| 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 """Get the size distribution of a Fasta / BED file""" | 
|  | 32 | 
|  | 33 import os | 
|  | 34 from optparse import OptionParser | 
|  | 35 from commons.core.parsing.FastaParser import * | 
|  | 36 from commons.core.parsing.FastqParser import * | 
|  | 37 from SMART.Java.Python.structure.TranscriptContainer import * | 
|  | 38 from commons.core.writer.TranscriptWriter import * | 
|  | 39 from commons.core.writer.FastaWriter import * | 
|  | 40 from commons.core.writer.FastqWriter import * | 
|  | 41 from SMART.Java.Python.misc.Progress import * | 
|  | 42 from SMART.Java.Python.misc.RPlotter import * | 
|  | 43 | 
|  | 44 | 
|  | 45 if __name__ == "__main__": | 
|  | 46 | 
|  | 47     # parse command line | 
|  | 48     description = "Restrict from Size v1.0.1: Select the elements of a list of sequences or transcripts with a given size. [Category: Data Selection]" | 
|  | 49 | 
|  | 50     parser = OptionParser(description = description) | 
|  | 51     parser.add_option("-i", "--input",     dest="inputFileName",  action="store",                     type="string", help="input file [compulsory] [format: file in transcript or sequence format given by -f]") | 
|  | 52     parser.add_option("-f", "--format",    dest="format",         action="store",                     type="string", help="format of the input [compulsory] [format: sequence or transcript file format]") | 
|  | 53     parser.add_option("-o", "--output",    dest="outputFileName", action="store",                     type="string", help="output file [compulsory] [format: output file in transcript or sequence format given by -f]") | 
|  | 54     parser.add_option("-m", "--minSize",   dest="minSize",        action="store",      default=None,  type="int",    help="minimum size [format: int]") | 
|  | 55     parser.add_option("-M", "--maxSize",   dest="maxSize",        action="store",      default=None,  type="int",    help="maximum size [format: int]") | 
|  | 56     parser.add_option("-v", "--verbosity", dest="verbosity",      action="store",      default=1,     type="int",    help="trace level [format: int]") | 
|  | 57     parser.add_option("-l", "--log",       dest="log",            action="store_true", default=False,                help="write a log file [format: bool] [default: false]") | 
|  | 58     (options, args) = parser.parse_args() | 
|  | 59 | 
|  | 60     if options.format == "fasta": | 
|  | 61         parser = FastaParser(options.inputFileName, options.verbosity) | 
|  | 62         writer = FastaWriter(options.outputFileName, options.verbosity) | 
|  | 63     elif options.format == "fastq": | 
|  | 64         parser = FastqParser(options.inputFileName, options.verbosity) | 
|  | 65         writer = FastqWriter(options.outputFileName, options.verbosity) | 
|  | 66     else: | 
|  | 67         parser = TranscriptContainer(options.inputFileName, options.format, options.verbosity) | 
|  | 68         writer = TranscriptWriter(options.outputFileName, options.format, options.verbosity) | 
|  | 69 | 
|  | 70 | 
|  | 71     # treat items | 
|  | 72     nbItems  = parser.getNbItems() | 
|  | 73     progress = Progress(nbItems, "Analyzing sequences of %s" % (options.inputFileName), options.verbosity) | 
|  | 74     nbKept   = 0 | 
|  | 75     nbRead   = 0 | 
|  | 76     nbClKept = 0 | 
|  | 77     nbClRead = 0 | 
|  | 78     for item in parser.getIterator(): | 
|  | 79         size      = item.getSize() | 
|  | 80         nb        = 1 if options.format in ("fasta", "fastq") or "nbElements" not in item.getTagNames() else float(item.getTagValue("nbElements")) | 
|  | 81         nbRead   += nb | 
|  | 82         nbClRead += 1 | 
|  | 83         if (options.minSize == None or options.minSize <= size) and (options.maxSize == None or options.maxSize >= size): | 
|  | 84             writer.addElement(item) | 
|  | 85             nbKept   += nb | 
|  | 86             nbClKept += 1 | 
|  | 87         progress.inc() | 
|  | 88     progress.done() | 
|  | 89 | 
|  | 90     writer.write() | 
|  | 91 | 
|  | 92     print "%d items,    %d kept (%.2f%%)" % (nbRead, nbKept, 0 if nbItems == 0 else float(nbKept) / nbItems * 100) | 
|  | 93     if nbKept != nbClKept or nbRead != nbClRead: | 
|  | 94         print "%d clusters, %d kept (%.2f%%)" % (nbClRead, nbClKept, 0 if nbClRead == 0 else float(nbClKept) / nbClRead * 100) |