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 from optparse import OptionParser
+ − 32 from commons.core.parsing.ParserChooser import ParserChooser
+ − 33 from commons.core.writer.TranscriptWriter import TranscriptWriter
+ − 34 from SMART.Java.Python.structure.Transcript import Transcript
+ − 35 from SMART.Java.Python.misc.Progress import Progress
+ − 36
+ − 37 zeroBaseToOneBaseConvertor = (lambda x: x - 1 if x > 0 else x)
+ − 38
+ − 39 class GetExons(object):
+ − 40
+ − 41 def __init__(self, verbosity):
+ − 42 self.verbosity = verbosity
+ − 43 self.selection = False
+ − 44
+ − 45 def setInputFile(self, fileName, format):
+ − 46 chooser = ParserChooser(self.verbosity)
+ − 47 chooser.findFormat(format)
+ − 48 self.parser = chooser.getParser(fileName)
+ − 49
+ − 50 def setSelection(self, selection):
+ − 51 if selection == None:
+ − 52 return
+ − 53 self.selection = True
+ − 54 self.selectionItems = []
+ − 55 self.selectionIntervals = []
+ − 56 for part in selection.split(","):
+ − 57 try:
+ − 58 splittedPart = map(int, part.split(".."))
+ − 59 except Exception:
+ − 60 raise Exception("Elements '" + splittedPart + "' of selection '" + selection + "' do no seem to be integers!")
+ − 61 if len(splittedPart) == 1:
+ − 62 self.selectionItems.append(splittedPart[0])
+ − 63 elif len(splittedPart) == 2:
+ − 64 self.selectionIntervals.append((splittedPart[0], splittedPart[1]))
+ − 65 else:
+ − 66 raise Exception("Cannot parse elements '" + splittedPart + "' of selection '" + selection + "'!")
+ − 67
+ − 68 def getSelectionExonIndices(self, nbExons):
+ − 69 if not self.selection:
+ − 70 return range(nbExons)
+ − 71 indices = []
+ − 72 for item in self.selectionItems:
+ − 73 indices.append(range(nbExons)[zeroBaseToOneBaseConvertor(item)])
+ − 74 for start, end in self.selectionIntervals:
+ − 75 start, end = map(zeroBaseToOneBaseConvertor, (start, end))
+ − 76 if end > 0:
+ − 77 end += 1
+ − 78 indices.extend(range(nbExons)[start:end])
+ − 79 return indices
+ − 80
+ − 81 def setOutputFile(self, fileName):
+ − 82 self.writer = TranscriptWriter(fileName, "gff3", self.verbosity)
+ − 83
+ − 84 def run(self):
+ − 85 progress = Progress(self.parser.getNbTranscripts(), "Reading input file", self.verbosity)
+ − 86 nbExons = 0
+ − 87 for cpt1, transcript in enumerate(self.parser.getIterator()):
+ − 88 selectedExons = self.getSelectionExonIndices(transcript.getNbExons())
+ − 89 transcript.sortExons()
+ − 90 for cpt2, exon in enumerate(transcript.getExons()):
+ − 91 if cpt2 not in selectedExons:
+ − 92 continue
+ − 93 exonTranscript = Transcript()
+ − 94 exonTranscript.copy(exon)
+ − 95 if "Parent" in exonTranscript.tags:
+ − 96 del exonTranscript.tags["Parent"]
+ − 97 exonTranscript.tags["feature"] = "transcript"
+ − 98 if "ID" not in exonTranscript.tags or exonTranscript.tags["ID"] == "unnamed transcript":
+ − 99 exonTranscript.tags["ID"] = "exon_%d-%d" % (cpt1+1, cpt2+1)
+ − 100 if exonTranscript.getName() == "unnamed transcript":
+ − 101 exonTranscript.setName("exon_%d-%d" % (cpt1+1, cpt2+1))
+ − 102 self.writer.addTranscript(exonTranscript)
+ − 103 nbExons += 1
+ − 104 progress.inc()
+ − 105 self.writer.write()
+ − 106 self.writer.close()
+ − 107 progress.done()
+ − 108 if self.verbosity > 1:
+ − 109 print "%d transcripts read" % (self.parser.getNbTranscripts())
+ − 110 print "%d exons written" % (nbExons)
+ − 111
+ − 112 if __name__ == "__main__":
+ − 113
+ − 114 description = "Get Exons v1.0.1: Get the exons of a set of transcripts. [Category: Data Modification]"
+ − 115
+ − 116 parser = OptionParser(description = description)
+ − 117 parser.add_option("-i", "--input", dest="inputFileName", action="store", type="string", help="input file [compulsory] [format: file in transcript format given by -f]")
+ − 118 parser.add_option("-f", "--format", dest="format", action="store", type="string", help="format of file [compulsory] [format: transcript file format]")
+ − 119 parser.add_option("-s", "--select", dest="select", action="store", default=None, type="string", help="select some of the exons (like '1,2,5..-3,-1') [format: string]")
+ − 120 parser.add_option("-o", "--output", dest="outputFileName", action="store", type="string", help="output file [format: output file in GFF3 format]")
+ − 121 parser.add_option("-v", "--verbosity", dest="verbosity", action="store", default=1, type="int", help="trace level [format: int]")
+ − 122 (options, args) = parser.parse_args()
+ − 123
+ − 124 ge = GetExons(options.verbosity)
+ − 125 ge.setInputFile(options.inputFileName, options.format)
+ − 126 ge.setSelection(options.select)
+ − 127 ge.setOutputFile(options.outputFileName)
+ − 128 ge.run()