diff options
Diffstat (limited to 'Makefile')
-rw-r--r-- | Makefile | 52 |
1 files changed, 46 insertions, 6 deletions
@@ -3,29 +3,69 @@ # efsa script via csv # remove headers from csv files # add header at merged csv +# remove \u003e/00 +# remove log messages in result data = data/kazius.csv data/efsa.csv data/hansen.csv -#all: $(data) -# experiments +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 -summaries/weighted_majority_kazius.json: experiments/weighted_majority_kazius.id +all: $(summaries) + +summaries/pa_carcinogenicity_neighbor_sets.json: experiments/pa_carcinogenicity_prediction.json + scripts/pa_neighbor_sets.rb $< > $@ + +summaries/pa_mutagenicity_neighbor_sets.json: experiments/pa_mutagenicity_prediction.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 $< > $@ + +experiments/weighted_majority_kazius_sim0.5.id: data/kazius.csv + scripts/repeated_crossvalidation.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/merged.csv + scripts/repeated_crossvalidation.rb $< > $@ + +summaries/weighted_majority_kazius_sim0.1.json: experiments/weighted_majority_kazius_sim0.1.id scripts/repeated_crossvalidation_summary.rb $< > $@ -experiments/weighted_majority_kazius.id: data/kazius.csv +experiments/weighted_majority_kazius_sim0.1.id: data/kazius.csv scripts/repeated_crossvalidation.rb $< > $@ -summaries/weighted_majority_merged.json: experiments/weighted_majority_merged.id +summaries/weighted_majority_merged_sim0.1.json: experiments/weighted_majority_merged_sim0.1.id scripts/repeated_crossvalidation_summary.rb $< > $@ -experiments/weighted_majority_merged.id: data/merged.csv +experiments/weighted_majority_merged_sim0.1.id: data/merged.csv scripts/repeated_crossvalidation.rb $< > $@ + +experiments/pa_carcinogenicity_prediction.json: data/carcinogenicity.csv data/PA_complete_SMILES_fixed.csv + scripts/predict.rb $^ > $@ + +experiments/pa_mutagenicity_prediction.json: data/merged.csv data/PA_complete_SMILES_fixed.csv + scripts/predict.rb $^ > $@ + +# test data + +data/PA_complete_SMILES_fixed.csv: data/PA_complete_SMILES.csv + cat $< | scripts/convert_pa.rb > $@ # training data data/merged.csv: $(data) echo "SMILES,Activity" > $@ && cat $(data) | sort -u | sed '/SMILES/d' >> $@ +data/carcinogenicity.csv: data/aid1205.csv + scripts/carcinogenicity2csv.rb $< > $@ + +# carcinogenicity + +data/aid1205.csv: + cd data && curl https://pubchem.ncbi.nlm.nih.gov/rest/pug/assay/aid/1205/CSV -o $@ + # kazius data/kazius.csv: data/cas_4337.sdf |