SRC = Mutagenicity-Salmonella_typhimurium.csv 
LAZAR_BIN = ../../bin
MODEL = independent-variable-type dependent-variable-type dependent-variable-values similarity-thresholds independent-variables dependent-variables smiles metadata.json

all: crossvalidation/summaries

model: $(MODEL)

# Crossvalidation

crossvalidation/summaries: crossvalidation
	$(LAZAR_BIN)/classification-summary.rb crossvalidation

crossvalidation: $(MODEL)
	$(LAZAR_BIN)/crossvalidation.rb .

# Model

independent-variables: smiles
	$(LAZAR_BIN)/fingerprints.rb smiles > $@

dependent-variables: $(SRC)
	cut -f2 -d ',' $< | sed '1d' > $@

smiles: $(SRC)
	cut -f1 -d ',' $< | sed '1d' > $@

# Metadata

metadata.json:
	echo '{"species":"Salmonella typhimurium","endpoint":"Mutagenicity","source":"http://cheminformatics.org/datasets/bursi/cas_4337.zip, http://doc.ml.tu-berlin.de/toxbenchmark/Mutagenicity_N6512.csv, https://data.europa.eu/euodp/data/storage/f/2017-07-19T142131/GENOTOX data and dictionary.xls","qmrf":{"group":"QMRF 4.10. Mutagenicity","name":"OECD 471 Bacterial Reverse Mutation Test"}}' > $@

# Model parameters

independent-variable-type:
	echo "binary" > $@

dependent-variable-type:
	echo "binary" > $@

dependent-variable-values:
	echo -e "\"0\"\n\"1\"" > $@

similarity-thresholds:
	echo -e "0.2\n0.5" > $@

# Merge data

Mutagenicity-Salmonella_typhimurium.csv: download/efsa.csv download/hansen.csv download/kazius.csv
	$(LAZAR_BIN)/merge_csv.rb $^

# Convert data

download/efsa.csv: download/efsa.tsv
	download/efsa_classification.rb $< > $@

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

download/hansen.csv: download/Mutagenicity_N6512.csv
	download/hansen_convert.rb $< > $@

download/kazius.csv: download/cas_4337.sdf
	$(LAZAR_BIN)/sdf2csv.rb $< > $@

# Download original data

download/cas_4337.sdf:
	cd download && wget http://cheminformatics.org/datasets/bursi/cas_4337.zip && unzip cas_4337.zip

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

download/efsa.xls:
	wget "https://data.europa.eu/euodp/data/storage/f/2017-07-19T142131/GENOTOX data and dictionary.xls" -o $@