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
|
#!/usr/bin/env ruby
# red groups
tab = []
File.read("data/pyrrolizidine-alkaloids/pa-groups.csv").each_line do |l|
items = l.chomp.split(';')
if items.first.empty?
items[0] = "ID"
else
id = items.shift
items.collect!{|i| i == "NA" ? 0 : 1}
items = [id]+items
end
tab << items
end
tab[0] += ["CID","SMILES","Canonical SMILES","Measured","lazar-MP2D","lazar-MP2D-high-confidence","lazar-CDK","lazar-CDK-high-confidence"]
i = 0
File.read("data/pyrrolizidine-alkaloids/180920_PA_complete_SMILES.csv").each_line do |l|
if i > 0
id,cid,name,smi = l.chomp.split(";")
tab[i] += [cid,'"'+smi+'"']
end
i += 1
end
i = 0
File.read("pyrrolizidine-alkaloids/mp2d/lazar/pa-mp2d-predictions.csv").each_line do |l|
if i > 0
id,cansmi,exp,mut,p0,p1,max_sim,nn = l.chomp.split(",")
max_sim.to_f < 0.5? hc = "F" : hc = "T"
hc = "" if mut.empty?
tab[i] += ['"'+cansmi+'"',exp,mut,hc]
end
i += 1
end
i=1
File.read("pyrrolizidine-alkaloids/cdk/lazar/pa-cdk-predictions.csv").each_line do |l|
#if i > 0
cansmi,exp,mut,p0,p1,max_sim,nn = l.chomp.split(",")
max_sim.to_f < 0.5? hc = "F" : hc = "T"
hc = "" if mut.empty?
tab[i] += [mut,hc]
#end
i += 1
end
=begin
Dir["pyrrolizidine-alkaloids/R/PA.*.outcome.csv"].each do |r|
tab[0] << "R-"+r.sub('pyrrolizidine-alkaloids/R/PA.','').sub('.outcome.csv','')
i = 0
File.read(r).each_line do |l|
if i > 0
items = l.chomp.split(";")
items.shift
if items.uniq.include? "1"
tab[i] << 1
elsif items.uniq.include? "0"
tab[i] << 0
end
end
i += 1
end
end
=end
Dir["pyrrolizidine-alkaloids/cdk/tensorflow/*.csv"].each do |r|
tab[0] << "TF-"+r.sub('pyrrolizidine-alkaloids/tensorflow/pred.','').sub('.v5-ext-Padel-2D.csv','').sub("lr2","LR-scikit").sub("lr","LR-sgd").sub("rf","RF").sub("nn","NN").sub("svm","SVM")
i = 0
File.read(r).each_line do |l|
if i > 0
id,pred = l.chomp.split(",")
pred.to_f > 0.5 ? tab[i] << 1 : tab[i] << 0
end
i += 1
end
end
Dir["pyrrolizidine-alkaloids/cdk/tensorflow/*.csv"].each do |r|
tab[0] << "TF-"+r.sub('pyrrolizidine-alkaloids/tensorflow/pred.','').sub('.v5-ext-Padel-2D.csv','').sub("lr2","LR-scikit").sub("lr","LR-sgd").sub("rf","RF").sub("nn","NN").sub("svm","SVM")
i = 0
File.read(r).each_line do |l|
if i > 0
id,pred = l.chomp.split(",")
pred.to_f > 0.5 ? tab[i] << 1 : tab[i] << 0
end
i += 1
end
end
puts tab.collect{|r| r.join(",")}.join("\n")
|
