Mercurial > repos > yufei-luo > s_mart

comparison SMART/Java/Python/mergeTranscriptLists.py @ 38:2c0c0a89fad7

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
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 #! /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 """Merge elements of two transcript lists with some condition"""
32
33 import os, random, shutil, glob
34 from optparse import OptionParser
35 from commons.core.parsing.SequenceListParser import SequenceListParser
36 from commons.core.parsing.BedParser import BedParser
37 from commons.core.parsing.GffParser import GffParser
38 from commons.core.writer.TranscriptWriter import TranscriptWriter
39 from SMART.Java.Python.structure.TranscriptListsComparator import TranscriptListsComparator
40 from SMART.Java.Python.structure.TranscriptContainer import TranscriptContainer
41 from SMART.Java.Python.misc.RPlotter import RPlotter
42 from SMART.Java.Python.misc.Progress import Progress
43
44
45
46 class MergeLists(object):
47
48 def __init__(self, verbosity):
49 self.verbosity = verbosity
50 self.seed = random.randint(0, 100000)
51 self.aggregation = False
52 self.normalization = False
53 self.distance = False
54 self.antisense = False
55 self.colinear = False
56 self.fileNames = {}
57 self.formats = {}
58 self.tmpFileNames = []
59 self.logHandle = None
60
61 # def __del__(self):
62 # for fileNameRoot in self.tmpFileNames:
63 # for fileName in glob.glob("%s*" % (fileNameRoot)):
64 # os.remove(fileName)
65 # if self.logHandle != None:
66 # self.logHandle.close()
67 # self.logHandle = None
68
69 def setLogFileName(self, fileName):
70 self.logHandle = open(fileName, "w")
71
72 def setInputFileName(self, fileName, format, id):
73 self.fileNames[id] = fileName
74 self.formats[id] = format
75
76 def setOutputFileName(self, fileName):
77 self.outputFileName = fileName
78
79 def setAggregate(self, aggregation):
80 self.aggregation = aggregation
81
82 def setNormalization(self, normalization):
83 self.normalization = normalization
84
85 def setDistance(self, distance):
86 self.distance = distance
87
88 def setAntisense(self, antisense):
89 self.antisense = antisense
90
91 def setColinear(self, colinear):
92 self.colinear = colinear
93
94 def createTmpFileName(self, root):
95 fileName = "tmp_%s_%d.gff3" % (root, self.seed)
96 self.tmpFileNames.append(fileName)
97 return fileName
98
99 def selfMerge(self, fileName, format, outputFileName):
100 transcriptListComparator = TranscriptListsComparator(self.logHandle, self.verbosity)
101 transcriptListComparator.getColinearOnly(True)
102 transcriptListComparator.setNormalization(self.normalization)
103 transcriptContainer = TranscriptContainer(fileName, format, self.verbosity)
104 writer = TranscriptWriter(outputFileName, "gff3", self.verbosity)
105 transcriptListComparator.setInputTranscriptContainer(transcriptListComparator.QUERY, transcriptContainer)
106 transcriptListComparator.setOutputWriter(writer)
107 transcriptListComparator.compareTranscriptListSelfMerge()
108
109 def keepOverlapping(self, fileNames, formats, outputFileName):
110 transcriptListComparator = TranscriptListsComparator(self.logHandle, self.verbosity)
111 transcriptListComparator.getAntisenseOnly(self.antisense)
112 transcriptListComparator.getColinearOnly(self.colinear)
113 for i in (0, 1):
114 transcriptContainer = TranscriptContainer(fileNames[i], formats[i], self.verbosity)
115 transcriptListComparator.setInputTranscriptContainer(i, transcriptContainer)
116 transcriptListComparator.aggregate(self.aggregation)
117 transcriptListComparator.setNormalization(self.normalization)
118 transcriptListComparator.setMaxDistance(self.distance)
119 writer = TranscriptWriter(outputFileName, "gff3", self.verbosity)
120 transcriptListComparator.setOutputWriter(writer)
121 transcriptListComparator.compareTranscriptList()
122
123 def mergeFiles(self, fileName1, fileName2, outputFileName):
124 outputFile = open(outputFileName, "w")
125 shutil.copyfileobj(open(fileName1, "r"), outputFile)
126 shutil.copyfileobj(open(fileName2, "r"), outputFile)
127 outputFile.close()
128
129 def run(self):
130 selectedFileQuery = self.createTmpFileName("query")
131 self.keepOverlapping({0: self.fileNames[0], 1: self.fileNames[0]}, {0: "gff3", 1: "gff3"}, selectedFileQuery)
132 mergeFileTarget = self.createTmpFileName("target")
133 self.selfMerge(self.fileNames[1], self.formats[1], mergeFileTarget)
134 if not self.aggregation:
135 overlapFile = self.createTmpFileName("overlap")
136 self.keepOverlapping({0: mergeFileTarget, 1: selectedFileQuery}, {0: "gff3", 1: "gff3"}, overlapFile)
137 mergeFileTarget = overlapFile
138 mergeFileMerged = self.createTmpFileName("merged")
139 self.mergeFiles(mergeFileTarget, selectedFileQuery, mergeFileMerged)
140 self.selfMerge(mergeFileMerged, "gff3", self.outputFileName)
141
142
143
144 if __name__ == "__main__":
145
146 # parse command line
147 description = "Merge Lists v1.0.3: Merge the elements of two lists of genomic coordinates. [Category: Merge]"
148
149 parser = OptionParser(description = description)
150 parser.add_option("-i", "--input1", dest="inputFileName1", action="store", type="string", help="input file 1 [compulsory] [format: file in transcript format given by -f]")
151 parser.add_option("-f", "--format1", dest="format1", action="store", type="string", help="format of file 1 [compulsory] [format: transcript file format]")
152 parser.add_option("-j", "--input2", dest="inputFileName2", action="store", default=None, type="string", help="input file 2 [compulsory] [format: file in transcript format given by -g]")
153 parser.add_option("-g", "--format2", dest="format2", action="store", default=None, type="string", help="format of file 2 [compulsory] [format: file in transcript format]")
154 parser.add_option("-o", "--output", dest="outputFileName", action="store", default=None, type="string", help="output file [compulsory] [format: output file in GFF3 format]")
155 parser.add_option("-k", "--all", dest="all", action="store_true", default=False, help="print all the transcripts, not only those overlapping [format: bool] [default: false]")
156 parser.add_option("-d", "--distance", dest="distance", action="store", default=0, type="int", help="max. distance between two transcripts [format: int] [default: 0]")
157 parser.add_option("-a", "--antisense", dest="antisense", action="store_true", default=False, help="antisense only [format: bool] [default: false]")
158 parser.add_option("-c", "--colinear", dest="colinear", action="store_true", default=False, help="colinear only [format: bool] [default: false]")
159 parser.add_option("-n", "--normalize", dest="normalize", action="store_true", default=False, help="normalize the number of reads per cluster by the number of mappings per read [format: bool] [default: false]")
160 parser.add_option("-v", "--verbosity", dest="verbosity", action="store", default=1, type="int", help="trace level [format: int]")
161 (options, args) = parser.parse_args()
162
163 # ml = MergeLists(logHandle, options.verbosity)
164
165 ml = MergeLists(0)
166 ml.setInputFileName(options.inputFileName1, options.format1, 0)
167 ml.setInputFileName(options.inputFileName2, options.format2, 1)
168 ml.setOutputFileName(options.outputFileName)
169 ml.setAntisense(options.antisense)
170 ml.setColinear(options.colinear)
171 ml.setAggregate(options.all)
172 ml.setNormalization(options.normalize)
173 ml.setDistance(options.distance)
174 ml.run()