Mercurial > repos > jay > pdaug_merge_dataframes
annotate PDAUG_TSVtoFASTA/PDAUG_TSVtoFASTA.py @ 2:728e04b97852 draft
"planemo upload for repository https://github.com/jaidevjoshi83/pdaug commit 8b18552f6d2b2261efebe1075ff4c18a295b94dd"
author | jay |
---|---|
date | Tue, 29 Dec 2020 18:20:59 +0000 |
parents | fcd5d259427c |
children | c47762435082 |
rev | line source |
---|---|
0
5bb52d4bf172
"planemo upload for repository https://github.com/jaidevjoshi83/pdaug commit a9bd83f6a1afa6338cb6e4358b63ebff5bed155e"
jay
parents:
diff
changeset
|
1 import os |
5bb52d4bf172
"planemo upload for repository https://github.com/jaidevjoshi83/pdaug commit a9bd83f6a1afa6338cb6e4358b63ebff5bed155e"
jay
parents:
diff
changeset
|
2 import argparse |
5bb52d4bf172
"planemo upload for repository https://github.com/jaidevjoshi83/pdaug commit a9bd83f6a1afa6338cb6e4358b63ebff5bed155e"
jay
parents:
diff
changeset
|
3 |
5bb52d4bf172
"planemo upload for repository https://github.com/jaidevjoshi83/pdaug commit a9bd83f6a1afa6338cb6e4358b63ebff5bed155e"
jay
parents:
diff
changeset
|
4 |
5bb52d4bf172
"planemo upload for repository https://github.com/jaidevjoshi83/pdaug commit a9bd83f6a1afa6338cb6e4358b63ebff5bed155e"
jay
parents:
diff
changeset
|
5 def TSVtoFASTA(InFile, Method, Positive, Negative, OutFile): |
5bb52d4bf172
"planemo upload for repository https://github.com/jaidevjoshi83/pdaug commit a9bd83f6a1afa6338cb6e4358b63ebff5bed155e"
jay
parents:
diff
changeset
|
6 |
5bb52d4bf172
"planemo upload for repository https://github.com/jaidevjoshi83/pdaug commit a9bd83f6a1afa6338cb6e4358b63ebff5bed155e"
jay
parents:
diff
changeset
|
7 if Method == 'WithClassLabel': |
5bb52d4bf172
"planemo upload for repository https://github.com/jaidevjoshi83/pdaug commit a9bd83f6a1afa6338cb6e4358b63ebff5bed155e"
jay
parents:
diff
changeset
|
8 |
5bb52d4bf172
"planemo upload for repository https://github.com/jaidevjoshi83/pdaug commit a9bd83f6a1afa6338cb6e4358b63ebff5bed155e"
jay
parents:
diff
changeset
|
9 f = open(InFile) |
5bb52d4bf172
"planemo upload for repository https://github.com/jaidevjoshi83/pdaug commit a9bd83f6a1afa6338cb6e4358b63ebff5bed155e"
jay
parents:
diff
changeset
|
10 lines = f.readlines() |
5bb52d4bf172
"planemo upload for repository https://github.com/jaidevjoshi83/pdaug commit a9bd83f6a1afa6338cb6e4358b63ebff5bed155e"
jay
parents:
diff
changeset
|
11 |
5bb52d4bf172
"planemo upload for repository https://github.com/jaidevjoshi83/pdaug commit a9bd83f6a1afa6338cb6e4358b63ebff5bed155e"
jay
parents:
diff
changeset
|
12 of1 = open(Positive,'w') |
5bb52d4bf172
"planemo upload for repository https://github.com/jaidevjoshi83/pdaug commit a9bd83f6a1afa6338cb6e4358b63ebff5bed155e"
jay
parents:
diff
changeset
|
13 of2 = open(Negative,'w') |
5bb52d4bf172
"planemo upload for repository https://github.com/jaidevjoshi83/pdaug commit a9bd83f6a1afa6338cb6e4358b63ebff5bed155e"
jay
parents:
diff
changeset
|
14 |
5bb52d4bf172
"planemo upload for repository https://github.com/jaidevjoshi83/pdaug commit a9bd83f6a1afa6338cb6e4358b63ebff5bed155e"
jay
parents:
diff
changeset
|
15 n = 0 |
5bb52d4bf172
"planemo upload for repository https://github.com/jaidevjoshi83/pdaug commit a9bd83f6a1afa6338cb6e4358b63ebff5bed155e"
jay
parents:
diff
changeset
|
16 m = 0 |
1
fcd5d259427c
"planemo upload for repository https://github.com/jaidevjoshi83/pdaug commit 3c91f421d26c8f42cf2671e47db735d2cf69dde8"
jay
parents:
0
diff
changeset
|
17 |
fcd5d259427c
"planemo upload for repository https://github.com/jaidevjoshi83/pdaug commit 3c91f421d26c8f42cf2671e47db735d2cf69dde8"
jay
parents:
0
diff
changeset
|
18 l = [] |
fcd5d259427c
"planemo upload for repository https://github.com/jaidevjoshi83/pdaug commit 3c91f421d26c8f42cf2671e47db735d2cf69dde8"
jay
parents:
0
diff
changeset
|
19 |
fcd5d259427c
"planemo upload for repository https://github.com/jaidevjoshi83/pdaug commit 3c91f421d26c8f42cf2671e47db735d2cf69dde8"
jay
parents:
0
diff
changeset
|
20 for line in lines[1:]: |
fcd5d259427c
"planemo upload for repository https://github.com/jaidevjoshi83/pdaug commit 3c91f421d26c8f42cf2671e47db735d2cf69dde8"
jay
parents:
0
diff
changeset
|
21 l.append(line.split('\t')[1].strip('\n').strip('\r')) |
fcd5d259427c
"planemo upload for repository https://github.com/jaidevjoshi83/pdaug commit 3c91f421d26c8f42cf2671e47db735d2cf69dde8"
jay
parents:
0
diff
changeset
|
22 l = list(set(l)) |
0
5bb52d4bf172
"planemo upload for repository https://github.com/jaidevjoshi83/pdaug commit a9bd83f6a1afa6338cb6e4358b63ebff5bed155e"
jay
parents:
diff
changeset
|
23 |
2
728e04b97852
"planemo upload for repository https://github.com/jaidevjoshi83/pdaug commit 8b18552f6d2b2261efebe1075ff4c18a295b94dd"
jay
parents:
1
diff
changeset
|
24 print(l) |
728e04b97852
"planemo upload for repository https://github.com/jaidevjoshi83/pdaug commit 8b18552f6d2b2261efebe1075ff4c18a295b94dd"
jay
parents:
1
diff
changeset
|
25 |
0
5bb52d4bf172
"planemo upload for repository https://github.com/jaidevjoshi83/pdaug commit a9bd83f6a1afa6338cb6e4358b63ebff5bed155e"
jay
parents:
diff
changeset
|
26 for line in lines: |
5bb52d4bf172
"planemo upload for repository https://github.com/jaidevjoshi83/pdaug commit a9bd83f6a1afa6338cb6e4358b63ebff5bed155e"
jay
parents:
diff
changeset
|
27 |
2
728e04b97852
"planemo upload for repository https://github.com/jaidevjoshi83/pdaug commit 8b18552f6d2b2261efebe1075ff4c18a295b94dd"
jay
parents:
1
diff
changeset
|
28 if l[1] in line.split('\t')[1].strip('\n').strip('\r'): |
0
5bb52d4bf172
"planemo upload for repository https://github.com/jaidevjoshi83/pdaug commit a9bd83f6a1afa6338cb6e4358b63ebff5bed155e"
jay
parents:
diff
changeset
|
29 n= n+1 |
1
fcd5d259427c
"planemo upload for repository https://github.com/jaidevjoshi83/pdaug commit 3c91f421d26c8f42cf2671e47db735d2cf69dde8"
jay
parents:
0
diff
changeset
|
30 of1.write('>peptide_'+str(n)+'_'+str(l[0])+'\n') |
0
5bb52d4bf172
"planemo upload for repository https://github.com/jaidevjoshi83/pdaug commit a9bd83f6a1afa6338cb6e4358b63ebff5bed155e"
jay
parents:
diff
changeset
|
31 of1.write(line.split('\t')[0]+'\n') |
5bb52d4bf172
"planemo upload for repository https://github.com/jaidevjoshi83/pdaug commit a9bd83f6a1afa6338cb6e4358b63ebff5bed155e"
jay
parents:
diff
changeset
|
32 |
2
728e04b97852
"planemo upload for repository https://github.com/jaidevjoshi83/pdaug commit 8b18552f6d2b2261efebe1075ff4c18a295b94dd"
jay
parents:
1
diff
changeset
|
33 if l[0] in line.split('\t')[1].strip('\n').strip('\r'): |
0
5bb52d4bf172
"planemo upload for repository https://github.com/jaidevjoshi83/pdaug commit a9bd83f6a1afa6338cb6e4358b63ebff5bed155e"
jay
parents:
diff
changeset
|
34 m= m+1 |
1
fcd5d259427c
"planemo upload for repository https://github.com/jaidevjoshi83/pdaug commit 3c91f421d26c8f42cf2671e47db735d2cf69dde8"
jay
parents:
0
diff
changeset
|
35 of2.write('>peptide_'+str(m)+'_'+str(l[1])+'\n') |
0
5bb52d4bf172
"planemo upload for repository https://github.com/jaidevjoshi83/pdaug commit a9bd83f6a1afa6338cb6e4358b63ebff5bed155e"
jay
parents:
diff
changeset
|
36 of2.write(line.split('\t')[0]+'\n') |
5bb52d4bf172
"planemo upload for repository https://github.com/jaidevjoshi83/pdaug commit a9bd83f6a1afa6338cb6e4358b63ebff5bed155e"
jay
parents:
diff
changeset
|
37 |
5bb52d4bf172
"planemo upload for repository https://github.com/jaidevjoshi83/pdaug commit a9bd83f6a1afa6338cb6e4358b63ebff5bed155e"
jay
parents:
diff
changeset
|
38 elif Method == 'NoClassLabel': |
5bb52d4bf172
"planemo upload for repository https://github.com/jaidevjoshi83/pdaug commit a9bd83f6a1afa6338cb6e4358b63ebff5bed155e"
jay
parents:
diff
changeset
|
39 |
5bb52d4bf172
"planemo upload for repository https://github.com/jaidevjoshi83/pdaug commit a9bd83f6a1afa6338cb6e4358b63ebff5bed155e"
jay
parents:
diff
changeset
|
40 f = open(InFile) |
5bb52d4bf172
"planemo upload for repository https://github.com/jaidevjoshi83/pdaug commit a9bd83f6a1afa6338cb6e4358b63ebff5bed155e"
jay
parents:
diff
changeset
|
41 lines = f.readlines() |
5bb52d4bf172
"planemo upload for repository https://github.com/jaidevjoshi83/pdaug commit a9bd83f6a1afa6338cb6e4358b63ebff5bed155e"
jay
parents:
diff
changeset
|
42 of1 = open(OutFile,'w') |
5bb52d4bf172
"planemo upload for repository https://github.com/jaidevjoshi83/pdaug commit a9bd83f6a1afa6338cb6e4358b63ebff5bed155e"
jay
parents:
diff
changeset
|
43 |
5bb52d4bf172
"planemo upload for repository https://github.com/jaidevjoshi83/pdaug commit a9bd83f6a1afa6338cb6e4358b63ebff5bed155e"
jay
parents:
diff
changeset
|
44 for i, line in enumerate(lines[1:]): |
5bb52d4bf172
"planemo upload for repository https://github.com/jaidevjoshi83/pdaug commit a9bd83f6a1afa6338cb6e4358b63ebff5bed155e"
jay
parents:
diff
changeset
|
45 of1.write('>peptide_'+str(i)+'\n') |
5bb52d4bf172
"planemo upload for repository https://github.com/jaidevjoshi83/pdaug commit a9bd83f6a1afa6338cb6e4358b63ebff5bed155e"
jay
parents:
diff
changeset
|
46 of1.write(line.split('\t')[0]+'\n') |
5bb52d4bf172
"planemo upload for repository https://github.com/jaidevjoshi83/pdaug commit a9bd83f6a1afa6338cb6e4358b63ebff5bed155e"
jay
parents:
diff
changeset
|
47 |
5bb52d4bf172
"planemo upload for repository https://github.com/jaidevjoshi83/pdaug commit a9bd83f6a1afa6338cb6e4358b63ebff5bed155e"
jay
parents:
diff
changeset
|
48 else: |
5bb52d4bf172
"planemo upload for repository https://github.com/jaidevjoshi83/pdaug commit a9bd83f6a1afa6338cb6e4358b63ebff5bed155e"
jay
parents:
diff
changeset
|
49 pass |
5bb52d4bf172
"planemo upload for repository https://github.com/jaidevjoshi83/pdaug commit a9bd83f6a1afa6338cb6e4358b63ebff5bed155e"
jay
parents:
diff
changeset
|
50 |
5bb52d4bf172
"planemo upload for repository https://github.com/jaidevjoshi83/pdaug commit a9bd83f6a1afa6338cb6e4358b63ebff5bed155e"
jay
parents:
diff
changeset
|
51 if __name__=="__main__": |
5bb52d4bf172
"planemo upload for repository https://github.com/jaidevjoshi83/pdaug commit a9bd83f6a1afa6338cb6e4358b63ebff5bed155e"
jay
parents:
diff
changeset
|
52 |
5bb52d4bf172
"planemo upload for repository https://github.com/jaidevjoshi83/pdaug commit a9bd83f6a1afa6338cb6e4358b63ebff5bed155e"
jay
parents:
diff
changeset
|
53 import argparse |
5bb52d4bf172
"planemo upload for repository https://github.com/jaidevjoshi83/pdaug commit a9bd83f6a1afa6338cb6e4358b63ebff5bed155e"
jay
parents:
diff
changeset
|
54 |
5bb52d4bf172
"planemo upload for repository https://github.com/jaidevjoshi83/pdaug commit a9bd83f6a1afa6338cb6e4358b63ebff5bed155e"
jay
parents:
diff
changeset
|
55 parser = argparse.ArgumentParser() |
5bb52d4bf172
"planemo upload for repository https://github.com/jaidevjoshi83/pdaug commit a9bd83f6a1afa6338cb6e4358b63ebff5bed155e"
jay
parents:
diff
changeset
|
56 |
5bb52d4bf172
"planemo upload for repository https://github.com/jaidevjoshi83/pdaug commit a9bd83f6a1afa6338cb6e4358b63ebff5bed155e"
jay
parents:
diff
changeset
|
57 parser.add_argument("-I", "--InFile", required=True, default=None, help=".fasta or .tsv") |
1
fcd5d259427c
"planemo upload for repository https://github.com/jaidevjoshi83/pdaug commit 3c91f421d26c8f42cf2671e47db735d2cf69dde8"
jay
parents:
0
diff
changeset
|
58 parser.add_argument("-P", "--Postvs", required=False, default='FirstDataFile.fasta', help="Path to target tsv file") |
fcd5d259427c
"planemo upload for repository https://github.com/jaidevjoshi83/pdaug commit 3c91f421d26c8f42cf2671e47db735d2cf69dde8"
jay
parents:
0
diff
changeset
|
59 parser.add_argument("-N", "--Negtvs", required=False, default='SecondDataFile.fasta', help="Path to target tsv file") |
0
5bb52d4bf172
"planemo upload for repository https://github.com/jaidevjoshi83/pdaug commit a9bd83f6a1afa6338cb6e4358b63ebff5bed155e"
jay
parents:
diff
changeset
|
60 parser.add_argument("-O", "--OutFile", required=False, default='OutFile.fasta', help="Path to target tsv file") |
5bb52d4bf172
"planemo upload for repository https://github.com/jaidevjoshi83/pdaug commit a9bd83f6a1afa6338cb6e4358b63ebff5bed155e"
jay
parents:
diff
changeset
|
61 parser.add_argument("-M", "--Method", required=True, default=None, help="Path to target tsv file") |
5bb52d4bf172
"planemo upload for repository https://github.com/jaidevjoshi83/pdaug commit a9bd83f6a1afa6338cb6e4358b63ebff5bed155e"
jay
parents:
diff
changeset
|
62 args = parser.parse_args() |
5bb52d4bf172
"planemo upload for repository https://github.com/jaidevjoshi83/pdaug commit a9bd83f6a1afa6338cb6e4358b63ebff5bed155e"
jay
parents:
diff
changeset
|
63 |
1
fcd5d259427c
"planemo upload for repository https://github.com/jaidevjoshi83/pdaug commit 3c91f421d26c8f42cf2671e47db735d2cf69dde8"
jay
parents:
0
diff
changeset
|
64 TSVtoFASTA(args.InFile, args.Method, args.Postvs, args.Negtvs, args.OutFile) |