|
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 Remove empty sequences from a FASTA or FASTQ file
|
|
|
33 """
|
|
|
34
|
|
|
35 import os, random
|
|
|
36 from optparse import OptionParser
|
|
|
37 from commons.core.parsing.FastaParser import *
|
|
|
38 from commons.core.parsing.FastqParser import *
|
|
|
39 from commons.core.writer.FastaWriter import *
|
|
|
40 from commons.core.writer.FastqWriter import *
|
|
|
41 from SMART.Java.Python.misc.Progress import *
|
|
|
42
|
|
|
43
|
|
|
44 class EmptySequenceRemover(object):
|
|
|
45
|
|
|
46 def __init__(self, verbosity = 1):
|
|
|
47 self.verbosity = verbosity
|
|
|
48 self.inputFileName = None
|
|
|
49 self.parser = None
|
|
|
50 self.format = None
|
|
|
51 self.writer = None
|
|
|
52 self.forbiddenNames = {}
|
|
|
53 self.removedNames = {}
|
|
|
54
|
|
|
55
|
|
|
56 def setInputFileName(self, fileName, format):
|
|
|
57 self.inputFileName = fileName
|
|
|
58 self.format = format
|
|
|
59 if options.format == "fasta":
|
|
|
60 self.parser = FastaParser(self.inputFileName, self.verbosity)
|
|
|
61 elif options.format == "fastq":
|
|
|
62 self.parser = FastqParser(self.inputFileName, self.verbosity)
|
|
|
63 else:
|
|
|
64 sys.exit("Do not understand '%s' file format." % (self.format))
|
|
|
65
|
|
|
66
|
|
|
67 def setOutputFileName(self, fileName):
|
|
|
68 if options.format == "fasta":
|
|
|
69 self.writer = FastaWriter("%s.mfa" % (fileName), self.verbosity)
|
|
|
70 elif options.format == "fastq":
|
|
|
71 self.writer = FastqWriter("%s.mfq" % (fileName), self.verbosity)
|
|
|
72
|
|
|
73
|
|
|
74 def parse(self):
|
|
|
75 progress = Progress(self.parser.getNbSequences(), "Reading sequences in %s" % (options.inputFileName), options.verbosity)
|
|
|
76 for sequence in self.parser.getIterator():
|
|
|
77 name = sequence.name.split("/")[0]
|
|
|
78 if name not in self.forbiddenNames:
|
|
|
79 if sequence.sequence == "":
|
|
|
80 self.removedNames[name] = 1
|
|
|
81 else:
|
|
|
82 self.writer.addSequence(sequence)
|
|
|
83 progress.inc()
|
|
|
84 progress.done()
|
|
|
85 self.writer.write()
|
|
|
86
|
|
|
87
|
|
|
88 if __name__ == "__main__":
|
|
|
89
|
|
|
90 # parse command line
|
|
|
91 description = "Remove Empty Sequences v1.0.2: Remove all the empty sequences in a list. [Category: Personal]"
|
|
|
92
|
|
|
93 parser = OptionParser(description = description)
|
|
|
94 parser.add_option("-i", "--input", dest="inputFileName", action="store", type="string", help="input file [compulsory] [format: file in sequence format given by -f]")
|
|
|
95 parser.add_option("-f", "--format", dest="format", action="store", type="string", help="format of the input file [compulsory] [format: sequence file format]")
|
|
|
96 parser.add_option("-j", "--input2", dest="inputFileName2", action="store", type="string", help="input file 2 (in case of pair end reads) [format: file in sequence format given by -f] [default: None]")
|
|
|
97 parser.add_option("-o", "--output", dest="outputFileName", action="store", default=None, type="string", help="output file [compulsory] [format: output file in format given by -f]")
|
|
|
98 parser.add_option("-p", "--output2", dest="outputFileName2", action="store", default=None, type="string", help="output file 2 (in case of pair end reads) [format: output file in sequence format given by -f] [default: None]")
|
|
|
99 parser.add_option("-v", "--verbosity", dest="verbosity", action="store", default=1, type="int", help="trace level [format: int] [default: 1]")
|
|
|
100 parser.add_option("-l", "--log", dest="log", action="store_true", default=False, help="write a log file [format: bool] [default: false]")
|
|
|
101 (options, args) = parser.parse_args()
|
|
|
102
|
|
|
103 if options.log:
|
|
|
104 logHandle = open("%s.log" % options.outputFileName, "w")
|
|
|
105
|
|
|
106 remover = EmptySequenceRemover(options.verbosity)
|
|
|
107 remover.setInputFileName(options.inputFileName, options.format)
|
|
|
108 remover.setOutputFileName(options.outputFileName)
|
|
|
109 remover.parse()
|
|
|
110 removedNames = remover.removedNames
|
|
|
111 if options.log:
|
|
|
112 for name in removedNames:
|
|
|
113 logHandle.write("Removed '%s' in %s\n" % (name, options.inputFileName))
|
|
|
114 nbSequences = remover.parser.getNbSequences()
|
|
|
115
|
|
|
116 newRemovedNames = {}
|
|
|
117 if options.inputFileName2 != None:
|
|
|
118 remover = EmptySequenceRemover(options.verbosity)
|
|
|
119 remover.setInputFileName(options.inputFileName2, options.format)
|
|
|
120 remover.setOutputFileName(options.outputFileName2)
|
|
|
121 remover.forbiddenNames = removedNames
|
|
|
122 remover.parse()
|
|
|
123 newRemovedNames = remover.removedNames
|
|
|
124 if options.log:
|
|
|
125 for name in newRemovedNames:
|
|
|
126 logHandle.write("Removed '%s' in %s\n" % (name, options.inputFileName2))
|
|
|
127
|
|
|
128 remover = EmptySequenceRemover(options.verbosity)
|
|
|
129 remover.setInputFileName(options.inputFileName, options.format)
|
|
|
130 remover.setOutputFileName(options.outputFileName)
|
|
|
131 remover.forbiddenNames = newRemovedNames
|
|
|
132 remover.parse()
|
|
|
133
|
|
|
134 nbRemoved = len(removedNames.keys()) + len(newRemovedNames.keys())
|
|
|
135 print "%d over %d sequences are empty (%.2f%%)." % (nbRemoved, nbSequences, float(nbRemoved) / nbSequences * 100)
|
