summaries = summaries/mutagenicity-merged-crossvalidations.json summaries/carcinogenicity-crossvalidations.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) $(exports)

# summaries

summaries/pa_carcinogenicity_neighbor_sets.json: data/pa_carcinogenicity.json
	scripts/pa_neighbor_sets.rb $< > $@

summaries/pa_mutagenicity_neighbor_sets.json: data/pa_mutagenicity.json
	scripts/pa_neighbor_sets.rb $< > $@

summaries/mutagenicity-merged-crossvalidations.json: models/mutagenicity-merged.id
	scripts/crossvalidation-summary.rb $< > $@

summaries/carcinogenicity-crossvalidations.json: models/carcinogenicity.id
	scripts/crossvalidation-summary.rb $< > $@

# exports

export/mutagenicity-merged.sdf: data/mutagenicity-merged.id
	scripts/export.rb $< > $@

export/pa_mutagenicity.csv: data/pa_mutagenicity.json
	scripts/json2csv.rb $< > $@

export/pa_carcinogenicity.csv: data/pa_carcinogenicity.json
	scripts/json2csv.rb $< > $@

# predictions

data/pa_carcinogenicity.json: models/carcinogenicity.id data/PA.id
	scripts/predict.rb $^ > $@

data/pa_mutagenicity.json: models/mutagenicity-merged.id data/PA.id
	scripts/predict.rb $^ > $@

# models and validations

models/mutagenicity-merged.id: data/mutagenicity-merged.id
	scripts/model.rb $< > $@

models/carcinogenicity.id: data/carcinogenicity.id
	scripts/model.rb $< > $@

# test data

data/PA.id: data/PA.sdf
	scripts/import.rb $< > $@
	
# training data

data/mutagenicity-merged.id: data/hansen.id data/efsa.id data/kazius.id
	scripts/merge.rb $^ > $@

data/carcinogenicity.id:
	scripts/import-pubchem.rb 1205 > $@

# kazius

data/kazius.id: data/cas_4337.sdf
	scripts/import.rb $< > $@

data/cas_4337.sdf: data/cas_4337.zip
	cd data && unzip cas_4337.zip

data/cas_4337.zip:
	cd data && wget "http://cheminformatics.org/datasets/bursi/cas_4337.zip"

# efsa

data/efsa.id: data/efsa.csv
	scripts/import.rb $< > $@ 

data/efsa.csv: data/GENOTOX_data_and_dictionary.tsv
	scripts/efsa2csv.rb $< > $@

data/GENOTOX_data_and_dictionary.tsv: data/GENOTOX_data_and_dictionary.xls
	xls2csv -s cp1252 -d utf-8 -x -c "	" $< > $@

data/GENOTOX_data_and_dictionary.xls:
	cd data && wget "https://data.europa.eu/euodp/data/storage/f/2017-07-19T142131/GENOTOX%20data%20and%20dictionary.xls" -o $@

# hansen

data/hansen.id: data/hansen.csv
	scripts/import.rb $< > $@ 

data/hansen.csv: data/Mutagenicity_N6512.csv
	scripts/hansen2csv.rb $< > $@

data/Mutagenicity_N6512.csv:
  cd data && wget "http://doc.ml.tu-berlin.de/toxbenchmark/Mutagenicity_N6512.csv"

# cleanup

clean:
	rm data/*.id

clean_db:
	rm data/*.id && scripts/drop-database.rb

cleanall:
	rm data/*