Mercurial > repos > jjohnson > spectrast

comparison link_scan_datasets.py @ 3:7f02fc51bddf draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/spectrast commit 379705f578f9a0465f497894c7d2b5f68b6a55e6-dirty
author jjohnson
date Wed, 25 Jul 2018 10:58:17 -0400
parents
children 274fdc50169b
comparison
equal deleted inserted replaced
2:e67b0cc10377 3:7f02fc51bddf
1 #!/usr/bin/env python
2
3 from __future__ import print_function
4
5 import argparse
6 import difflib
7 from difflib import SequenceMatcher
8 import os
9 import os.path
10 import sys
11 import xml.sax
12
13
14
15 def __main__():
16 parser = argparse.ArgumentParser(
17 description='link spectrum datasets to the name used' +
18 ' in the identification dataset')
19 parser.add_argument(
20 'ident_files', nargs='+',
21 help='Pepxml or mzIdentML')
22 parser.add_argument(
23 '-n', '--scan_name', default=[], action='append',
24 help='Name for scan file')
25 parser.add_argument(
26 '-f', '--scan_file', default=[], action='append',
27 help='Path for scan file')
28 args = parser.parse_args()
29
30 class MzidHandler( xml.sax.ContentHandler):
31 def __init__(self):
32 xml.sax.ContentHandler.__init__(self)
33 self.spectraDataFiles = []
34 self.spectraDataNames = []
35 self.searchDatabaseFiles = []
36 self.searchDatabaseNames = []
37 def startElement(self, tag, attrs):
38 if tag == 'SpectraData':
39 id = attrs['id']
40 path = attrs['location']
41 filename = os.path.basename(path)
42 name = attrs['name'] if 'name' in attrs else None
43 self.spectraDataFiles.append(filename)
44 self.spectraDataNames.append(name if name else id)
45 print ("SpectraData: %s %s" % (name if name else id, path))
46 if tag == 'SearchDatabase':
47 id = attrs['id']
48 path = attrs['location']
49 filename = os.path.basename(path)
50 name = attrs['name'] if 'name' in attrs else None
51 self.searchDatabaseFiles.append(filename)
52 self.searchDatabaseNames.append(name if name else id)
53 print ("SearchDatabase: %s %s" % (name if name else id, path))
54 def endElement( self, name):
55 pass
56 def characters( self, data):
57 pass
58
59 class PepXmlHandler( xml.sax.ContentHandler):
60 def __init__(self):
61 xml.sax.ContentHandler.__init__(self)
62 self.spectraDataFiles = []
63 self.spectraDataNames = []
64 def startElement(self, tag, attrs):
65 if tag == 'msms_run_summary':
66 basename = attrs['base_name']
67 name = os.path.basename(basename)
68 ext = attrs['raw_data']
69 path = '%s%s' % (basename,ext)
70 filename = os.path.basename(path)
71 self.spectraDataFiles.append(filename)
72 self.spectraDataNames.append(name)
73 print ("SpectraData: %s %s" % (name, path))
74 def endElement( self, name):
75 pass
76 def characters( self, data):
77 pass
78
79 parser = xml.sax.make_parser()
80 parser.setFeature(xml.sax.handler.feature_namespaces, 0)
81 handler = PepXmlHandler()
82 parser.setContentHandler( handler )
83 for ident in args.ident_files:
84 parser.parse(ident)
85
86 spectra_names = handler.spectraDataFiles
87
88 def best_match(name):
89 if name in spectra_names:
90 return name
91 try:
92 r = [SequenceMatcher(None, name, spectra_names[x]).ratio() for x in range(len(spectra_names))]
93 return spectra_names[r.index(max(r))]
94 except Exception, e:
95 print ("best_match: %s %s" % (name, e))
96
97 for i,name in enumerate(args.scan_name):
98 path = args.scan_file[i] if len(args.scan_file) > i else ''
99 (root, ext) = os.path.splitext(name)
100 print ("SpectraFile: %s %s" % (name, path))
101 iname = best_match(name)
102 print ("IdentName: %s %s" % (name, iname))
103 if not os.path.exists(iname) and os.path.exists(path):
104 os.symlink(path, iname)
105 print ("%s -> %s" % (iname, path))
106
107
108 if __name__ == "__main__":
109 __main__()
110