| 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.FastaParser import FastaParser | 
|  | 37 from commons.core.parsing.FastqParser import FastqParser | 
|  | 38 from SMART.Java.Python.misc.RPlotter import RPlotter | 
|  | 39 from SMART.Java.Python.misc.Progress import Progress | 
|  | 40 from SMART.Java.Python.misc import Utils | 
|  | 41 | 
|  | 42 | 
|  | 43 if __name__ == "__main__": | 
|  | 44 | 
|  | 45     # parse command line | 
|  | 46     description = "Get Read Distribution v1.0.1: Plot the number of identical reads and give the most represented. [Category: Visualization]" | 
|  | 47 | 
|  | 48     parser = OptionParser(description = description) | 
|  | 49     parser.add_option("-i", "--input",     dest="inputFileName",  action="store",               type="string", help="input file sequence [compulsory] [format: file in sequence format given by -f]") | 
|  | 50     parser.add_option("-f", "--format",    dest="format",         action="store",               type="string", help="format of the file [compulsory] [format: sequence file format]") | 
|  | 51     parser.add_option("-n", "--number",    dest="number",         action="store", default=None, type="int",    help="keep the best n    [format: int]") | 
|  | 52     parser.add_option("-p", "--percent",   dest="percent",        action="store", default=None, type="float",  help="keep the best n\% [format: float]") | 
|  | 53     parser.add_option("-o", "--output",    dest="outputFileName", action="store",               type="string", help="output file [compulsory] [format: output files in PNG format and txt format]") | 
|  | 54     parser.add_option("-x", "--xMax",      dest="xMax",           action="store", default=None, type="int",    help="maximum value on the x-axis to plot [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     parser.add_option("-v", "--verbosity", dest="verbosity",      action="store", default=1,    type="int",    help="trace level [format: int]") | 
|  | 57     (options, args) = parser.parse_args() | 
|  | 58 | 
|  | 59     if options.working_Dir[-1] != '/': | 
|  | 60         options.outputFileName = options.working_Dir + '/' + options.outputFileName | 
|  | 61 | 
|  | 62     if options.format == "fasta": | 
|  | 63         parser = FastaParser(options.inputFileName, options.verbosity) | 
|  | 64     elif options.format == "fastq": | 
|  | 65         parser = FastqParser(options.inputFileName, options.verbosity) | 
|  | 66     else: | 
|  | 67         raise Exception("Do not understand '%s' file format." % (options.format)) | 
|  | 68 | 
|  | 69     progress  = Progress(parser.getNbSequences(), "Reading %s" % (options.inputFileName), options.verbosity) | 
|  | 70     sequences = {} | 
|  | 71     for sequence in parser.getIterator(): | 
|  | 72         sequence = sequence.sequence | 
|  | 73         if sequence not in sequences: | 
|  | 74             sequences[sequence] = 1 | 
|  | 75         else: | 
|  | 76             sequences[sequence] += 1 | 
|  | 77         progress.inc() | 
|  | 78     progress.done() | 
|  | 79 | 
|  | 80     values = sequences.values() | 
|  | 81     values.sort() | 
|  | 82     if options.percent != None: | 
|  | 83         threshold = values[int(float(options.percent) / 100 * len(values))] | 
|  | 84     elif options.number != None: | 
|  | 85         threshold = values[-options.number] | 
|  | 86     else: | 
|  | 87         threshold = 0 | 
|  | 88 | 
|  | 89     # sort by value | 
|  | 90     progress     = Progress(parser.getNbSequences(), "Sorting values", options.verbosity) | 
|  | 91     sortedValues = dict([(value, []) for value in sequences.values()]) | 
|  | 92     for sequence, value in sequences.iteritems(): | 
|  | 93         sortedValues[value].append(sequence) | 
|  | 94         progress.inc() | 
|  | 95     progress.done() | 
|  | 96 | 
|  | 97     outputFileName = "%s.txt" % (options.outputFileName) | 
|  | 98     handle         = open(outputFileName, "w") | 
|  | 99     progress       = Progress(parser.getNbSequences(), "Writing into %s" % (outputFileName), options.verbosity) | 
|  | 100     for value in reversed(sorted(sortedValues.keys())): | 
|  | 101         if value >= threshold: | 
|  | 102             for sequence in sortedValues[value]: | 
|  | 103                 handle.write("%s\t%d\n" % (sequence, value)) | 
|  | 104         progress.inc() | 
|  | 105     progress.done() | 
|  | 106     handle.close() | 
|  | 107 | 
|  | 108     line     = {} | 
|  | 109     progress = Progress(len(values), "Preparing plot", options.verbosity) | 
|  | 110     for value in values: | 
|  | 111         if value not in line: | 
|  | 112             line[value] = 1 | 
|  | 113         else: | 
|  | 114             line[value] += 1 | 
|  | 115         progress.inc() | 
|  | 116     progress.done() | 
|  | 117 | 
|  | 118     plot = RPlotter("%s.png" % (options.outputFileName), options.verbosity) | 
|  | 119     plot.setFill(0) | 
|  | 120     plot.setMaximumX(options.xMax) | 
|  | 121     plot.setXLabel("# occurrences") | 
|  | 122     plot.setYLabel("# reads") | 
|  | 123     plot.addLine(line) | 
|  | 124     plot.plot() | 
|  | 125 | 
|  | 126     if options.verbosity > 0: | 
|  | 127         print "%d/%.2f/%.1f/%d occurrences" % (Utils.getMinAvgMedMax(line)) | 
|  | 128 | 
|  | 129 |