Mercurial > repos > yufei-luo > s_mart
diff smart_toolShed/SMART/Java/Python/getIntrons.py @ 0:e0f8dcca02ed
Uploaded S-MART tool. A toolbox manages RNA-Seq and ChIP-Seq data.
author | yufei-luo |
---|---|
date | Thu, 17 Jan 2013 10:52:14 -0500 |
parents | |
children |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/smart_toolShed/SMART/Java/Python/getIntrons.py Thu Jan 17 10:52:14 2013 -0500 @@ -0,0 +1,89 @@ +#! /usr/bin/env python +# +# Copyright INRA-URGI 2009-2010 +# +# This software is governed by the CeCILL license under French law and +# abiding by the rules of distribution of free software. You can use, +# modify and/ or redistribute the software under the terms of the CeCILL +# license as circulated by CEA, CNRS and INRIA at the following URL +# "http://www.cecill.info". +# +# As a counterpart to the access to the source code and rights to copy, +# modify and redistribute granted by the license, users are provided only +# with a limited warranty and the software's author, the holder of the +# economic rights, and the successive licensors have only limited +# liability. +# +# In this respect, the user's attention is drawn to the risks associated +# with loading, using, modifying and/or developing or reproducing the +# software by the user in light of its specific status of free software, +# that may mean that it is complicated to manipulate, and that also +# therefore means that it is reserved for developers and experienced +# professionals having in-depth computer knowledge. Users are therefore +# encouraged to load and test the software's suitability as regards their +# requirements in conditions enabling the security of their systems and/or +# data to be ensured and, more generally, to use and operate it in the +# same conditions as regards security. +# +# The fact that you are presently reading this means that you have had +# knowledge of the CeCILL license and that you accept its terms. +# +from optparse import OptionParser +from commons.core.parsing.ParserChooser import ParserChooser +from commons.core.writer.TranscriptWriter import TranscriptWriter +from SMART.Java.Python.structure.Transcript import Transcript +from SMART.Java.Python.misc.Progress import Progress + +class GetIntrons(object): + + def __init__(self, verbosity): + self.verbosity = verbosity + + def setInputFile(self, fileName, format): + chooser = ParserChooser(self.verbosity) + chooser.findFormat(format) + self.parser = chooser.getParser(fileName) + + def setOutputFile(self, fileName): + self.writer = TranscriptWriter(fileName, "gff3", self.verbosity) + + def run(self): + progress = Progress(self.parser.getNbTranscripts(), "Reading input file", self.verbosity) + nbIntrons = 0 + for cpt1, transcript in enumerate(self.parser.getIterator()): + for cpt2, intron in enumerate(transcript.getIntrons()): + intronTranscript = Transcript() + intronTranscript.copy(intron) + if "Parent" in intronTranscript.tags: + del intronTranscript.tags["Parent"] + intronTranscript.tags["feature"] = "transcript" + if "ID" not in intronTranscript.tags or intronTranscript.tags["ID"] == "unnamed transcript": + intronTranscript.tags["ID"] = "intron_%d-%d" % (cpt1+1, cpt2+1) + if intronTranscript.getName() == "unnamed transcript": + intronTranscript.setName("intron_%d-%d" % (cpt1+1, cpt2+1)) + self.writer.addTranscript(intronTranscript) + nbIntrons += 1 + progress.inc() + self.writer.write() + self.writer.close() + progress.done() + if self.verbosity > 1: + print "%d transcripts read" % (self.parser.getNbTranscripts()) + print "%d introns written" % (nbIntrons) + + +if __name__ == "__main__": + + description = "Get Introns v1.0.1: Get the introns of a set of transcripts. [Category: Data Modification]" + + parser = OptionParser(description = description) + parser.add_option("-i", "--input", dest="inputFileName", action="store", type="string", help="input file [compulsory] [format: file in transcript format given by -f]") + parser.add_option("-f", "--format", dest="format", action="store", type="string", help="format of file [compulsory] [format: transcript file format]") + parser.add_option("-o", "--output", dest="outputFileName", action="store", type="string", help="output file [format: output file in GFF3 format]") + parser.add_option("-v", "--verbosity", dest="verbosity", action="store", default=1, type="int", help="trace level [format: int]") + (options, args) = parser.parse_args() + + gi = GetIntrons(options.verbosity) + gi.setInputFile(options.inputFileName, options.format) + gi.setOutputFile(options.outputFileName) + gi.run()