diff SMART/Java/Python/GetUpDownStream.py @ 6:769e306b7933

Change the repository level.
author yufei-luo
date Fri, 18 Jan 2013 04:54:14 -0500
parents
children
line wrap: on
line diff
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/SMART/Java/Python/GetUpDownStream.py	Fri Jan 18 04:54:14 2013 -0500
@@ -0,0 +1,152 @@
+#! /usr/bin/env python
+#
+# Copyright INRA-URGI 2009-2012
+# 
+# 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.
+#
+import os
+from optparse import OptionParser, OptionGroup
+from commons.core.parsing.ParserChooser import ParserChooser
+from commons.core.writer.Gff3Writer import Gff3Writer
+from SMART.Java.Python.structure.Transcript import Transcript
+from SMART.Java.Python.ncList.NCListFilePickle import NCListFileUnpickle
+from SMART.Java.Python.ncList.FileSorter import FileSorter
+from SMART.Java.Python.misc.Progress import Progress
+from SMART.Java.Python.misc import Utils
+
+
+class GetUpDownStream(object):
+
+    def __init__(self, verbosity = 0):
+        self.verbosity         = verbosity
+        self.inputReader       = None
+        self.outputWriter      = None
+        self.nbRead            = 0
+        self.nbWritten         = 0
+        self.nbMerges          = 0
+        self.splittedFileNames = {}
+
+    def __del__(self):
+        for fileName in self.splittedFileNames.values():
+            os.remove(fileName)
+            
+    def setInputFile(self, fileName, format):
+        parserChooser = ParserChooser(self.verbosity)
+        parserChooser.findFormat(format, "transcript")
+        self.parser = parserChooser.getParser(fileName)
+        self.sortedFileName = "%s_sorted.pkl" % (os.path.splitext(fileName)[0])
+
+    def setOutputFile(self, fileName):
+        self.outputWriter = Gff3Writer(fileName, self.verbosity)
+
+    def setDistances(self, up, down):
+        self.upDistance   = up
+        self.downDistance = down
+
+    def _sortFile(self):
+        fs = FileSorter(self.parser, self.verbosity-4)
+        fs.perChromosome(True)
+        fs.setOutputFileName(self.sortedFileName)
+        fs.sort()
+        self.splittedFileNames       = fs.getOutputFileNames()
+        self.nbElementsPerChromosome = fs.getNbElementsPerChromosome()
+        self.nbRead                  = fs.getNbElements()
+
+    def _write(self, start, end, reference, after):
+        if start > end:
+            return
+        transcript = Transcript()
+        transcript.setChromosome(reference.getChromosome())
+        transcript.setStart(start)
+        transcript.setEnd(end)
+        transcript.setDirection("+")
+        transcript.setName("%s_%s" % ("up" if Utils.xor(reference.getDirection() == 1, after) else "down", reference.getName()))
+        self.outputWriter.addTranscript(transcript)
+        
+    def _getFlanking(self, chromosome):
+        progress    = Progress(self.nbElementsPerChromosome[chromosome], "Analyzing chromosome %s" % (chromosome), self.verbosity)
+        parser      = NCListFileUnpickle(self.splittedFileNames[chromosome], self.verbosity)
+        previous    = None
+        for transcript in parser.getIterator():
+            progress.inc()
+            transcript.removeExons()
+            if previous == None:
+                distance = self.upDistance if transcript.getDirection() == 1 else self.downDistance
+                start    = max(1, transcript.getStart() - distance)
+                self._write(start, transcript.getStart()-1, transcript, False)
+                previous = transcript
+                continue
+            if previous.include(transcript):
+                continue
+            if transcript.overlapWith(previous):
+                previous = transcript
+                continue
+            distancePrevious = self.downDistance if previous.getDirection()   == 1 else self.upDistance
+            distanceCurrent  = self.upDistance   if transcript.getDirection() == 1 else self.downDistance
+            distance = transcript.getDistance(previous)
+            if distancePrevious + distanceCurrent == 0:
+                previous = transcript
+                continue
+            if distance >= distancePrevious + distanceCurrent:
+                endPrevious  = previous.getEnd() + distancePrevious
+                startCurrent = transcript.getStart() - distanceCurrent
+            else:
+                middle       = previous.getEnd() + int((distance-1) * float(distancePrevious) / (distancePrevious + distanceCurrent))
+                endPrevious  = middle
+                startCurrent = middle+1
+            self._write(previous.getEnd() + 1, endPrevious, previous, True)
+            self._write(startCurrent, transcript.getStart() - 1, transcript, False)
+            previous = transcript
+        distance = self.downDistance if previous.getDirection() == 1 else self.upDistance
+        self._write(previous.getEnd() + 1, previous.getEnd() + distance, previous, True)
+        progress.done()
+
+    def run(self):
+        self._sortFile()
+        for chromosome in sorted(self.nbElementsPerChromosome.keys()):
+            self._getFlanking(chromosome)
+        self.outputWriter.close()
+
+if __name__ == "__main__":
+    
+    # parse command line
+    description = "Get Up and Down Stream v1.0.0: Get the flanking regions of an annotation. [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 mapping format given by -f]")
+    parser.add_option("-f", "--format",    dest="format",         action="store",                     type="string", help="format of the file [compulsory] [format: mapping file format]")
+    parser.add_option("-o", "--output",    dest="outputFileName", action="store",                     type="string", help="output file [compulsory] [format: output file in GFF3 format]")
+    parser.add_option("-u", "--up",        dest="up",             action="store",      default=0,     type="int",    help="the upstream distance  [format: int]")
+    parser.add_option("-d", "--down",      dest="down",           action="store",      default=0,     type="int",    help="the downstream distance  [format: int]")
+    parser.add_option("-v", "--verbosity", dest="verbosity",      action="store",      default=1,     type="int",    help="trace level [default: 1] [format: int]")
+    (options, args) = parser.parse_args()
+
+    guds = GetUpDownStream(options.verbosity)
+    guds.setInputFile(options.inputFileName, options.format)
+    guds.setOutputFile(options.outputFileName)
+    guds.setDistances(options.up, options.down)
+    guds.run()