6
+ − 1 #! /usr/bin/env python
+ − 2 #
+ − 3 # Copyright INRA-URGI 2009-2012
+ − 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
+ − 32 from optparse import OptionParser, OptionGroup
+ − 33 from commons.core.parsing.ParserChooser import ParserChooser
+ − 34 from commons.core.writer.Gff3Writer import Gff3Writer
+ − 35 from SMART.Java.Python.structure.Transcript import Transcript
+ − 36 from SMART.Java.Python.ncList.NCListFilePickle import NCListFileUnpickle
+ − 37 from SMART.Java.Python.ncList.FileSorter import FileSorter
+ − 38 from SMART.Java.Python.misc.Progress import Progress
+ − 39 from SMART.Java.Python.misc import Utils
+ − 40
+ − 41
+ − 42 class GetUpDownStream(object):
+ − 43
+ − 44 def __init__(self, verbosity = 0):
+ − 45 self.verbosity = verbosity
+ − 46 self.inputReader = None
+ − 47 self.outputWriter = None
+ − 48 self.nbRead = 0
+ − 49 self.nbWritten = 0
+ − 50 self.nbMerges = 0
+ − 51 self.splittedFileNames = {}
+ − 52
+ − 53 def __del__(self):
+ − 54 for fileName in self.splittedFileNames.values():
+ − 55 os.remove(fileName)
+ − 56
+ − 57 def setInputFile(self, fileName, format):
+ − 58 parserChooser = ParserChooser(self.verbosity)
+ − 59 parserChooser.findFormat(format, "transcript")
+ − 60 self.parser = parserChooser.getParser(fileName)
+ − 61 self.sortedFileName = "%s_sorted.pkl" % (os.path.splitext(fileName)[0])
+ − 62
+ − 63 def setOutputFile(self, fileName):
+ − 64 self.outputWriter = Gff3Writer(fileName, self.verbosity)
+ − 65
+ − 66 def setDistances(self, up, down):
+ − 67 self.upDistance = up
+ − 68 self.downDistance = down
+ − 69
+ − 70 def _sortFile(self):
+ − 71 fs = FileSorter(self.parser, self.verbosity-4)
+ − 72 fs.perChromosome(True)
+ − 73 fs.setOutputFileName(self.sortedFileName)
+ − 74 fs.sort()
+ − 75 self.splittedFileNames = fs.getOutputFileNames()
+ − 76 self.nbElementsPerChromosome = fs.getNbElementsPerChromosome()
+ − 77 self.nbRead = fs.getNbElements()
+ − 78
+ − 79 def _write(self, start, end, reference, after):
+ − 80 if start > end:
+ − 81 return
+ − 82 transcript = Transcript()
+ − 83 transcript.setChromosome(reference.getChromosome())
+ − 84 transcript.setStart(start)
+ − 85 transcript.setEnd(end)
+ − 86 transcript.setDirection("+")
+ − 87 transcript.setName("%s_%s" % ("up" if Utils.xor(reference.getDirection() == 1, after) else "down", reference.getName()))
+ − 88 self.outputWriter.addTranscript(transcript)
+ − 89
+ − 90 def _getFlanking(self, chromosome):
+ − 91 progress = Progress(self.nbElementsPerChromosome[chromosome], "Analyzing chromosome %s" % (chromosome), self.verbosity)
+ − 92 parser = NCListFileUnpickle(self.splittedFileNames[chromosome], self.verbosity)
+ − 93 previous = None
+ − 94 for transcript in parser.getIterator():
+ − 95 progress.inc()
+ − 96 transcript.removeExons()
+ − 97 if previous == None:
+ − 98 distance = self.upDistance if transcript.getDirection() == 1 else self.downDistance
+ − 99 start = max(1, transcript.getStart() - distance)
+ − 100 self._write(start, transcript.getStart()-1, transcript, False)
+ − 101 previous = transcript
+ − 102 continue
+ − 103 if previous.include(transcript):
+ − 104 continue
+ − 105 if transcript.overlapWith(previous):
+ − 106 previous = transcript
+ − 107 continue
+ − 108 distancePrevious = self.downDistance if previous.getDirection() == 1 else self.upDistance
+ − 109 distanceCurrent = self.upDistance if transcript.getDirection() == 1 else self.downDistance
+ − 110 distance = transcript.getDistance(previous)
+ − 111 if distancePrevious + distanceCurrent == 0:
+ − 112 previous = transcript
+ − 113 continue
+ − 114 if distance >= distancePrevious + distanceCurrent:
+ − 115 endPrevious = previous.getEnd() + distancePrevious
+ − 116 startCurrent = transcript.getStart() - distanceCurrent
+ − 117 else:
+ − 118 middle = previous.getEnd() + int((distance-1) * float(distancePrevious) / (distancePrevious + distanceCurrent))
+ − 119 endPrevious = middle
+ − 120 startCurrent = middle+1
+ − 121 self._write(previous.getEnd() + 1, endPrevious, previous, True)
+ − 122 self._write(startCurrent, transcript.getStart() - 1, transcript, False)
+ − 123 previous = transcript
+ − 124 distance = self.downDistance if previous.getDirection() == 1 else self.upDistance
+ − 125 self._write(previous.getEnd() + 1, previous.getEnd() + distance, previous, True)
+ − 126 progress.done()
+ − 127
+ − 128 def run(self):
+ − 129 self._sortFile()
+ − 130 for chromosome in sorted(self.nbElementsPerChromosome.keys()):
+ − 131 self._getFlanking(chromosome)
+ − 132 self.outputWriter.close()
+ − 133
+ − 134 if __name__ == "__main__":
+ − 135
+ − 136 # parse command line
+ − 137 description = "Get Up and Down Stream v1.0.0: Get the flanking regions of an annotation. [Category: Data Modification]"
+ − 138
+ − 139 parser = OptionParser(description = description)
+ − 140 parser.add_option("-i", "--input", dest="inputFileName", action="store", type="string", help="input file [compulsory] [format: file in mapping format given by -f]")
+ − 141 parser.add_option("-f", "--format", dest="format", action="store", type="string", help="format of the file [compulsory] [format: mapping file format]")
+ − 142 parser.add_option("-o", "--output", dest="outputFileName", action="store", type="string", help="output file [compulsory] [format: output file in GFF3 format]")
+ − 143 parser.add_option("-u", "--up", dest="up", action="store", default=0, type="int", help="the upstream distance [format: int]")
+ − 144 parser.add_option("-d", "--down", dest="down", action="store", default=0, type="int", help="the downstream distance [format: int]")
+ − 145 parser.add_option("-v", "--verbosity", dest="verbosity", action="store", default=1, type="int", help="trace level [default: 1] [format: int]")
+ − 146 (options, args) = parser.parse_args()
+ − 147
+ − 148 guds = GetUpDownStream(options.verbosity)
+ − 149 guds.setInputFile(options.inputFileName, options.format)
+ − 150 guds.setOutputFile(options.outputFileName)
+ − 151 guds.setDistances(options.up, options.down)
+ − 152 guds.run()
