comparison commons/core/parsing/GtfParser.py @ 38:2c0c0a89fad7

Uploaded
author m-zytnicki
date Thu, 02 May 2013 09:56:47 -0400
parents 769e306b7933
children
comparison
equal deleted inserted replaced
37:d22fadc825e3 38:2c0c0a89fad7
1 #
2 # Copyright INRA-URGI 2009-2010
3 #
4 # This software is governed by the CeCILL license under French law and
5 # abiding by the rules of distribution of free software. You can use,
6 # modify and/ or redistribute the software under the terms of the CeCILL
7 # license as circulated by CEA, CNRS and INRIA at the following URL
8 # "http://www.cecill.info".
9 #
10 # As a counterpart to the access to the source code and rights to copy,
11 # modify and redistribute granted by the license, users are provided only
12 # with a limited warranty and the software's author, the holder of the
13 # economic rights, and the successive licensors have only limited
14 # liability.
15 #
16 # In this respect, the user's attention is drawn to the risks associated
17 # with loading, using, modifying and/or developing or reproducing the
18 # software by the user in light of its specific status of free software,
19 # that may mean that it is complicated to manipulate, and that also
20 # therefore means that it is reserved for developers and experienced
21 # professionals having in-depth computer knowledge. Users are therefore
22 # encouraged to load and test the software's suitability as regards their
23 # requirements in conditions enabling the security of their systems and/or
24 # data to be ensured and, more generally, to use and operate it in the
25 # same conditions as regards security.
26 #
27 # The fact that you are presently reading this means that you have had
28 # knowledge of the CeCILL license and that you accept its terms.
29 #
30 import re
31 import sys
32 from SMART.Java.Python.structure.Interval import Interval
33 from SMART.Java.Python.structure.Transcript import Transcript
34 from commons.core.parsing.TranscriptListParser import TranscriptListParser
35
36
37 class GtfParser(TranscriptListParser):
38 """A class that parses a GTF file and create a transcript list"""
39
40
41 def __init__(self, fileName, verbosity = 0):
42 super(GtfParser, self).__init__(fileName, verbosity)
43
44
45 def __del__(self):
46 super(GtfParser, self).__del__()
47
48
49 def getFileFormats():
50 return ["gtf", "gtf2"]
51 getFileFormats = staticmethod(getFileFormats)
52
53
54 def skipFirstLines(self):
55 pass
56
57
58 def parseLine(self, line):
59 if line[0] == "#":
60 return None
61 m = re.search(r"^\s*(\S+)\s+(\S+)\s+(\S+)\s+(\d+)\s+(\d+)\s+(\S+)\s+([+-.])\s+(\S+)\s+(\S.*)$", line)
62 if m == None:
63 raise Exception("\nLine %d '%s' does not have a GTF format\n" % (self.currentLineNb, line))
64 interval = Interval()
65 interval.setChromosome(m.group(1))
66 interval.setName("unnamed transcript")
67 interval.setStart(min(int(m.group(4)), int(m.group(5))))
68 interval.setEnd(max(int(m.group(4)), int(m.group(5))))
69 if m.group(7) == ".":
70 interval.setDirection("+")
71 else:
72 interval.setDirection(m.group(7))
73 if m.group(6).isdigit():
74 interval.setTagValue("score", m.group(6))
75 type = m.group(3)
76
77 if type not in ("transcript", "exon"):
78 return None
79
80 remainings = m.group(9).split(";")
81 for remaining in remainings:
82 remaining = remaining.strip()
83 if remaining == "":
84 continue
85 parts = remaining.split(" ", 1)
86 field = parts[0].strip()
87 value = " ".join(parts[1:]).strip(" \"")
88 if field == "transcript_id":
89 interval.setTagValue("ID", value)
90 elif field == "gene_name":
91 interval.setName(value)
92 elif field == "transcript_name":
93 interval.setName(value)
94 elif field == "exon_number":
95 continue
96 else:
97 try:
98 intValue = int(value)
99 interval.setTagValue(field, intValue)
100 except ValueError:
101 interval.setTagValue(field, value)
102
103 self.currentTranscriptAddress = self.previousTranscriptAddress
104 if self.currentTranscript == None or interval.getTagValue("ID") != self.currentTranscript.getTagValue("ID"):
105 transcript = self.currentTranscript
106 self.currentTranscript = Transcript()
107 self.currentTranscript.copy(interval)
108 self.currentTranscript.setTagValue("feature", "transcript")
109 self.previousTranscriptAddress = self.currentAddress
110 return transcript
111 if type == "exon":
112 self.currentTranscript.addExon(interval)
113 return None