36
+ − 1 #! /usr/bin/env python
+ − 2 #
+ − 3 # Copyright INRA-URGI 2009-2011
+ − 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 import os, random
+ − 32 from optparse import OptionParser, OptionGroup
+ − 33 from SMART.Java.Python.structure.TranscriptContainer import TranscriptContainer
+ − 34 from SMART.Java.Python.misc.Progress import Progress
+ − 35 from commons.core.writer.Gff3Writer import Gff3Writer
+ − 36
+ − 37
+ − 38 class CoverageComputer(object):
+ − 39
+ − 40 def __init__(self, verbosity = 0):
+ − 41 self.verbosity = verbosity
+ − 42 self.queryReader = None
+ − 43 self.referenceReader = None
+ − 44 self.outputWriter = None
+ − 45 self.introns = False
+ − 46 self.nbNucleotides = 0
+ − 47 self.nbCovered = 0
+ − 48
+ − 49 def setInputQueryFile(self, fileName, format):
+ − 50 self.queryReader = TranscriptContainer(fileName, format, self.verbosity-1)
+ − 51
+ − 52 def setInputReferenceFile(self, fileName, format):
+ − 53 self.referenceReader = TranscriptContainer(fileName, format, self.verbosity-1)
+ − 54
+ − 55 def includeIntrons(self, boolean):
+ − 56 self.introns = boolean
+ − 57
+ − 58 def setOutputFileName(self, fileName, title="S-MART", feature="transcript", featurePart="exon"):
+ − 59 self.outputWriter = Gff3Writer(fileName, self.verbosity-1)
+ − 60 self.outputWriter.setTitle(title)
+ − 61 self.outputWriter.setFeature(feature)
+ − 62 self.outputWriter.setFeaturePart(featurePart)
+ − 63
+ − 64 def readReference(self):
+ − 65 self.coveredRegions = {}
+ − 66 progress = Progress(self.referenceReader.getNbTranscripts(), "Reading reference file", self.verbosity-1)
+ − 67 for transcript in self.referenceReader.getIterator():
+ − 68 chromosome = transcript.getChromosome()
+ − 69 if chromosome not in self.coveredRegions:
+ − 70 self.coveredRegions[chromosome] = {}
+ − 71 if self.introns:
+ − 72 transcript.removeExons()
+ − 73 for exon in transcript.getExons():
+ − 74 for position in range(exon.getStart(), exon.getEnd()+1):
+ − 75 self.coveredRegions[chromosome][position] = 1
+ − 76 progress.inc()
+ − 77 progress.done()
+ − 78
+ − 79 def readQuery(self):
+ − 80 progress = Progress(self.queryReader.getNbTranscripts(), "Reading query file", self.verbosity-1)
+ − 81 for transcript in self.queryReader.getIterator():
+ − 82 progress.inc()
+ − 83 chromosome = transcript.getChromosome()
+ − 84 if chromosome not in self.coveredRegions:
+ − 85 continue
+ − 86 if self.introns:
+ − 87 transcript.removeExons()
+ − 88 for exon in transcript.getExons():
+ − 89 for position in range(exon.getStart(), exon.getEnd()+1):
+ − 90 self.nbNucleotides += 1
+ − 91 self.nbCovered += self.coveredRegions[chromosome].get(position, 0)
+ − 92 progress.done()
+ − 93
+ − 94 def write(self):
+ − 95 progress = Progress(self.queryReader.getNbTranscripts(), "Writing output file", self.verbosity-1)
+ − 96 for transcript in self.queryReader.getIterator():
+ − 97 chromosome = transcript.getChromosome()
+ − 98 if self.introns:
+ − 99 transcript.removeExons()
+ − 100 size = transcript.getSize()
+ − 101 coverage = 0
+ − 102 for exon in transcript.getExons():
+ − 103 for position in range(exon.getStart(), exon.getEnd()+1):
+ − 104 coverage += self.coveredRegions[chromosome].get(position, 0)
+ − 105 transcript.setTagValue("coverage", 0 if size == 0 else float(coverage) / size * 100)
+ − 106 self.outputWriter.addTranscript(transcript)
+ − 107 progress.inc()
+ − 108 progress.done()
+ − 109
+ − 110 def sumUp(self):
+ − 111 print "%d nucleotides in query, %d (%.f%%) covered" % (self.nbNucleotides, self.nbCovered, 0 if self.nbNucleotides == 0 else float(self.nbCovered) / self.nbNucleotides * 100)
+ − 112
+ − 113 def run(self):
+ − 114 self.readReference()
+ − 115 self.readQuery()
+ − 116 if self.outputWriter != None:
+ − 117 self.write()
+ − 118 self.sumUp()
+ − 119
+ − 120
+ − 121 if __name__ == "__main__":
+ − 122
+ − 123 # parse command line
+ − 124 description = "Compute Coverage v1.0.1: Compute the coverage of a set with respect to another set. [Category: Personal]"
+ − 125
+ − 126 parser = OptionParser(description = description)
+ − 127 parser.add_option("-i", "--input1", dest="inputFileName1", action="store", type="string", help="input query file [compulsory] [format: file in transcript format given by -f]")
+ − 128 parser.add_option("-f", "--format1", dest="format1", action="store", type="string", help="format of the first file [compulsory] [format: transcript file format]")
+ − 129 parser.add_option("-j", "--input2", dest="inputFileName2", action="store", type="string", help="input reference file [compulsory] [format: file in transcript format given by -f]")
+ − 130 parser.add_option("-g", "--format2", dest="format2", action="store", type="string", help="format of the second file [compulsory] [format: transcript file format]")
+ − 131 parser.add_option("-t", "--introns", dest="introns", action="store_true", default=False, help="also include introns [format: boolean] [default: false]")
+ − 132 parser.add_option("-o", "--output", dest="outputFileName", action="store", default=None, type="string", help="output file [format: output file in GFF3 format]")
46
+ − 133 parser.add_option("-v", "--verbosity", dest="verbosity", action="store", type="int", help="trace level [default: 1] [format: int]")
36
+ − 134 (options, args) = parser.parse_args()
+ − 135
+ − 136 computer = CoverageComputer(options.verbosity)
+ − 137 computer.setInputQueryFile(options.inputFileName1, options.format1)
+ − 138 computer.setInputReferenceFile(options.inputFileName2, options.format2)
+ − 139 computer.includeIntrons(options.introns)
+ − 140 computer.setOutputFileName(options.outputFileName)
+ − 141 computer.run()
+ − 142
