Makefile


1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51

# TODO
# efsa smiles errors (encodings?)
# efsa script via csv
# remove headers from csv files
# add header at merged csv

data  = data/kazius.csv data/efsa.csv data/hansen.csv

#all: $(data)
# experiments

experiments/weighted_majority_merged.id: data/merged.csv
	scripts/repeated_crossvalidation.rb data/merged.csv > $@
	
# training data

data/merged.csv: $(data)
	echo "SMILES,Activity" > $@ && cat $(data) | sort -u | sed '/SMILES/d' >> $@

# kazius

data/kazius.csv: data/cas_4337.sdf
	scripts/kazius2csv.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.csv: data/GENOTOX_data_and_dictionary.csv
	scripts/efsa2csv.rb  $< > $@

data/GENOTOX_data_and_dictionary.csv: data/GENOTOX_data_and_dictionary.xls
	xls2csv  $< > $@

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.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"

clean:
	rm data/hansen.csv