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 """Restrict a sequence list with some names"""
|
|
32
|
|
33 from optparse import OptionParser
|
|
34 from commons.core.parsing.ParserChooser import ParserChooser
|
|
35 from commons.core.writer.WriterChooser import WriterChooser
|
|
36 from SMART.Java.Python.misc.Progress import Progress
|
|
37 from SMART.Java.Python.misc import Utils
|
|
38
|
|
39 class RestrictSequenceList(object):
|
|
40
|
|
41 def __init__(self, verbosity):
|
|
42 self.verbosity = verbosity
|
|
43 self.exclude = False
|
|
44
|
|
45 def setInputFileName(self, fileName, format):
|
|
46 chooser = ParserChooser(self.verbosity)
|
|
47 chooser.findFormat(format)
|
|
48 self.parser = chooser.getParser(fileName)
|
|
49
|
|
50 def setExclusion(self, boolean):
|
|
51 self.exclude = boolean
|
|
52
|
|
53 def setOutputFileName(self, fileName, format):
|
|
54 chooser = WriterChooser(self.verbosity)
|
|
55 chooser.findFormat(format)
|
|
56 self.writer = chooser.getWriter(fileName)
|
|
57
|
|
58 def setNamesFileName(self, fileName):
|
|
59 self.namesFileName = fileName
|
|
60
|
|
61 def _readNames(self):
|
|
62 self.names = []
|
|
63 handle = open(self.namesFileName)
|
|
64 for name in handle:
|
|
65 self.names.append(name.strip())
|
|
66 handle.close()
|
|
67
|
|
68 def _write(self):
|
|
69 nbElements = self.parser.getNbItems()
|
|
70 progress = Progress(nbElements, "Parsing input file", self.verbosity)
|
|
71 nbRead = 0
|
|
72 nbWritten = 0
|
|
73 for element in self.parser.getIterator():
|
|
74 name = element.getName()
|
|
75 nbRead += 1
|
|
76 if Utils.xor(name in self.names, self.exclude):
|
|
77 self.writer.addElement(element)
|
|
78 nbWritten += 1
|
|
79 if name in self.names:
|
|
80 self.names.remove(name)
|
|
81 progress.inc()
|
|
82 progress.done()
|
|
83 if self.verbosity > 0:
|
|
84 print "%d read" % (nbRead)
|
|
85 print "%d written (%d%%)" % (nbWritten, 0 if nbRead == 0 else round(float(nbWritten) / nbRead * 100))
|
|
86
|
|
87 def run(self):
|
|
88 self._readNames()
|
|
89 self._write()
|
|
90 if self.names:
|
|
91 print "Some names are not present in the file: %s" % ", ".join(self.names)
|
|
92
|
|
93
|
|
94
|
|
95 if __name__ == "__main__":
|
|
96
|
|
97 description = "Restrict Sequence List v1.0.1: Keep the elements of a list of sequences whose name is mentionned in a given file. [Category: Data Selection]"
|
|
98
|
|
99 parser = OptionParser(description = description)
|
|
100 parser.add_option("-i", "--input", dest="inputFile", action="store", type="string", help="input file [compulsory] [format: file in sequence format given by -f]")
|
|
101 parser.add_option("-f", "--format", dest="format", action="store", default="fasta", type="string", help="format of the input and output files [compulsory] [format: sequence file format] [default: fasta]")
|
|
102 parser.add_option("-n", "--name", dest="names", action="store", type="string", help="names of the transcripts [compulsory] [format: file in TXT format]")
|
|
103 parser.add_option("-o", "--output", dest="outputFile", action="store", type="string", help="output file [format: output file in sequence format given by -f]")
|
|
104 parser.add_option("-x", "--exclude", dest="exclude", action="store_true", default=False, help="output all those whose name is NOT on the list [format: boolean]")
|
|
105 parser.add_option("-v", "--verbosity", dest="verbosity", action="store", default=1, type="int", help="trace level [format: int]")
|
|
106 (options, args) = parser.parse_args()
|
|
107
|
|
108 rsl = RestrictSequenceList(options.verbosity)
|
|
109 rsl.setInputFileName(options.inputFile, options.format)
|
|
110 rsl.setOutputFileName(options.outputFile, options.format)
|
|
111 rsl.setNamesFileName(options.names)
|
|
112 rsl.setExclusion(options.exclude)
|
|
113 rsl.run()
|