|
10
|
1 #! /usr/bin/env python
|
|
|
2 """
|
|
|
3 Yufei LUO
|
|
|
4 """
|
|
|
5
|
|
|
6 #This program is a wrapp for CompareOverlapping.py.
|
|
|
7 import optparse, os, sys, subprocess, tempfile, shutil, tarfile, glob
|
|
|
8 import os, struct, time, random
|
|
|
9 from optparse import OptionParser
|
|
|
10 from commons.core.parsing.ParserChooser import ParserChooser
|
|
|
11 from commons.core.writer.Gff3Writer import Gff3Writer
|
|
|
12 from SMART.Java.Python.CompareOverlapping import CompareOverlapping
|
|
|
13 from SMART.Java.Python.structure.Transcript import Transcript
|
|
|
14 from SMART.Java.Python.structure.Interval import Interval
|
|
|
15 from SMART.Java.Python.ncList.NCList import NCList
|
|
|
16 from SMART.Java.Python.ncList.NCListCursor import NCListCursor
|
|
|
17 from SMART.Java.Python.ncList.NCListFilePickle import NCListFilePickle, NCListFileUnpickle
|
|
|
18 from SMART.Java.Python.ncList.FileSorter import FileSorter
|
|
|
19 from SMART.Java.Python.misc.Progress import Progress
|
|
|
20 from SMART.Java.Python.misc.UnlimitedProgress import UnlimitedProgress
|
|
|
21 from SMART.Java.Python.misc import Utils
|
|
|
22
|
|
|
23
|
|
|
24
|
|
|
25 def stop_err( msg ):
|
|
|
26 sys.stderr.write( "%s\n" % msg )
|
|
|
27 sys.exit()
|
|
|
28
|
|
|
29 def toTar(tarFileName, overlapOutputNames):
|
|
|
30 dir = os.path.dirname(tarFileName)
|
|
|
31 tfile = tarfile.open(tarFileName + ".tmp.tar", "w")
|
|
|
32 currentPath = os.getcwd()
|
|
|
33 os.chdir(dir)
|
|
|
34 for file in overlapOutputNames:
|
|
|
35 relativeFileName = os.path.basename(file)
|
|
|
36 tfile.add(relativeFileName)
|
|
|
37 os.system("mv %s %s" % (tarFileName + ".tmp.tar", tarFileName))
|
|
|
38 tfile.close()
|
|
|
39 os.chdir(currentPath)
|
|
|
40
|
|
|
41 def __main__():
|
|
|
42 description = "Compare Overlapping wrapp script: Get the a list of data which overlap with a reference set. [Category: Data Comparison]"
|
|
|
43 parser = OptionParser(description = description)
|
|
|
44 parser.add_option("-i", "--input1", dest="inputFileName1", action="store", type="string", help="input file 1 (for annotation) [compulsory] [format: file in transcript format given by -f]")
|
|
|
45 parser.add_option("-f", "--format1", dest="format1", action="store", type="string", help="format of file 1 [compulsory] [format: transcript file format]")
|
|
|
46 parser.add_option("", "--inputTxt", dest="inputTxt", action="store", type="string", help="input, a txt file for a list of input reads files. Should identify all reads files format, given by -g [compulsory]")
|
|
|
47 #parser.add_option("-j", "--input2", dest="inputFileName2", action="store", default="inputRead", type="string", help="input file 2 [compulsory] [format: file in transcript format given by -g]")
|
|
|
48 parser.add_option("-g", "--format2", dest="format2", action="store", type="string", help="format of file 2 [compulsory] [format: transcript file format]")
|
|
|
49 #parser.add_option("-o", "--output", dest="output", action="store", default=None, type="string", help="output file [compulsory] [format: output file in GFF3 format]")
|
|
|
50 parser.add_option("-S", "--start1", dest="start1", action="store", default=None, type="int", help="only consider the n first nucleotides of the transcripts in file 1 (do not use it with -U) [format: int]")
|
|
|
51 parser.add_option("-s", "--start2", dest="start2", action="store", default=None, type="int", help="only consider the n first nucleotides of the transcripts in file 2 (do not use it with -u) [format: int]")
|
|
|
52 parser.add_option("-U", "--end1", dest="end1", action="store", default=None, type="int", help="only consider the n last nucleotides of the transcripts in file 1 (do not use it with -S) [format: int]")
|
|
|
53 parser.add_option("-u", "--end2", dest="end2", action="store", default=None, type="int", help="only consider the n last nucleotides of the transcripts in file 2 (do not use it with -s) [format: int]")
|
|
|
54 parser.add_option("-t", "--intron", dest="introns", action="store_true", default=False, help="also report introns [format: bool] [default: false]")
|
|
|
55 parser.add_option("-E", "--5primeExtension1", dest="fivePrime1", action="store", default=None, type="int", help="extension towards 5' in file 1 [format: int]")
|
|
|
56 parser.add_option("-e", "--5primeExtension2", dest="fivePrime2", action="store", default=None, type="int", help="extension towards 5' in file 2 [format: int]")
|
|
|
57 parser.add_option("-N", "--3primeExtension1", dest="threePrime1", action="store", default=None, type="int", help="extension towards 3' in file 1 [format: int]")
|
|
|
58 parser.add_option("-n", "--3primeExtension2", dest="threePrime2", action="store", default=None, type="int", help="extension towards 3' in file 2 [format: int]")
|
|
|
59 parser.add_option("-c", "--colinear", dest="colinear", action="store_true", default=False, help="colinear only [format: bool] [default: false]")
|
|
|
60 parser.add_option("-a", "--antisense", dest="antisense", action="store_true", default=False, help="antisense only [format: bool] [default: false]")
|
|
|
61 parser.add_option("-d", "--distance", dest="distance", action="store", default=None, type="int", help="accept some distance between query and reference [format: int]")
|
|
|
62 parser.add_option("-k", "--included", dest="included", action="store_true", default=False, help="keep only elements from file 1 which are included in an element of file 2 [format: bool] [default: false]")
|
|
|
63 parser.add_option("-K", "--including", dest="including", action="store_true", default=False, help="keep only elements from file 2 which are included in an element of file 1 [format: bool] [default: false]")
|
|
|
64 parser.add_option("-m", "--minOverlap", dest="minOverlap", action="store", default=None, type="int", help="minimum number of nucleotides overlapping to declare an overlap [format: int] [default: 1]")
|
|
|
65 parser.add_option("-p", "--pcOverlap", dest="pcOverlap", action="store", default=None, type="int", help="minimum percentage of nucleotides to overlap to declare an overlap [format: int]")
|
|
|
66 parser.add_option("-O", "--notOverlapping", dest="notOverlapping", action="store_true", default=False, help="also output not overlapping data [format: bool] [default: false]")
|
|
|
67 parser.add_option("-x", "--exclude", dest="exclude", action="store_true", default=False, help="invert the match [format: bool] [default: false]")
|
|
|
68 parser.add_option("-v", "--verbosity", dest="verbosity", action="store", default=1, type="int", help="trace level [format: int]")
|
|
|
69 parser.add_option('', '--tar', dest='outputTar', default=None, help='output all SAM results in a tar file.' )
|
|
|
70 parser.add_option( '', '--outTxt', dest='outTxtFile', help='The output list of results files on txt format.[compulsory]' )
|
|
|
71 (options, args) = parser.parse_args()
|
|
|
72
|
|
|
73
|
|
|
74 #Parse the input txt file and read a list of BAM files.
|
|
|
75 file = open(options.inputTxt, "r")
|
|
|
76 lines = file.readlines()
|
|
|
77 inputFileNames = []
|
|
|
78 overlapOutputNames = []
|
|
|
79 outputName = options.outTxtFile
|
|
|
80 resDirName = os.path.dirname(outputName) + "/"
|
|
|
81 #Write output txt file and define all output sam file names.
|
|
|
82 out = open(outputName, "w")
|
|
|
83 for line in lines:
|
|
|
84 tab = line.split()
|
|
|
85 inputFileNames.append(tab[1])
|
|
|
86 overlapOutName = resDirName + tab[0] + '_overlapOut_%s.gff3' % random.randrange(0, 10000)
|
|
|
87 overlapOutputNames.append(overlapOutName)
|
|
|
88 out.write(tab[0] + '\t' + overlapOutName + '\n')
|
|
|
89 file.close()
|
|
|
90 out.close()
|
|
|
91
|
|
|
92 #construction the commandes for each input file
|
|
|
93 cmds = []
|
|
|
94 for i in range(len(inputFileNames)):
|
|
|
95 absFile = sys.argv[0]
|
|
|
96 absDir = os.path.dirname(absFile)
|
|
|
97 parentDir = os.path.abspath(os.path.join(absDir, os.path.pardir))
|
|
|
98 cmd = "python %s/Java/Python/CompareOverlappingSmallQuery.py " % parentDir
|
|
|
99 opts = "-i %s -f %s -j %s -g %s -o %s " % (options.inputFileName1, options.format1, inputFileNames[i], options.format2, overlapOutputNames[i])
|
|
|
100 #if options.start1 != None:
|
|
|
101 # opts += "-S %s " % options.start1
|
|
|
102 #if options.start2 != None:
|
|
|
103 # opts += "-s %s " % options.start2
|
|
|
104 #if options.end1 != None:
|
|
|
105 # opts += "-U %s " % options.end1
|
|
|
106 #if options.end2 != None:
|
|
|
107 # opts += "-u %s " % options.end2
|
|
|
108 #if options.fivePrime1 != None:
|
|
|
109 # opts += "-E %s " % options.fivePrime1
|
|
|
110 #if options.fivePrime2 != None:
|
|
|
111 # opts += "-e %s " % options.fivePrime2
|
|
|
112 #if options.threePrime1 != None:
|
|
|
113 # opts += "-N %s " % options.threePrime1
|
|
|
114 #if options.threePrime2 != None:
|
|
|
115 # opts += "-n %s " % options.threePrime2
|
|
|
116 #if options.colinear:
|
|
|
117 # opts += "-c "
|
|
|
118 #if options.antisense:
|
|
|
119 # opts +="-a "
|
|
|
120 #if options.included:
|
|
|
121 # opts += "-k "
|
|
|
122 #if options.including:
|
|
|
123 # opts += "-K "
|
|
|
124 #if options.pcOverlap != None:
|
|
|
125 # opts += "-p %s " % options.pcOverlap
|
|
|
126 if options.notOverlapping:
|
|
|
127 opts += "-O "
|
|
|
128 if options.exclude:
|
|
|
129 opts += "-x "
|
|
|
130 if options.distance != None:
|
|
|
131 opts += "-d %s " % options.distance
|
|
|
132 #if options.minOverlap != None:
|
|
|
133 # opts += "-m %s " % options.minOverlap
|
|
|
134 cmd += opts
|
|
|
135 cmds.append(cmd)
|
|
|
136
|
|
|
137
|
|
|
138 print "les commandes sont %s \n" % cmds
|
|
|
139
|
|
|
140 tmp_files = []
|
|
|
141 for i in range(len(cmds)):
|
|
|
142 try:
|
|
|
143 tmp_out = tempfile.NamedTemporaryFile().name
|
|
|
144 tmp_files.append(tmp_out)
|
|
|
145 tmp_stdout = open( tmp_out, 'wb' )
|
|
|
146 tmp_err = tempfile.NamedTemporaryFile().name
|
|
|
147 tmp_files.append(tmp_err)
|
|
|
148 tmp_stderr = open( tmp_err, 'wb' )
|
|
|
149 proc = subprocess.Popen( args=cmds[i], shell=True, cwd=".", stdout=tmp_stdout, stderr=tmp_stderr )
|
|
|
150 returncode = proc.wait()
|
|
|
151 tmp_stderr.close()
|
|
|
152 # get stderr, allowing for case where it's very large
|
|
|
153 tmp_stderr = open( tmp_err, 'rb' )
|
|
|
154 stderr = ''
|
|
|
155 buffsize = 1048576
|
|
|
156 try:
|
|
|
157 while True:
|
|
|
158 stderr += tmp_stderr.read( buffsize )
|
|
|
159 if not stderr or len( stderr ) % buffsize != 0:
|
|
|
160 break
|
|
|
161 except OverflowError:
|
|
|
162 pass
|
|
|
163 tmp_stdout.close()
|
|
|
164 tmp_stderr.close()
|
|
|
165 if returncode != 0:
|
|
|
166 raise Exception, stderr
|
|
|
167 except Exception, e:
|
|
|
168 stop_err( 'Error in :\n' + str( e ) )
|
|
|
169
|
|
|
170 if options.outputTar != None:
|
|
|
171 toTar(options.outputTar, overlapOutputNames)
|
|
|
172
|
|
|
173 for tmp_file in tmp_files:
|
|
|
174 os.remove(tmp_file)
|
|
|
175
|
|
|
176
|
|
|
177 if __name__=="__main__": __main__()
|
|
|
178
|
|
|
179
|
