comparison SMART/Java/Python/trimAdaptor.py @ 38:2c0c0a89fad7

Uploaded
author m-zytnicki
date Thu, 02 May 2013 09:56:47 -0400
parents 769e306b7933
children
comparison
equal deleted inserted replaced
37:d22fadc825e3 38:2c0c0a89fad7
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 """Trim the sequences from a 5' adaptor"""
32
33 import sys
34 from optparse import OptionParser
35 from commons.core.parsing.FastaParser import FastaParser
36 from commons.core.parsing.FastqParser import FastqParser
37 from commons.core.writer.FastaWriter import FastaWriter
38 from commons.core.writer.FastqWriter import FastqWriter
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 = "Trim Adaptor v1.0.1: Remove the 3' adaptor of a list of reads. [Category: Data Modification]"
47
48 parser = OptionParser(description = description)
49 parser.add_option("-i", "--input", dest="inputFileName", action="store", type="string", help="input file [compulsory] [format: file in sequence format given by -f]")
50 parser.add_option("-f", "--format", dest="format", action="store", type="string", help="format of file [compulsory] [format: sequence file format]")
51 parser.add_option("-o", "--output", dest="outputFileName", action="store", type="string", help="output file [compulsory] [format: output file in sequence format given by -f]")
52 parser.add_option("-a", "--adaptor", dest="adaptor", action="store", type="string", help="adaptor [compulsory] [format: string]")
53 parser.add_option("-e", "--errors", dest="errors", action="store", default=0, type="int" , help="number of errors in percent [format: int] [default: 0]")
54 parser.add_option("-n", "--noAdaptor", dest="noAdaptor", action="store", default=None, type="string", help="file name where to print sequences with no adaptor [format: output file in sequence format given by -f]")
55 parser.add_option("-v", "--verbosity", dest="verbosity", action="store", default=1, type="int", help="trace level [format: int]")
56 (options, args) = parser.parse_args()
57
58 minSize = 2
59
60 if options.format == "fasta":
61 parser = FastaParser(options.inputFileName, options.verbosity)
62 elif options.format == "fastq":
63 parser = FastqParser(options.inputFileName, options.verbosity)
64 else:
65 sys.exit("Cannot handle files with '%s' format." % (options.format))
66
67 if options.format == "fasta":
68 writer = FastaWriter(options.outputFileName, options.verbosity)
69 elif options.format == "fastq":
70 writer = FastqWriter(options.outputFileName, options.verbosity)
71 else:
72 sys.exit("Cannot handle files with '%s' format." % (options.format))
73
74 writerNoAdaptor = None
75 if options.noAdaptor != None:
76 if options.format == "fasta":
77 writerNoAdaptor = FastaWriter(options.noAdaptor, options.verbosity)
78 elif options.format == "fastq":
79 writerNoAdaptor = FastqWriter(options.noAdaptor, options.verbosity)
80 else:
81 sys.exit("Cannot handle files with '%s' format." % (options.format))
82
83 nbFound = 0
84
85 progress = Progress(parser.getNbSequences(), "Reading %s" % (options.inputFileName), options.verbosity)
86 for sequence in parser.getIterator():
87 progress.inc()
88 nucleotides = sequence.getSequence()
89 found = False
90 for i in range(len(nucleotides) - minSize):
91 nucleotidesPart = nucleotides[i:]
92 adaptorPart = options.adaptor if len(nucleotidesPart) >= len(options.adaptor) else options.adaptor[:len(nucleotidesPart)]
93 nucleotidesPart = nucleotidesPart if len(adaptorPart) == len(nucleotidesPart) else nucleotidesPart[:len(adaptorPart)]
94 if Utils.getHammingDistance(adaptorPart, nucleotidesPart) <= int(options.errors / 100.0 * len(adaptorPart)):
95 nbFound += 1
96 sequence.shrinkToFirstNucleotides(i)
97 writer.addSequence(sequence)
98 found = True
99 break
100 if not found:
101 writer.addSequence(sequence)
102 if writerNoAdaptor != None:
103 writerNoAdaptor.addSequence(sequence)
104 progress.done()
105
106 print "%d sequences with adaptors on %d (%.2f%%)" % (nbFound, parser.getNbSequences(), float(nbFound) / parser.getNbSequences() * 100)
107