adjustments for latest lazar version

1 files changed, 30 insertions, 41 deletions

diff --git a/Makefile b/Makefile
index 015f075..4db0d26 100644
--- a/Makefile
+++ b/Makefile
@@ -1,81 +1,67 @@
-data  = data/kazius.csv data/efsa.csv data/hansen.csv
+summaries = summaries/mutagenicity-merged-crossvalidations.json summaries/carcinogenicity-crossvalidations.json summaries/pa_mutagenicity_neighbor_sets.json summaries/pa_carcinogenicity_neighbor_sets.json
 
-summaries = summaries/weighted_majority_merged_sim0.1.json summaries/weighted_majority_kazius_sim0.1.json summaries/weighted_majority_merged_sim0.5.json summaries/weighted_majority_kazius_sim0.5.json summaries/pa_mutagenicity_neighbor_sets.json summaries/pa_carcinogenicity_neighbor_sets.json
+exports = export/mutagenicity-merged.sdf export/pa_mutagenicity.csv export/pa_carcinogenicity.csv
 
-all: $(summaries)
+all: $(summaries) $(exports)
 
-# exports
-
-export/mutagenicity-merged.sdf: data/mutagenicity-merged.id
-	scripts/export.rb $< sdf > $@
-
-export/mutagenicity-merged.csv: data/mutagenicity-merged.id
-	scripts/export.rb $< > $@
-
-export/carcinogenicity.csv: data/carcinogenicity.id
-	scripts/export.rb $< > $@
+# summaries
 
-summaries/pa_carcinogenicity_neighbor_sets.json: experiments/pa_carcinogenicity_prediction.json
+summaries/pa_carcinogenicity_neighbor_sets.json: data/pa_carcinogenicity.json
 	scripts/pa_neighbor_sets.rb $< > $@
 
-summaries/pa_mutagenicity_neighbor_sets.json: experiments/pa_mutagenicity_prediction.json
+summaries/pa_mutagenicity_neighbor_sets.json: data/pa_mutagenicity.json
 	scripts/pa_neighbor_sets.rb $< > $@
 
-summaries/weighted_majority_kazius_sim0.5.json: experiments/weighted_majority_kazius_sim0.5.id
-	scripts/repeated_crossvalidation_summary.rb $< > $@
+summaries/mutagenicity-merged-crossvalidations.json: models/mutagenicity-merged.id
+	scripts/crossvalidation-summary.rb $< > $@
 
-experiments/weighted_majority_kazius_sim0.5.id: data/kazius.csv
-	scripts/repeated_crossvalidation.rb $< > $@
+summaries/carcinogenicity-crossvalidations.json: models/carcinogenicity.id
+	scripts/crossvalidation-summary.rb $< > $@
 
-summaries/weighted_majority_merged_sim0.5.json: experiments/weighted_majority_merged_sim0.5.id
-	scripts/repeated_crossvalidation_summary.rb $< > $@
-
-experiments/weighted_majority_merged_sim0.5.id: data/mutagenicity-merged.csv
-	scripts/repeated_crossvalidation.rb $< > $@
+# exports
 
-summaries/weighted_majority_kazius_sim0.1.json: experiments/weighted_majority_kazius_sim0.1.id
-	scripts/repeated_crossvalidation_summary.rb $< > $@
+export/mutagenicity-merged.sdf: data/mutagenicity-merged.id
+	scripts/export.rb $< > $@
 
-experiments/weighted_majority_kazius_sim0.1.id: data/kazius.csv
-	scripts/repeated_crossvalidation.rb $< > $@
+export/pa_mutagenicity.csv: data/pa_mutagenicity.json
+	scripts/json2csv.rb $< > $@
 
-summaries/weighted_majority_merged_sim0.1.json: experiments/weighted_majority_merged_sim0.1.id
-	scripts/repeated_crossvalidation_summary.rb $< > $@
+export/pa_carcinogenicity.csv: data/pa_carcinogenicity.json
+	scripts/json2csv.rb $< > $@
 
-experiments/weighted_majority_merged_sim0.1.id: data/mutagenicity-merged.csv
-	scripts/repeated_crossvalidation.rb $< > $@
+# predictions
 
-experiments/pa_carcinogenicity.id: data/carcinogenicity.id data/PA.id
+data/pa_carcinogenicity.json: models/carcinogenicity.id data/PA.id
 	scripts/predict.rb $^ > $@
 
-experiments/pa_mutagenicity.id: data/mutagenicity-merged.id data/PA.id
+data/pa_mutagenicity.json: models/mutagenicity-merged.id data/PA.id
 	scripts/predict.rb $^ > $@
 
-# models
+# models and validations
 
 models/mutagenicity-merged.id: data/mutagenicity-merged.id
-	scripts/merge.rb $^ > $@
+	scripts/model.rb $< > $@
 
 models/carcinogenicity.id: data/carcinogenicity.id
-	scripts/import-pubchem.rb 1205
+	scripts/model.rb $< > $@
 
 # test data
 
 data/PA.id: data/PA.sdf
-	scripts/import.rb $< sdf > $@
+	scripts/import.rb $< > $@
 	
 # training data
 
-data/mutagenicity-merged.id: data/hansen.id data/kazius.id data/efsa.id
+data/mutagenicity-merged.id: data/hansen.id data/efsa.id data/kazius.id
 	scripts/merge.rb $^ > $@
 
 data/carcinogenicity.id:
-	scripts/import-pubchem.rb 1205
+	scripts/import-pubchem.rb 1205 > $@
 
 # kazius
 
 data/kazius.id: data/cas_4337.sdf
-	scripts/import.rb $< sdf > $@
+	scripts/import.rb $< > $@
 
 data/cas_4337.sdf: data/cas_4337.zip
 	cd data && unzip cas_4337.zip
@@ -113,5 +99,8 @@ data/Mutagenicity_N6512.csv:
 clean:
 	rm data/*.id
 
+clean_db:
+	rm data/*.id && scripts/drop-database.rb
+
 cleanall:
 	rm data/*