blob: 1ab10b2894334a9789b83a195a5e336065a1d57d (
plain)
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
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
|
ARTICLE_FILE = mutagenicity.md
PANDOC_SCHOLAR_PATH = pandoc-scholar
OUTFILE_PREFIX = mutagenicity
DEFAULT_EXTENSIONS = latex pdf docx #odt epub html
#PANDOC_WRITER_OPTIONS = --filter=pandoc-placetable --filter=pandoc-citeproc
TEMPLATE_FILE_LATEX = pandoc-scholar.latex
include $(PANDOC_SCHOLAR_PATH)/Makefile
#tables = tables/R-SVM.csv tables/R-RF.csv tables/R-DL.csv
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/mutagenicity-merged.csv export/pa_mutagenicity.csv export/pa_carcinogenicity.csv export/pa-fingerprints.csv export/mutagenicity-merged-fingerprints.csv
all: $(summaries) $(exports) #$(tables)
# confusion matrices
summaries/confusion-matrices/R-SVM.csv: 10-fold-crossvalidations/R/Sgl-Observations-SVM.csv
scripts/cv-r-confusion-matrix.rb $< > $@
summaries/confusion-matrices/R-RF.csv: 10-fold-crossvalidations/R/Sgl-Observations-RF.csv
scripts/cv-r-confusion-matrix.rb $< > $@
summaries/confusion-matrices/R-DL.csv: 10-fold-crossvalidations/R/Sgl-Observations-DL.csv
scripts/cv-r-confusion-matrix.rb $< > $@
# 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/pa-fingerprints.csv: data/PA.id
scripts/export-fingerprints.rb $< > $@
export/mutagenicity-merged-fingerprints.csv: data/mutagenicity-merged.id
scripts/export-fingerprints.rb $< > $@
export/mutagenicity-merged.csv: data/mutagenicity-merged.id
scripts/export.rb $< csv > $@
export/mutagenicity-merged.sdf: data/mutagenicity-merged.id
scripts/export.rb $< sdf > $@
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: data/PA.id models/carcinogenicity.id
scripts/predict.rb $^ > $@
data/pa_mutagenicity.json: data/PA.id models/mutagenicity-merged.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/*
|
