| 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 class GetIntrons(object): | 
|  | 38 | 
|  | 39     def __init__(self, verbosity): | 
|  | 40         self.verbosity = verbosity | 
|  | 41 | 
|  | 42     def setInputFile(self, fileName, format): | 
|  | 43         chooser = ParserChooser(self.verbosity) | 
|  | 44         chooser.findFormat(format) | 
|  | 45         self.parser = chooser.getParser(fileName) | 
|  | 46 | 
|  | 47     def setOutputFile(self, fileName): | 
|  | 48         self.writer = TranscriptWriter(fileName, "gff3", self.verbosity) | 
|  | 49 | 
|  | 50     def run(self): | 
|  | 51         progress  = Progress(self.parser.getNbTranscripts(), "Reading input file", self.verbosity) | 
|  | 52         nbIntrons = 0 | 
|  | 53         for cpt1, transcript in enumerate(self.parser.getIterator()): | 
|  | 54             for cpt2, intron in enumerate(transcript.getIntrons()): | 
|  | 55                 intronTranscript = Transcript() | 
|  | 56                 intronTranscript.copy(intron) | 
|  | 57                 if "Parent" in intronTranscript.tags: | 
|  | 58                     del intronTranscript.tags["Parent"] | 
|  | 59                 intronTranscript.tags["feature"] = "transcript" | 
|  | 60                 if "ID" not in intronTranscript.tags or intronTranscript.tags["ID"] == "unnamed transcript": | 
|  | 61                     intronTranscript.tags["ID"] = "intron_%d-%d" % (cpt1+1, cpt2+1) | 
|  | 62                 if intronTranscript.getName() == "unnamed transcript": | 
|  | 63                     intronTranscript.setName("intron_%d-%d" % (cpt1+1, cpt2+1)) | 
|  | 64                 self.writer.addTranscript(intronTranscript) | 
|  | 65                 nbIntrons += 1 | 
|  | 66             progress.inc() | 
|  | 67         self.writer.write() | 
|  | 68         self.writer.close() | 
|  | 69         progress.done() | 
|  | 70         if self.verbosity > 1: | 
|  | 71             print "%d transcripts read" % (self.parser.getNbTranscripts()) | 
|  | 72             print "%d introns written" % (nbIntrons) | 
|  | 73 | 
|  | 74 | 
|  | 75 if __name__ == "__main__": | 
|  | 76 | 
|  | 77     description = "Get Introns v1.0.1: Get the introns of a set of transcripts. [Category: Data Modification]" | 
|  | 78 | 
|  | 79     parser = OptionParser(description = description) | 
|  | 80     parser.add_option("-i", "--input",     dest="inputFileName",  action="store",             type="string", help="input file [compulsory] [format: file in transcript format given by -f]") | 
|  | 81     parser.add_option("-f", "--format",    dest="format",         action="store",             type="string", help="format of file [compulsory] [format: transcript file format]") | 
|  | 82     parser.add_option("-o", "--output",    dest="outputFileName", action="store",             type="string", help="output file [format: output file in GFF3 format]") | 
|  | 83     parser.add_option("-v", "--verbosity", dest="verbosity",      action="store",  default=1, type="int",    help="trace level [format: int]") | 
|  | 84     (options, args) = parser.parse_args() | 
|  | 85 | 
|  | 86     gi = GetIntrons(options.verbosity) | 
|  | 87     gi.setInputFile(options.inputFileName, options.format) | 
|  | 88     gi.setOutputFile(options.outputFileName) | 
|  | 89     gi.run() |