|
6
|
1 #! /usr/bin/env python
|
|
|
2 #
|
|
|
3 # Copyright INRA-URGI 2009-2010
|
|
|
4 #
|
|
|
5 # This software is governed by the CeCILL license under French law and
|
|
|
6 # abiding by the rules of distribution of free software. You can use,
|
|
|
7 # modify and/ or redistribute the software under the terms of the CeCILL
|
|
|
8 # license as circulated by CEA, CNRS and INRIA at the following URL
|
|
|
9 # "http://www.cecill.info".
|
|
|
10 #
|
|
|
11 # As a counterpart to the access to the source code and rights to copy,
|
|
|
12 # modify and redistribute granted by the license, users are provided only
|
|
|
13 # with a limited warranty and the software's author, the holder of the
|
|
|
14 # economic rights, and the successive licensors have only limited
|
|
|
15 # liability.
|
|
|
16 #
|
|
|
17 # In this respect, the user's attention is drawn to the risks associated
|
|
|
18 # with loading, using, modifying and/or developing or reproducing the
|
|
|
19 # software by the user in light of its specific status of free software,
|
|
|
20 # that may mean that it is complicated to manipulate, and that also
|
|
|
21 # therefore means that it is reserved for developers and experienced
|
|
|
22 # professionals having in-depth computer knowledge. Users are therefore
|
|
|
23 # encouraged to load and test the software's suitability as regards their
|
|
|
24 # requirements in conditions enabling the security of their systems and/or
|
|
|
25 # data to be ensured and, more generally, to use and operate it in the
|
|
|
26 # same conditions as regards security.
|
|
|
27 #
|
|
|
28 # The fact that you are presently reading this means that you have had
|
|
|
29 # knowledge of the CeCILL license and that you accept its terms.
|
|
|
30 #
|
|
|
31 """
|
|
|
32 Clean a GTF file
|
|
|
33 """
|
|
|
34
|
|
|
35 import shlex
|
|
|
36 from SMART.Java.Python.cleaning.TranscriptListCleaner import TranscriptListCleaner
|
|
|
37 from SMART.Java.Python.misc.Progress import Progress
|
|
|
38 from SMART.Java.Python.misc.UnlimitedProgress import UnlimitedProgress
|
|
|
39
|
|
|
40 count = {}
|
|
|
41
|
|
|
42 class ParsedLine(object):
|
|
|
43 def __init__(self, line, cpt):
|
|
|
44 self.line = line
|
|
|
45 self.cpt = cpt
|
|
|
46 self.parse()
|
|
|
47
|
|
|
48 def parse(self):
|
|
|
49 self.line = self.line.strip()
|
|
|
50 self.splittedLine = self.line.split(None, 8)
|
|
|
51 if len(self.splittedLine) < 9:
|
|
|
52 raise Exception("Line '%s' has less than 9 fields. Exiting..." % (self.line))
|
|
|
53 self.type = self.splittedLine[2]
|
|
|
54 self.parseOptions()
|
|
|
55
|
|
|
56 def parseOptions(self):
|
|
|
57 self.parsedOptions = {}
|
|
|
58 key = None
|
|
|
59 value = ""
|
|
|
60 for option in shlex.split(self.splittedLine[8]):
|
|
|
61 option = option.strip()
|
|
|
62 if option == "": continue
|
|
|
63 if key == None:
|
|
|
64 key = option
|
|
|
65 else:
|
|
|
66 endValue = False
|
|
|
67 if option[-1] == ";":
|
|
|
68 endValue = True
|
|
|
69 option.rstrip(";")
|
|
|
70 value = "%s \"%s\"" % (value, option)
|
|
|
71 if endValue:
|
|
|
72 self.parsedOptions[key] = value
|
|
|
73 if key == "transcript_id":
|
|
|
74 self.transcriptId = value
|
|
|
75 key = None
|
|
|
76 value = ""
|
|
|
77
|
|
|
78 def export(self):
|
|
|
79 return "%s\n" % (self.line)
|
|
|
80
|
|
|
81
|
|
|
82 class GtfCleaner(TranscriptListCleaner):
|
|
|
83
|
|
|
84 def __init__(self, verbosity = 1):
|
|
|
85 super(GtfCleaner, self).__init__(verbosity)
|
|
|
86 self.acceptedTypes = ["exon"]
|
|
|
87 self.parents = {}
|
|
|
88
|
|
|
89 def getFileFormats():
|
|
|
90 return ["gtf"]
|
|
|
91 getFileFormats = staticmethod(getFileFormats)
|
|
|
92
|
|
|
93 def setAcceptedTypes(self, types):
|
|
|
94 self.acceptedTypes = types
|
|
|
95
|
|
|
96 def parse(self):
|
|
|
97 progress = UnlimitedProgress(100000, "Reading input file", self.verbosity)
|
|
|
98 for cpt, line in enumerate(self.inputHandle):
|
|
|
99 if not line or line[0] == "#": continue
|
|
|
100 parsedLine = ParsedLine(line, cpt)
|
|
|
101 if self.acceptedTypes == None or parsedLine.type in self.acceptedTypes:
|
|
|
102 transcriptId = parsedLine.transcriptId
|
|
|
103 if transcriptId not in self.parents:
|
|
|
104 self.parents[parsedLine.transcriptId] = [parsedLine]
|
|
|
105 else:
|
|
|
106 self.parents[parsedLine.transcriptId].append(parsedLine)
|
|
|
107 progress.inc()
|
|
|
108 progress.done()
|
|
|
109
|
|
|
110 def write(self):
|
|
|
111 progress = Progress(len(self.parents.keys()), "Writing output file", self.verbosity)
|
|
|
112 for parent in sorted(self.parents.keys()):
|
|
|
113 for line in self.parents[parent]:
|
|
|
114 self.outputHandle.write(line.export())
|
|
|
115 progress.inc()
|
|
|
116 progress.done()
|
|
|
117
|
|
|
118 def _clean(self):
|
|
|
119 self.parse()
|
|
|
120 self.write()
|
|
|
121
|
