annotate pca_cosine.py @ 2:795a5996cdc8 draft default tip

"planemo upload for repository https://github.com/galaxycomputationalchemistry/galaxy-tools-compchem/ commit f1c3c88c7395f2e84cbc533199406aadb79c5c07"
author chemteam
date Fri, 13 Nov 2020 19:40:30 +0000
parents 78aa3659fcd1
children
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
0
78aa3659fcd1 "planemo upload for repository https://github.com/galaxycomputationalchemistry/galaxy-tools-compchem/ commit 1b23e024af45cc0999d9142d07de6897d4189ec2"
chemteam
parents:
diff changeset
1 #!/usr/bin/env python
78aa3659fcd1 "planemo upload for repository https://github.com/galaxycomputationalchemistry/galaxy-tools-compchem/ commit 1b23e024af45cc0999d9142d07de6897d4189ec2"
chemteam
parents:
diff changeset
2
78aa3659fcd1 "planemo upload for repository https://github.com/galaxycomputationalchemistry/galaxy-tools-compchem/ commit 1b23e024af45cc0999d9142d07de6897d4189ec2"
chemteam
parents:
diff changeset
3 import argparse
78aa3659fcd1 "planemo upload for repository https://github.com/galaxycomputationalchemistry/galaxy-tools-compchem/ commit 1b23e024af45cc0999d9142d07de6897d4189ec2"
chemteam
parents:
diff changeset
4 import csv
78aa3659fcd1 "planemo upload for repository https://github.com/galaxycomputationalchemistry/galaxy-tools-compchem/ commit 1b23e024af45cc0999d9142d07de6897d4189ec2"
chemteam
parents:
diff changeset
5 import sys
78aa3659fcd1 "planemo upload for repository https://github.com/galaxycomputationalchemistry/galaxy-tools-compchem/ commit 1b23e024af45cc0999d9142d07de6897d4189ec2"
chemteam
parents:
diff changeset
6
78aa3659fcd1 "planemo upload for repository https://github.com/galaxycomputationalchemistry/galaxy-tools-compchem/ commit 1b23e024af45cc0999d9142d07de6897d4189ec2"
chemteam
parents:
diff changeset
7 import MDAnalysis as mda
78aa3659fcd1 "planemo upload for repository https://github.com/galaxycomputationalchemistry/galaxy-tools-compchem/ commit 1b23e024af45cc0999d9142d07de6897d4189ec2"
chemteam
parents:
diff changeset
8 import MDAnalysis.analysis.pca as pca
78aa3659fcd1 "planemo upload for repository https://github.com/galaxycomputationalchemistry/galaxy-tools-compchem/ commit 1b23e024af45cc0999d9142d07de6897d4189ec2"
chemteam
parents:
diff changeset
9
78aa3659fcd1 "planemo upload for repository https://github.com/galaxycomputationalchemistry/galaxy-tools-compchem/ commit 1b23e024af45cc0999d9142d07de6897d4189ec2"
chemteam
parents:
diff changeset
10 import numpy as np
78aa3659fcd1 "planemo upload for repository https://github.com/galaxycomputationalchemistry/galaxy-tools-compchem/ commit 1b23e024af45cc0999d9142d07de6897d4189ec2"
chemteam
parents:
diff changeset
11
78aa3659fcd1 "planemo upload for repository https://github.com/galaxycomputationalchemistry/galaxy-tools-compchem/ commit 1b23e024af45cc0999d9142d07de6897d4189ec2"
chemteam
parents:
diff changeset
12
78aa3659fcd1 "planemo upload for repository https://github.com/galaxycomputationalchemistry/galaxy-tools-compchem/ commit 1b23e024af45cc0999d9142d07de6897d4189ec2"
chemteam
parents:
diff changeset
13 def parse_command_line(argv):
78aa3659fcd1 "planemo upload for repository https://github.com/galaxycomputationalchemistry/galaxy-tools-compchem/ commit 1b23e024af45cc0999d9142d07de6897d4189ec2"
chemteam
parents:
diff changeset
14 parser = argparse.ArgumentParser()
78aa3659fcd1 "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')
78aa3659fcd1 "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')
78aa3659fcd1 "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')
78aa3659fcd1 "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')
78aa3659fcd1 "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')
78aa3659fcd1 "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')
78aa3659fcd1 "planemo upload for repository https://github.com/galaxycomputationalchemistry/galaxy-tools-compchem/ commit 1b23e024af45cc0999d9142d07de6897d4189ec2"
chemteam
parents:
diff changeset
21 parser.add_argument('--output', help='output')
78aa3659fcd1 "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')
78aa3659fcd1 "planemo upload for repository https://github.com/galaxycomputationalchemistry/galaxy-tools-compchem/ commit 1b23e024af45cc0999d9142d07de6897d4189ec2"
chemteam
parents:
diff changeset
23 return parser.parse_args()
78aa3659fcd1 "planemo upload for repository https://github.com/galaxycomputationalchemistry/galaxy-tools-compchem/ commit 1b23e024af45cc0999d9142d07de6897d4189ec2"
chemteam
parents:
diff changeset
24
78aa3659fcd1 "planemo upload for repository https://github.com/galaxycomputationalchemistry/galaxy-tools-compchem/ commit 1b23e024af45cc0999d9142d07de6897d4189ec2"
chemteam
parents:
diff changeset
25
78aa3659fcd1 "planemo upload for repository https://github.com/galaxycomputationalchemistry/galaxy-tools-compchem/ commit 1b23e024af45cc0999d9142d07de6897d4189ec2"
chemteam
parents:
diff changeset
26 args = parse_command_line(sys.argv)
78aa3659fcd1 "planemo upload for repository https://github.com/galaxycomputationalchemistry/galaxy-tools-compchem/ commit 1b23e024af45cc0999d9142d07de6897d4189ec2"
chemteam
parents:
diff changeset
27
78aa3659fcd1 "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,
78aa3659fcd1 "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)
78aa3659fcd1 "planemo upload for repository https://github.com/galaxycomputationalchemistry/galaxy-tools-compchem/ commit 1b23e024af45cc0999d9142d07de6897d4189ec2"
chemteam
parents:
diff changeset
30
78aa3659fcd1 "planemo upload for repository https://github.com/galaxycomputationalchemistry/galaxy-tools-compchem/ commit 1b23e024af45cc0999d9142d07de6897d4189ec2"
chemteam
parents:
diff changeset
31 components = int(args.icomponents)
78aa3659fcd1 "planemo upload for repository https://github.com/galaxycomputationalchemistry/galaxy-tools-compchem/ commit 1b23e024af45cc0999d9142d07de6897d4189ec2"
chemteam
parents:
diff changeset
32 pca_index = int(args.iindex)
78aa3659fcd1 "planemo upload for repository https://github.com/galaxycomputationalchemistry/galaxy-tools-compchem/ commit 1b23e024af45cc0999d9142d07de6897d4189ec2"
chemteam
parents:
diff changeset
33
78aa3659fcd1 "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')
78aa3659fcd1 "planemo upload for repository https://github.com/galaxycomputationalchemistry/galaxy-tools-compchem/ commit 1b23e024af45cc0999d9142d07de6897d4189ec2"
chemteam
parents:
diff changeset
35 PSF_pca.run()
78aa3659fcd1 "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]
78aa3659fcd1 "planemo upload for repository https://github.com/galaxycomputationalchemistry/galaxy-tools-compchem/ commit 1b23e024af45cc0999d9142d07de6897d4189ec2"
chemteam
parents:
diff changeset
37 atomgroup = u.select_atoms('backbone')
78aa3659fcd1 "planemo upload for repository https://github.com/galaxycomputationalchemistry/galaxy-tools-compchem/ commit 1b23e024af45cc0999d9142d07de6897d4189ec2"
chemteam
parents:
diff changeset
38
78aa3659fcd1 "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)
78aa3659fcd1 "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)
78aa3659fcd1 "planemo upload for repository https://github.com/galaxycomputationalchemistry/galaxy-tools-compchem/ commit 1b23e024af45cc0999d9142d07de6897d4189ec2"
chemteam
parents:
diff changeset
41
78aa3659fcd1 "planemo upload for repository https://github.com/galaxycomputationalchemistry/galaxy-tools-compchem/ commit 1b23e024af45cc0999d9142d07de6897d4189ec2"
chemteam
parents:
diff changeset
42 PCA = list(pca_space)
78aa3659fcd1 "planemo upload for repository https://github.com/galaxycomputationalchemistry/galaxy-tools-compchem/ commit 1b23e024af45cc0999d9142d07de6897d4189ec2"
chemteam
parents:
diff changeset
43
78aa3659fcd1 "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:
78aa3659fcd1 "planemo upload for repository https://github.com/galaxycomputationalchemistry/galaxy-tools-compchem/ commit 1b23e024af45cc0999d9142d07de6897d4189ec2"
chemteam
parents:
diff changeset
45 writer = csv.writer(f, delimiter='\t')
78aa3659fcd1 "planemo upload for repository https://github.com/galaxycomputationalchemistry/galaxy-tools-compchem/ commit 1b23e024af45cc0999d9142d07de6897d4189ec2"
chemteam
parents:
diff changeset
46 writer.writerows(PCA)
78aa3659fcd1 "planemo upload for repository https://github.com/galaxycomputationalchemistry/galaxy-tools-compchem/ commit 1b23e024af45cc0999d9142d07de6897d4189ec2"
chemteam
parents:
diff changeset
47
78aa3659fcd1 "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:
78aa3659fcd1 "planemo upload for repository https://github.com/galaxycomputationalchemistry/galaxy-tools-compchem/ commit 1b23e024af45cc0999d9142d07de6897d4189ec2"
chemteam
parents:
diff changeset
49 f1.write(str(cosine))