+CCCCOCCOCCOCc1cc2OCOc2cc1CCC,0.51708,0.33736880263337077,1
+COc1c(Cl)ccc(c1C(=O)O)Cl,0.52027,0.7970170741237582,1
+CCOc1cc(ccc1C1COC(=N1)c1c(F)cccc1F)C(C)(C)C,0.5203,0.037064996552743056,1
+COCC(N(c1c(C)cccc1CC)C(=O)CCl)C,0.52855,0.11047407307423077,1
+O=CCC1CC(C)C(=O)C=CC(=CC(C(OC(=O)CC(C(C1OC1(C)OC(C)C(C(C1O)N(C)C)OC1(C)OC(C)C(C(C1)(C)O)O)C)O)CC)COC1OC(C)C(C(C1OC)OC)O)C,0.52958,0.10505273244057638,1
+[O-][N+](=O)/N=C\1/N(Cc2cnc(s2)Cl)COCN1C,0.53134,0.13016999999999998,0.23076923076923078
+COC(=O)C1(O)c2cc(Cl)ccc2c2c1cccc2,0.54605,0.01616796987547263,1
+COC(=O)c1cc(ccc1[N+](=O)[O-])Oc1ccc(cc1Cl)Cl,0.54657,0.24037806116700672,1
+CC(C12CCC(O2)(C(C1)OCc1ccccc1C)C)C,0.54665,0.27807881599856743,1
+Oc1ccc2c(c1N=Nc1ccccc1)ccc(c2)S(=O)(=O)O,0.54821,0.8611361228100273,1
+Nc1ccc(c(c1)N(=O)=O)N,0.56811,0.299490186232195,1
+CCCN(c1c(cc(cc1[N+](=O)[O-])C(F)(F)F)[N+](=O)[O-])CCCl,0.56902,0.06141900609157883,1
+NC1CCCCC1,0.5974349999999999,0.16869122618294258,1
+COC(=O)c1csc(c1S(=O)(=O)NC(=O)n1nc(n(c1=O)C)OC)C,0.5994,0.4941147442894595,1
+COc1cc(Cl)c(cc1Cl)OC,0.60371,0.1545937661767588,1
+COCCN(c1c(C)cccc1C)C(=O)CCl,0.6139,0.041958816899342014,1
+OC(=O)C1C2CCC(C1C(=O)O)O2,0.61774,0.5005268490775181,1
+O=Cc1ccco1,0.62445,0.12487,0.1111111111111111
+CCCCNC(=O)n1c(NC(=O)OC)nc2c1cccc2,0.628625,0.2503332503939969,1
+CN(C(=O)Nc1ccc(cc1)Cl)C,0.62925,0.02500960746892452,1
+COc1c(OC)cc(c(c1OC)C(=O)c1c(OC)ccc(c1C)Br)C,0.63528,0.12205709134262516,1
+OC1(Cn2ncnc2)/C(=C/c2ccc(cc2)Cl)/CCC1(C)C,0.64063,0.06361617379989579,1
+COC(=O)c1ccc(cc1)C(=O)OC,0.64372,1.5841096283212404,1
+Clc1ccc(cc1)S(=O)(=O)c1cc(Cl)c(cc1Cl)Cl,0.64597,0.04644512982101082,1
+CC(OC(=O)NC(C(=O)NC(c1nc2c(s1)cc(cc2)F)C)C(C)C)C,0.65432,0.22600178609579571,1
+CCCOC(=O)NCCCN(C)C.Cl,0.66747,0.14074552608667681,1
+CCCCOCC(OCC(O)C)C,0.67269,0.7448925410337572,1
+CC1OC(C)OC(C1)OC(=O)C,0.71759,0.1800567934233961,0.25
+[O-][N+](=O)c1cc(Cl)c(c(c1)Cl)N,0.72459,0.07504630337361097,1
+COc1nc(nc(c1)OC)NC(=O)NS(=O)(=O)Cc1ccccc1C(=O)OC,0.75292,0.5716066577541087,1
+O=C(C1C(C1(C)C)C=C(C)C)OCN1C(=O)C2=C(C1=O)CCCC2,0.75436,0.08889078538826793,1
+CCOc1nc(F)cc2n1nc(n2)S(=O)(=O)Nc1c(Cl)cccc1C(=O)OC,0.75615,0.6409959245303145,1
+CCCN(c1c(cc(cc1[N+](=O)[O-])C(F)(F)F)[N+](=O)[O-])CCC,0.760539,0.04776601269281189,1
+COC(=O)c1c(Cl)c(Cl)c(c(c1Cl)Cl)C(=O)OC,0.768162,0.28726897553198094,1
+COc1cc(OC)nc(n1)NC(=O)NS(=O)(=O)Cc1ccccc1C(=O)O,0.77956,0.7012778442128711,1
+Clc1ccc(c(n1)C(=O)O)Cl,0.78125,0.4397569387597831,1
+COC(=O)NS(=O)(=O)c1ccc(cc1)N,0.78179,0.2524369291494625,1
+ClCC[N+](C)(C)C.[Cl-],0.79079,2.2114081091282856,1
+COC(CCCC(C/C=C/C(=C/C(=O)OC(C)C)/C)C)(C)C,0.80523,0.14386287661105182,1
+CCOc1cc(ccc1OCC)NC(=O)OC(C)C,0.8241,0.25755109712128177,1
+OC(=O)c1nc(Cl)c(c(c1Cl)N)Cl,0.8283,1.6420292083585597,1
+CC(C1(C)N=C(NC1=O)c1nc2ccccc2cc1C(=O)O)C,0.8351195,0.7347553426962068,1
+Nc1ccc(c(c1)C)NOS(=O)(=O)O,0.84315,0.5422208204103196,1
+CCOC(=O)C1OC1(C)c1ccccc1,0.84854,0.18971032223534873,1
+COC(=O)Nc1nc2c([nH]1)cccc2,0.8499450000000001,0.031646097466502696,1
+OCCn1c(C)ncc1[N+](=O)[O-],0.8764,0.0814568738572416,1
+CC(Oc1cccc(c1)NC(=O)c1ccccc1C(F)(F)F)C,0.907795,0.14492382354991246,1
+COP(=O)OC,0.90869,0.1163372948750952,1
+OCCNc1ccc(cc1OCCO)N(=O)=O,0.94539,0.9154563739636503,1
+O=N(=O)c1cccc2c1cccc2,0.95283,0.3896724363306079,1
+O=C(C1(C)CCCCC1)Nc1ccc(c(c1Cl)Cl)O,0.96626,0.38098624299804523,1
+ClCCP(=O)(O)O,0.9723550000000001,2.415446889200535,1
+Oc1cccc2c1nccc2,0.98513,0.7990901464465562,1
+CCCOC(=O)c1ccc(cn1)C(=O)OCCC,0.99491,1.9178210321755,1
+Oc1noc(c1)C,0.99911,4.460800000000001,0.1
+CC[N](=C1C=CC(=C(c2ccc(cc2)N(Cc2cccc(c2)S(=O)(=O)O)CC)c2ccc(cc2)N(C)C)C=C1)Cc1cccc(c1)S(=O)(=O)O,1.01,0.15167422823485843,1
+ClCC[N+](C)(C)C,1.0602,2.279841889180028,1
+Clc1ccccc1,1.0661,0.08587760345100343,1
+O=C1CCCCCN1,1.1047,0.3875358039131163,1
+Cc1cc(C)nc(n1)Nc1ccccc1,1.1091,0.04573379643775025,1
+COc1cccc(c1C)C(=O)NN(C(C)(C)C)C(=O)c1cc(C)cc(c1)C,1.1154,0.7955622523163041,1
+COC(=O)C(=CC=CC(=CC=CC=C(C=CC=C(C=CC1=C(C)CCCC1(C)C)C)C)C)C,1.1194,0.020676050303422577,1
+Clc1ccccc1CC(C1(Cl)CC1)(Cn1nc[nH]c1=S)O,1.1619199999999998,0.03916659697986967,1
+Oc1ccc(cc1Cl)C(C)(C)C,1.1697,0.06552167575074479,1
+COc1cc(OC)nc(n1)NC(=O)NS(=O)(=O)Nc1ccccc1C(=O)N(C)C,1.178,1.9537855393202848,1
+CON=C(c1ccccc1COc1ccccc1C)C(=O)OC,1.1888,1.2682455873993468,1
+CCCOc1nn(c(=O)n1C)C(=O)[N-]S(=O)(=O)c1ccccc1C(=O)OC.[Na+],1.1894,0.7998668255808354,1
+OC(=O)Cc1cccc2c1cccc2,1.2057,0.3441264032971345,1
+OCc1cc(N=Nc2ccc(c3c2cccc3)S(=O)(=O)O)c(c(c1O)N=Nc1ccc(c2c1cccc2)S(=O)(=O)O)O,1.2093,0.965214018670024,1
+CC1=CC(=O)CC(C1)(C)C,1.2952,0.1131559776714462,1
+C[N]1(C)CCCCC1,1.3134,1.2054882989184301,1
+OC1CCC2(C(C1)CCC1C2CCC2(C1CCC2C(CCC(=O)O)C)C)C,1.3278,2.3006685270787415,1
+COc1cc(OC)nc(n1)NC(=O)NS(=O)(=O)N(S(=O)(=O)C)C,1.3412,0.3698967426539189,1
+Oc1ccc(c(c1)C(C)(C)C)O,1.3537,0.3395966131630982,1
+COc1ncc(c2n1nc(n2)S(=O)(=O)Nc1c(F)cccc1F)F,1.3917,0.182692394567328,1
+OCC1OC2OC3C(CO)OC(C(C3O)O)OC3C(CO)OC(C(C3O)O)OC3C(CO)OC(C(C3O)O)OC3C(OC(OC4C(OC(OC5C(OC(OC1C(C2O)O)C(O)C5O)CO)C(O)C4O)CO)C(O)C3O)CO,1.4097,19.552865568086077,1
+O=C(Nc1cc(F)cc(c1)F)N/N=C(/c1ncccc1C(=O)O)\C,1.412,0.48996871387244556,1
+CCCCOC(=O)c1ccccc1C(=O)OCc1ccccc1,1.5047,1.3246275217550465,1
+Fc1cc2CCC(n3c2c(c1)c(=O)c(c3)C(=O)O)C,1.5311,0.22682314364423445,1
+CC(N(c1c(cc(cc1N(=O)=O)C(F)(F)F)N(=O)=O)C(C)C)C,1.55095,0.05485872407242003,1
+CCC(c1noc(c1)NC(=O)c1c(OC)cccc1OC)(CC)C,1.5855,0.510962006759911,1
+c1ccc(cc1)c1ccccc1,1.6212,0.25004917540941873,1
+NCC(c1ccc(cc1)O)O,1.6321,0.763129370142482,1
+CCc1c(C(=O)O)c(=O)cnn1c1ccc(cc1)Cl,1.6865,0.13670714482817245,1
+ClCC#CCOC(=O)Nc1cccc(c1)Cl,1.7435,0.2563923654242082,1
+O/C(=C\1/C(=O)CC(CC1=O)C(=O)O)/C1CC1,1.7528,1.1164855772875812,1
+CO/N=C(\c1ccccc1COc1ccccc1C)/C(=O)OC,1.7985,0.764113504378649,1
+COc1ccc(c(c1)OC)N,1.8018,1.1821769600464371,1
+CCC(=O)C1=C([O-])CC(CC1=O)C(=O)[O-].[Ca+2],1.874,0.7779135467595814,1
+CC(C1(C)N=C(NC1=O)c1ncccc1C(=O)O)C,1.9137,0.3915316820059443,1
+OC(=O)COc1nc(F)c(c(c1Cl)N)Cl,1.9605,0.06027845593690741,1
+Clc1ccc(cc1)Cl,2.0408,0.07231350295657593,1
+CCCCOC(=O)c1ccccc1C(=O)OCCCC,2.1556,2.1469128859933164,1
+c1ccc(cc1)c1ccccc1OCC1CO1,2.2097,0.6041735123170521,1
+ClCC[N](C)(C)C,2.2428,0.6547382064094504,1
+COc1cc(OC)n2c(n1)nc(n2)NS(=O)(=O)c1c(OC)nccc1C(F)(F)F,2.3023,0.0844484241335687,1
+CC=Cc1ccc(cc1)OC,2.3212,1.0164585812387092,1
+CC(OC(=O)Nc1cccc(c1)Cl)C,2.3402,0.39127152258046005,1
+COC(=O)c1ccccc1O,2.3661,0.47595539237820567,1
+CCOC(=O)C=C,2.4771,0.09022650313479785,1
+COC(=O)CC(c1ccc(cc1)Cl)NC(=O)C(C(C)C)NC(=O)OC(C)C,2.507,0.14272792191684947,1
+COc1nn(c(=O)n1C)C(=O)NS(=O)(=O)c1ccccc1OC(F)(F)F,2.5233,0.7753663722121583,1
+C=Cc1ccccc1,2.7365,0.5985692489804522,1
+COc1cc(OC)nc(n1)NC(=O)NS(=O)(=O)c1n2ccccc2nc1S(=O)(=O)CC,2.7557,0.2312041070547178,1
+CN(NC(=O)CCC(=O)O)C,3.0343,0.49949,0.13043478260869565
+Oc1ccccc1c1ccccc1,3.1197,0.6847627630978469,1
+Clc1cnc2c(c1)ccc(c2C(=O)O)Cl,3.1273,1.6823436744580118,1
+C[N+]1(C)CCCCC1.[Cl-],3.1805,0.3452422769348818,1
+CCc1ccccc1,3.29205,0.1206899946920461,1
+CC(c1ccccc1)C,3.2988999999999997,0.15186257903462685,1
+Cc1cnc2c(c1)ccc(c2C(=O)O)Cl,3.3388,1.5074283553189385,1
+CCCOC(=O)NCCCN(C)C,3.6119,0.13590977228782125,1
+CCOP(=O)O,3.6347,0.01517916239248223,1
+Oc1ccccc1,3.6552,0.47607938439063624,1
+[O-]P(=O)OCC.[O-]P(=O)OCC.[O-]P(=O)OCC.[Al+3],3.6854,0.004121061936807558,1
+CC1CCC(C(C1)O)C(C)C,3.7948,8.944123306619971,1
+COc1ccc(cc1)N,3.8489,0.6065311188033274,1
+CCCCC(COC(=O)CCCCC(=O)OCC(CCCC)CC)CC,4.0479,1.2803383469734682,1
+CCCOC(=O)c1cc(O)c(c(c1)O)O,4.0716,1.4754838301646156,1
+CC(CCCC1(C)CCc2c(O1)c(C)c(c(c2C)OC(=O)C)C)CCCC(CCCC(C)C)C,4.2306,0.9982324982068121,1
+COc1ccc(cc1N=Nc1c(O)c(cc2c1cccc2)C(=O)Nc1cccc(c1)N(=O)=O)N(=O)=O,4.3084,0.25198686562669265,1
+Oc1ccc(nn1)O,4.4608,0.99911,0.1
+S=c1sc2c([nH]1)cccc2,4.4843,0.11685692276229762,1
+Clc1cc(N)c(c(n1)C(=O)O)Cl,4.8306,0.6002142403364729,1
+CNC(=N[N](=O)[O])NCC1COCC1,4.9008,0.13016999999999998,0.12
+COc1cc(OC)nc(n1)NC(=O)NS(=O)(=O)c1ncccc1C(=O)N(C)C,5.0877,0.2634147048496456,1
+OC(=O)CNCP(=O)(O)O,5.5597,0.7008374592406026,0.16666666666666666
+CCOc1ccc(cc1N)NC(=O)C,6.101,0.7403481944990059,1
+Nc1ccc(cc1)O,6.2863,0.7947444601921512,1
+NC(=S)NNC(=S)N,6.3038,0.009103354136383681,1
+NC(=O)c1cnccn1,6.4088,0.08617861868365052,1
+OC(=O)c1ccc(cc1N)N(=O)=O,6.5062,1.2631044559026148,1
+Oc1cc(O)c2c(c1)oc(c(c2=O)O)c1ccc(c(c1)O)O,6.7298,0.7655804043523278,1
+ClCC(=O)c1ccc(cc1)NC(=O)C,7.4653,0.3708051399423042,1
+O=C1OC(=O)c2c1cccc2,8.0005,0.7191946668280782,1
+CCCOC(=O)c1ccc(cc1)O,8.3241,1.5593988034815423,1
+CCOC(=O)COC(=O)c1ccccc1C(=O)OCC,8.9199,1.0111441770764438,1
+O=C1CCCCC1,9.2722,0.24153253639350966,1
+COC(=O)c1ccc(cc1)O,9.8589,0.663930513166199,1
+COC(=O)c1ccccc1C(=O)OC,10.3,0.5358141091230644,1
+OC1C2C(N(C)C)C(=O)C(=C(O)N)C(=O)C2(O)C(=O)C2=C(O)c3c(C(C12)(C)O)c(Cl)ccc3O,10.508,0.33751000000000003,0.6216216216216216
+OCC(C1OC(=O)C(=C1O)O)O,13.07315,74.73900000000006,0.23076923076923078
+OCCO,14.822,5.3945180903544765,1
+CCCCCCCCCCCCCCCCCC(=O)OCC(C1OCC(C1O)O)O,16.727,22.6939250474709,1
+[O-]S(=O)(=O)NC1CCCCC1.[Na+],17.901,0.18626027910642426,1
+O=C1NS(=O)(=O)c2c1cccc2,19.663,0.20088345882784658,1
+CCCCCCCCCCCC(=O)OCC(C1OCC(C1O)O)O,19.867,28.168388967981247,1
+CCOC(=O)c1ccccc1C(=O)OCC,19.956,0.83873574855164,1
+OC(=O)c1ccccc1N,20.06,1.02206863040127,1
+OCC(CO)O,74.739,1.2359643227930828,1
diff --git a/data/training-cv-1.id b/data/training-cv-1.id
new file mode 100644
index 0000000..074349d
--- /dev/null
+++ b/data/training-cv-1.id
@@ -0,0 +1 @@
+56d5e5662b72ed265a000001
diff --git a/data/training-cv-2.csv b/data/training-cv-2.csv
new file mode 100644
index 0000000..7cbbd67
--- /dev/null
+++ b/data/training-cv-2.csv
@@ -0,0 +1,636 @@
+SMILES,LOAEL_measured_median,LOAEL_predicted,Confidence
+ClC12C3C4(C(C1(Cl)Cl)(C1(C2(C3(Cl)C(C41Cl)(Cl)Cl)Cl)Cl)Cl)Cl,1.9566e-05,0.0018377000000000018,0.25
+ClC1=C(Cl)C2(C(C1(Cl)C1C2C2CC1C=C2)(Cl)Cl)Cl,2.7404e-05,0.0014286257712741353,1
+N#Cc1nn(c(c1S(=O)C(F)(F)F)N)c1c(Cl)cc(cc1Cl)C(F)(F)F,0.00013611,0.010768275686535727,1
+Clc1ccc2c(c1)[n+]([O-])nc(n2)n1cncc1,0.00020191,0.0703800730823712,1
+OC(=O)C(Oc1ccc(cc1)Oc1ncc(cc1Cl)C(F)(F)F)C,0.00027647,0.009584462064549125,1
+CCOP(=S)(SCSC(C)(C)C)OCC,0.00027736000000000004,0.0023959628464292207,1
+ClC1C2OC2C2C1C1(Cl)C(=C(C2(C1(Cl)Cl)Cl)Cl)Cl,0.00028896749999999995,0.0008133919013026461,1
+ClC1=C(Cl)C2(C(C1(Cl)C1C2C2CC1C1C2O1)(Cl)Cl)Cl,0.000295345,0.00042831779869634647,1
+CCSCCSP(=S)(OCC)OCC,0.00036443,0.001896468610059568,1
+CNC(=O)ON=CC(SC)(C)C,0.00052559,0.060919494369489686,1
+COC(=O)C(Oc1ccc(cc1)Oc1ccc(cc1Cl)Cl)C,0.00058619,0.09982005414868787,1
+CCSCSP(=S)(OCC)OCC,0.00061449,0.0007937147377159493,1
+OC1CCCCCc2cc(O)cc(c2C(=O)OC(CCC1)C)O,0.00062036,0.46407564001892226,1
+ClC1C=CC2C1C1(Cl)C(=C(C2(C1(Cl)Cl)Cl)Cl)Cl,0.000843785,0.0002385960642707865,1
+c1ccc(cc1)[Sn](c1ccccc1)c1ccccc1,0.00085711,0.6397057331757809,1
+CCOP(=O)(SC(CC)C)SC(CC)C,0.000872805,0.004304742760365683,1
+CCS(=O)CCSP(=O)(OC)OC,0.00089328,0.0013951101578154512,1
+ClC1CC2C(C1Cl)C1(C(C2(Cl)C(=C1Cl)Cl)(Cl)Cl)Cl,0.000939545,0.00013454529642362563,1
+COP(=S)(Oc1ccc(cc1)N(=O)=O)OC,0.00094982,0.00971358102445769,1
+Clc1c(Cl)c(Cl)c(c(c1Cl)Cl)Cl,0.0010183,0.10288014553454179,1
+CNC(=O)CSP(=S)(OC)OC,0.0010905,0.009515127939063834,1
+COP(=O)(SCCS(=O)(=O)CC)OC,0.0011438,0.0012475492886251487,1
+COC1CC(OC2C(C)C=CC=C3COC4C3(O)C(C=C(C4O)C)C(=O)OC3CC(CC=C2C)OC2(C3)C=CC(C(O2)C(CC)C)C)OC(C1OC1CC(OC)C(C(O1)C)O)C.COC1CC(OC(C1OC1CC(OC)C(C(O1)C)O)C)OC1C(C)C=CC=C2COC3C2(O)C(C=C(C3O)C)C(=O)OC2CC(CC=C1C)OC1(C2)C=CC(C(O1)C(C)C)C,0.0011546,0.004561050541923855,1
+ClC12C(Cl)(Cl)C3(C4(C1(Cl)C1(C2(Cl)C3(C4(C1(Cl)Cl)Cl)Cl)Cl)Cl)Cl,0.0012831,0.0018376999999999998,0.21428571428571427
+CCOP(=O)(N1CCSC1=O)SC(CC)C,0.0013411,0.013458067032651793,1
+O=C1CCCC(=O)C1C(=O)c1ccc(cc1[N+](=O)[O-])S(=O)(=O)C,0.0014146,0.012657810238506893,1
+CCOP(=S)(Oc1ccccc1C(=O)OC(C)C)NC(C)C,0.0014476,0.1865959227891729,1
+CCSCCSP(=O)(OC)OC,0.0015199,0.000892447632027103,1
+CCOc1cc(nc(n1)CC)OP(=S)(OC)OC,0.0015396,0.008735989693461706,1
+COC(=O)C=C(OP(=O)(OC)OC)C,0.0015615,0.0019374612836842897,1
+COC(=O)/C=C(/OP(=O)(OC)OC)\C,0.0015615,0.0023812687906506857,1
+OC(=O)c1ccccc1.CCC(C1OC2(C=CC1C)OC1CC=C(C)C(OC3CC(OC)C(C(O3)C)OC3CC(OC)C(C(O3)C)NC)C(C)C=CC=C3C4(C(C(=O)OC(C2)C1)C=C(C)C(C4OC3)O)O)C,0.001735715,0.0015985644724030843,1
+C1CCC(CC1)[Sn](n1ncnc1)(C1CCCCC1)C1CCCCC1,0.001811,0.008460298774188546,1
+ClC1C2(Cl)C3C4C5C1(Cl)C(C2(Cl)C5C3C1C4O1)(Cl)Cl,0.0018377,0.00020875483295948783,1
+CNC(=O)CCSCCSP(=O)(OC)OC,0.0018793,0.0033386848364462857,1
+COC1CC(OC2C(C)C=CC=C3COC4C3(O)C(C=C(C4O)C)C(=O)OC3CC(CC=C2C)OC2(C3)C=CC(C(O2)C(C)C)C)OC(C1OC1CC(OC)C(C(O1)C)NC(=O)C)C,0.00194425,0.0020143710247334714,1
+N#CC(c1cccc(c1)Oc1ccccc1)OC(=O)[C@H](C(C)C)Nc1ccc(cc1Cl)C(F)(F)F,0.0019884,0.0076981325245616,1
+CNC(=O)C=C(OP(=O)(OC)OC)C,0.0020165,0.006177167042632852,1
+COP(=O)(SC)N,0.0020549,0.33146588454802073,1
+COP(=S)(Oc1ccc(cc1)[N+](=O)[O-])OC,0.0020896,0.012983526722500053,1
+CSc1ccc(cc1C)OP(=S)(OC)OC,0.00210185,0.005320692177639907,1
+CO[C@H]1C[C@H](O[C@H]2[C@@H](C)C=CC=C3CO[C@H]4[C@]3(O)[C@@H](C=C([C@H]4O)C)C(=O)O[C@H]3C[C@@H](CC=C2C)O[C@]2(C3)C=C[C@@H]([C@H](O2)[C@H](CC)C)C)O[C@H]([C@@H]1O[C@H]1C[C@H](OC)[C@H]([C@@H](O1)C)O)C,0.0022907,0.011582167147627994,1
+O=C1CCCC(=O)C1C(=O)c1ccc(c(c1Cl)COCC(F)(F)F)S(=O)(=O)C,0.0023819,0.01161082890621692,1
+S=C1NCCN1,0.0024472,0.10060506855819094,1
+COC(=O)C(Oc1ccc(cc1)Oc1ncc(cc1Cl)C(F)(F)F)C,0.0026615,0.00019208559973307702,1
+CCOP(=S)(OCC)SCSc1ccc(cc1)Cl,0.0029166,0.005596997777393952,1
+C1CCN2C(C1)C1CCCCN1CC2,0.0029591,0.14662384480405752,1
+Fc1ccc(cc1)N(C(=O)COc1nnc(s1)C(F)(F)F)C(C)C,0.0033028,0.06832973356895798,1
+CCOP(=S)(Oc1ccc2c(c1)oc(=O)c(c2C)Cl)OCC,0.0033631,0.03300231995545067,1
+CNC(=O)Oc1cccc2c1OC(O2)(C)C,0.0035838,0.12101892517941863,1
+O[Sn](C1CCCCC1)(C1CCCCC1)C1CCCCC1,0.0036089,0.2530228410823332,1
+CCc1nn(c(c1Cl)C(=O)NCc1ccc(cc1)Oc1ccc(cc1)C)C,0.0039076,0.02662915316523073,1
+CCCCSP(=O)(SCCCC)SCCCC,0.0039744,0.10983758967815381,1
+CCOP(=S)(Oc1ncn(n1)c1ccccc1)OCC,0.0041492,0.02885177735998658,1
+CCOP(=O)(OC(=CCl)c1ccc(cc1Cl)Cl)OCC,0.0041717,0.008743085768806605,1
+CCOP(=O)(O/C(=C/Cl)/c1ccc(cc1Cl)Cl)OCC,0.0041717,0.014923975565331742,1
+Clc1nc(nc(n1)Cl)Nc1ccccc1Cl,0.0041739,0.09860886699679428,1
+Clc1cccc(n1)C(Cl)(Cl)Cl,0.0043308,0.2937201288867553,1
+N#CC(c1cccc(c1)Oc1ccccc1)OC(=O)C1C(C1(C)C)C(C(Br)(Br)Br)Br,0.0045112,0.05153306096689031,1
+COc1sc(=O)n(n1)CSP(=S)(OC)OC,0.00471335,0.0098233419774848,1
+N#CC(c1ccc(c(c1)Oc1ccccc1)F)OC(=O)C1C(C1(C)C)/C=C(/c1ccc(cc1)Cl)\Cl,0.0048983,0.02646060829035957,1
+CCOP(=S)(OCC)SCSP(=S)(OCC)OCC,0.0049418,0.00289671937964297,1
+CCOP(=O)(Oc1ccc(c(c1)C)SC)NC(C)C,0.0049447,0.009237493358223225,1
+N#CC(c1cccc(c1)Oc1ccccc1)OC(=O)C(C(C)C)Nc1ccc(cc1Cl)C(F)(F)F,0.004971,0.006735318057269352,1
+CCNc1nc(nc(n1)Cl)NC(C#N)(C)C,0.0051933,0.020162243183459532,1
+CC(Cc1ccc(cc1)C(C)(C)C)CN1CC(C)OC(C1)C,0.0056016,0.06867843129491749,1
+COP(=S)(Oc1nc(Cl)c(cc1Cl)Cl)OC,0.00620095,0.010805659777341832,1
+COC(=O)Nc1nc2c([nH]1)cc(cc2)S(=O)c1ccccc1,0.0063422,0.411498657480619,1
+ClCC(N1C(=O)c2c(C1=O)cccc2)SP(=S)(OCC)OCC,0.0063477,0.010270543883879418,1
+CCOP(=S)(Oc1ccc(cc1)N(=O)=O)OCC,0.0067295,0.007185721681550899,1
+OC(C(Cl)(Cl)Cl)(c1ccc(cc1)Cl)c1ccc(cc1)Cl,0.0067479,0.051697974947930006,1
+CNC(=O)Oc1cc(C)c(c(c1)C)N(C)C,0.0067481,0.05001223957485274,1
+COC(=O)N(C(=O)N1COC2(C(=N1)c1ccc(cc1C2)Cl)C(=O)OC)c1ccc(cc1)OC(F)(F)F,0.0068203,0.06269233640610042,1
+CCNc1nc(Cl)nc(n1)NC(C)(C)C,0.0069218,0.021265565272011896,1
+CCOP(=S)(Oc1ccc(cc1)[N+](=O)[O-])OCC,0.0070384,0.004952730534104147,1
+Cc1nn(c(c1/C=N/OCc1ccc(cc1)C(=O)OC(C)(C)C)Oc1ccccc1)C,0.0071176,0.004482607950821791,1
+Cc1nn(c(c1C=NOCc1ccc(cc1)C(=O)OC(C)(C)C)Oc1ccccc1)C,0.0073074,0.004959281689187692,1
+Clc1ccc(cc1)C(c1ccccc1Cl)(c1cncnc1)O,0.0075484,0.026071543860770922,1
+COP(=S)(SCn1nnc2c(c1=O)cccc2)OC,0.0076105,0.02623950605450441,1
+Fc1ccc(cc1)[Si](c1ccc(cc1)F)Cn1cncn1,0.0076575,0.015906048044563685,1
+N#CC(c1cccc(c1)Oc1ccccc1)OC(=O)C1C(C1(C)C)C=C(Br)Br,0.00781875,0.03782533095820241,1
+Fc1ccc(cc1)C(c1ccccc1Cl)(c1cncnc1)O,0.007943,0.003607424639634793,1
+N#Cc1nn(c(c1S(=O)CC)N)c1c(Cl)cc(cc1Cl)C(F)(F)F,0.0080563,0.0003454609239203949,1
+CCN(c1nc(cc(n1)C)OP(=S)(OC)OC)CC,0.0081878,0.016789556747265955,1
+Clc1ccc(cc1)OS(=O)(=O)c1ccc(cc1)Cl,0.0082464,0.09857847047965122,1
+Clc1cc(cnc1Nc1c(cc(c(c1[N+](=O)[O-])Cl)C(F)(F)F)[N+](=O)[O-])C(F)(F)F,0.008299399999999998,0.06208594993819649,1
+[O-][N+](=O)c1cc([N+](=O)[O-])c(c(c1)[N+](=O)[O-])C,0.0088055,0.07578338302194927,1
+CCCCOC(=O)C(Oc1ccc(cc1)Oc1ccc(cn1)C(F)(F)F)C,0.00885585,0.004322903998031862,1
+CSC(=O)c1c(nc(c(c1CC(C)C)C(=O)SC)C(F)(F)F)C(F)F,0.009043,0.204836351521947,1
+Clc1ccc(c(c1)Cl)C(Cn1cncn1)COC(C(F)F)(F)F,0.0091362,0.045190680683123034,1
+CCCN(C(=O)SCc1ccccc1)CCC,0.0091492,0.09176053975898289,1
+CON(C(=O)Nc1ccc(cc1)Cl)C,0.0093175,0.02920187736950783,1
+CCCCOC(=O)C(Oc1ccc(cc1)Oc1ccc(cc1F)C#N)C,0.0096257,0.03358046075314323,1
+N#C/N=C\1/SCCN1Cc1ccc(nc1)Cl,0.0098922,0.07580141426377905,1
+Cc1c(ccc(c1C1=NOCC1)S(=O)(=O)C)C(=O)c1cnn(c1O)C,0.0099068,0.014734981060753658,1
+CC1(C)CNC(=NC1)NN=C(C=Cc1ccc(cc1)C(F)(F)F)C=Cc1ccc(cc1)C(F)(F)F,0.0099095,0.020768175304755707,1
+COP(=O)(OC=C(Cl)Cl)OC,0.0100688,0.03379255796926954,1
+CCCSP(=O)(SCCC)OCC,0.010069,0.007591185181302402,1
+FC(c1ccc(cc1)C=CC(=NN=C1NCC(CN1)(C)C)C=Cc1ccc(cc1)C(F)(F)F)(F)F,0.010112,0.03790632591627435,1
+CCOC(=O)Nc1cccc(c1)OC(=O)Nc1ccccc1,0.010656,0.21736189550637955,1
+O=C(C1C(C1(C)C)C=C(C(F)(F)F)Cl)OCc1c(F)c(F)c(c(c1F)F)C,0.010986,0.014160325531627889,1
+O=C(C1C(C1(C)C)C=C(C(F)(F)F)Cl)OCc1cccc(c1C)c1ccccc1,0.011824,0.037433889489080996,1
+O=S1OCC2C(CO1)C1(C(C2(Cl)C(=C1Cl)Cl)(Cl)Cl)Cl,0.012287,0.00013519009625326088,1
+Clc1cc(Cl)c(c(c1O)Cc1c(O)c(Cl)cc(c1Cl)Cl)Cl,0.012288,0.12410261134282267,1
+CC(Oc1cc(c(cc1Cl)Cl)n1nc(oc1=O)C(C)(C)C)C,0.0124555,0.0639086556427057,1
+Clc1ccc(c(c1)Cl)n1c(nc2c(c1=O)cc(cc2)F)n1cncn1,0.01268,0.022113282062292138,1
+CCC1CCCC(OC2CCC(C(O2)C)N(C)C)C(C)C(=O)C2=CC3C(C2CC(=O)O1)C=C(C)C1C3CC(C1)OC1OC(C)C(C(C1OC)OC)OC,0.012735,0.039944372672364246,1
+CC1C=CC=C2COC3C2(O)C(C=C(C3O)C)C(=O)OC2CC(CC=C(C1)C)OC1(C2)CCC(C(O1)C)C,0.012862,0.004239636609434808,1
+COc1ccc(cc1NNC(=O)OC(C)C)c1ccccc1,0.012985,1.7165367738543584,1
+N#CC(c1cccc(c1)Oc1ccccc1)OC(=O)C(c1ccc(cc1)OC(F)F)C(C)C,0.01329,0.015620047142159268,1
+CCP(=S)(Sc1ccccc1)OCC,0.0133561,0.08166804167712995,1
+O=c1c(Cl)c(SCc2ccc(cc2)C(C)(C)C)cnn1C(C)(C)C,0.013701,0.07206503286773763,1
+CNP(=O)(Oc1ccc(cc1Cl)C(C)(C)C)OC,0.013712,0.11082661078831918,1
+NC1=C(Cl)C(=O)c2c(C1=O)cccc2,0.01392,0.868329775900756,1
+CCN(C(=O)SCC)C1CCCCC1,0.01393,0.09304421555376778,1
+CNC(=O)Oc1cccc2c1OC(C2)(C)C,0.01394355,0.03386892670757582,1
+O=C(C1C(C1(C)C)/C=C(/C(F)(F)F)\Cl)OCc1c(F)c(F)c(c(c1F)F)C,0.01409,0.014160325531627889,1
+CC(c1ccccc1)(C[Sn](O[Sn](CC(c1ccccc1)(C)C)(CC(c1ccccc1)(C)C)CC(c1ccccc1)(C)C)(CC(c1ccccc1)(C)C)CC(c1ccccc1)(C)C)C,0.01425,0.15228957837129897,1
+CCCN(c1c(cc(cc1[N+](=O)[O-])C(F)(F)F)[N+](=O)[O-])CC1CC1,0.014397,0.12927164240705638,1
+CC(c1ccc(cc1)CCOc1ncnc2c1cccc2)(C)C,0.014687,0.07483435604716758,1
+CCCCC(c1ccc(cc1Cl)Cl)(Cn1cncn1)O,0.014958,0.06939946763643491,1
+N#CC(c1ccc(cc1)Oc1ccccc1)OC(=O)C1C(C1(C)C)/C=C\C(=O)OC(C(F)(F)F)C(F)(F)F,0.01496,0.03345246303884768,1
+N#Cc1c(Cl)c(C#N)c(c(c1Cl)Cl)Cl,0.015043,0.02247529563549625,1
+N#CC(c1cc(C)c(cc1Cl)NC(=O)c1cc(I)cc(c1O)I)c1ccc(cc1)Cl,0.015081,0.0714173761733492,1
+Clc1cc(cnc1CCNC(=O)c1ccccc1C(F)(F)F)C(F)(F)F,0.015124,0.08012154105418477,1
+N#CN=S(=O)(C(c1ccc(nc1)C(F)(F)F)C)C,0.015292,0.04300237799322262,1
+CC(C1C2CCC1c1c2cccc1NC(=O)c1cn(nc1C(F)F)C)C,0.015303,0.1251424938908345,1
+Fc1ccc(cc1)[Si](c1ccc(cc1)F)(Cn1cncn1)C,0.015853,0.012163743291697346,1
+CN1CCC(CC1)C1CCN(CC1)C,0.016044,0.08536100236003388,1
+CCCCN(c1c(cc(cc1[N+](=O)[O-])C(F)(F)F)[N+](=O)[O-])CC,0.016106,0.08566071706073071,1
+CCOP(=S)(Oc1cc(C)nc(n1)C(C)C)OCC,0.016429,0.015095535744907507,1
+N#Cc1c(Cl)cccc1Cl,0.0165685,0.10209847219085816,1
+Fc1ccc(cc1)C1(Cn2cncn2)OC1c1ccccc1Cl,0.016679,0.02301344450990011,1
+CCOP(=S)(Oc1nc(Cl)c(cc1Cl)Cl)OCC,0.017114,0.002758033553865191,1
+BrC1COC(C1)(Cn1cncn1)c1ccc(cc1Cl)Cl,0.017185,0.028738293170172482,1
+CC(NC(=S)[S])CNC(=S)S[Zn],0.017255,0.2878835027623078,1
+CCN(C(=O)SCc1ccc(cc1)Cl)CC,0.0180385,0.022713862273005925,1
+COCC(N(c1c(C)csc1C)C(=O)CCl)C,0.018129,0.35716518615393833,1
+c1cc[n+]2c(c1)c1cccc[n+]1CC2,0.018481499999999998,0.09447726030618263,1
+CCc1nn(c(c1Cl)C(=O)NCc1ccc(cc1)C(C)(C)C)C,0.019469,0.006983350270874694,1
+CCCN(C(=O)n1cncc1)CCOc1c(Cl)cc(cc1Cl)Cl,0.019912,0.040413566467213516,1
+CCOC(=O)c1cn2nc(cc2nc1C)OP(=S)(OCC)OCC,0.0200875,0.11758320207076739,1
+C[n+]1ccc(cc1)c1cc[n+](cc1)C,0.020134,0.03242328770222657,1
+COP(=S)(SCN1C(=O)c2c(C1=O)cccc2)OC,0.020484,0.04607532127757082,1
+ClC=C,0.020801,0.045958000000000006,0.14285714285714285
+Clc1cccc(c1)c1ccccc1,0.021203,0.20305563255454476,1
+CNC(=O)ON=C(C(=O)N(C)C)SC,0.022348,0.024014096723382096,1
+CSC1=NC(C(=O)N1Nc1ccccc1)(C)c1ccccc1,0.0228,0.13132008923012195,1
+CCN(C(=O)C(=C(OP(=O)(OC)OC)C)Cl)CC,0.023024100000000002,0.004686062102400703,1
+COC(=O)N(c1ccccc1COc1ccn(n1)c1ccc(cc1)Cl)OC,0.023207,0.1302218719186941,1
+CCCCCCCCCCCCC1=C(OC(=O)C)C(=O)c2c(C1=O)cccc2,0.023407,0.3855554402628966,1
+OC(COc1cccc2c1c1ccccc1[nH]2)CNC(C)C,0.02346,0.6438307981194181,1
+O=C(NC(=O)c1ccccc1Cl)Nc1ccc(cc1)OC(F)(F)F,0.023557,0.1669839577595619,1
+CCOC(=O)C(Oc1ccc(cc1)Oc1nc2c(o1)cc(cc2)Cl)C,0.024877,0.04554329496654185,1
+CON(C(=O)Nc1ccc(c(c1)Cl)Cl)C,0.025091,0.012937987088412789,1
+CN(C(=S)S[Zn]SC(=S)N(C)C)C,0.02534245,0.1008090248545193,1
+O=C(NC(=O)c1c(F)cccc1F)Nc1ccc(cc1)Cl,0.025428,0.14085282088899825,1
+CCNc1nc(NCC)nc(n1)Cl,0.0255385,0.015573036780268973,1
+OC(=O)C(Oc1ccc(cc1C)Cl)C,0.025624,0.025906979856593612,1
+Clc1ccccc1CC(C1(Cl)CC1)(Cn1cncn1)O,0.025625,0.04618298292736014,1
+O=C(N(C)C)Nc1ccc(c(c1)Cl)Cl,0.025741,0.13386459164425232,1
+CCOC(=O)C(Oc1ccc(cc1)Oc1cnc2c(n1)ccc(c2)Cl)C,0.0257509,0.05446490228306457,1
+CC(OC(=O)C(c1ccc(cc1)Cl)(c1ccc(cc1)Cl)O)C,0.026532,0.0665911589485201,1
+N#CC(c1cccc(c1)Oc1ccccc1)OC(=O)C1C(C1(C)C)/C=C(/C(F)(F)F)\Cl,0.026676,0.007750118114458359,1
+O=C(C1C(C1(C)C)C=C(Cl)Cl)OCc1c(F)c(F)cc(c1F)F,0.026943,0.09185188449451615,1
+N#Cc1sc2=c(sc1C#N)c(=O)c1c(c2=O)cccc1,0.0269975,0.2028324421743077,1
+CCOC(=O)c1ccccc1C1=c2cc(C)c(cc2=[O]c2c1cc(C)c(c2)NCC)NCC,0.027054,0.3078986412939623,1
+CSCC(=NOC(=O)NC)C(C)(C)C,0.027483,0.060525207696953694,1
+Cc1nn(c(c1C(=O)c1ccc(cc1S(=O)(=O)C)C(F)(F)F)O)C,0.0276,0.026781932035424158,1
+CCOc1cc(ccc1N(=O)=O)Oc1ccc(cc1Cl)C(F)(F)F,0.027647,0.17351533161861185,1
+[O-][N+](=O)c1cc(C(=O)N)c(c(c1)[N+](=O)[O-])C,0.027758,0.06812382073970605,1
+N#CC(c1cccc(c1)Oc1ccccc1)OC(=O)C1C(C1(C)C)C=C(C(F)(F)F)Cl,0.027787,0.0077962240761942185,1
+C=CC1(C)OC(=O)N(C1=O)c1cc(Cl)cc(c1)Cl,0.027961,0.12861678755198092,1
+OC(=O)C(Oc1ccc(cc1)Oc1nc2c(o1)cc(cc2)Cl)C,0.028167,0.016368734114245876,1
+N#CC(c1ccc(c(c1)Oc1ccccc1)F)OC(=O)C1C(C1(C)C)C=C(Cl)Cl,0.028207,0.04048887978139598,1
+CSC(=NOC(=O)N(SN(C(=O)ON=C(SC)C)C)C)C,0.028211,0.023794313203711337,1
+CS/C(=N/OC(=O)N(SN(C(=O)O/N=C(/SC)\C)C)C)/C,0.028211,0.02821100000000001,1
+CC(N1C(=NC(C)(C)C)SCN(C1=O)c1ccccc1)C,0.028484,0.0324802498009358,1
+CCO[C@H]1[C@@H](OC)[C@H](O[C@@H]2C[C@@H]3[C@@H](C2)[C@@H]2C=C4[C@H]([C@@H]2CC3)CC(=O)O[C@@H](CC)CCC[C@@H]([C@H](C4=O)C)O[C@H]2CC[C@@H]([C@H](O2)C)N(C)C)O[C@H]([C@@H]1OC)C,0.028877,0.0022907000000000005,0.20238095238095238
+N#Cc1cc(Br)c(c(c1)Br)O,0.02889,0.029525068038902712,1
+CCOC(=O)C(Cc1cc(c(cc1Cl)F)n1nc(n(c1=O)C(F)F)C)Cl,0.029113,0.17322061752382273,1
+C#CCOC(=O)C(Oc1ccc(cc1)Oc1ncc(cc1F)Cl)C,0.029164,0.023744055289170382,1
+CC(N1/C(=N/C(C)(C)C)/SCN(C1=O)c1ccccc1)C,0.029466,0.031298297859973165,1
+COc1nc(Oc2cccc(c2C(=O)[O-])Oc2nc(OC)cc(n2)OC)nc(c1)OC.[Na+],0.030507,0.8625716733958936,1
+CON(C(=O)Nc1ccc(cc1)Br)C,0.0313005,0.0826654870796409,1
+COc1nc(C)nc(n1)N(C(=O)NS(=O)(=O)c1ccccc1C(=O)OC)C,0.031614,0.39555401975579213,1
+Cc1ccc2c(c1)nc1c(n2)sc(=O)s1,0.032011,0.07754998593281597,1
+Fc1ccc(cc1)NC(=O)c1cccc(n1)Oc1cccc(c1)C(F)(F)F,0.032155,0.08325777980558183,1
+CCCn1c(OCCC)nc2c(c1=O)cc(cc2)I,0.032241,0.11240974023972475,0.10810810810810811
+CC(C(=O)O)Oc1cc(Cl)c(cc1Cl)Cl,0.032281,0.04798039542219823,1
+COc1cc(OC)nc(n1)NC(=O)NS(=O)(=O)c1ncccc1C(F)(F)F,0.032652,1.0857331436704296,1
+CN1CN(C)CSC1=S,0.03266,0.05748016757235302,1
+CCC1CCCC(OC2CCC(C(O2)C)N(C)C)C(C)C(=O)C2C(CC(=O)O1)C1CCC3C(C1C2)CC(C3)OC1CC(C)C(C(C1OC)OC)OC,0.032697,0.033780681313069064,1
+ClCC1CN(C(=O)C1Cl)c1cccc(c1)C(F)(F)F,0.033160999999999996,0.04962197428615905,1
+O=C(C(Oc1ccc(cc1)Oc1cnc2c(n1)ccc(c2)Cl)C)OCCON=C(C)C,0.033793,0.027764738721926648,1
+Fc1ccc(cc1)C(c1ccccc1F)(Cn1cncn1)O,0.033854,0.02042341203467295,1
+CN(/C=N/c1ccc(cc1C)C)/C=N/c1ccc(cc1C)C,0.034082,0.03313272471112565,1
+CCCCC(c1ccc(cc1)Cl)(Cn1cncn1)C#N,0.034179,0.1573137715225342,1
+CN(C=Nc1ccc(cc1C)C)C=Nc1ccc(cc1C)C,0.034423,0.04229763267890287,1
+CCOP(=S)(SCn1c(=O)oc2c1ccc(c2)Cl)OCC,0.0345288,0.0026122558284499492,1
+ClC(=CCOc1cc(Cl)c(c(c1)Cl)OCCCOc1ccc(cn1)C(F)(F)F)Cl,0.034819,0.041351932036622144,1
+CCOCn1c(c2ccc(cc2)Cl)c(c(c1C(F)(F)F)Br)C#N,0.0350825,0.07541296103937431,1
+Fc1ccc(c(c1)c1ccc(c(c1)Cl)Cl)NC(=O)c1cn(nc1C(F)F)C,0.035609999999999996,0.030893136552665106,1
+CCCSP(=S)(Oc1ccc(cc1)SC)OCC,0.035665,0.0028718934687450366,1
+CCC(C(=O)OC1=C(C(=O)OC21CCCCC2)c1ccc(cc1Cl)Cl)(C)C,0.035787,0.021288285553364893,1
+C#CCOC(c1ccc(cc1)Cl)C(=O)NCCc1ccc(c(c1)OC)OCC#C,0.036904,0.15682428021078798,1
+CC(Cc1ccccc1)N,0.036981,0.35820983509172727,1
+OC(C(C)(C)C)C(n1ncnc1)Cc1ccc(cc1)Cl,0.037441,0.11007742726118461,1
+CCN(c1c(cc(cc1N(=O)=O)C(F)(F)F)N(=O)=O)CC(=C)C,0.037508,0.11185125402156088,1
+Clc1c(O)c(Cl)c(c(c1Cl)Cl)Cl,0.037546,0.03648811467752711,1
+CC(OP(=S)(OC(C)C)SCCNS(=O)(=O)c1ccccc1)C,0.037735,0.003483461373934047,1
+Clc1ccc(cc1)c1ccccc1NC(=O)c1cccnc1Cl,0.037878,0.5187891691933314,1
+Clc1ccc(c(c1)Cl)C1(OCCO1)Cn1cncn1,0.0379825,0.06615505637954623,1
+CCOC(=O)CSc1nc(nn1C(=O)N(C)C)C(C)(C)C,0.038167,0.2753219879598893,1
+ClC(C(SN1C(=O)C2C(C1=O)CC=CC2)(Cl)Cl)Cl,0.038675,0.3297078612771189,0.42857142857142855
+CC(C(c1cncnc1)(c1ccc(cc1)OC(F)(F)F)O)C,0.038746,0.06614807725138554,1
+OC(=O)COc1cc(Cl)c(cc1Cl)Cl,0.039142,0.06689305156364092,1
+CCOP(=S)(Oc1nn(c(n1)Cl)C(C)C)OCC,0.039842,0.014721427793486716,1
+O=C(NC(=O)c1c(F)cccc1F)Nc1cc(Cl)c(cc1Cl)OC(C(C(F)(F)F)F)(F)F,0.03991,0.09119051915428844,1
+CNC(=S)S,0.040113,0.1167836808123427,1
+CCCOC/C(=N\c1ccc(cc1C(F)(F)F)Cl)/n1cncc1,0.040492,0.013524031475323772,1
+CC(N(C(=O)SCC(=C(Cl)Cl)Cl)C(C)C)C,0.041029,0.034659116233835524,1
+O=C(CC(C)(C)C)OC1=C(C(=O)OC21CCCC2)c1c(C)cc(cc1C)C,0.0414325,0.06716323023627083,1
+OC1(Cn2ncnc2)C(CCC1(C)C)Cc1ccc(cc1)Cl,0.0420535,0.04968985196582714,1
+COP(=S)(Oc1ccc(c(c1)C)[N+](=O)[O-])OC,0.0424911,0.0019341023111427472,1
+CCOC(=O)CCN(C(C)C)SN(C(=O)Oc1cccc2c1OC(C2)(C)C)C,0.042628,0.010231171120921501,1
+CC(Cc1ccc(cc1)C(C)(C)C)CN1CCCCC1,0.043261,0.0035981520453534288,1
+Nc1n[nH]cn1,0.0446005,0.04204987250872469,0.2727272727272727
+Nc1ncn[nH]1,0.0446005,0.04204987250872469,0.2727272727272727
+[S-]C(=S)NCCNC(=S)[S-].[Zn+2],0.044607,0.18364725436604454,1
+CCSC(=O)N1CCCCCC1,0.044874,0.1222518161386908,1
+O=C1OC(C(=O)N1Nc1ccccc1)(C)c1ccc(cc1)Oc1ccccc1,0.04514,0.046052880991559915,1
+ClC(C(c1ccc(cc1)Cl)c1ccc(cc1)Cl)(Cl)Cl,0.045488125000000004,0.07176584693998721,1
+S=C1NCCCN1,0.045617,0.01384383462435663,1
+ClCC=CCl,0.045958,0.07420608230927385,0.14285714285714285
+CCOC(=O)Cn1c(=O)sc2c1c(Cl)ccc2,0.046003,0.17747526199455307,1
+N#CC(c1c(Cl)ccc(c1Cl)n1ncc(=O)[nH]c1=O)c1ccc(cc1)Cl,0.04661,0.049596091576390555,1
+CN(C(=S)SSC(=S)N(C)C)C,0.04783,0.06284942476138784,1
+Cc1cccc(c1O)C,0.049114,0.2266694688461277,1
+CCC(C(=O)NCc1ccccc1)Oc1ccc(c(c1)C(F)(F)F)F,0.049813,0.051176608956587995,1
+COC(=O)Nc1nc2c([nH]1)cc(cc2)Sc1ccccc1,0.050109,0.13102940755311185,1
+CCSC(CC1CC(=O)C(C(=O)C1)C(=NOCC)CCC)C,0.050568,0.12460566123801867,1
+C#CCN1C(=O)COc2c1cc(c(c2)F)N1C(=O)C2=C(C1=O)CCCC2,0.0508,0.0033028000000000007,0.1111111111111111
+CNC(=O)Oc1cc(C)c(c(c1)C)C,0.051749,0.05645466144779804,1
+CNC(=O)Oc1cccc(c1)/N=C/N(C)C,0.051976,0.0281607580180568,1
+CN(C(=O)Oc1nc(nc(c1C)C)N(C)C)C,0.0520385,0.06499656410240343,1
+O=N(=O)c1ccc(c(c1)N)C,0.052579,0.23093661681883104,1
+CCO/N=C(\C1=C(O)CC(CC1=O)C1CCCSC1)/CCC,0.052847,0.07824045781528054,1
+CC(C(c1ccc(cc1)Cl)(Cn1ncnc1)O)C1CC1,0.05326,0.02683258277280798,1
+O=C(N/C(=N\OCC1CC1)/c1c(F)c(F)ccc1C(F)(F)F)Cc1ccccc1,0.053352,0.0655305528463518,1
+NC(=NCCCCCCCCNCCCCCCCCN=C(N)N)N,0.053436,0.05681533336655957,1
+C=CCOC(c1ccc(cc1Cl)Cl)Cn1cncc1,0.053503,0.013892412099187719,1
+COCN(c1c(CC)cccc1CC)C(=O)CCl,0.0537505,0.5542194098795326,1
+CNC1=C(c2cccc(c2)C(F)(F)F)C(=O)C(O1)c1ccccc1,0.055205,0.11291678635354624,1
+CCOc1ccc2c(c1)C(=CC(N2)(C)C)C,0.055221,0.40257887380953766,1
+O=C(c1ccc(cc1S(=O)(=O)C)C(F)(F)F)c1cnoc1C1CC1,0.055661,0.02921225398411233,1
+CCOC(=O)COC(=O)c1cc(ccc1[N+](=O)[O-])Oc1ccc(cc1Cl)C(F)(F)F,0.055835,0.6653456368017054,1
+COc1nc(nc(n1)C)NC(=O)[N-]S(=O)(=O)c1cc(I)ccc1C(=O)OC.[Na+],0.056118,0.1667382913178488,1
+CNC(=O)Oc1cccc(c1)N=CN(C)C,0.056496,0.042368706344005004,1
+CCOC(=O)C(c1ccc(cc1)Cl)(c1ccc(cc1)Cl)O,0.056583,0.056908274196164975,1
+OC(=O)COc1ccc(cc1C)Cl,0.0573225,0.08764079632329055,1
+CCOCCN(C(=C(C)C)c1ccccc1)C(=O)CCl,0.05747,0.5236237897070305,1
+CCOC(=O)NCCOc1ccc(cc1)Oc1ccccc1,0.0575765,0.1481923022338741,1
+CN(C(CN1c2ccccc2Sc2c1cccc2)C)C,0.058365,0.08967187496473839,1
+CC1COC(O1)(Cn1cncn1)c1ccc(cc1Cl)Oc1ccc(cc1)Cl,0.059321,0.11588976459334906,1
+N#CC(c1cccc(c1)Oc1ccccc1)OC(=O)C(c1ccc(cc1)Cl)C(C)C,0.059538,0.014939388340130984,1
+CCN(c1c(cc(cc1[N+](=O)[O-])C(F)(F)F)[N+](=O)[O-])CC(=C)C,0.0595625,0.02739652405092243,1
+N#CC(c1cccc(c1)Oc1ccccc1)OC(=O)C1C(C1(C)C)(C)C,0.060099,0.027769720527461333,1
+CC(OC(=O)C(c1ccc(cc1)Br)(c1ccc(cc1)Br)O)C,0.0606145,0.016978707712501727,1
+C=CC=CCC1=C(C)C(CC1=O)OC(=O)C1C(C1(C)C)C=C(C)C.C=CC=CCC1=C(C)C(CC1=O)OC(=O)C1C(C1(C)C)C=C(C(=O)OC)C,0.06135,0.16209736680242204,1
+Clc1ccccc1c1nnc(nn1)c1ccccc1Cl,0.06152150000000001,0.1490562329002087,1
+COC(=O)c1cccc(c1S(=O)(=O)NC(=O)Nc1nc(OCC(F)(F)F)nc(n1)N(C)C)C,0.062141,0.04009749227281286,1
+CCNc1nc(SC)nc(n1)NC(C)(C)C,0.062149,0.012447117278175216,1
+[O-][N+](=O)c1cc(cc(c1)[N+](=O)[O-])[N+](=O)[O-],0.062458,0.03777610386743243,1
+Clc1cc(ccc1Oc1ccc(c(c1)C(=O)NS(=O)(=O)C)[N+](=O)[O-])C(F)(F)F,0.062678,0.17688635136038366,1
+Clc1cc(F)c(cc1C(=O)NS(=O)(=O)N(C(C)C)C)n1c(=O)cc(n(c1=O)C)C(F)(F)F,0.062693,0.029112999999999997,0.10416666666666667
+COc1nc(nc(n1)C)NC(=O)NS(=O)(=O)c1ccccc1Cl,0.062889,0.1286890696183696,1
+O=C(NS(=O)(=O)c1c(C)cccc1C(=O)O)Nc1nc(OCC(F)(F)F)nc(n1)N(C)C,0.063963,0.11189816516207657,1
+COc1nc(nc(n1)C)NC(=O)NS(=O)(=O)c1ccsc1C(=O)OC,0.064534,0.12547824426808382,1
+O=C(N(C)C)Nc1ccc(c(c1)Cl)n1nc(oc1=O)C(C)(C)C,0.064937,0.012471412310884751,1
+CCCCN(SN(C(=O)Oc1cccc2c1OC(C2)(C)C)C)CCCC,0.065695,0.012234193035874173,1
+[O-][N+](=O)NC1=NCCN1Cc1ccc(nc1)Cl,0.066494,0.06983499732815489,1
+O=C(NC(=O)c1c(F)cccc1F)Nc1cc(Cl)c(c(c1F)Cl)F,0.06691,0.08283471456455249,1
+CSc1nnc(c(=O)n1N)C(C)(C)C,0.067199,0.01370099999999999,0.11538461538461539
+O=C(NC(=O)c1c(F)cccc1F)Nc1ccc(c(c1)Cl)OC(C(OC(F)(F)F)F)(F)F,0.06758600000000001,0.11435801991711596,1
+CCOc1ccc(cc1)C(COCc1cccc(c1)Oc1ccccc1)(C)C,0.068395,0.12256530014835244,1
+C#CCOS(=O)OC1CCCCC1Oc1ccc(cc1)C(C)(C)C,0.06905,0.10068431155461997,1
+CCO/N=C(/C1=C(O)CC(CC1=O)c1c(C)cc(cc1C)C)\CC,0.069817,0.14736033883141783,1
+CO/N=C(/c1ccccc1COc1cc(C)ccc1C)\C(=O)NC,0.070468,0.6726718419351129,1
+COc1cc(OC)n2c(n1)nc(n2)S(=O)(=O)Nc1c(Cl)ccc(c1Cl)C,0.071727,0.3443644563338727,1
+OC(=O)COc1nc(Cl)c(cc1Cl)Cl,0.07213454999999999,0.021538123048105567,1
+CCCN(c1c(cc(cc1[N+](=O)[O-])S(=O)(=O)N)[N+](=O)[O-])CCC,0.07218,0.08095712387333837,1
+CCN1CCN(CC1)c1cc2c(cc1F)c(=O)c(cn2C1CC1)C(=O)O,0.072344,0.3330752569146831,0.5862068965517241
+Nc1ccc(cc1)Cl,0.072508,0.2257342310477128,1
+CO/N=C(\c1ccccc1CO/N=C(/c1cccc(c1)C(F)(F)F)\C)/C(=O)OC,0.072728,0.15910843769893582,1
+O=C(N(C)C)Nc1cccc(c1)C(F)(F)F,0.073957,0.02114633136389124,1
+OC(C(C)(C)C)C(n1cncn1)Oc1ccc(cc1)c1ccccc1,0.074093,0.2314082998077251,1
+CCCSc1ccc2c(c1)[nH]c(n2)NC(=O)OC,0.075377,0.19863545527695797,1
+Cn1nc(c(c1)C(=O)Nc1cccc2c1C1CCC2C1=C(Cl)Cl)C(F)F,0.075835,0.06540091325358338,1
+CCNc1nc(NC(C)C)nc(n1)Cl,0.077892,0.09557547621401412,1
+N#C/N=C(/N(Cc1ccc(nc1)Cl)C)\C,0.07859,0.024151860196621765,1
+CC(c1cc(ccc1O)C(c1ccc(c(c1)C(C)C)O)(C)C)C,0.080014,0.4337913188388365,1
+C=CCC1=C(C)C(CC1=O)OC(=O)C1C(C1(C)C)C=C(C)C,0.081016,0.09459242464095385,1
+NC(=N)NCCCCCCCCNC(=N)N,0.08102,0.12282753342910002,1
+O=C(C1=C(C)OCCS1)Nc1ccccc1,0.0811745,0.11813306239560711,1
+Clc1cc(cnc1CNC(=O)c1c(Cl)cccc1Cl)C(F)(F)F,0.082121,0.015899699701777743,1
+CNC(=O)Oc1cc(C)c(c(c1)C)SC,0.0827735,0.01745439339699323,1
+O=C(c1cccc(c1C(=O)NC(CS(=O)(=O)C)(C)C)I)Nc1ccc(cc1C)C(C(F)(F)F)(C(F)(F)F)F,0.0827975,0.1433768668260628,1
+COC(=O)Nc1cccc(c1)OC(=O)Nc1cccc(c1)C,0.083248,0.04124176665314473,1
+CCCN(c1c(cc(c(c1[N+](=O)[O-])N)C(F)(F)F)[N+](=O)[O-])CCC,0.08393,0.1493006243572841,1
+OC(C(C)(C)C)C(n1ncnc1)Oc1ccc(cc1)Cl,0.084527,0.08858310655989451,1
+O=C(C(C)(C)C)C(n1ncnc1)Oc1ccc(cc1)Cl,0.085107,0.05407217031419339,1
+CCCC(=C1C(=O)CC(CC1=O)C1CCCSC1)NOCC,0.08603,0.029427973343164302,1
+Cn1cc(c2cccc(c2)C(F)(F)F)c(=O)c(c1)c1ccccc1,0.08730199999999999,0.06351307941770289,1
+CC(NC(=O)N1CC(=O)N(C1=O)c1cc(Cl)cc(c1)Cl)C,0.08783250000000001,0.06762698562465963,1
+CC(=O)Nc1cc(NS(=O)(=O)C(F)(F)F)c(cc1C)C,0.088948,0.8563488390111477,1
+COCC(=O)Nc1cc(ccc1NC(=NC(=O)OC)NC(=O)OC)Sc1ccccc1,0.08959,0.14714194060705973,1
+CCCN(C(=O)SCC)CCC,0.0897945,0.0385202690181602,1
+COc1cc(ccc1OC)/C(=C/C(=O)N1CCOCC1)/c1ccc(cc1)Cl,0.0902395,0.16194822085407576,1
+CCC(=O)Nc1ccc(c(c1)Cl)Cl,0.09171,0.2762565955009296,1
+N#CC(c1ccccc1)(Cn1cncn1)CCc1ccc(cc1)Cl,0.092038,0.08788613792301608,1
+Clc1ccc2c(c1)ncc(n2)Oc1ccc(cc1)OC(C(=O)OCC1CCCO1)C,0.092103,0.04323944778006104,1
+CNC(=O)ON=C(SC)C,0.092474,0.04008680217571634,1
+NC(=O)c1c(Cl)cccc1Cl,0.092619,0.20337174464044985,1
+Clc1ccc(c(c1)Cl)NC(=O)C1(CC1)C(=O)O,0.093032,0.18680950312249067,1
+Clc1cc(Cl)cc(c1)C1(CO1)CC(Cl)(Cl)Cl,0.093625,0.06118175683822364,1
+ClC(=CC1C(C1(C)C)C(=O)OCc1cccc(c1)Oc1ccccc1)Cl,0.095836,0.11949553937058968,1
+OC(=O)C(Oc1ccc(cc1Cl)Cl)C,0.0967835,0.03387956718268448,1
+[O-][N+](=O)/N=C/1\NCCN1Cc1ccc(nc1)Cl,0.097395,0.09059586582208207,1
+NC(=N)NCCCCCCCCCCCCOC(=O)C,0.1016,0.08664971026374407,1
+OC1CC2(O)CC(O)C(C(O2)(C)CC(C=CC=CC=CC=CCC(OC(=O)C=CC2C(C1)(C)O2)C)OC1(C)OC(C)C(C(C1O)N)O)C(=O)O,0.10172,0.41522212752861354,1
+COP(=O)(NC(=O)C)SC,0.1023645,0.020049393739713695,1
+COc1ncc(c2n1nc(n2)NS(=O)(=O)c1c(cccc1C(F)(F)F)OCC(F)F)OC,0.10344,0.23889028194719353,1
+COCc1c(F)c(F)c(c(c1F)F)COC(=O)C1C(C1(C)C)/C=C/C,0.10573,0.03252106704823217,1
+[O-][N+](=O)c1cnc(n1C)C,0.10629,0.4258006458906727,1
+CCOC(=O)C(OC(=O)c1cc(ccc1N(=O)=O)Oc1cc(ccc1Cl)C(F)(F)F)C,0.10828,0.08241492749141009,1
+CCOC(=O)C(OC(=O)c1cc(ccc1[N+](=O)[O-])Oc1ccc(cc1Cl)C(F)(F)F)C,0.10828,0.2386906583992992,1
+COc1c(OC)cc(c(c1OC)C(=O)c1c(OC)ncc(c1C)Cl)C,0.108388,0.47251185201133056,1
+S=C1NCCNC(=S)S[Mn+2]S1,0.10856,0.039604469134128406,1
+ClCC(=O)N(c1ccccc1)C(C)C,0.10865,0.0636191888897636,1
+O=C1CCCC(=O)C1C(=O)c1ccc(cc1Cl)S(=O)(=O)C,0.11010835,0.005162002756685888,1
+CCCN(CC1COC2(O1)CCC(CC2)C(C)(C)C)CC,0.11029,1.3278,0.1
+O=C1N(c2cc(Cl)cc(c2)Cl)C(=O)C2(C1(C)C2)C,0.1108605,0.10470126815637591,1
+COC(=O)c1c(nc(c(c1CC(C)C)C1=NCCS1)C(F)(F)F)C(F)F,0.11151,0.06043692115939849,1
+Oc1ccc(c(c1)C)C,0.1146,0.27719238323836526,1
+Clc1ccc(cc1)CCC(C(C)(C)C)(Cn1cncn1)O,0.115167,0.05680153787091011,1
+CNc1cnn(c(=O)c1Cl)c1cccc(c1)C(F)(F)F,0.1152575,0.09752409298962122,1
+N#Cc1c(N)nc(nc1N)NC1CC1,0.11566,0.1009617149303171,1
+CC(N(c1c(cc(cc1N(=O)=O)S(=O)(=O)N)N(=O)=O)C(C)C)C,0.11817,0.41913381480648365,1
+CNC(=O)O/N=C(\SC)/C,0.11837,0.05612717639974856,1
+Nc1ccc(cc1)S(=O)(=O)Nc1nc(C)cc(n1)C,0.11856,0.7364137182398955,1
+CCN(c1c(cc(cc1[N+](=O)[O-])C(F)(F)F)[N+](=O)[O-])Cc1c(F)cccc1Cl,0.11856,0.07834564341936183,1
+COc1cc(ccc1OC)C(=CC(=O)N1CCOCC1)c1ccc(cc1)Cl,0.11937,0.09050508187876836,1
+CCCCc1c(=O)nc([nH]c1C)NCC,0.11945,0.20934840608954194,1
+COC(=O)NC(=S)Nc1ccccc1NC(=S)NC(=O)OC,0.12412500000000001,0.2909002941141425,1
+c1coc(c1)c1nc2c([nH]1)cccc2,0.12487,0.14792895919683197,1
+CN(C(=O)C(c1ccccc1)c1ccccc1)C,0.12536,0.23028276742620554,1
+CCOc1cc(ccc1[N+](=O)[O-])Oc1ccc(cc1Cl)C(F)(F)F,0.12856,0.11342255257944955,1
+[O-][N+](=O)/N=C(\NC)/NCc1cnc(s1)Cl,0.13017,1.4984994797645517,1
+Clc1c(ccc(c1N)[N+](=O)[O-])Oc1ccccc1,0.13224349999999999,0.45951640184534837,1
+OC(C(C)(C)C)C(=Cc1ccc(cc1)Cl)n1ncnc1,0.13507,0.18548801442829876,1
+CCNC(=O)NC(=O)/C(=N\OC)/C#N,0.135735,0.15289,1
+O=C(Nc1cnns1)Nc1ccccc1,0.13621,0.07683410063574432,1
+CCc1ccc(cc1)C(=O)NN(C(C)(C)C)C(=O)c1cc(C)cc(c1)C,0.13674999999999998,1.1179092021424053,1
+CN1CC2CC1CN2c1cc2c(cc1F)c(=O)c(cn2C1CC1)C(=O)O,0.13991,0.2090946529245896,0.5862068965517241
+OCC(CCl)O,0.14067559999999998,14.497001490430202,1
+COC(=O)C(N(c1c(C)cccc1C)C(=O)Cc1ccccc1)C,0.14136,0.23748560914584088,1
+COc1nc(C)nc(n1)N(C(=O)NS(=O)(=O)c1ccccc1C(=O)O)C,0.14422,0.14146003950986155,1
+ClC(=C)Cl,0.14441,0.010100837249467656,0.1
+CC(=O)O.CCCCCCCCCCCCNC(=N)N,0.14612,0.06315546914112784,1
+CON=C(c1ccccc1CON=C(c1cccc(c1)C(F)(F)F)C)C(=O)OC,0.14693,0.11246649181328962,1
+COC(CCCC(CC=CC(=CC(=O)OC(C)C)C)C)(C)C,0.14816,0.8558928058794961,1
+c1scc(n1)c1nc2c([nH]1)cccc2,0.14907,0.16697452985801875,1
+CC(N1C(=O)c2ccccc2NS1(=O)=O)C,0.14983,0.576112265206655,1
+N#CC(c1cccc(c1)Oc1ccccc1)OC(=O)C1C(C1(C)C)C=C(Cl)Cl,0.150135,0.03037702295535186,1
+Cc1cccc2c1n1cnnc1s2,0.150605,0.3205809677156071,1
+ClC(SN1C(=O)c2c(C1=O)cccc2)(Cl)Cl,0.15173999999999999,0.21509597972458702,1
+CON=C(c1ccc(cc1Cl)Cl)Cc1cccnc1,0.15246,0.0403255210062426,1
+CCNC(=O)NC(=O)C(=NOC)C#N,0.15289,0.13464656029769195,1
+Clc1ccc(c(c1)Cl)C=C(C(C(C)(C)C)O)n1cncn1,0.15327,0.1239792738735501,1
+CCC(Nc1c(cc(cc1[N+](=O)[O-])C(C)(C)C)[N+](=O)[O-])C,0.153385,0.055800253302791696,1
+COC=C(c1ccccc1Oc1ncnc(c1)Oc1ccccc1C#N)C(=O)OC,0.15432,0.21541160679805005,1
+COP(=S)(Oc1cc(Cl)c(cc1Cl)Cl)OC,0.1555,0.009294755343743084,1
+CCCCCCCCc1cc(N(=O)=O)c(c(c1)N(=O)=O)OC(=O)C=CC,0.15642,0.4237752587535801,1
+Cc1nc(Nc2ccccc2)nc(c1)C1CC1,0.15802,0.5553748019083816,1
+CCOC(=O)CN(c1c(CC)cccc1CC)C(=O)CCl,0.16036,0.11266421901438851,1
+CC(OC(=O)Nc1ccccc1)C,0.16182,1.002547247423522,1
+c1ccc(cc1)Nc1ccccc1,0.16546,0.45448822034538994,1
+C#CC(NC(=O)c1cc(Cl)cc(c1)Cl)(C)C,0.16593,0.11372565702525209,1
+Cc1ccc(c2c1cccc2)C,0.17283,0.13504143399977772,1
+Clc1cc(Cl)c(cc1n1nc(n(c1=O)C(F)F)C)NS(=O)(=O)C,0.17304,0.02384153039577781,1
+COC(=O)c1ccc(cc1C1=NC(C(=O)N1)(C)C(C)C)C,0.17341,0.40180569039443664,1
+CNC(=O)N(c1nnc(s1)C(C)(C)C)C,0.1752,0.15654919233821035,0.4
+CCCCCCC(c1cc(cc(c1OC(=O)/C=C/C)[N+](=O)[O-])[N+](=O)[O-])C,0.17563,0.3228827670672102,1
+CCCCCCCCCC[N+](CCCCCCCCCC)(C)C.[Cl-],0.17676,1.1435662547735692,1
+CCCC1COC(O1)(Cn1cncn1)c1ccc(cc1Cl)Cl,0.176786,0.04916038048782871,1
+N#Cc1cc(C)c(c(c1)C(=O)NC)NC(=O)c1cc(nn1c1ncccc1Cl)Br,0.17901,0.02589916243307784,1
+COCC(=O)N(c1c(C)cccc1C)N1CCOC1=O,0.17966,0.14697994498463737,1
+CC1=NNC(=O)N(C1)/N=C/c1cccnc1,0.18092,0.5714087517689246,1
+C#CCC1=C(C)C(CC1=O)OC(=O)C1C(C1(C)C)C=C(C)C,0.18558899999999998,0.10552519923419938,1
+O=N(=O)c1ccc(c(c1)N(=O)=O)C,0.18668,0.08470842491190124,1
+ClCC(=O)N(c1c(C)cccc1C)Cn1cccn1,0.18829800000000002,0.14724882250904567,1
+N#CCNC(=O)c1cnccc1C(F)(F)F,0.19244,0.5428266925258607,1
+OC1CN(C(=O)N1c1nnc(s1)C(C)(C)C)C,0.19507,0.17520000000000005,0.4
+O=c1nc(N(C)C)n(c(=O)n1C1CCCCC1)C,0.19817,0.5036400000000001,0.16666666666666666
+COc1nc(nc(n1)C)NC(=O)NS(=O)(=O)c1ccccc1CCC(F)(F)F,0.200175,0.07798826417496972,1
+Nc1ccc(c(c1)N)O,0.20138,1.456457812343639,1
+Cn1nc(c(c1)C(=O)Nc1ccccc1C1CC1C1CC1)C(F)F,0.2022,0.04576732199933958,1
+O=C(NS(=O)(=O)c1ccccc1C(=O)OC1COC1)Nc1nc(C)cc(n1)C,0.20423,0.1511241493249887,1
+CO/C=C(\c1ccccc1Oc1ncnc(c1)Oc1ccccc1C#N)/C(=O)OC,0.20427,0.1649921478439711,1
+ClC=C(c1cc(Cl)c(cc1Cl)Cl)OP(=O)(OC)OC,0.20494,0.00468018397548797,1
+CC(=CC1C(C1(C)C)C(=O)OCc1coc(c1)Cc1ccccc1)C,0.2068305,0.24950799740892696,1
+ClCC(=O)N(c1c(CC)cccc1CC)CNC(=O)C,0.21058,0.2652816115339773,1
+CCOCN(c1c(C)cccc1CC)C(=O)CCl,0.21666999999999997,0.1417567751129022,1
+CC(c1ccc(cc1)O)(c1ccc(cc1)O)C,0.21902,0.3883578995493014,1
+CC(Nc1nc(NC(C)C)nc(n1)Cl)C,0.219845,0.06538338226462309,1
+Fc1ccc(cc1)C(=O)CCCN1CCN(CC1)c1ccccn1,0.221446,0.3201791486752209,1
+COCC(=O)N(c1c(C)cccc1C)C(C(=O)OC)C,0.22375,0.16194144266566238,1
+Nc1ccc2c(c1)nc1c(c2)ccc(c1)N,0.22462,0.31183121631075367,1
+Cc1nnc(c(=O)n1N)c1ccccc1,0.2326765,0.1930748486488201,1
+CCNC(=O)C(OC(=O)Nc1ccccc1)C,0.23279,0.23218358582651033,1
+CNC(=O)Oc1ccccc1OC(C)C,0.23418,0.013723673121154247,1
+Cl/C=C/CO/N=C(\C1=C(O)CC(CC1=O)CC(SCC)C)/CC,0.23895,0.17623271825645226,1
+CCCCCCCCSC(=O)Oc1cc(Cl)nnc1c1ccccc1,0.24081999999999998,0.11259709736280737,1
+Nc1cnn(c(=O)c1Cl)c1ccccc1,0.24815,0.11203441626746227,1
+CCc1cc(C)cc(c1c1c(OC(=O)C(C)(C)C)n2n(c1=O)CCOCC2)CC,0.24968,0.08843778074541372,1
+CC1OC(C)OC(OC(O1)C)C,0.2497,0.71759,0.25
+[S]C(=S)NCCNC(=S)S[Mn],0.25254,0.029230690430281737,1
+O=C1N(OCC1(C)C)Cc1ccccc1Cl,0.253443,0.05992946912912855,1
+CC(CC(c1sccc1NC(=O)c1cn(nc1C(F)(F)F)C)C)C,0.25458,0.12140293055430215,1
+CCSC(CC1CC(=O)C(=C(NOCC=CCl)CC)C(=O)C1)C,0.25839999999999996,0.18080210641569622,1
+Cc1ccc(cc1)N(S(=O)(=O)N(C)C)SC(Cl)(Cl)F,0.25917,0.07331735808644732,1
+CC1N(C(=O)NC2CCCCC2)C(=O)SC1c1ccc(cc1)Cl,0.259436,0.037912302696197005,1
+Fc1ccc(cc1)Oc1ccnc2c1c(Cl)cc(c2)Cl,0.25963,0.05125040435593908,1
+CCCCCCC(c1cc(cc(c1OC(=O)/C=C\C)[N+](=O)[O-])[N+](=O)[O-])C,0.26317500000000005,0.10229610697854082,1
+CCN(C(=O)C(Oc1cccc2c1cccc2)C)CC,0.271895,0.745274637672488,1
+OC(=O)C(Cl)(Cl)C,0.273385,0.42676906198092396,0.125
+COc1cc(OC)nc(n1)NC(=O)NS(=O)(=O)c1ncccc1S(=O)(=O)CC,0.28045,0.6704101902207241,1
+OC(=O)COc1ccc(cc1Cl)Cl,0.2805,0.10271741014229156,1
+CO/C=C(\c1ccccc1COc1cccc(n1)C(F)(F)F)/C(=O)OC,0.28313,0.146402128757787,1
+CCOC(=O)CC(C(=O)OCC)SP(=S)(OC)OC,0.292105,0.03391475855850981,1
+CNC(=O)Oc1cccc2c1cccc2,0.29818,0.28117095139261655,1
+COC(=O)c1ccccc1S(=O)(=O)NC(=O)Nc1nc(OC(F)F)cc(n1)OC(F)F,0.29893,0.7880265755333096,1
+CN(C(=S)[S-])C.CN(C(=S)[S-])C.CN(C(=S)[S-])C.[Fe+3],0.30012,0.033370225153194974,1
+CCOC(=O)c1ccccc1S(=O)(=O)NC(=O)Nc1nc(Cl)cc(n1)OC,0.30133,0.45327731552145556,1
+Fc1ccc(c(c1)F)NC(=O)c1cccnc1Oc1cccc(c1)C(F)(F)F,0.30333,0.061915560656867534,1
+NC1CC(N=C(C(=O)O)N)C(OC1OC1C(O)C(O)C(C(C1O)O)O)C,0.30578,2.5744890364385027,1
+CNC(=O)Oc1cc(C)cc(c1C)C,0.30635,0.07395808661743995,1
+Clc1ccc(cc1)CN(C(=O)Nc1ccccc1)C1CCCC1,0.31170800000000004,0.07980069008535982,1
+ClCCOc1ccccc1S(=O)(=O)NC(=O)Nc1nc(C)nc(n1)OC,0.31207450000000003,0.10396030912791916,1
+CCC(n1c(=O)[nH]c(c(c1=O)Br)C)C,0.31690999999999997,0.2868010916268421,1
+OC(=O)CCl,0.31747,0.1671151871942349,1
+ClC(SN1C(=O)C2C(C1=O)CC=CC2)(Cl)Cl,0.32935499999999995,0.07976078042600018,1
+CN(C1C(=O)C(=C(O)N)C(=O)C2(C1CC1C(=C(O)c3c(C1(C)O)cccc3O)C2=O)O)C,0.33751,7.451766115785945,1
+Clc1cc(ccc1Oc1ccc(c(c1)C(=O)O)[N+](=O)[O-])C(F)(F)F,0.34563,0.39916384329888444,1
+N=C(NC(=N)N)NCCc1ccccc1,0.35565,0.30348165502583013,1
+COc1ccc(cc1)C(C(Cl)(Cl)Cl)c1ccc(cc1)OC,0.36164,0.08918692534652885,1
+Cc1cc(C)cc(c1)C(=O)N(C(C)(C)C)NC(=O)c1ccc2c(c1C)CCCO2,0.3678,0.455824100215936,1
+O=C(Nc1ccnc(c1)Cl)Nc1ccccc1,0.37548,0.04004178313694108,1
+CO/N=C(\c1ccccc1Oc1ncnc(c1F)Oc1ccccc1Cl)/C1=NOCCO1,0.39448,0.08889431100143208,1
+N#Cc1ccc(cc1)C/C(=N/NC(=O)Nc1ccc(cc1)OC(F)(F)F)/c1ccc(cc1)C(F)(F)F,0.39494,0.10814864512129653,1
+NCCNc1cccc2c1cccc2,0.42415,0.36040379880122003,1
+CC(=CC1C(C1(C)C)C(=O)OCc1cccc(c1)Oc1ccccc1)C,0.42802,0.06098065410332806,1
+CC(Oc1ccccn1)COc1ccc(cc1)Oc1ccccc1,0.433615,0.07906976678972555,1
+N#Cc1c[nH]cc1c1cccc2c1OC(O2)(F)F,0.449265,0.6659873077766337,1
+O=C(NC(=O)c1c(F)cccc1F)Nc1ccc(cc1F)Oc1ccc(cc1Cl)C(F)(F)F,0.458295,0.04103726796851559,1
+CCSC(=O)N(CC(C)C)CC(C)C,0.46004,0.043615892575973765,1
+CSC(=O)c1cccc2c1snn2,0.46082,0.2934345305875386,1
+ClCC(=O)N(c1c(C)cccc1CC)COC(C)C,0.463365,0.13753389505085853,1
+Cc1cc(N)c(cc1C)C,0.46595,0.09798385480638508,1
+Clc1cc(ccc1Oc1ccc(c(c1)C(=O)[O-])[N+](=O)[O-])C(F)(F)F.[Na+],0.46919,0.3635168668154065,1
+Clc1c(Cl)c([N+](=O)[O-])c(c(c1Cl)Cl)Cl,0.47404,0.041504267369480506,1
+CC1OC(C)CN(C1)C1CCCCCCCCCCC1,0.48317,0.040365094277215886,1
+COc1nc(nc(n1)C)NC(=O)NS(=O)(=O)c1ccccc1C(=O)OC,0.48379,0.10759955650134392,1
+CCCCc1c(C)nc(nc1OS(=O)(=O)N(C)C)NCC,0.49302,0.06170339457236694,1
+CN1N(C)C(CC1c1ccccc1)c1ccccc1,0.49534,0.21437620561389462,1
+OC(=O)C(Oc1cccc(c1)Cl)C,0.49846,0.021860896323342857,1
+COC(=O)C(NC(=O)C(CC(=O)O)N)Cc1ccccc1,0.49949,0.6275164474255649,1
+O=c1[nH]c2CCCc2c(=O)n1C1CCCCC1,0.50364,0.21011019904236536,1
+CCOC(=O)OC1=C(C(=O)NC21CCC(CC2)OC)c1cc(C)ccc1C,0.5061,0.06896722653826452,1
+N#Cc1c[nH]cc1c1cccc(c1Cl)Cl,0.50615,0.0428084772195063,1
+CCOc1nc(nc(n1)NC)NC(=O)NS(=O)(=O)c1ccccc1C(=O)OC,0.51169,0.23109012425755235,1
+CCCCC(COC(=O)c1ccccc1C(=O)OCC(CCCC)CC)CC,0.51209,2.8831482164285367,1
+Nc1nc(NC2CC2)nc(n1)N,0.514491,0.162564088288422,1
+CCCCOCCOCCOCc1cc2OCOc2cc1CCC,0.51708,0.33736880263337077,1
+COc1c(Cl)ccc(c1C(=O)O)Cl,0.52027,0.6505026638341295,1
+CCOc1cc(ccc1C1COC(=N1)c1c(F)cccc1F)C(C)(C)C,0.5203,0.04082031543546992,1
+COCC(N(c1c(C)cccc1CC)C(=O)CCl)C,0.52855,0.17817332169609335,1
+O=CCC1CC(C)C(=O)C=CC(=CC(C(OC(=O)CC(C(C1OC1(C)OC(C)C(C(C1O)N(C)C)OC1(C)OC(C)C(C(C1)(C)O)O)C)O)CC)COC1OC(C)C(C(C1OC)OC)O)C,0.52958,0.10886837672416151,1
+[O-][N+](=O)/N=C\1/N(Cc2cnc(s2)Cl)COCN1C,0.53134,0.1157001357916454,1
+COC(=O)C1(O)c2cc(Cl)ccc2c2c1cccc2,0.54605,0.018282461695916862,1
+COC(=O)c1cc(ccc1[N+](=O)[O-])Oc1ccc(cc1Cl)Cl,0.54657,0.36834076407589234,1
+CC(C12CCC(O2)(C(C1)OCc1ccccc1C)C)C,0.54665,0.3783949106536331,1
+Oc1ccc2c(c1N=Nc1ccccc1)ccc(c2)S(=O)(=O)O,0.54821,1.4088530675048707,1
+Nc1ccc(c(c1)N(=O)=O)N,0.56811,0.35938075888637544,1
+CCCN(c1c(cc(cc1[N+](=O)[O-])C(F)(F)F)[N+](=O)[O-])CCCl,0.56902,0.08151592614057675,1
+NC1CCCCC1,0.5974349999999999,0.16869122618294258,1
+COC(=O)c1csc(c1S(=O)(=O)NC(=O)n1nc(n(c1=O)C)OC)C,0.5994,0.4352679359570929,1
+COc1cc(Cl)c(cc1Cl)OC,0.60371,0.10457457875063368,1
+COCCN(c1c(C)cccc1C)C(=O)CCl,0.6139,0.066789199179077,1
+OC(=O)C1C2CCC(C1C(=O)O)O2,0.61774,0.4980768387009046,1
+O=Cc1ccco1,0.62445,0.12487,0.1111111111111111
+CCCCNC(=O)n1c(NC(=O)OC)nc2c1cccc2,0.628625,0.2199467364099138,1
+CN(C(=O)Nc1ccc(cc1)Cl)C,0.62925,0.02451483540622636,1
+COc1c(OC)cc(c(c1OC)C(=O)c1c(OC)ccc(c1C)Br)C,0.63528,0.1534580319280037,1
+OC1(Cn2ncnc2)/C(=C/c2ccc(cc2)Cl)/CCC1(C)C,0.64063,0.060480564125465784,1
+COC(=O)c1ccc(cc1)C(=O)OC,0.64372,1.5232392628873108,1
+Clc1ccc(cc1)S(=O)(=O)c1cc(Cl)c(cc1Cl)Cl,0.64597,0.03970697534428981,1
+CC(OC(=O)NC(C(=O)NC(c1nc2c(s1)cc(cc2)F)C)C(C)C)C,0.65432,0.18864749814004692,1
+CCCOC(=O)NCCCN(C)C.Cl,0.66747,3.1518592912026056,1
+CCCCOCC(OCC(O)C)C,0.67269,0.6057183370857274,1
+CC1OC(C)OC(C1)OC(=O)C,0.71759,0.1800567934233961,0.25
+[O-][N+](=O)c1cc(Cl)c(c(c1)Cl)N,0.72459,0.0974426146623003,1
+COc1nc(nc(c1)OC)NC(=O)NS(=O)(=O)Cc1ccccc1C(=O)OC,0.75292,0.6802182167559607,1
+O=C(C1C(C1(C)C)C=C(C)C)OCN1C(=O)C2=C(C1=O)CCCC2,0.75436,0.07580764763625997,1
+CCOc1nc(F)cc2n1nc(n2)S(=O)(=O)Nc1c(Cl)cccc1C(=O)OC,0.75615,0.5003711558129528,1
+CCCN(c1c(cc(cc1[N+](=O)[O-])C(F)(F)F)[N+](=O)[O-])CCC,0.760539,0.04573417513755395,1
+COC(=O)c1c(Cl)c(Cl)c(c(c1Cl)Cl)C(=O)OC,0.768162,0.2888263884813736,1
+COc1cc(OC)nc(n1)NC(=O)NS(=O)(=O)Cc1ccccc1C(=O)O,0.77956,0.6536201858608215,1
+Clc1ccc(c(n1)C(=O)O)Cl,0.78125,0.42462576778303013,1
+COC(=O)NS(=O)(=O)c1ccc(cc1)N,0.78179,0.5842969444450055,1
+ClCC[N+](C)(C)C.[Cl-],0.79079,3.3587364920090987,1
+COC(CCCC(C/C=C/C(=C/C(=O)OC(C)C)/C)C)(C)C,0.80523,0.13732812785699586,1
+CCOc1cc(ccc1OCC)NC(=O)OC(C)C,0.8241,0.1793367710559056,1
+OC(=O)c1nc(Cl)c(c(c1Cl)N)Cl,0.8283,0.7131490150774492,1
+CC(C1(C)N=C(NC1=O)c1nc2ccccc2cc1C(=O)O)C,0.8351195,0.5468381897088649,1
+Nc1ccc(c(c1)C)NOS(=O)(=O)O,0.84315,0.5422208204103196,1
+CCOC(=O)C1OC1(C)c1ccccc1,0.84854,0.13204668749013046,1
+COC(=O)Nc1nc2c([nH]1)cccc2,0.8499450000000001,0.034281549897798795,1
+OCCn1c(C)ncc1[N+](=O)[O-],0.8764,0.11268411956938622,1
+CC(Oc1cccc(c1)NC(=O)c1ccccc1C(F)(F)F)C,0.907795,0.24581610020027767,1
+COP(=O)OC,0.90869,0.1163372948750952,1
+OCCNc1ccc(cc1OCCO)N(=O)=O,0.94539,0.933026452183397,1
+O=N(=O)c1cccc2c1cccc2,0.95283,0.3348979055626918,1
+O=C(C1(C)CCCCC1)Nc1ccc(c(c1Cl)Cl)O,0.96626,0.38148538585170594,1
+ClCCP(=O)(O)O,0.9723550000000001,2.415446889200535,1
+Oc1cccc2c1nccc2,0.98513,0.8658493400958024,1
+CCCOC(=O)c1ccc(cn1)C(=O)OCCC,0.99491,2.577485737503307,1
+Oc1noc(c1)C,0.99911,4.460800000000001,0.1
+CC[N](=C1C=CC(=C(c2ccc(cc2)N(Cc2cccc(c2)S(=O)(=O)O)CC)c2ccc(cc2)N(C)C)C=C1)Cc1cccc(c1)S(=O)(=O)O,1.01,0.35439817581861227,1
+ClCC[N+](C)(C)C,1.0602,0.769322382021074,1
+Clc1ccccc1,1.0661,0.09135478771308206,1
+O=C1CCCCCN1,1.1047,0.4043892593874615,1
+Cc1cc(C)nc(n1)Nc1ccccc1,1.1091,0.0737976978862917,1
+COc1cccc(c1C)C(=O)NN(C(C)(C)C)C(=O)c1cc(C)cc(c1)C,1.1154,0.7821714373267393,1
+COC(=O)C(=CC=CC(=CC=CC=C(C=CC=C(C=CC1=C(C)CCCC1(C)C)C)C)C)C,1.1194,0.020676050303422566,1
+Clc1ccccc1CC(C1(Cl)CC1)(Cn1nc[nH]c1=S)O,1.1619199999999998,0.058943462141135015,1
+Oc1ccc(cc1Cl)C(C)(C)C,1.1697,0.06937930270229405,1
+COc1cc(OC)nc(n1)NC(=O)NS(=O)(=O)Nc1ccccc1C(=O)N(C)C,1.178,1.9742151147471259,1
+CON=C(c1ccccc1COc1ccccc1C)C(=O)OC,1.1888,1.0845014565361817,1
+CCCOc1nn(c(=O)n1C)C(=O)[N-]S(=O)(=O)c1ccccc1C(=O)OC.[Na+],1.1894,0.8239881300986028,1
+OC(=O)Cc1cccc2c1cccc2,1.2057,0.2631460117991914,1
+OCc1cc(N=Nc2ccc(c3c2cccc3)S(=O)(=O)O)c(c(c1O)N=Nc1ccc(c2c1cccc2)S(=O)(=O)O)O,1.2093,0.9453956798919527,1
+C[N]1(C)CCCCC1,1.3134,1.1080940786579139,1
+OC1CCC2(C(C1)CCC1C2CCC2(C1CCC2C(CCC(=O)O)C)C)C,1.3278,0.07542708343534506,1
+COc1cc(OC)nc(n1)NC(=O)NS(=O)(=O)N(S(=O)(=O)C)C,1.3412,0.28167672766944896,1
+Oc1ccc(c(c1)C(C)(C)C)O,1.3537,0.3585951109070325,1
+COc1ncc(c2n1nc(n2)S(=O)(=O)Nc1c(F)cccc1F)F,1.3917,0.182692394567328,1
+OCC1OC2OC3C(CO)OC(C(C3O)O)OC3C(CO)OC(C(C3O)O)OC3C(CO)OC(C(C3O)O)OC3C(OC(OC4C(OC(OC5C(OC(OC1C(C2O)O)C(O)C5O)CO)C(O)C4O)CO)C(O)C3O)CO,1.4097,2.86894354722703,1
+O=C(Nc1cc(F)cc(c1)F)N/N=C(/c1ncccc1C(=O)O)\C,1.412,0.6222263909228765,1
+CCCCOC(=O)c1ccccc1C(=O)OCc1ccccc1,1.5047,1.2476262846894939,1
+Fc1cc2CCC(n3c2c(c1)c(=O)c(c3)C(=O)O)C,1.5311,0.22682314364423445,1
+CC(N(c1c(cc(cc1N(=O)=O)C(F)(F)F)N(=O)=O)C(C)C)C,1.55095,0.049842003172590674,1
+CCC(c1noc(c1)NC(=O)c1c(OC)cccc1OC)(CC)C,1.5855,0.48345555649061533,1
+c1ccc(cc1)c1ccccc1,1.6212,0.19695607887005936,1
+NCC(c1ccc(cc1)O)O,1.6321,0.6606348605926128,1
+CCc1c(C(=O)O)c(=O)cnn1c1ccc(cc1)Cl,1.6865,0.1176637232985991,1
+ClCC#CCOC(=O)Nc1cccc(c1)Cl,1.7435,0.3398943350894961,1
+O/C(=C\1/C(=O)CC(CC1=O)C(=O)O)/C1CC1,1.7528,1.1164855772875812,1
+CO/N=C(\c1ccccc1COc1ccccc1C)/C(=O)OC,1.7985,1.0088143490618942,1
+COc1ccc(c(c1)OC)N,1.8018,1.1213631788509328,1
+CCC(=O)C1=C([O-])CC(CC1=O)C(=O)[O-].[Ca+2],1.874,0.7779135467595814,1
+CC(C1(C)N=C(NC1=O)c1ncccc1C(=O)O)C,1.9137,0.40905762233234644,1
+OC(=O)COc1nc(F)c(c(c1Cl)N)Cl,1.9605,0.17778111806150118,1
+Clc1ccc(cc1)Cl,2.0408,0.05668123713462514,1
+CCCCOC(=O)c1ccccc1C(=O)OCCCC,2.1556,3.4207048541789407,1
+c1ccc(cc1)c1ccccc1OCC1CO1,2.2097,0.35478700957419773,1
+ClCC[N](C)(C)C,2.2428,0.6547382064094504,1
+COc1cc(OC)n2c(n1)nc(n2)NS(=O)(=O)c1c(OC)nccc1C(F)(F)F,2.3023,0.06568205953408954,1
+CC=Cc1ccc(cc1)OC,2.3212,0.9863861428098205,1
+CC(OC(=O)Nc1cccc(c1)Cl)C,2.3402,0.27622277410511276,1
+COC(=O)c1ccccc1O,2.3661,0.4928865612021886,1
+CCOC(=O)C=C,2.4771,0.0902265031347979,1
+COC(=O)CC(c1ccc(cc1)Cl)NC(=O)C(C(C)C)NC(=O)OC(C)C,2.507,0.12334128172020414,1
+COc1nn(c(=O)n1C)C(=O)NS(=O)(=O)c1ccccc1OC(F)(F)F,2.5233,0.6316622264895095,1
+C=Cc1ccccc1,2.7365,0.5364643979184449,1
+COc1cc(OC)nc(n1)NC(=O)NS(=O)(=O)c1n2ccccc2nc1S(=O)(=O)CC,2.7557,0.2325225295230604,1
+CC(=C)C(=O)O,2.8807,9.313199999999998,0.14285714285714285
+CN(NC(=O)CCC(=O)O)C,3.0343,0.49949,0.13043478260869565
+Oc1ccccc1c1ccccc1,3.1197,0.7853299391125398,1
+Clc1cnc2c(c1)ccc(c2C(=O)O)Cl,3.1273,1.314162575581675,1
+C[N+]1(C)CCCCC1.[Cl-],3.1805,0.37179235012225387,1
+CCc1ccccc1,3.29205,0.12357812396843722,1
+CC(c1ccccc1)C,3.2988999999999997,0.16550075538260078,1
+Cc1cnc2c(c1)ccc(c2C(=O)O)Cl,3.3388,1.0514727923982707,1
+CCCOC(=O)NCCCN(C)C,3.6119,0.7414484443986524,1
+CCOP(=O)O,3.6347,0.043636364714084296,1
+Oc1ccccc1,3.6552,0.7581555736232084,1
+[O-]P(=O)OCC.[O-]P(=O)OCC.[O-]P(=O)OCC.[Al+3],3.6854,0.027507369804584878,1
+CC1CCC(C(C1)O)C(C)C,3.7948,16.0029013919712,1
+COc1ccc(cc1)N,3.8489,0.7567046658392361,1
+CCCCC(COC(=O)CCCCC(=O)OCC(CCCC)CC)CC,4.0479,1.1516438052403521,1
+CCCOC(=O)c1cc(O)c(c(c1)O)O,4.0716,1.36948925973691,1
+CC(CCCC1(C)CCc2c(O1)c(C)c(c(c2C)OC(=O)C)C)CCCC(CCCC(C)C)C,4.2306,2.0012821457781538,1
+COc1ccc(cc1N=Nc1c(O)c(cc2c1cccc2)C(=O)Nc1cccc(c1)N(=O)=O)N(=O)=O,4.3084,0.2518085528685041,1
+Oc1ccc(nn1)O,4.4608,0.99911,0.1
+S=c1sc2c([nH]1)cccc2,4.4843,0.07001826504802523,1
+Clc1cc(N)c(c(n1)C(=O)O)Cl,4.8306,1.1577521052384814,1
+CNC(=N[N](=O)[O])NCC1COCC1,4.9008,0.13016999999999998,0.12
+COc1cc(OC)nc(n1)NC(=O)NS(=O)(=O)c1ncccc1C(=O)N(C)C,5.0877,0.22071260347039603,1
+OC(=O)CNCP(=O)(O)O,5.5597,0.7008374592406026,0.16666666666666666
+CCOc1ccc(cc1N)NC(=O)C,6.101,0.21020718396302843,1
+Nc1ccc(cc1)O,6.2863,0.8638880213771946,1
+NC(=S)NNC(=S)N,6.3038,0.009103354136383681,1
+NC(=O)c1cnccn1,6.4088,0.08617861868365052,1
+OC(=O)c1ccc(cc1N)N(=O)=O,6.5062,0.18151132215622945,1
+Oc1cc(O)c2c(c1)oc(c(c2=O)O)c1ccc(c(c1)O)O,6.7298,0.779643201282797,1
+ClCC(=O)c1ccc(cc1)NC(=O)C,7.4653,0.13907779981592758,1
+O=C1OC(=O)c2c1cccc2,8.0005,0.9639909247662849,1
+CCCOC(=O)c1ccc(cc1)O,8.3241,3.6389420029079838,1
+CCOC(=O)COC(=O)c1ccccc1C(=O)OCC,8.9199,0.3553695017839142,1
+O=C1CCCCC1,9.2722,0.2458123214419957,1
+OC(=O)C=CC(=O)O,9.3132,2.8807000000000005,0.14285714285714285
+COC(=O)c1ccc(cc1)O,9.8589,1.0578304662732887,1
+COC(=O)c1ccccc1C(=O)OC,10.3,0.8954401948549734,1
+OC1C2C(N(C)C)C(=O)C(=C(O)N)C(=O)C2(O)C(=O)C2=C(O)c3c(C(C12)(C)O)c(Cl)ccc3O,10.508,0.33751000000000003,0.6216216216216216
+OCC(C1OC(=O)C(=C1O)O)O,13.07315,9.16523469965696,1
+OCCO,14.822,5.394518090354487,1
+CCCCCCCCCCCCCCCCCC(=O)OCC(C1OCC(C1O)O)O,16.727,32.41761573263369,1
+[O-]S(=O)(=O)NC1CCCCC1.[Na+],17.901,0.18626027910642426,1
+O=C1NS(=O)(=O)c2c1cccc2,19.663,0.20088345882784658,1
+CCCCCCCCCCCC(=O)OCC(C1OCC(C1O)O)O,19.867,19.05448419710287,1
+CCOC(=O)c1ccccc1C(=O)OCC,19.956,0.6492927199585653,1
+OC(=O)c1ccccc1N,20.06,0.33773737981612734,1
+OCC(CO)O,74.739,1.2359643227930828,1
diff --git a/data/training-cv-2.id b/data/training-cv-2.id
new file mode 100644
index 0000000..973b4af
--- /dev/null
+++ b/data/training-cv-2.id
@@ -0,0 +1 @@
+56d5ec552b72ed36c4000001
diff --git a/data/training-test-predictions.csv b/data/training-test-predictions.csv
new file mode 100644
index 0000000..ca34b33
--- /dev/null
+++ b/data/training-test-predictions.csv
@@ -0,0 +1,151 @@
+SMILES,LOAEL_measured_median,LOAEL_predicted,Confidence,Dataset
+N#Cc1nn(c(c1S(=O)C(F)(F)F)N)c1c(Cl)cc(cc1Cl)C(F)(F)F,0.00013611,0.01148216373256843,1,training-prediction
+OC(=O)C(Oc1ccc(cc1)Oc1ncc(cc1Cl)C(F)(F)F)C,0.00027647,0.012370470701925899,1,training-prediction
+CCOP(=S)(SCSC(C)(C)C)OCC,0.00027736000000000004,0.003520511683277722,1,training-prediction
+CCSCSP(=S)(OCC)OCC,0.00061449,0.0007932432885978219,1,training-prediction
+CCOP(=O)(SC(CC)C)SC(CC)C,0.000872805,0.005020259791233174,1,training-prediction
+CNC(=O)CSP(=S)(OC)OC,0.0010905,0.009515127939063834,1,training-prediction
+COP(=O)(SC)N,0.0020549,0.33146588454802073,1,training-prediction
+CSc1ccc(cc1C)OP(=S)(OC)OC,0.00210185,0.0052770620054827895,1,training-prediction
+CCOP(=S)(Oc1ccc2c(c1)oc(=O)c(c2C)Cl)OCC,0.0033631,0.036592963422387284,1,training-prediction
+CCOP(=S)(Oc1ncn(n1)c1ccccc1)OCC,0.0041492,0.021132003617537098,1,training-prediction
+COc1sc(=O)n(n1)CSP(=S)(OC)OC,0.00471335,0.0098233419774848,1,training-prediction
+CCOP(=S)(OCC)SCSP(=S)(OCC)OCC,0.0049418,0.0028924725896877944,1,training-prediction
+CCOP(=O)(Oc1ccc(c(c1)C)SC)NC(C)C,0.0049447,0.004831305474311618,1,training-prediction
+CC(Cc1ccc(cc1)C(C)(C)C)CN1CC(C)OC(C1)C,0.0056016,0.06867843129491752,1,training-prediction
+COP(=S)(Oc1nc(Cl)c(cc1Cl)Cl)OC,0.00620095,0.008969949496846933,1,training-prediction
+OC(C(Cl)(Cl)Cl)(c1ccc(cc1)Cl)c1ccc(cc1)Cl,0.0067479,0.0575408460077049,1,training-prediction
+COC(=O)N(C(=O)N1COC2(C(=N1)c1ccc(cc1C2)Cl)C(=O)OC)c1ccc(cc1)OC(F)(F)F,0.0068203,0.03706152163770416,1,training-prediction
+Clc1ccc(cc1)C(c1ccccc1Cl)(c1cncnc1)O,0.0075484,0.02455655297557998,1,training-prediction
+COP(=S)(SCn1nnc2c(c1=O)cccc2)OC,0.0076105,0.025703032163536588,1,training-prediction
+N#CC(c1cccc(c1)Oc1ccccc1)OC(=O)C1C(C1(C)C)C=C(Br)Br,0.00781875,0.042853347293390985,1,training-prediction
+CCN(c1nc(cc(n1)C)OP(=S)(OC)OC)CC,0.0081878,0.01609250673284384,1,training-prediction
+CCCCOC(=O)C(Oc1ccc(cc1)Oc1ccc(cn1)C(F)(F)F)C,0.00885585,0.00642945433938663,1,training-prediction
+COP(=O)(OC=C(Cl)Cl)OC,0.0100688,0.03379255796926954,1,training-prediction
+CCCSP(=O)(SCCC)OCC,0.010069,0.012657180818924377,1,training-prediction
+O=S1OCC2C(CO1)C1(C(C2(Cl)C(=C1Cl)Cl)(Cl)Cl)Cl,0.012287,0.00022929597195349384,1,training-prediction
+CC(Oc1cc(c(cc1Cl)Cl)n1nc(oc1=O)C(C)(C)C)C,0.0124555,0.0639086556427057,1,training-prediction
+CNC(=O)Oc1cccc2c1OC(C2)(C)C,0.01394355,0.04063021221263945,1,training-prediction
+N#Cc1c(Cl)c(C#N)c(c(c1Cl)Cl)Cl,0.015043,0.0038259351864843435,1,training-prediction
+Fc1ccc(cc1)[Si](c1ccc(cc1)F)(Cn1cncn1)C,0.015853,0.012131065927580155,1,training-prediction
+CCOP(=S)(Oc1cc(C)nc(n1)C(C)C)OCC,0.016429,0.015095535744907523,1,training-prediction
+N#Cc1c(Cl)cccc1Cl,0.0165685,0.09350368116996392,1,training-prediction
+CCOP(=S)(Oc1nc(Cl)c(cc1Cl)Cl)OCC,0.017114,0.0021312647369153546,1,training-prediction
+BrC1COC(C1)(Cn1cncn1)c1ccc(cc1Cl)Cl,0.017185,0.028600129544374974,1,training-prediction
+CCN(C(=O)SCc1ccc(cc1)Cl)CC,0.0180385,0.018489302950787725,1,training-prediction
+CCCN(C(=O)n1cncc1)CCOc1c(Cl)cc(cc1Cl)Cl,0.019912,0.026822534406393834,1,training-prediction
+CCOC(=O)c1cn2nc(cc2nc1C)OP(=S)(OCC)OCC,0.0200875,0.11679267971674383,1,training-prediction
+COP(=S)(SCN1C(=O)c2c(C1=O)cccc2)OC,0.020484,0.03656348401256463,1,training-prediction
+CNC(=O)ON=C(C(=O)N(C)C)SC,0.022348,0.02628660622078008,1,training-prediction
+COC(=O)N(c1ccccc1COc1ccn(n1)c1ccc(cc1)Cl)OC,0.023207,0.09137694501130139,1,training-prediction
+CON(C(=O)Nc1ccc(c(c1)Cl)Cl)C,0.025091,0.013151125795315764,1,training-prediction
+O=C(NC(=O)c1c(F)cccc1F)Nc1ccc(cc1)Cl,0.025428,0.1397706187651392,1,training-prediction
+O=C(N(C)C)Nc1ccc(c(c1)Cl)Cl,0.025741,0.10989045521624603,1,training-prediction
+CCOC(=O)C(Oc1ccc(cc1)Oc1cnc2c(n1)ccc(c2)Cl)C,0.0257509,0.05260415007019946,1,training-prediction
+N#Cc1sc2=c(sc1C#N)c(=O)c1c(c2=O)cccc1,0.0269975,0.20283244217430776,1,training-prediction
+C=CC1(C)OC(=O)N(C1=O)c1cc(Cl)cc(c1)Cl,0.027961,0.15193157204083732,1,training-prediction
+N#CC(c1ccc(c(c1)Oc1ccccc1)F)OC(=O)C1C(C1(C)C)C=C(Cl)Cl,0.028207,0.04274266752996184,1,training-prediction
+CCOC(=O)C(Cc1cc(c(cc1Cl)F)n1nc(n(c1=O)C(F)F)C)Cl,0.029113,0.16324594176713225,1,training-prediction
+CON(C(=O)Nc1ccc(cc1)Br)C,0.0313005,0.05246320059678898,1,training-prediction
+CN1CN(C)CSC1=S,0.03266,0.05748016757235302,1,training-prediction
+ClCC1CN(C(=O)C1Cl)c1cccc(c1)C(F)(F)F,0.033160999999999996,0.04469562555717614,1,training-prediction
+CCCCC(c1ccc(cc1)Cl)(Cn1cncn1)C#N,0.034179,0.1328889568108142,1,training-prediction
+CCOP(=S)(SCn1c(=O)oc2c1ccc(c2)Cl)OCC,0.0345288,0.003341107232217978,1,training-prediction
+CCOCn1c(c2ccc(cc2)Cl)c(c(c1C(F)(F)F)Br)C#N,0.0350825,0.05914997942399124,1,training-prediction
+Clc1ccc(c(c1)Cl)C1(OCCO1)Cn1cncn1,0.0379825,0.06987596762503774,1,training-prediction
+CC(C(c1cncnc1)(c1ccc(cc1)OC(F)(F)F)O)C,0.038746,0.05734371433548944,1,training-prediction
+CC(N(C(=O)SCC(=C(Cl)Cl)Cl)C(C)C)C,0.041029,0.034659116233835524,1,training-prediction
+COP(=S)(Oc1ccc(c(c1)C)[N+](=O)[O-])OC,0.0424911,0.0025094363530126854,1,training-prediction
+O=C1OC(C(=O)N1Nc1ccccc1)(C)c1ccc(cc1)Oc1ccccc1,0.04514,0.0451334899121889,1,training-prediction
+CN(C(=S)SSC(=S)N(C)C)C,0.04783,0.06926194842492117,1,training-prediction
+CN(C(=O)Oc1nc(nc(c1C)C)N(C)C)C,0.0520385,0.030679541298093704,1,training-prediction
+C=CCOC(c1ccc(cc1Cl)Cl)Cn1cncc1,0.053503,0.013704285647549115,1,training-prediction
+COCN(c1c(CC)cccc1CC)C(=O)CCl,0.0537505,0.5608944524211554,1,training-prediction
+CCOc1ccc2c(c1)C(=CC(N2)(C)C)C,0.055221,0.3806288619670735,1,training-prediction
+O=C(c1ccc(cc1S(=O)(=O)C)C(F)(F)F)c1cnoc1C1CC1,0.055661,0.029566929200617712,1,training-prediction
+OC(=O)COc1ccc(cc1C)Cl,0.0573225,0.12085906204575554,1,training-prediction
+CCOC(=O)NCCOc1ccc(cc1)Oc1ccccc1,0.0575765,0.20536079691300863,1,training-prediction
+N#CC(c1cccc(c1)Oc1ccccc1)OC(=O)C(c1ccc(cc1)Cl)C(C)C,0.059538,0.00852789812015851,1,training-prediction
+N#CC(c1cccc(c1)Oc1ccccc1)OC(=O)C1C(C1(C)C)(C)C,0.060099,0.026958947205883887,1,training-prediction
+CC(OC(=O)C(c1ccc(cc1)Br)(c1ccc(cc1)Br)O)C,0.0606145,0.020841190814278196,1,training-prediction
+Clc1ccccc1c1nnc(nn1)c1ccccc1Cl,0.06152150000000001,0.1399543448524091,1,training-prediction
+Clc1cc(ccc1Oc1ccc(c(c1)C(=O)NS(=O)(=O)C)[N+](=O)[O-])C(F)(F)F,0.062678,0.1405937915030098,1,training-prediction
+COc1nc(nc(n1)C)NC(=O)NS(=O)(=O)c1ccccc1Cl,0.062889,0.08792722420062483,1,training-prediction
+CCCCN(SN(C(=O)Oc1cccc2c1OC(C2)(C)C)C)CCCC,0.065695,0.02839365100101789,1,training-prediction
+O=C(NC(=O)c1c(F)cccc1F)Nc1cc(Cl)c(c(c1F)Cl)F,0.06691,0.07597385658090804,1,training-prediction
+CSc1nnc(c(=O)n1N)C(C)(C)C,0.067199,0.01370099999999999,0.11538461538461539,training-prediction
+O=C(NC(=O)c1c(F)cccc1F)Nc1ccc(c(c1)Cl)OC(C(OC(F)(F)F)F)(F)F,0.06758600000000001,0.05038188357688792,1,training-prediction
+CCOc1ccc(cc1)C(COCc1cccc(c1)Oc1ccccc1)(C)C,0.068395,0.1116456809729931,1,training-prediction
+C#CCOS(=O)OC1CCCCC1Oc1ccc(cc1)C(C)(C)C,0.06905,0.11430467855215604,1,training-prediction
+OC(=O)COc1nc(Cl)c(cc1Cl)Cl,0.07213454999999999,0.05814521838332604,1,training-prediction
+O=C(N(C)C)Nc1cccc(c1)C(F)(F)F,0.073957,0.04001363451555916,1,training-prediction
+OC(C(C)(C)C)C(n1cncn1)Oc1ccc(cc1)c1ccccc1,0.074093,0.2057465588486493,1,training-prediction
+CCNc1nc(NC(C)C)nc(n1)Cl,0.077892,0.09557547621401412,1,training-prediction
+O=C(C1=C(C)OCCS1)Nc1ccccc1,0.0811745,0.15573428524718813,1,training-prediction
+CNC(=O)Oc1cc(C)c(c(c1)C)SC,0.0827735,0.017454393396993218,1,training-prediction
+OC(C(C)(C)C)C(n1ncnc1)Oc1ccc(cc1)Cl,0.084527,0.09609312639982802,1,training-prediction
+O=C(C(C)(C)C)C(n1ncnc1)Oc1ccc(cc1)Cl,0.085107,0.0611332279073438,1,training-prediction
+CC(NC(=O)N1CC(=O)N(C1=O)c1cc(Cl)cc(c1)Cl)C,0.08783250000000001,0.06681328467405699,1,training-prediction
+CCC(=O)Nc1ccc(c(c1)Cl)Cl,0.09171,0.2915369419467815,1,training-prediction
+N#CC(c1ccccc1)(Cn1cncn1)CCc1ccc(cc1)Cl,0.092038,0.0965869480256574,1,training-prediction
+ClC(=CC1C(C1(C)C)C(=O)OCc1cccc(c1)Oc1ccccc1)Cl,0.095836,0.12663135322831742,1,training-prediction
+OC(=O)C(Oc1ccc(cc1Cl)Cl)C,0.0967835,0.03322294575694361,1,training-prediction
+COP(=O)(NC(=O)C)SC,0.1023645,0.020049393739713695,1,training-prediction
+O=C1N(c2cc(Cl)cc(c2)Cl)C(=O)C2(C1(C)C2)C,0.1108605,0.117838029035702,1,training-prediction
+COC(=O)c1c(nc(c(c1CC(C)C)C1=NCCS1)C(F)(F)F)C(F)F,0.11151,0.06043692115939837,1,training-prediction
+Clc1ccc(cc1)CCC(C(C)(C)C)(Cn1cncn1)O,0.115167,0.05895345220093288,1,training-prediction
+COC(=O)NC(=S)Nc1ccccc1NC(=S)NC(=O)OC,0.12412500000000001,0.2482244502543378,1,training-prediction
+CCOc1cc(ccc1[N+](=O)[O-])Oc1ccc(cc1Cl)C(F)(F)F,0.12856,0.11079797742359224,1,training-prediction
+CCc1ccc(cc1)C(=O)NN(C(C)(C)C)C(=O)c1cc(C)cc(c1)C,0.13674999999999998,1.1006126894921346,1,training-prediction
+c1scc(n1)c1nc2c([nH]1)cccc2,0.14907,0.10738182341473035,1,training-prediction
+CC(N1C(=O)c2ccccc2NS1(=O)=O)C,0.14983,0.7288084834900276,1,training-prediction
+N#CC(c1cccc(c1)Oc1ccccc1)OC(=O)C1C(C1(C)C)C=C(Cl)Cl,0.150135,0.030035240719250313,1,training-prediction
+Cc1cccc2c1n1cnnc1s2,0.150605,0.3285321844774098,1,training-prediction
+ClC(SN1C(=O)c2c(C1=O)cccc2)(Cl)Cl,0.15173999999999999,0.20071832491891514,1,training-prediction
+CCC(Nc1c(cc(cc1[N+](=O)[O-])C(C)(C)C)[N+](=O)[O-])C,0.153385,0.050879540298715914,1,training-prediction
+Cc1nc(Nc2ccccc2)nc(c1)C1CC1,0.15802,0.5553748019083816,1,training-prediction
+c1ccc(cc1)Nc1ccccc1,0.16546,0.38230959751715715,1,training-prediction
+Clc1cc(Cl)c(cc1n1nc(n(c1=O)C(F)F)C)NS(=O)(=O)C,0.17304,0.02384153039577781,1,training-prediction
+CCCC1COC(O1)(Cn1cncn1)c1ccc(cc1Cl)Cl,0.176786,0.04467686699937855,1,training-prediction
+C#CCC1=C(C)C(CC1=O)OC(=O)C1C(C1(C)C)C=C(C)C,0.18558899999999998,0.10572035414293104,1,training-prediction
+COc1nc(nc(n1)C)NC(=O)NS(=O)(=O)c1ccccc1CCC(F)(F)F,0.200175,0.07901150381157088,1,training-prediction
+CC(=CC1C(C1(C)C)C(=O)OCc1coc(c1)Cc1ccccc1)C,0.2068305,0.22838174280166534,1,training-prediction
+CCOCN(c1c(C)cccc1CC)C(=O)CCl,0.21666999999999997,0.13739679956582262,1,training-prediction
+CC(Nc1nc(NC(C)C)nc(n1)Cl)C,0.219845,0.06430354395190928,1,training-prediction
+CNC(=O)Oc1ccccc1OC(C)C,0.23418,0.013725243045764276,1,training-prediction
+CCCCCCCCSC(=O)Oc1cc(Cl)nnc1c1ccccc1,0.24081999999999998,0.13659751142830953,1,training-prediction
+O=C1N(OCC1(C)C)Cc1ccccc1Cl,0.253443,0.06439799828920362,1,training-prediction
+Cc1ccc(cc1)N(S(=O)(=O)N(C)C)SC(Cl)(Cl)F,0.25917,0.07245747881555553,1,training-prediction
+CC1N(C(=O)NC2CCCCC2)C(=O)SC1c1ccc(cc1)Cl,0.259436,0.03487898392097964,1,training-prediction
+CCN(C(=O)C(Oc1cccc2c1cccc2)C)CC,0.271895,0.8706009631290119,1,training-prediction
+OC(=O)COc1ccc(cc1Cl)Cl,0.2805,0.08845179227631193,1,training-prediction
+CCOC(=O)CC(C(=O)OCC)SP(=S)(OC)OC,0.292105,0.02711766232686377,1,training-prediction
+CNC(=O)Oc1cccc2c1cccc2,0.29818,0.19393577674782117,1,training-prediction
+Clc1ccc(cc1)CN(C(=O)Nc1ccccc1)C1CCCC1,0.31170800000000004,0.06922818715332912,1,training-prediction
+ClCCOc1ccccc1S(=O)(=O)NC(=O)Nc1nc(C)nc(n1)OC,0.31207450000000003,0.18963884941795092,1,training-prediction
+CCC(n1c(=O)[nH]c(c(c1=O)Br)C)C,0.31690999999999997,0.2868010916268421,1,training-prediction
+ClC(SN1C(=O)C2C(C1=O)CC=CC2)(Cl)Cl,0.32935499999999995,0.07976078042600035,1,training-prediction
+CC(=CC1C(C1(C)C)C(=O)OCc1cccc(c1)Oc1ccccc1)C,0.42802,0.06099139561841655,1,training-prediction
+CC(Oc1ccccn1)COc1ccc(cc1)Oc1ccccc1,0.433615,0.06873630510174474,1,training-prediction
+N#Cc1c[nH]cc1c1cccc2c1OC(O2)(F)F,0.449265,0.7723832498999111,1,training-prediction
+Clc1c(Cl)c([N+](=O)[O-])c(c(c1Cl)Cl)Cl,0.47404,0.051655712417785805,1,training-prediction
+COc1nc(nc(n1)C)NC(=O)NS(=O)(=O)c1ccccc1C(=O)OC,0.48379,0.08591404752056958,1,training-prediction
+Nc1nc(NC2CC2)nc(n1)N,0.514491,0.162564088288422,1,training-prediction
+CCCCOCCOCCOCc1cc2OCOc2cc1CCC,0.51708,0.33736880263337066,1,training-prediction
+COCC(N(c1c(C)cccc1CC)C(=O)CCl)C,0.52855,0.2025217756930338,1,training-prediction
+O=Cc1ccco1,0.62445,0.12487,0.1111111111111111,training-prediction
+[O-][N+](=O)c1cc(Cl)c(c(c1)Cl)N,0.72459,0.09940992923363313,1,training-prediction
+COC(=O)c1c(Cl)c(Cl)c(c(c1Cl)Cl)C(=O)OC,0.768162,0.3068265745479209,1,training-prediction
+COC(=O)NS(=O)(=O)c1ccc(cc1)N,0.78179,0.3077280396919008,1,training-prediction
+OC(=O)c1nc(Cl)c(c(c1Cl)N)Cl,0.8283,1.5935322771354081,1,training-prediction
+CC(C1(C)N=C(NC1=O)c1nc2ccccc2cc1C(=O)O)C,0.8351195,0.5362888665627945,1,training-prediction
+COC(=O)Nc1nc2c([nH]1)cccc2,0.8499450000000001,0.03427857980425423,1,training-prediction
+CC(Oc1cccc(c1)NC(=O)c1ccccc1C(F)(F)F)C,0.907795,0.16556720793841956,1,training-prediction
+O=C(C1(C)CCCCC1)Nc1ccc(c(c1Cl)Cl)O,0.96626,0.38098624299804507,1,training-prediction
+ClCCP(=O)(O)O,0.9723550000000001,2.415446889200535,1,training-prediction
+COc1cccc(c1C)C(=O)NN(C(C)(C)C)C(=O)c1cc(C)cc(c1)C,1.1154,0.7700149356098216,1,training-prediction
+CCC(c1noc(c1)NC(=O)c1c(OC)cccc1OC)(CC)C,1.5855,0.4882234386036716,1,training-prediction
+OC(=O)COc1nc(F)c(c(c1Cl)N)Cl,1.9605,0.07824793915942921,1,training-prediction
+CC(OC(=O)Nc1cccc(c1)Cl)C,2.3402,0.2668742137819341,1,training-prediction
+Oc1ccccc1c1ccccc1,3.1197,0.8616321068040766,1,training-prediction
+OC(=O)CNCP(=O)(O)O,5.5597,0.7008374592406026,0.16666666666666666,training-prediction
diff --git a/data/training-test-predictions.id b/data/training-test-predictions.id
new file mode 100644
index 0000000..2dcc43a
--- /dev/null
+++ b/data/training-test-predictions.id
@@ -0,0 +1 @@
+56d5de732b72ed162f000005
diff --git a/data/combined.csv b/data/training.csv
index b788ab5..b788ab5 100644
--- a/data/combined.csv
+++ b/data/training.csv
diff --git a/data/combined.json b/data/training.json
index 10b52ac..10b52ac 100644
--- a/data/combined.json
+++ b/data/training.json
diff --git a/figure/crossvalidation.pdf b/figure/crossvalidation.pdf
index b8f512b..5c31c0c 100644
--- a/figure/crossvalidation.pdf
+++ b/figure/crossvalidation.pdf
Binary files differ
diff --git a/figure/dataset-variability.pdf b/figure/dataset-variability.pdf
index 26a2483..fdcddf8 100644
--- a/figure/dataset-variability.pdf
+++ b/figure/dataset-variability.pdf
Binary files differ
diff --git a/figure/functional-groups.pdf b/figure/functional-groups.pdf
index 378d26d..ca189c8 100644
--- a/figure/functional-groups.pdf
+++ b/figure/functional-groups.pdf
Binary files differ
diff --git a/figure/matching-ClC(C)Cl.png b/figure/matching-ClC(C)Cl.png
deleted file mode 100644
index 8641b24..0000000
--- a/figure/matching-ClC(C)Cl.png
+++ /dev/null
Binary files differ
diff --git a/figure/test-correlation.pdf b/figure/test-correlation.pdf
index 8332ae9..6097332 100644
--- a/figure/test-correlation.pdf
+++ b/figure/test-correlation.pdf
Binary files differ
diff --git a/figure/test-prediction.pdf b/figure/test-prediction.pdf
index 9fb9245..3403b8d 100644
--- a/figure/test-prediction.pdf
+++ b/figure/test-prediction.pdf
Binary files differ
diff --git a/figure/unnamed-chunk-4-1.png b/figure/unnamed-chunk-4-1.png
deleted file mode 100644
index 27b9a79..0000000
--- a/figure/unnamed-chunk-4-1.png
+++ /dev/null
Binary files differ
diff --git a/loael-variability.rb b/loael-variability.rb
deleted file mode 100644
index 5a8f1ca..0000000
--- a/loael-variability.rb
+++ /dev/null
@@ -1,61 +0,0 @@
-require_relative '../../lazar/lib/lazar'
-include OpenTox
-#$mongo.database.drop
-#$gridfs = $mongo.database.fs # recreate GridFS indexes
-# compare duplicates within datasets
-#old = Dataset.from_csv_file File.join(File.dirname(__FILE__),"regression","LOAEL_mmol_corrected_smiles.csv")
-old = Dataset.from_csv_file File.join(File.dirname(__FILE__),"regression","LOAEL_mg_corrected_smiles_mmol.csv")
-#new = Dataset.from_csv_file File.join(File.dirname(__FILE__),"regression","swissRat_chron_LOAEL.csv")
-new = Dataset.from_csv_file File.join(File.dirname(__FILE__),"regression","swissRat_chron_LOAEL_mmol.csv")
-#combined = Dataset.from_csv_file File.join(File.dirname(__FILE__),"regression","LOAEL-rat-combined.csv")
-
-compound_vector = []
-value_vector = []
-dataset_vector = []
-
-vars = []
-
-[old, new].each do |dataset|
- vars << []
- #vars[dataset.name] = []
- p dataset.name
- p dataset.compounds.size
- p dataset.duplicates(dataset.features.first).size
- dataset.duplicates.each do |cid,values|
- R.assign "values", values
- var = R.eval("var(-log(values))").to_f
- vars.last << var
- #smi = Compound.find(cid).smiles
- smi = cid.to_s
- values.each do |val|
- compound_vector << smi
- value_vector << - Math.log(val)
- dataset_vector << dataset.name
- end
- #vars << { :var => var, :values => values, :smiles => smi }
- end
- #vars.sort!{|a,b| a[:var] <=> b[:var]}
- #vars.each do |dup|
- #dup[:values].each do |v|
- #compound_vector << dup[:smiles]
- #value_vector << v
- #end
- #end
-end
-p vars
-# TODO statistical test for variances
-R.assign "vars1", vars[0]
-R.assign "vars2", vars[1]
-print "p-value: #{R.eval("t.test(vars1,vars2)$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$values)"
-R.eval "img <- ggplot(df, aes(smi,values,ymin = min(values), ymax=max(values),color=dataset))"
-R.eval "img <- img + ylab('-log(LOAEL mg/kg_bw/day)') + xlab('Compound') + theme(axis.text.x = element_blank())"
-R.eval "img <- img + geom_point()"
-#R.eval "img <- img + scale_x_discrete(breaks=NULL) + geom_point() + coord_flip()"# + xlab('-log(LOAEL)'), ylab('Compound')"
-#R.eval "ggsave(file='/home/ch/opentox/lazar-nestec-data/loael_variance.svg', plot=img)"
-R.eval "ggsave(file='/home/ch/opentox/lazar-nestec-data/loael-variance.svg', plot=img,width=12, height=8)"
diff --git a/loael.Rmd b/loael.Rmd
index 5686698..8fb301f 100644
--- a/loael.Rmd
+++ b/loael.Rmd
@@ -41,7 +41,7 @@ Elena: do you have a reference and the name of the department?
m = read.csv("data/mazzatorta.csv",header=T)
s = read.csv("data/swiss.csv",header=T)
t = read.csv("data/test.csv",header=T)
-c = read.csv("data/combined.csv",header=T)
+c = read.csv("data/training.csv",header=T)
```
`r length(unique(t$SMILES))` compounds are common in both datasets and we use them as a test set in our investigation. For this test set we will
@@ -81,38 +81,42 @@ chemical structures.
Elena + Swiss Federal Office contribution (input)
-The Swiss Federal Office dataset consists of `r length(s$SMILES)` LOAEL values
-for `r length(unique(s$SMILES))` unique chemical structures.
+The original Swiss Federal Office dataset has chronic toxicity data for rats,
+mice and multi generation effects. For the purpose of this study only rat LOAEL
+data was used. This leads to the *Swiss Federal Office* dataset with `r length(s$SMILES)` rat LOAEL
+values for `r length(unique(s$SMILES))` unique chemical structures.
### Preprocessing
-Chemical structures in both datasets were initially represented as SMILES
-strings [@doi:10.1021/ci00057a005]. Syntactically incorrect and missing SMILES
-were generated from other identifiers (e.g names, CAS numbers). Unique smiles
-from the OpenBabel library [@OBoyle2011] were used for the identification of
-duplicated structures.
+Chemical structures (represented as SMILES [@doi:10.1021/ci00057a005]) in both
+datasets were checked for correctness, syntactically incorrect and missing
+SMILES were generated from other identifiers (e.g names, CAS numbers). Unique
+smiles from the OpenBabel library [@OBoyle2011] were used for the
+identification of duplicated structures.
Studies with undefined or empty LOAEL entries were removed from the datasets.
-LOAEL values were converted to mmol/kg_bw/day units. For prediction, validation
-and visualisation purposes -log10 transformations are used.
-
-David: please check if we have missed something
+LOAEL values were converted to mmol/kg_bw/day units and rounded to five
+significant digits. For prediction, validation and visualisation purposes
+-log10 transformations are used.
### Derived datasets
Two derived datasets were obtained from the original datasets:
The *test* dataset contains data of compounds that occur in both datasets.
-Exact duplications of LOAEL values were removed, because it is very likely that
-they originate from the same study. The test dataset has `r length(t$SMILES)`
-LOAEL values for `r length(unique(t$SMILES))` unique chemical structures.
-
-The *combined* dataset is the union of the Mazzatorta and the Swiss Federal
-Office dataset and it is used to build predictive models. Exact LOAEL
-duplications were removed, as for the test dataset. The combined dataset has
-`r length(c$SMILES)` LOAEL values for `r length(unique(c$SMILES))` unique
+LOAEL values equal at five significant digits were considered as duplicates
+originating from the same study/publication and only one instance was kept in
+the test dataset. Exact duplications of LOAEL values were removed, because it
+is very likely that they originate from the same study. The test dataset has
+`r length(t$SMILES)` LOAEL values for `r length(unique(t$SMILES))` unique
chemical structures.
+The *training* dataset is the union of the Mazzatorta and the Swiss Federal
+Office dataset and it is used to build predictive models. LOAEL duplicates were
+removed, as for the test dataset. The training dataset has `r
+length(c$SMILES)` LOAEL values for `r length(unique(c$SMILES))` unique chemical
+structures.
+
Algorithms
----------
@@ -203,7 +207,7 @@ Prediction intervals were obtained from the `predict` function.
For the comparison of experimental variability with predictive accuracies we
are using a test set of compounds that occur in both datasets. The
-*Mazzatorta*, *Swiss Federal Office* and *combined* datasets are used as
+*Mazzatorta*, *Swiss Federal Office* and *training* datasets are used as
training data for read across predictions. In order to obtain unbiased
predictions *all* information from the test compound is removed from the
training set prior to predictions. This procedure is hardcoded into the
@@ -231,11 +235,17 @@ baseline for evaluating prediction performance.
##### Ches-Mapper analysis
We applied the visualization tool CheS-Mapper (Chemical Space Mapping and Visualization in 3D,
-http://ches-mapper.org, @Gütlein2012) to compare both datasets. CheS-Mapper can be used to analyze the relationship between the structure of chemical compounds, their physico-chemical properties, and biological or toxic effects. It embeds a dataset into 3D space, such that compounds with similar feature values are close to each other. CheS-Mapper is generic and can be employed with different kinds of features. [@fig:ches-mapper-pc] shows an embedding that is based on physico-chemical (PC) descriptors: we determined that both datasets have very similar PC feature values.
+http://ches-mapper.org, @Gütlein2012) to compare both datasets. CheS-Mapper can be used to analyze the relationship between the structure of chemical compounds, their physico-chemical properties, and biological or toxic effects. It embeds a dataset into 3D space, such that compounds with similar feature values are close to each other. CheS-Mapper is generic and can be employed with different kinds of features. [@fig:ches-mapper-pc] shows an embedding that is based on physico-chemical (PC) descriptors.
+
+![Compounds from the Mazzatorta and the Swiss Federal Office dataset are highlighted in red and green. Compounds that occur in both datasets are highlighted in magenta. ](figure/pc-small-compounds-highlighted.png){#fig:ches-mapper-pc}
+
+Martin: explain light colors at bottom of histograms
+In this example, CheS-Mapper applied a principal components analysis to map compounds according to their physico-chemical (PC) feature values into 3D space. Both datasets have in general very similar PC feature values. As an exception, the Mazzatorta dataset includes most of the tiny compound structures: we have selected the 78 smallest compounds (with 10 atoms and less, marked with a blue box in the screen-shot) and found that 61 of these compounds occur in the Mazzatorta dataset, whereas only 19 are contained in the Swiss dataset (p-value 3.7E-7).
-We extended CheS-Mapper with a functionality to mine the same MolPrint2D features that are utilized for model building in this work. Applying a minimum frequency of 3 yields 760 distinguished MolPrint2D fragments for the composed dataset of 671 unique compounds. Again, a visual inspection confirmed that both datasets are structurally very similar. However, CheS-Mapper allows the detection of features that help to distinguish groups of selected compounds from the entire dataset. Hence, we found discriminating features for compounds that occur in only one of both datasets, and for the most active or in-active compounds (see [@tbl:molprint]). As an example, [@fig:ches-mapper-alert] shows 9 compounds that match a specific fragment (all other compounds in the dataset do not match this fragment) and have very low mean LOAEL values.
+This result was confirmed for structural features (fingerprints) including MolPrint2D features that are utilized for model building in this work.
+In general we concluded that both datasets are very similar, in terms of chemical structures and physico-chemical properties.
##### Distribution of functional groups
@@ -311,9 +321,9 @@ The Mazzatorta, the Swiss Federal Office dataset and a combined dataset were use
![Comparison of experimental with predicted LOAEL values, each vertical line represents a compound, dots are individual measurements (red) or predictions (green).](figure/test-prediction.pdf){#fig:comp}
```{r echo=F}
-combined = read.csv("data/combined-test-predictions.csv",header=T)
-combined.r_square = round(rsquare(-log(combined$LOAEL_measured_median),-log(combined$LOAEL_predicted)),2)
-combined.rmse = round(rmse(-log(combined$LOAEL_measured_median),-log(combined$LOAEL_predicted)),2)
+training = read.csv("data/training-test-predictions.csv",header=T)
+training.r_square = round(rsquare(-log(training$LOAEL_measured_median),-log(training$LOAEL_predicted)),2)
+training.rmse = round(rmse(-log(training$LOAEL_measured_median),-log(training$LOAEL_predicted)),2)
```
TODO: nr unpredicted, nr predictions outside of experimental values
@@ -325,16 +335,22 @@ These results are presented in [@fig:corr] and [@tbl:cv]. Please bear in mind th
Training data | $r^2$ | RMSE
--------------|---------------------------|-------------------------
Experimental | `r median.r.square` | `r median.rmse`
-Combined | `r combined.r_square` | `r combined.rmse`
+Combined | `r training.r_square` | `r training.rmse`
: Comparison of model predictions with experimental variability. {#tbl:common-pred}
![Correlation of experimental with predicted LOAEL values (test set)](figure/test-correlation.pdf){#fig:corr}
```{r echo=F}
-combined = read.csv("data/combined-cv.csv",header=T)
-cv.combined.r_square = round(rsquare(-log(combined$LOAEL_measured_median),-log(combined$LOAEL_predicted)),2)
-cv.combined.rmse = round(rmse(-log(combined$LOAEL_measured_median),-log(combined$LOAEL_predicted)),2)
+t0 = read.csv("data/training-cv-0.csv",header=T)
+cv.t0.r_square = round(rsquare(-log(t0$LOAEL_measured_median),-log(t0$LOAEL_predicted)),2)
+cv.t0.rmse = round(rmse(-log(t0$LOAEL_measured_median),-log(t0$LOAEL_predicted)),2)
+t1 = read.csv("data/training-cv-1.csv",header=T)
+cv.t1.r_square = round(rsquare(-log(t1$LOAEL_measured_median),-log(t1$LOAEL_predicted)),2)
+cv.t1.rmse = round(rmse(-log(t1$LOAEL_measured_median),-log(t1$LOAEL_predicted)),2)
+t2 = read.csv("data/training-cv-2.csv",header=T)
+cv.t2.r_square = round(rsquare(-log(t2$LOAEL_measured_median),-log(t2$LOAEL_predicted)),2)
+cv.t2.rmse = round(rmse(-log(t2$LOAEL_measured_median),-log(t2$LOAEL_predicted)),2)
```
TODO: repeated CV
@@ -343,7 +359,9 @@ All correlations are statistically highly significant with a p-value < 2.2e-16.
Training dataset | $r^2$ | RMSE
-----------------|-------|------
-Combined | `r round(cv.combined.r_square,2)` | `r round(cv.combined.rmse,2)`
+Combined | `r round(cv.t0.r_square,2)` | `r round(cv.t0.rmse,2)`
+Combined | `r round(cv.t1.r_square,2)` | `r round(cv.t1.rmse,2)`
+Combined | `r round(cv.t2.r_square,2)` | `r round(cv.t2.rmse,2)`
: 10-fold crossvalidation results {#tbl:cv}
diff --git a/loael.md b/loael.md
index 07efadd..9f6224e 100644
--- a/loael.md
+++ b/loael.md
@@ -73,38 +73,42 @@ chemical structures.
Elena + Swiss Federal Office contribution (input)
-The Swiss Federal Office dataset consists of 493 LOAEL values
-for 381 unique chemical structures.
+The original Swiss Federal Office dataset has chronic toxicity data for rats,
+mice and multi generation effects. For the purpose of this study only rat LOAEL
+data was used. This leads to the *Swiss Federal Office* dataset with 493 rat LOAEL
+values for 381 unique chemical structures.
### Preprocessing
-Chemical structures in both datasets were initially represented as SMILES
-strings [@doi:10.1021/ci00057a005]. Syntactically incorrect and missing SMILES
-were generated from other identifiers (e.g names, CAS numbers). Unique smiles
-from the OpenBabel library [@OBoyle2011] were used for the identification of
-duplicated structures.
+Chemical structures (represented as SMILES [@doi:10.1021/ci00057a005]) in both
+datasets were checked for correctness, syntactically incorrect and missing
+SMILES were generated from other identifiers (e.g names, CAS numbers). Unique
+smiles from the OpenBabel library [@OBoyle2011] were used for the
+identification of duplicated structures.
Studies with undefined or empty LOAEL entries were removed from the datasets.
-LOAEL values were converted to mmol/kg_bw/day units. For prediction, validation
-and visualisation purposes -log10 transformations are used.
-
-David: please check if we have missed something
+LOAEL values were converted to mmol/kg_bw/day units and rounded to five
+significant digits. For prediction, validation and visualisation purposes
+-log10 transformations are used.
### Derived datasets
Two derived datasets were obtained from the original datasets:
The *test* dataset contains data of compounds that occur in both datasets.
-Exact duplications of LOAEL values were removed, because it is very likely that
-they originate from the same study. The test dataset has 375
-LOAEL values for 155 unique chemical structures.
-
-The *combined* dataset is the union of the Mazzatorta and the Swiss Federal
-Office dataset and it is used to build predictive models. Exact LOAEL
-duplications were removed, as for the test dataset. The combined dataset has
-998 LOAEL values for 671 unique
+LOAEL values equal at five significant digits were considered as duplicates
+originating from the same study/publication and only one instance was kept in
+the test dataset. Exact duplications of LOAEL values were removed, because it
+is very likely that they originate from the same study. The test dataset has
+375 LOAEL values for 155 unique
chemical structures.
+The *training* dataset is the union of the Mazzatorta and the Swiss Federal
+Office dataset and it is used to build predictive models. LOAEL duplicates were
+removed, as for the test dataset. The training dataset has `r
+length(c$SMILES)` LOAEL values for 671 unique chemical
+structures.
+
Algorithms
----------
@@ -195,7 +199,7 @@ Prediction intervals were obtained from the `predict` function.
For the comparison of experimental variability with predictive accuracies we
are using a test set of compounds that occur in both datasets. The
-*Mazzatorta*, *Swiss Federal Office* and *combined* datasets are used as
+*Mazzatorta*, *Swiss Federal Office* and *training* datasets are used as
training data for read across predictions. In order to obtain unbiased
predictions *all* information from the test compound is removed from the
training set prior to predictions. This procedure is hardcoded into the
@@ -223,13 +227,17 @@ baseline for evaluating prediction performance.
##### Ches-Mapper analysis
We applied the visualization tool CheS-Mapper (Chemical Space Mapping and Visualization in 3D,
-http://ches-mapper.org, @Gütlein2012) to compare both datasets. CheS-Mapper can be used to analyze the relationship between the structure of chemical compounds, their physico-chemical properties, and biological or toxic effects. It embeds a dataset into 3D space, such that compounds with similar feature values are close to each other. CheS-Mapper is generic and can be employed with different kinds of features. [@fig:ches-mapper-pc] shows an embedding that is based on physico-chemical (PC) descriptors: we determined that both datasets have very similar PC feature values.
+http://ches-mapper.org, @Gütlein2012) to compare both datasets. CheS-Mapper can be used to analyze the relationship between the structure of chemical compounds, their physico-chemical properties, and biological or toxic effects. It embeds a dataset into 3D space, such that compounds with similar feature values are close to each other. CheS-Mapper is generic and can be employed with different kinds of features. [@fig:ches-mapper-pc] shows an embedding that is based on physico-chemical (PC) descriptors.
+
+![Compounds from the Mazzatorta and the Swiss Federal Office dataset are highlighted in red and green. Compounds that occur in both datasets are highlighted in magenta. ](figure/pc-small-compounds-highlighted.png){#fig:ches-mapper-pc}
+
+Martin: explain light colors at bottom of histograms
-![Compounds from the Mazzatorta and the Swiss dataset are highlighted in red and green. Compounds that occur in both datasets are highlighted in magenta. In this example, CheS-Mapper applied a principal components analysis to map compounds according to their physico-chemical (PC) feature values into 3D space. Both datasets have in general similar PC feature values. As an exception, the Mazzatorta dataset includes most of the tiny compound structures: we have selected the 78 smallest compounds (with 10 atoms and less, marked with a blue box in the screen-shot) and found that 61 of these compounds occur in the Mazzatorta dataset, whereas only 19 are contained in the Swiss dataset (p-value 3.7E-7).](figure/pc-small-compounds-highlighted.png){#fig:ches-mapper-pc}
+In this example, CheS-Mapper applied a principal components analysis to map compounds according to their physico-chemical (PC) feature values into 3D space. Both datasets have in general very similar PC feature values. As an exception, the Mazzatorta dataset includes most of the tiny compound structures: we have selected the 78 smallest compounds (with 10 atoms and less, marked with a blue box in the screen-shot) and found that 61 of these compounds occur in the Mazzatorta dataset, whereas only 19 are contained in the Swiss dataset (p-value 3.7E-7).
-We extended CheS-Mapper with a functionality to mine the same MolPrint2D features that are utilized for model building in this work. Applying a minimum frequency of 3 yields 760 distinguished MolPrint2D fragments for the composed dataset of 671 unique compounds. Again, a visual inspection confirmed that both datasets are structurally very similar. However, CheS-Mapper allows the detection of features that help to distinguish groups of selected compounds from the entire dataset. Hence, we found discriminating features for compounds that occur in only one of both datasets, and for the most active or in-active compounds (see [@tbl:molprint]). As an example, [@fig:ches-mapper-alert] shows 9 compounds that match a specific fragment (all other compounds in the dataset do not match this fragment) and have very low mean LOAEL values.
+This result was confirmed for structural features (fingerprints) including MolPrint2D features that are utilized for model building in this work.
-![A CheS-Mapper screen-shot showing 9 compounds that match the MolPrint2D fragment 15;1-1-1;2-2-1;2-1-15; (as SMILES syntax: ClC(C)Cl). Apart from the selected compound (blue box), the other 8 compounds belong to the top 10 percent of compounds with the lowest LOAEL values. I.e., this feature can be regarded as a structural alert in our dataset, as it is matched by only 9 compounds in the entire dataset and 8 of these compounds are highly active.](figure/matching-ClC(C)Cl.png){#fig:ches-mapper-alert}
+In general we concluded that both datasets are very similar, in terms of chemical structures and physico-chemical properties.
##### Distribution of functional groups
@@ -239,7 +247,7 @@ In order to confirm the results of CheS-Mapper analysis we have evaluated the
frequency of functional groups from the OpenBabel FP4
fingerprint. [@fig:fg] shows the frequency of functional groups
in
-both datasets. Only 139 functional groups with a frequency > 25 are depicted, the complete table for all functional groups can be found in the
+both datasets. 139 functional groups with a frequency > 25 are depicted, the complete table for all functional groups can be found in the
data directory of the supplemental material (`data/functional-groups.csv`).
![Frequency of functional groups.](figure/functional-groups.pdf){#fig:fg}
@@ -293,7 +301,7 @@ These results are presented in [@fig:corr] and [@tbl:cv]. Please bear in mind th
Training data | $r^2$ | RMSE
--------------|---------------------------|-------------------------
Experimental | 0.49 | 1.41
-Combined | 0.41 | 1.47
+Combined | 0.4 | 1.47
: Comparison of model predictions with experimental variability. {#tbl:common-pred}
@@ -307,7 +315,9 @@ All correlations are statistically highly significant with a p-value < 2.2e-16.
Training dataset | $r^2$ | RMSE
-----------------|-------|------
-Combined | 0.39 | 1.84
+Combined | 0.4 | 1.8
+Combined | 0.38 | 1.84
+Combined | 0.4 | 1.81
: 10-fold crossvalidation results {#tbl:cv}
diff --git a/loael.pdf b/loael.pdf
index 1cc1417..db69185 100644
--- a/loael.pdf
+++ b/loael.pdf
Binary files differ
diff --git a/test-correlation-plot.R b/test-correlation-plot.R
index b8cbb76..74a2739 100644
--- a/test-correlation-plot.R
+++ b/test-correlation-plot.R
@@ -5,11 +5,11 @@ library(gridExtra)
experimental <- read.csv("data/median-correlation.csv",header=T)
p1 = qplot(-log10(mazzatorta),-log10(swiss),data=experimental,xlab="-log10(LOAEL Mazzatorta median)",ylab="-log10(LOAEL Swiss Federal Office median)",main="Experimental data") + geom_point() + geom_abline(intercept=0.0) + xlim(-1,4) + ylim(-1,4)
-combined = read.csv("data/combined-test-predictions.csv",header=T)
+training = read.csv("data/training-test-predictions.csv",header=T)
-p2 = qplot(-log10(LOAEL_predicted),-log10(LOAEL_measured_median),data=combined,xlab="-log10(LOAEL predicted)",ylab="-log10(LOAEL measured median)",main="Combined") + geom_point() + geom_abline(intercept=0.0) + xlim(-1,4) + ylim(-1,4)
+p2 = qplot(-log10(LOAEL_predicted),-log10(LOAEL_measured_median),data=training,xlab="-log10(LOAEL predicted)",ylab="-log10(LOAEL measured median)",main="Combined") + geom_point() + geom_abline(intercept=0.0) + xlim(-1,4) + ylim(-1,4)
pdf('figure/test-correlation.pdf')
-grid.arrange(p1,p2,ncol=1)
+grid.arrange(p1,p2,ncol=1,respect=T)
dev.off()
diff --git a/test-prediction-plot.R b/test-prediction-plot.R
index d1d6acb..4cee05e 100644
--- a/test-prediction-plot.R
+++ b/test-prediction-plot.R
@@ -1,13 +1,13 @@
library(ggplot2)
-combined = read.csv("data/combined-test-predictions.csv",header=T)
+training = read.csv("data/training-test-predictions.csv",header=T)
test <- read.csv("data/test.csv",header=T)
n = c("SMILES","LOAEL","Source")
data = data.frame(factor(test$SMILES),test$LOAEL,factor(test$Dataset))
names(data) = n
data$Type = "experimental"
-comb = data.frame(factor(combined$SMILES),combined$LOAEL_predicted,factor(combined$Dataset))
+comb = data.frame(factor(training$SMILES),training$LOAEL_predicted,factor(training$Dataset))
names(comb) = n
comb$Type = "predicted"
data = rbind(data,comb)