annotate pca_cosine.py @ 2:589f8ef21e58 draft default tip

"planemo upload for repository https://github.com/galaxycomputationalchemistry/galaxy-tools-compchem/ commit f1c3c88c7395f2e84cbc533199406aadb79c5c07"
author chemteam
date Fri, 13 Nov 2020 19:44:09 +0000
parents 743bd6aa3c7a
children
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
0
743bd6aa3c7a "planemo upload for repository https://github.com/galaxycomputationalchemistry/galaxy-tools-compchem/ commit 1b23e024af45cc0999d9142d07de6897d4189ec2"
chemteam
parents:
diff changeset
1 #!/usr/bin/env python
743bd6aa3c7a "planemo upload for repository https://github.com/galaxycomputationalchemistry/galaxy-tools-compchem/ commit 1b23e024af45cc0999d9142d07de6897d4189ec2"
chemteam
parents:
diff changeset
2
743bd6aa3c7a "planemo upload for repository https://github.com/galaxycomputationalchemistry/galaxy-tools-compchem/ commit 1b23e024af45cc0999d9142d07de6897d4189ec2"
chemteam
parents:
diff changeset
3 import argparse
743bd6aa3c7a "planemo upload for repository https://github.com/galaxycomputationalchemistry/galaxy-tools-compchem/ commit 1b23e024af45cc0999d9142d07de6897d4189ec2"
chemteam
parents:
diff changeset
4 import csv
743bd6aa3c7a "planemo upload for repository https://github.com/galaxycomputationalchemistry/galaxy-tools-compchem/ commit 1b23e024af45cc0999d9142d07de6897d4189ec2"
chemteam
parents:
diff changeset
5 import sys
743bd6aa3c7a "planemo upload for repository https://github.com/galaxycomputationalchemistry/galaxy-tools-compchem/ commit 1b23e024af45cc0999d9142d07de6897d4189ec2"
chemteam
parents:
diff changeset
6
743bd6aa3c7a "planemo upload for repository https://github.com/galaxycomputationalchemistry/galaxy-tools-compchem/ commit 1b23e024af45cc0999d9142d07de6897d4189ec2"
chemteam
parents:
diff changeset
7 import MDAnalysis as mda
743bd6aa3c7a "planemo upload for repository https://github.com/galaxycomputationalchemistry/galaxy-tools-compchem/ commit 1b23e024af45cc0999d9142d07de6897d4189ec2"
chemteam
parents:
diff changeset
8 import MDAnalysis.analysis.pca as pca
743bd6aa3c7a "planemo upload for repository https://github.com/galaxycomputationalchemistry/galaxy-tools-compchem/ commit 1b23e024af45cc0999d9142d07de6897d4189ec2"
chemteam
parents:
diff changeset
9
743bd6aa3c7a "planemo upload for repository https://github.com/galaxycomputationalchemistry/galaxy-tools-compchem/ commit 1b23e024af45cc0999d9142d07de6897d4189ec2"
chemteam
parents:
diff changeset
10 import numpy as np
743bd6aa3c7a "planemo upload for repository https://github.com/galaxycomputationalchemistry/galaxy-tools-compchem/ commit 1b23e024af45cc0999d9142d07de6897d4189ec2"
chemteam
parents:
diff changeset
11
743bd6aa3c7a "planemo upload for repository https://github.com/galaxycomputationalchemistry/galaxy-tools-compchem/ commit 1b23e024af45cc0999d9142d07de6897d4189ec2"
chemteam
parents:
diff changeset
12
743bd6aa3c7a "planemo upload for repository https://github.com/galaxycomputationalchemistry/galaxy-tools-compchem/ commit 1b23e024af45cc0999d9142d07de6897d4189ec2"
chemteam
parents:
diff changeset
13 def parse_command_line(argv):
743bd6aa3c7a "planemo upload for repository https://github.com/galaxycomputationalchemistry/galaxy-tools-compchem/ commit 1b23e024af45cc0999d9142d07de6897d4189ec2"
chemteam
parents:
diff changeset
14 parser = argparse.ArgumentParser()
743bd6aa3c7a "planemo upload for repository https://github.com/galaxycomputationalchemistry/galaxy-tools-compchem/ commit 1b23e024af45cc0999d9142d07de6897d4189ec2"
chemteam
parents:
diff changeset
15 parser.add_argument('--itraj', help='input traj')
743bd6aa3c7a "planemo upload for repository https://github.com/galaxycomputationalchemistry/galaxy-tools-compchem/ commit 1b23e024af45cc0999d9142d07de6897d4189ec2"
chemteam
parents:
diff changeset
16 parser.add_argument('--istr', help='input str')
743bd6aa3c7a "planemo upload for repository https://github.com/galaxycomputationalchemistry/galaxy-tools-compchem/ commit 1b23e024af45cc0999d9142d07de6897d4189ec2"
chemteam
parents:
diff changeset
17 parser.add_argument('--itrajext', help='input traj ext')
743bd6aa3c7a "planemo upload for repository https://github.com/galaxycomputationalchemistry/galaxy-tools-compchem/ commit 1b23e024af45cc0999d9142d07de6897d4189ec2"
chemteam
parents:
diff changeset
18 parser.add_argument('--istrext', help='input str ext')
743bd6aa3c7a "planemo upload for repository https://github.com/galaxycomputationalchemistry/galaxy-tools-compchem/ commit 1b23e024af45cc0999d9142d07de6897d4189ec2"
chemteam
parents:
diff changeset
19 parser.add_argument('--icomponents', help='number of principle components')
743bd6aa3c7a "planemo upload for repository https://github.com/galaxycomputationalchemistry/galaxy-tools-compchem/ commit 1b23e024af45cc0999d9142d07de6897d4189ec2"
chemteam
parents:
diff changeset
20 parser.add_argument('--iindex', help='index of the PC')
743bd6aa3c7a "planemo upload for repository https://github.com/galaxycomputationalchemistry/galaxy-tools-compchem/ commit 1b23e024af45cc0999d9142d07de6897d4189ec2"
chemteam
parents:
diff changeset
21 parser.add_argument('--output', help='output')
743bd6aa3c7a "planemo upload for repository https://github.com/galaxycomputationalchemistry/galaxy-tools-compchem/ commit 1b23e024af45cc0999d9142d07de6897d4189ec2"
chemteam
parents:
diff changeset
22 parser.add_argument('--cosout', help='cosine output')
743bd6aa3c7a "planemo upload for repository https://github.com/galaxycomputationalchemistry/galaxy-tools-compchem/ commit 1b23e024af45cc0999d9142d07de6897d4189ec2"
chemteam
parents:
diff changeset
23 return parser.parse_args()
743bd6aa3c7a "planemo upload for repository https://github.com/galaxycomputationalchemistry/galaxy-tools-compchem/ commit 1b23e024af45cc0999d9142d07de6897d4189ec2"
chemteam
parents:
diff changeset
24
743bd6aa3c7a "planemo upload for repository https://github.com/galaxycomputationalchemistry/galaxy-tools-compchem/ commit 1b23e024af45cc0999d9142d07de6897d4189ec2"
chemteam
parents:
diff changeset
25
743bd6aa3c7a "planemo upload for repository https://github.com/galaxycomputationalchemistry/galaxy-tools-compchem/ commit 1b23e024af45cc0999d9142d07de6897d4189ec2"
chemteam
parents:
diff changeset
26 args = parse_command_line(sys.argv)
743bd6aa3c7a "planemo upload for repository https://github.com/galaxycomputationalchemistry/galaxy-tools-compchem/ commit 1b23e024af45cc0999d9142d07de6897d4189ec2"
chemteam
parents:
diff changeset
27
743bd6aa3c7a "planemo upload for repository https://github.com/galaxycomputationalchemistry/galaxy-tools-compchem/ commit 1b23e024af45cc0999d9142d07de6897d4189ec2"
chemteam
parents:
diff changeset
28 u = mda.Universe(args.istr, args.itraj,
743bd6aa3c7a "planemo upload for repository https://github.com/galaxycomputationalchemistry/galaxy-tools-compchem/ commit 1b23e024af45cc0999d9142d07de6897d4189ec2"
chemteam
parents:
diff changeset
29 topology_format=args.istrext, format=args.itrajext)
743bd6aa3c7a "planemo upload for repository https://github.com/galaxycomputationalchemistry/galaxy-tools-compchem/ commit 1b23e024af45cc0999d9142d07de6897d4189ec2"
chemteam
parents:
diff changeset
30
743bd6aa3c7a "planemo upload for repository https://github.com/galaxycomputationalchemistry/galaxy-tools-compchem/ commit 1b23e024af45cc0999d9142d07de6897d4189ec2"
chemteam
parents:
diff changeset
31 components = int(args.icomponents)
743bd6aa3c7a "planemo upload for repository https://github.com/galaxycomputationalchemistry/galaxy-tools-compchem/ commit 1b23e024af45cc0999d9142d07de6897d4189ec2"
chemteam
parents:
diff changeset
32 pca_index = int(args.iindex)
743bd6aa3c7a "planemo upload for repository https://github.com/galaxycomputationalchemistry/galaxy-tools-compchem/ commit 1b23e024af45cc0999d9142d07de6897d4189ec2"
chemteam
parents:
diff changeset
33
743bd6aa3c7a "planemo upload for repository https://github.com/galaxycomputationalchemistry/galaxy-tools-compchem/ commit 1b23e024af45cc0999d9142d07de6897d4189ec2"
chemteam
parents:
diff changeset
34 PSF_pca = pca.PCA(u, select='backbone')
743bd6aa3c7a "planemo upload for repository https://github.com/galaxycomputationalchemistry/galaxy-tools-compchem/ commit 1b23e024af45cc0999d9142d07de6897d4189ec2"
chemteam
parents:
diff changeset
35 PSF_pca.run()
743bd6aa3c7a "planemo upload for repository https://github.com/galaxycomputationalchemistry/galaxy-tools-compchem/ commit 1b23e024af45cc0999d9142d07de6897d4189ec2"
chemteam
parents:
diff changeset
36 n_pcs = np.where(PSF_pca.cumulated_variance > 0.95)[0][0]
743bd6aa3c7a "planemo upload for repository https://github.com/galaxycomputationalchemistry/galaxy-tools-compchem/ commit 1b23e024af45cc0999d9142d07de6897d4189ec2"
chemteam
parents:
diff changeset
37 atomgroup = u.select_atoms('backbone')
743bd6aa3c7a "planemo upload for repository https://github.com/galaxycomputationalchemistry/galaxy-tools-compchem/ commit 1b23e024af45cc0999d9142d07de6897d4189ec2"
chemteam
parents:
diff changeset
38
743bd6aa3c7a "planemo upload for repository https://github.com/galaxycomputationalchemistry/galaxy-tools-compchem/ commit 1b23e024af45cc0999d9142d07de6897d4189ec2"
chemteam
parents:
diff changeset
39 pca_space = PSF_pca.transform(atomgroup, n_components=components)
743bd6aa3c7a "planemo upload for repository https://github.com/galaxycomputationalchemistry/galaxy-tools-compchem/ commit 1b23e024af45cc0999d9142d07de6897d4189ec2"
chemteam
parents:
diff changeset
40 cosine = mda.analysis.pca.cosine_content(pca_space, pca_index)
743bd6aa3c7a "planemo upload for repository https://github.com/galaxycomputationalchemistry/galaxy-tools-compchem/ commit 1b23e024af45cc0999d9142d07de6897d4189ec2"
chemteam
parents:
diff changeset
41
743bd6aa3c7a "planemo upload for repository https://github.com/galaxycomputationalchemistry/galaxy-tools-compchem/ commit 1b23e024af45cc0999d9142d07de6897d4189ec2"
chemteam
parents:
diff changeset
42 PCA = list(pca_space)
743bd6aa3c7a "planemo upload for repository https://github.com/galaxycomputationalchemistry/galaxy-tools-compchem/ commit 1b23e024af45cc0999d9142d07de6897d4189ec2"
chemteam
parents:
diff changeset
43
743bd6aa3c7a "planemo upload for repository https://github.com/galaxycomputationalchemistry/galaxy-tools-compchem/ commit 1b23e024af45cc0999d9142d07de6897d4189ec2"
chemteam
parents:
diff changeset
44 with open(args.output, 'w') as f:
743bd6aa3c7a "planemo upload for repository https://github.com/galaxycomputationalchemistry/galaxy-tools-compchem/ commit 1b23e024af45cc0999d9142d07de6897d4189ec2"
chemteam
parents:
diff changeset
45 writer = csv.writer(f, delimiter='\t')
743bd6aa3c7a "planemo upload for repository https://github.com/galaxycomputationalchemistry/galaxy-tools-compchem/ commit 1b23e024af45cc0999d9142d07de6897d4189ec2"
chemteam
parents:
diff changeset
46 writer.writerows(PCA)
743bd6aa3c7a "planemo upload for repository https://github.com/galaxycomputationalchemistry/galaxy-tools-compchem/ commit 1b23e024af45cc0999d9142d07de6897d4189ec2"
chemteam
parents:
diff changeset
47
743bd6aa3c7a "planemo upload for repository https://github.com/galaxycomputationalchemistry/galaxy-tools-compchem/ commit 1b23e024af45cc0999d9142d07de6897d4189ec2"
chemteam
parents:
diff changeset
48 with open(args.cosout, 'w') as f1:
743bd6aa3c7a "planemo upload for repository https://github.com/galaxycomputationalchemistry/galaxy-tools-compchem/ commit 1b23e024af45cc0999d9142d07de6897d4189ec2"
chemteam
parents:
diff changeset
49 f1.write(str(cosine))