|
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 """Compare overlap of two transcript lists"""
|
|
|
32 import sys
|
|
|
33 import os
|
|
|
34 from optparse import OptionParser
|
|
|
35 from SMART.Java.Python.misc import Utils
|
|
|
36 from SMART.Java.Python.structure.TranscriptContainer import TranscriptContainer
|
|
|
37 from commons.core.writer.TranscriptWriter import TranscriptWriter
|
|
|
38 from SMART.Java.Python.structure.TranscriptListsComparator import TranscriptListsComparator
|
|
|
39 from SMART.Java.Python.misc.RPlotter import RPlotter
|
|
|
40 from commons.core.writer.Gff3Writer import Gff3Writer
|
|
|
41
|
|
|
42 class CompareOverlapping(object):
|
|
|
43
|
|
|
44 def __init__(self):
|
|
|
45 self._options = None
|
|
|
46
|
|
|
47
|
|
|
48 def setAttributesFromCmdLine(self):
|
|
|
49 description = "Compare Overlapping v1.0.3: Get the data which overlap with a reference set. [Category: Data Comparison]"
|
|
|
50
|
|
|
51 parser = OptionParser(description = description)
|
|
|
52 parser.add_option("-i", "--input1", dest="inputFileName1", action="store", type="string", help="input file 1 [compulsory] [format: file in transcript format given by -f]")
|
|
|
53 parser.add_option("-f", "--format1", dest="format1", action="store", type="string", help="format of file 1 [compulsory] [format: transcript file format]")
|
|
|
54 parser.add_option("-j", "--input2", dest="inputFileName2", action="store", type="string", help="input file 2 [compulsory] [format: file in transcript format given by -g]")
|
|
|
55 parser.add_option("-g", "--format2", dest="format2", action="store", type="string", help="format of file 2 [compulsory] [format: transcript file format]")
|
|
|
56 parser.add_option("-o", "--output", dest="output", action="store", default=None, type="string", help="output file [compulsory] [format: output file in GFF3 format]")
|
|
|
57 parser.add_option("-S", "--start1", dest="start1", action="store", default=None, type="int", help="only consider the n first nucleotides of the transcripts in file 1 (do not use it with -U) [format: int]")
|
|
|
58 parser.add_option("-s", "--start2", dest="start2", action="store", default=None, type="int", help="only consider the n first nucleotides of the transcripts in file 2 (do not use it with -u) [format: int]")
|
|
|
59 parser.add_option("-U", "--end1", dest="end1", action="store", default=None, type="int", help="only consider the n last nucleotides of the transcripts in file 1 (do not use it with -S) [format: int]")
|
|
|
60 parser.add_option("-u", "--end2", dest="end2", action="store", default=None, type="int", help="only consider the n last nucleotides of the transcripts in file 2 (do not use it with -s) [format: int]")
|
|
|
61 parser.add_option("-t", "--intron", dest="introns", action="store_true", default=False, help="also report introns [format: bool] [default: false]")
|
|
|
62 parser.add_option("-E", "--5primeExtension1", dest="fivePrime1", action="store", default=None, type="int", help="extension towards 5' in file 1 [format: int]")
|
|
|
63 parser.add_option("-e", "--5primeExtension2", dest="fivePrime2", action="store", default=None, type="int", help="extension towards 5' in file 2 [format: int]")
|
|
|
64 parser.add_option("-N", "--3primeExtension1", dest="threePrime1", action="store", default=None, type="int", help="extension towards 3' in file 1 [format: int]")
|
|
|
65 parser.add_option("-n", "--3primeExtension2", dest="threePrime2", action="store", default=None, type="int", help="extension towards 3' in file 2 [format: int]")
|
|
|
66 parser.add_option("-c", "--colinear", dest="colinear", action="store_true", default=False, help="colinear only [format: bool] [default: false]")
|
|
|
67 parser.add_option("-a", "--antisense", dest="antisense", action="store_true", default=False, help="antisense only [format: bool] [default: false]")
|
|
|
68 parser.add_option("-d", "--distance", dest="distance", action="store", default=None, type="int", help="accept some distance between query and reference [format: int]")
|
|
|
69 parser.add_option("-k", "--included", dest="included", action="store_true", default=False, help="keep only elements from file 1 which are included in an element of file 2 [format: bool] [default: false]")
|
|
|
70 parser.add_option("-K", "--including", dest="including", action="store_true", default=False, help="keep only elements from file 2 which are included in an element of file 1 [format: bool] [default: false]")
|
|
|
71 parser.add_option("-m", "--minOverlap", dest="minOverlap", action="store", default=1, type="int", help="minimum number of nucleotides overlapping to declare an overlap [format: int] [default: 1]")
|
|
|
72 parser.add_option("-p", "--pcOverlap", dest="pcOverlap", action="store", default=None, type="int", help="minimum percentage of nucleotides to overlap to declare an overlap [format: int]")
|
|
|
73 parser.add_option("-O", "--notOverlapping", dest="notOverlapping", action="store_true", default=False, help="also output not overlapping data [format: bool] [default: false]")
|
|
|
74 parser.add_option("-x", "--exclude", dest="exclude", action="store_true", default=False, help="invert the match [format: bool] [default: false]")
|
|
|
75 parser.add_option("-v", "--verbosity", dest="verbosity", action="store", default=1, type="int", help="trace level [format: int]")
|
|
|
76 parser.add_option("-l", "--log", dest="log", action="store_true", default=False, help="write a log file [format: bool] [default: false]")
|
|
|
77 (self._options, args) = parser.parse_args()
|
|
|
78
|
|
|
79
|
|
|
80 def run(self):
|
|
|
81 logHandle = None
|
|
|
82 if self._options.log:
|
|
|
83 logHandle = open(self._options.output, "w")
|
|
|
84
|
|
|
85 transcriptContainer1 = TranscriptContainer(self._options.inputFileName1, self._options.format1, self._options.verbosity)
|
|
|
86 transcriptContainer2 = TranscriptContainer(self._options.inputFileName2, self._options.format2, self._options.verbosity)
|
|
|
87 writer = TranscriptWriter(self._options.output, "gff3", self._options.verbosity)
|
|
|
88
|
|
|
89 transcriptListComparator = TranscriptListsComparator(logHandle, self._options.verbosity)
|
|
|
90 transcriptListComparator.restrictToStart(transcriptListComparator.QUERY, self._options.start1)
|
|
|
91 transcriptListComparator.restrictToStart(transcriptListComparator.REFERENCE, self._options.start2)
|
|
|
92 transcriptListComparator.restrictToEnd(transcriptListComparator.QUERY, self._options.end1)
|
|
|
93 transcriptListComparator.restrictToEnd(transcriptListComparator.REFERENCE, self._options.end2)
|
|
|
94 transcriptListComparator.extendFivePrime(transcriptListComparator.QUERY, self._options.fivePrime1)
|
|
|
95 transcriptListComparator.extendFivePrime(transcriptListComparator.REFERENCE, self._options.fivePrime2)
|
|
|
96 transcriptListComparator.extendThreePrime(transcriptListComparator.QUERY, self._options.threePrime1)
|
|
|
97 transcriptListComparator.extendThreePrime(transcriptListComparator.REFERENCE, self._options.threePrime2)
|
|
|
98 transcriptListComparator.acceptIntrons(transcriptListComparator.QUERY, self._options.introns)
|
|
|
99 transcriptListComparator.acceptIntrons(transcriptListComparator.REFERENCE, self._options.introns)
|
|
|
100 transcriptListComparator.getAntisenseOnly(self._options.antisense)
|
|
|
101 transcriptListComparator.getColinearOnly(self._options.colinear)
|
|
|
102 transcriptListComparator.getInvert(self._options.exclude)
|
|
|
103 transcriptListComparator.setMaxDistance(self._options.distance)
|
|
|
104 transcriptListComparator.setMinOverlap(self._options.minOverlap)
|
|
|
105 transcriptListComparator.setPcOverlap(self._options.pcOverlap)
|
|
|
106 transcriptListComparator.setIncludedOnly(self._options.included)
|
|
|
107 transcriptListComparator.setIncludingOnly(self._options.including)
|
|
|
108 transcriptListComparator.includeNotOverlapping(self._options.notOverlapping)
|
|
|
109 transcriptListComparator.computeOdds(True)
|
|
|
110 transcriptListComparator.setInputTranscriptContainer(transcriptListComparator.QUERY, transcriptContainer1)
|
|
|
111 transcriptListComparator.setInputTranscriptContainer(transcriptListComparator.REFERENCE, transcriptContainer2)
|
|
|
112 transcriptListComparator.setOutputWriter(writer)
|
|
|
113 transcriptListComparator.compareTranscriptList()
|
|
|
114
|
|
|
115 if self._options.log:
|
|
|
116 logHandle.close()
|
|
|
117
|
|
|
118 if not self._options.exclude:
|
|
|
119 odds = transcriptListComparator.getOdds()
|
|
|
120 if self._options.verbosity > 0 and odds:
|
|
|
121 print "min/avg/med/max transcripts: %d/%.2f/%.1f/%d" % Utils.getMinAvgMedMax(odds)
|
|
|
122
|
|
|
123 if __name__ == "__main__":
|
|
|
124 icompareOverlapping = CompareOverlapping()
|
|
|
125 icompareOverlapping.setAttributesFromCmdLine()
|
|
|
126 icompareOverlapping.run()
|
