6
|
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 GbParser(TranscriptListParser):
|
|
38 """A class that parses a GBrowse file and create a transcript list"""
|
|
39
|
|
40
|
|
41 def __init__(self, fileName, verbosity = 0):
|
|
42 self.reference = None
|
|
43 self.color = None
|
|
44 super(GbParser, self).__init__(fileName, verbosity)
|
|
45
|
|
46
|
|
47 def __del__(self):
|
|
48 super(GbParser, self).__del__()
|
|
49
|
|
50
|
|
51 def getFileFormats():
|
|
52 return ["gb", "gbrowse"]
|
|
53 getFileFormats = staticmethod(getFileFormats)
|
|
54
|
|
55
|
|
56 def skipFirstLines(self):
|
|
57 for line in self.handle:
|
|
58 self.currentLineNb += 1
|
|
59 line = line.strip()
|
|
60 m = re.search(r"^\s*bgcolor\s*=\s*(\S+)\s*$", line)
|
|
61 if m != None:
|
|
62 self.color = m.group(1)
|
|
63 if line == "":
|
|
64 return
|
|
65
|
|
66
|
|
67 def parseLine(self, line):
|
|
68 transcript = Transcript()
|
|
69 # first line (reference)
|
|
70 m = re.search(r"^\s*reference\s*=\s*(\S+)\s*$", line)
|
|
71 if m != None:
|
|
72 self.reference = m.group(1)
|
|
73 for line in self.handle:
|
|
74 line = line.strip()
|
|
75 self.currentLineNb += 1
|
|
76 break
|
|
77 # second line (genomic coordinates)
|
|
78 m = re.search(r"^\s*READS\s+(\S+)\s+(\S+)\s+\"([^\"]*)\"\s*$", line)
|
|
79 if m == None:
|
|
80 sys.exit("\nLine %d '%s' does not have a GBrowse format" % (self.currentLineNb, line))
|
|
81 if self.reference == None:
|
|
82 sys.exit("Cannot get reference of GBrowse line %d '%s'" % (self.currentLineNb, line))
|
|
83 transcript.setChromosome(self.reference)
|
|
84 transcript.setName(m.group(1))
|
|
85 transcript.setComment(m.group(3))
|
|
86 # exons
|
|
87 exons = m.group(2).split(",")
|
|
88 transcriptStart = 1000000000
|
|
89 transcriptEnd = 0
|
|
90 direction = 0
|
|
91 for exon in exons:
|
|
92 m = re.search(r"^(\d+)-(\d+)$", exon)
|
|
93 if m == None:
|
|
94 sys.exit("\nCannot read GBrowse exon line %d '%s'" % (self.currentLineNb, exon))
|
|
95 interval = Interval()
|
|
96 interval.setChromosome(transcript.chromosome)
|
|
97 direction += int(m.group(2)) - int(m.group(1))
|
|
98 start = min(int(m.group(1)), int(m.group(2)))
|
|
99 end = max(int(m.group(1)), int(m.group(2)))
|
|
100 interval.setStart(start)
|
|
101 interval.setEnd(end)
|
|
102 transcriptStart = min(transcriptStart, start)
|
|
103 transcriptEnd = max(transcriptEnd, end)
|
|
104 transcript.addExon(interval)
|
|
105 transcript.setStart(transcriptStart)
|
|
106 transcript.setEnd(transcriptEnd)
|
|
107 transcript.setDirection(direction)
|
|
108 for exon in transcript.getExons():
|
|
109 exon.setDirection(direction)
|
|
110 return transcript
|
|
111
|