|
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 from commons.core.writer.TranscriptListWriter import TranscriptListWriter
|
|
|
31
|
|
|
32
|
|
|
33 class Gff3Writer(TranscriptListWriter):
|
|
|
34 """
|
|
|
35 A class that writes a transcript list into a file with GFF3 format
|
|
|
36 @ivar fileName: name of the file
|
|
|
37 @type fileName: string
|
|
|
38 @ivar handle: handle to the file
|
|
|
39 @type handle: file handle
|
|
|
40 """
|
|
|
41
|
|
|
42
|
|
|
43 def __init__(self, fileName, verbosity = 0, title="S-MART", feature="transcript", featurePart="exon"):
|
|
|
44 """
|
|
|
45 Constructor
|
|
|
46 @param fileName: name of the file
|
|
|
47 @type fileName: string
|
|
|
48 @param verbosity: verbosity
|
|
|
49 @type verbosity: int
|
|
|
50 """
|
|
|
51 self.header = ""
|
|
|
52 self.title = title
|
|
|
53 self.feature = feature
|
|
|
54 self.featurePart = featurePart
|
|
|
55 super(Gff3Writer, self).__init__(fileName, verbosity)
|
|
|
56
|
|
|
57
|
|
|
58 @staticmethod
|
|
|
59 def getFileFormats():
|
|
|
60 """
|
|
|
61 Get the format of the file
|
|
|
62 """
|
|
|
63 return ["gff3", "gff"]
|
|
|
64
|
|
|
65
|
|
|
66 @staticmethod
|
|
|
67 def getExtension():
|
|
|
68 """
|
|
|
69 Get the usual extension for the file
|
|
|
70 """
|
|
|
71 return "gff3"
|
|
|
72
|
|
|
73
|
|
|
74 def setTitle(self, title):
|
|
|
75 """
|
|
|
76 Set the title of the transcripts
|
|
|
77 @param title: the title of the transcripts
|
|
|
78 @type title: string
|
|
|
79 """
|
|
|
80 self.title = title
|
|
|
81
|
|
|
82 def setFeature(self, feature):
|
|
|
83 """
|
|
|
84 Set the name of the feature
|
|
|
85 @param title: the title of the feature
|
|
|
86 @type feature: string
|
|
|
87 """
|
|
|
88 self.feature = feature
|
|
|
89
|
|
|
90 def setFeaturePart(self, featurePart):
|
|
|
91 """
|
|
|
92 Set the name of the feature part
|
|
|
93 @param title: the title of the feature part
|
|
|
94 @type featurePart: string
|
|
|
95 """
|
|
|
96 self.featurePart = featurePart
|
|
|
97
|
|
|
98
|
|
|
99 def printTranscript(self, transcript):
|
|
|
100 """
|
|
|
101 Export the given transcript with GFF2 format
|
|
|
102 @param transcript: transcript to be printed
|
|
|
103 @type transcript: class L{Transcript<Transcript>}
|
|
|
104 @return: a string
|
|
|
105 """
|
|
|
106 direction = "+"
|
|
|
107 if transcript.getDirection() == -1:
|
|
|
108 direction = "-"
|
|
|
109 transcript.sortExonsIncreasing()
|
|
|
110 if "ID" not in transcript.getTagValues():
|
|
|
111 transcript.setTagValue("ID", transcript.getUniqueName())
|
|
|
112 feature = self.feature
|
|
|
113 tags = transcript.tags
|
|
|
114 if "feature" in transcript.getTagNames():
|
|
|
115 feature = transcript.getTagValue("feature")
|
|
|
116 del transcript.tags["feature"]
|
|
|
117 score = "."
|
|
|
118 if "score" in transcript.getTagNames():
|
|
|
119 score = "%d" % (int(transcript.getTagValue("score")))
|
|
|
120 del transcript.tags["score"]
|
|
|
121 comment = transcript.getTagValues(";", "=")
|
|
|
122 string = "%s\t%s\t%s\t%d\t%d\t%s\t%s\t.\t%s\n" % (transcript.getChromosome(), self.title, feature, transcript.getStart(), transcript.getEnd(), score, direction, comment)
|
|
|
123 if len(transcript.exons) > 1:
|
|
|
124 for i, exon in enumerate(transcript.getExons()):
|
|
|
125 if "score" in exon.getTagNames():
|
|
|
126 score = "%d" % (int(exon.getTagValue("score")))
|
|
|
127 string += "%s\t%s\t%s\t%d\t%d\t%s\t%s\t.\tID=%s-%s%d;Name=%s-%s%d;Parent=%s\n" % (transcript.getChromosome(), self.title,self.featurePart, exon.getStart(), exon.getEnd(), score, direction, transcript.getTagValue("ID"),self.featurePart, i+1, transcript.name,self.featurePart, i+1, transcript.getTagValue("ID"))
|
|
|
128 self.tags = tags
|
|
|
129 return string
|
|
|
130
|
