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 """
+ − 32 Plot the data from the data files
+ − 33 """
+ − 34 import os
+ − 35 from optparse import OptionParser
+ − 36 from commons.core.parsing.GffParser import GffParser
+ − 37 from SMART.Java.Python.misc.RPlotter import RPlotter
+ − 38 from SMART.Java.Python.misc.Progress import Progress
+ − 39
+ − 40
+ − 41 if __name__ == "__main__":
+ − 42
+ − 43 # parse command line
+ − 44 description = "Plot Repartition v1.0.1: Plot the repartition of different data on a whole genome. (This tool uses 1 input file only, the different values being stored in the tags. See documentation to know more about it.) [Category: Visualization]"
+ − 45
+ − 46 parser = OptionParser(description = description)
+ − 47 parser.add_option("-i", "--input", dest="inputFileName", action="store", type="string", help="input file name [compulsory] [format: file in GFF3 format]")
+ − 48 parser.add_option("-n", "--names", dest="names", action="store", default=None, type="string", help="name for the tags (separated by commas and no space) [default: None] [format: string]")
+ − 49 parser.add_option("-o", "--output", dest="outputFileName", action="store", type="string", help="output file [compulsory] [format: output file in PNG format]")
+ − 50 parser.add_option("-c", "--color", dest="colors", action="store", default=None, type="string", help="color of the lines (separated by commas and no space) [format: string]")
+ − 51 parser.add_option("-f", "--format", dest="format", action="store", default="png", type="string", help="format of the output file [format: string] [default: png]")
+ − 52 parser.add_option("-r", "--normalize", dest="normalize", action="store_true", default=False, help="normalize data (when panels are different) [format: bool] [default: false]")
+ − 53 parser.add_option("-l", "--log", dest="log", action="store", default="", type="string", help="use log on x- or y-axis (write 'x', 'y' or 'xy') [format: string]")
+ − 54 parser.add_option("-v", "--verbosity", dest="verbosity", action="store", default=1, type="int", help="trace level [format: int]")
+ − 55 parser.add_option("-D", "--directory", dest="working_Dir", action="store", default=os.getcwd(), type="string", help="the directory to store the results [format: directory]")
+ − 56 (options, args) = parser.parse_args()
+ − 57
+ − 58 strands = [1, -1]
+ − 59 strandToString = {1: "+", -1: "-"}
+ − 60 names = [None] if options.names == None else options.names.split(",")
+ − 61 maxs = {}
+ − 62 nbElements = [0 for name in names]
+ − 63 lines = [{} for i in range(len(names))]
+ − 64 if options.colors == None:
+ − 65 colors = [None for i in range(len(names))]
+ − 66 else:
+ − 67 colors = options.colors.split(",")
+ − 68
+ − 69 parser = GffParser(options.inputFileName, options.verbosity)
+ − 70 progress = Progress(parser.getNbTranscripts(), "Reading %s" % (options.inputFileName), options.verbosity)
+ − 71 for transcript in parser.getIterator():
+ − 72 chromosome = transcript.getChromosome()
+ − 73 direction = transcript.getDirection()
+ − 74 start = transcript.getStart()
+ − 75 for i, name in enumerate(names):
+ − 76 if chromosome not in lines[i]:
+ − 77 lines[i][chromosome] = dict([(strand, {}) for strand in strands])
+ − 78 if chromosome not in maxs:
+ − 79 maxs[chromosome] = transcript.getStart()
+ − 80 else:
+ − 81 maxs[chromosome] = max(maxs[chromosome], start)
+ − 82 if start not in lines[i][chromosome][direction]:
+ − 83 lines[i][chromosome][direction][start] = 0
+ − 84 thisNbElements = float(transcript.getTagValue(name)) if name != None and name in transcript.getTagNames() else 1
+ − 85 lines[i][chromosome][direction][start] += thisNbElements * direction
+ − 86 nbElements[i] += thisNbElements
+ − 87 progress.inc()
+ − 88 progress.done()
+ − 89
+ − 90 if options.normalize:
+ − 91 if options.verbosity >= 10:
+ − 92 print "Normalizing..."
+ − 93 for i, linesPerCondition in enumerate(lines):
+ − 94 for linesPerChromosome in linesPerCondition.values():
+ − 95 for line in linesPerChromosome.values():
+ − 96 for key, value in line.iteritems():
+ − 97 line[key] = value / float(nbElements[i]) * max(nbElements)
+ − 98 if options.verbosity >= 10:
+ − 99 print "... done."
+ − 100
+ − 101 progress = Progress(len(maxs.keys()), "Plotting", options.verbosity)
+ − 102 for chromosome in maxs:
+ − 103 plot = RPlotter("%s%s.%s" % (options.outputFileName, chromosome.capitalize(), options.format), options.verbosity)
+ − 104 plot.setLog(options.log)
+ − 105 plot.setImageSize(2000, 500)
+ − 106 plot.setFormat(options.format)
+ − 107 if maxs[chromosome] <= 1000:
+ − 108 unit = "nt."
+ − 109 ratio = 1.0
+ − 110 elif maxs[chromosome] <= 1000000:
+ − 111 unit = "kb"
+ − 112 ratio = 1000.0
+ − 113 else:
+ − 114 unit = "Mb"
+ − 115 ratio = 1000000.0
+ − 116 plot.setXLabel("Position on %s (in %s)" % (chromosome.replace("_", " "), unit))
+ − 117 plot.setYLabel("# reads")
+ − 118 plot.setLegend(True)
+ − 119 for i, name in enumerate(names):
+ − 120 for strand in strands:
+ − 121 correctedLine = dict([(key / ratio, value) for key, value in lines[i][chromosome][strand].iteritems()])
+ − 122 if name != None:
+ − 123 name = "%s (%s)" % (name.replace("_", " "), strandToString[strand])
+ − 124 plot.addLine(correctedLine, None, colors[i])
+ − 125 plot.plot()
+ − 126 progress.inc()
+ − 127 progress.done()
+ − 128