|
10
|
1 #!/usr/bin/env python
|
|
|
2 """
|
|
|
3 Yufei LUO
|
|
|
4 """
|
|
|
5
|
|
|
6 import optparse, os, shutil, subprocess, sys, tempfile, fileinput, tarfile,random
|
|
|
7
|
|
|
8 def stop_err( msg ):
|
|
|
9 sys.stderr.write( "%s\n" % msg )
|
|
|
10 sys.exit()
|
|
|
11
|
|
|
12 def toTar(tarFileName, accepted_hits_outputNames):
|
|
|
13 fileName = os.path.splitext(tarFileName)[0]
|
|
|
14 fileNameBaseName = os.path.basename(fileName)
|
|
|
15 dir = os.path.dirname(tarFileName)
|
|
|
16 tfile = tarfile.open(tarFileName + ".tmp.tar", "w")
|
|
|
17 currentPath = os.getcwd()
|
|
|
18 os.chdir(dir)
|
|
|
19 for file in accepted_hits_outputNames:
|
|
|
20 relativeFileName = os.path.basename(file)
|
|
|
21 tfile.add(relativeFileName)
|
|
|
22 os.system("mv %s %s" % (tarFileName + ".tmp.tar", tarFileName))
|
|
|
23 tfile.close()
|
|
|
24 os.chdir(currentPath)
|
|
|
25
|
|
|
26
|
|
|
27 def __main__():
|
|
|
28 #Parse Command Line
|
|
|
29 parser = optparse.OptionParser()
|
|
|
30 parser.add_option('-o', '--outputTxtFile', dest='outputTxtFile', help='for Differential expression analysis pipeline, new output option gives a txt output containing the list of mapping results.')
|
|
|
31 parser.add_option('-t', '--tar', dest='outputTar', default=None, help='output all accepted hits results in a tar file.' )
|
|
|
32 parser.add_option( '-p', '--num-threads', dest='num_threads', help='Use this many threads to align reads. The default is 1.' )
|
|
|
33 parser.add_option( '-C', '--color-space', dest='color_space', action='store_true', help='This indicates color-space data' )
|
|
|
34 parser.add_option( '-J', '--junctions-output', dest='junctions_output_file', default='junctions_output.bed', help='Junctions output file; formate is BED.' )
|
|
|
35 parser.add_option( '-H', '--hits-output', dest='accepted_hits_output_file', default='hits_output_%s.bam' % random.randrange(0, 10000), help='Accepted hits output file; formate is BAM.' )
|
|
|
36 parser.add_option( '', '--own-file', dest='own_file', help='' )
|
|
|
37 parser.add_option( '-D', '--indexes-path', dest='index_path', help='Indexes directory; location of .ebwt and .fa files.' )
|
|
|
38 parser.add_option( '-r', '--mate-inner-dist', dest='mate_inner_dist', help='This is the expected (mean) inner distance between mate pairs. \
|
|
|
39 For, example, for paired end runs with fragments selected at 300bp, \
|
|
|
40 where each end is 50bp, you should set -r to be 200. There is no default, \
|
|
|
41 and this parameter is required for paired end runs.')
|
|
|
42 parser.add_option( '', '--mate-std-dev', dest='mate_std_dev', help='Standard deviation of distribution on inner distances between male pairs.' )
|
|
|
43 parser.add_option( '-a', '--min-anchor-length', dest='min_anchor_length',
|
|
|
44 help='The "anchor length". TopHat will report junctions spanned by reads with at least this many bases on each side of the junction.' )
|
|
|
45 parser.add_option( '-m', '--splice-mismatches', dest='splice_mismatches', help='The maximum number of mismatches that can appear in the anchor region of a spliced alignment.' )
|
|
|
46 parser.add_option( '-i', '--min-intron-length', dest='min_intron_length',
|
|
|
47 help='The minimum intron length. TopHat will ignore donor/acceptor pairs closer than this many bases apart.' )
|
|
|
48 parser.add_option( '-I', '--max-intron-length', dest='max_intron_length',
|
|
|
49 help='The maximum intron length. When searching for junctions ab initio, TopHat will ignore donor/acceptor pairs farther than this many bases apart, except when such a pair is supported by a split segment alignment of a long read.' )
|
|
|
50 parser.add_option( '-F', '--junction_filter', dest='junction_filter', help='Filter out junctions supported by too few alignments (number of reads divided by average depth of coverage)' )
|
|
|
51 parser.add_option( '-g', '--max_multihits', dest='max_multihits', help='Maximum number of alignments to be allowed' )
|
|
|
52 parser.add_option( '', '--initial-read-mismatches', dest='initial_read_mismatches', help='Number of mismatches allowed in the initial read mapping' )
|
|
|
53 parser.add_option( '', '--seg-mismatches', dest='seg_mismatches', help='Number of mismatches allowed in each segment alignment for reads mapped independently' )
|
|
|
54 parser.add_option( '', '--seg-length', dest='seg_length', help='Minimum length of read segments' )
|
|
|
55 parser.add_option( '', '--library-type', dest='library_type', help='TopHat will treat the reads as strand specific. Every read alignment will have an XS attribute tag. Consider supplying library type options below to select the correct RNA-seq protocol.' )
|
|
|
56 parser.add_option( '', '--allow-indels', action="store_true", help='Allow indel search. Indel search is disabled by default.(Not used since version 1.3.0)' )
|
|
|
57 parser.add_option( '', '--max-insertion-length', dest='max_insertion_length', help='The maximum insertion length. The default is 3.' )
|
|
|
58 parser.add_option( '', '--max-deletion-length', dest='max_deletion_length', help='The maximum deletion length. The default is 3.' )
|
|
|
59
|
|
|
60 # Options for supplying own junctions
|
|
|
61 parser.add_option( '-G', '--GTF', dest='gene_model_annotations', help='Supply TopHat with a list of gene model annotations. \
|
|
|
62 TopHat will use the exon records in this file to build \
|
|
|
63 a set of known splice junctions for each gene, and will \
|
|
|
64 attempt to align reads to these junctions even if they \
|
|
|
65 would not normally be covered by the initial mapping.')
|
|
|
66 parser.add_option( '-j', '--raw-juncs', dest='raw_juncs', help='Supply TopHat with a list of raw junctions. Junctions are \
|
|
|
67 specified one per line, in a tab-delimited format. Records \
|
|
|
68 look like: <chrom> <left> <right> <+/-> left and right are \
|
|
|
69 zero-based coordinates, and specify the last character of the \
|
|
|
70 left sequenced to be spliced to the first character of the right \
|
|
|
71 sequence, inclusive.')
|
|
|
72 parser.add_option( '', '--no-novel-juncs', action="store_true", dest='no_novel_juncs', help="Only look for junctions indicated in the \
|
|
|
73 supplied GFF file. (ignored without -G)")
|
|
|
74 parser.add_option( '', '--no-novel-indels', action="store_true", dest='no_novel_indels', help="Skip indel search. Indel search is enabled by default.")
|
|
|
75 # Types of search.
|
|
|
76 parser.add_option( '', '--microexon-search', action="store_true", dest='microexon_search', help='With this option, the pipeline will attempt to find alignments incident to microexons. Works only for reads 50bp or longer.')
|
|
|
77 parser.add_option( '', '--closure-search', action="store_true", dest='closure_search', help='Enables the mate pair closure-based search for junctions. Closure-based search should only be used when the expected inner distance between mates is small (<= 50bp)')
|
|
|
78 parser.add_option( '', '--no-closure-search', action="store_false", dest='closure_search' )
|
|
|
79 parser.add_option( '', '--coverage-search', action="store_true", dest='coverage_search', help='Enables the coverage based search for junctions. Use when coverage search is disabled by default (such as for reads 75bp or longer), for maximum sensitivity.')
|
|
|
80 parser.add_option( '', '--no-coverage-search', action="store_false", dest='coverage_search' )
|
|
|
81 parser.add_option( '', '--min-segment-intron', dest='min_segment_intron', help='Minimum intron length that may be found during split-segment search' )
|
|
|
82 parser.add_option( '', '--max-segment-intron', dest='max_segment_intron', help='Maximum intron length that may be found during split-segment search' )
|
|
|
83 parser.add_option( '', '--min-closure-exon', dest='min_closure_exon', help='Minimum length for exonic hops in potential splice graph' )
|
|
|
84 parser.add_option( '', '--min-closure-intron', dest='min_closure_intron', help='Minimum intron length that may be found during closure search' )
|
|
|
85 parser.add_option( '', '--max-closure-intron', dest='max_closure_intron', help='Maximum intron length that may be found during closure search' )
|
|
|
86 parser.add_option( '', '--min-coverage-intron', dest='min_coverage_intron', help='Minimum intron length that may be found during coverage search' )
|
|
|
87 parser.add_option( '', '--max-coverage-intron', dest='max_coverage_intron', help='Maximum intron length that may be found during coverage search' )
|
|
|
88
|
|
|
89 # Wrapper options.
|
|
|
90 parser.add_option( '-1', '--input1', dest='input1', help='A list of the (forward or single-end) reads files of Sanger FASTQ format, txt format' )
|
|
|
91 #parser.add_option( '-1', '--input1', dest='input1', help='The (forward or single-end) reads file in Sanger FASTQ format' )
|
|
|
92 #parser.add_option( '-2', '--input2', dest='input2', help='The reverse reads file in Sanger FASTQ format' )
|
|
|
93 parser.add_option( '-2', '--input2', dest='input2', help='The list of reverse reads file in Sanger FASTQ format' )
|
|
|
94 parser.add_option( '', '--single-paired', dest='single_paired', help='' )
|
|
|
95 parser.add_option( '', '--settings', dest='settings', help='' )
|
|
|
96
|
|
|
97 (options, args) = parser.parse_args()
|
|
|
98
|
|
|
99 # output version # of tool
|
|
|
100 try:
|
|
|
101 tmp_files = []
|
|
|
102 tmp = tempfile.NamedTemporaryFile().name
|
|
|
103 tmp_files.append(tmp)
|
|
|
104 tmp_stdout = open( tmp, 'wb' )
|
|
|
105 proc = subprocess.Popen( args='tophat -v', shell=True, stdout=tmp_stdout )
|
|
|
106 tmp_stdout.close()
|
|
|
107 returncode = proc.wait()
|
|
|
108 stdout = open( tmp_stdout.name, 'rb' ).readline().strip()
|
|
|
109 if stdout:
|
|
|
110 sys.stdout.write( '%s\n' % stdout )
|
|
|
111 else:
|
|
|
112 raise Exception
|
|
|
113 except:
|
|
|
114 sys.stdout.write( 'Could not determine Tophat version\n' )
|
|
|
115
|
|
|
116 # Color or base space
|
|
|
117 space = ''
|
|
|
118 if options.color_space:
|
|
|
119 space = '-C'
|
|
|
120
|
|
|
121
|
|
|
122 #reads = options.input1
|
|
|
123 file = open(options.input1,"r")
|
|
|
124 lines = file.readlines()
|
|
|
125 inputFileNames = []
|
|
|
126 accepted_hits_outputNames = []
|
|
|
127 outputName = options.outputTxtFile
|
|
|
128 resDirName = os.path.dirname(outputName) + '/'
|
|
|
129 out = open(outputName, "w")
|
|
|
130 for line in lines:
|
|
|
131 tab = line.split()
|
|
|
132 inputFileNames.append(tab[1])
|
|
|
133 aHitOutName = resDirName + tab[0] + '_' + options.accepted_hits_output_file
|
|
|
134 accepted_hits_outputNames.append(aHitOutName)
|
|
|
135 out.write(tab[0] + '\t' + aHitOutName + '\n')
|
|
|
136 file.close()
|
|
|
137 out.close()
|
|
|
138
|
|
|
139 if options.input2:
|
|
|
140 revFile = open(options.input2,"r")
|
|
|
141 lines = revFile.readlines()
|
|
|
142 inputRevFileNames = []
|
|
|
143 for line in lines:
|
|
|
144 revTab = line.split()
|
|
|
145 inputRevFileNames.append(revTab[1])
|
|
|
146 revFile.close()
|
|
|
147
|
|
|
148
|
|
|
149 # Creat bowtie index if necessary.
|
|
|
150 tmp_index_dirs = []
|
|
|
151 index_paths = []
|
|
|
152 tmp_index_dir = tempfile.mkdtemp()
|
|
|
153 tmp_index_dirs.append(tmp_index_dir)
|
|
|
154 if options.own_file:
|
|
|
155 index_path = os.path.join( tmp_index_dir, '.'.join( os.path.split( options.own_file )[1].split( '.' )[:-1] ) )
|
|
|
156 index_paths.append(index_path)
|
|
|
157 try:
|
|
|
158 os.link( options.own_file, index_path + '.fa' )
|
|
|
159 except:
|
|
|
160 # Tophat prefers (but doesn't require) fasta file to be in same directory, with .fa extension
|
|
|
161 pass
|
|
|
162 cmd_index = 'bowtie-build %s -f %s %s' % ( space, options.own_file, index_path )
|
|
|
163 try:
|
|
|
164 tmp = tempfile.NamedTemporaryFile( dir=tmp_index_dir ).name
|
|
|
165 tmp_stderr = open( tmp, 'wb' )
|
|
|
166 proc = subprocess.Popen( args=cmd_index, shell=True, cwd=tmp_index_dir, stderr=tmp_stderr.fileno() )
|
|
|
167 returncode = proc.wait()
|
|
|
168 tmp_stderr.close()
|
|
|
169 # get stderr, allowing for case where it's very large
|
|
|
170 tmp_stderr = open( tmp, 'rb' )
|
|
|
171 stderr = ''
|
|
|
172 buffsize = 1048576
|
|
|
173 try:
|
|
|
174 while True:
|
|
|
175 stderr += tmp_stderr.read( buffsize )
|
|
|
176 if not stderr or len( stderr ) % buffsize != 0:
|
|
|
177 break
|
|
|
178 except OverflowError:
|
|
|
179 pass
|
|
|
180 tmp_stderr.close()
|
|
|
181 if returncode != 0:
|
|
|
182 raise Exception, stderr
|
|
|
183 except Exception, e:
|
|
|
184 if os.path.exists( tmp_index_dir ):
|
|
|
185 shutil.rmtree( tmp_index_dir )
|
|
|
186 stop_err( 'Error indexing reference sequence\n' + str( e ) )
|
|
|
187 else:
|
|
|
188 for file in inputFileNames:
|
|
|
189 tmp_index_dir = tempfile.mkdtemp()
|
|
|
190 index_path = tmp_index_dir + '/' + os.path.basename(file).split('.')[0]
|
|
|
191 index_paths.append(index_path)
|
|
|
192 tmp_index_dirs.append(tmp_index_dir)
|
|
|
193
|
|
|
194
|
|
|
195
|
|
|
196 # Build tophat command.
|
|
|
197 cmds = []
|
|
|
198 # for inputFileName in inputFileNames:
|
|
|
199 for i in range(len(inputFileNames)):
|
|
|
200 cmd = 'tophat %s %s %s '
|
|
|
201 input_files = inputFileNames[i]
|
|
|
202 if options.input2:
|
|
|
203 input_files += ' ' + inputRevFileNames[i]
|
|
|
204 opts = '-p %s %s' % ( options.num_threads, space )
|
|
|
205 if options.single_paired == 'paired':
|
|
|
206 opts += '-r %s ' % options.mate_inner_dist
|
|
|
207 if options.settings == 'preSet':
|
|
|
208 if options.own_file:
|
|
|
209 cmd = cmd % ( opts, index_paths[0], input_files ) #here add paired end file
|
|
|
210 else:
|
|
|
211 cmd = cmd % ( opts, index_paths[i], input_files ) #here add paired end file
|
|
|
212 else:
|
|
|
213 try:
|
|
|
214 if int( options.min_anchor_length ) >= 3:
|
|
|
215 opts += '-a %s ' % options.min_anchor_length
|
|
|
216 else:
|
|
|
217 raise Exception, 'Minimum anchor length must be 3 or greater'
|
|
|
218 opts += '-m %s ' % options.splice_mismatches
|
|
|
219 opts += '-i %s ' % options.min_intron_length
|
|
|
220 opts += '-I %s ' % options.max_intron_length
|
|
|
221 if float( options.junction_filter ) != 0.0:
|
|
|
222 opts += '-F %s ' % options.junction_filter
|
|
|
223 opts += '-g %s ' % options.max_multihits
|
|
|
224 # Custom junctions options.
|
|
|
225 if options.gene_model_annotations:
|
|
|
226 opts += '-G %s ' % options.gene_model_annotations
|
|
|
227 if options.raw_juncs:
|
|
|
228 opts += '-j %s ' % options.raw_juncs
|
|
|
229 if options.no_novel_juncs:
|
|
|
230 opts += '--no-novel-juncs '
|
|
|
231 if options.library_type:
|
|
|
232 opts += '--library-type %s ' % options.library_type
|
|
|
233 if options.no_novel_indels:
|
|
|
234 opts += '--no-novel-indels '
|
|
|
235 else:
|
|
|
236 if options.max_insertion_length:
|
|
|
237 opts += '--max-insertion-length %i ' % int( options.max_insertion_length )
|
|
|
238 if options.max_deletion_length:
|
|
|
239 opts += '--max-deletion-length %i ' % int( options.max_deletion_length )
|
|
|
240 # Max options do not work for Tophat v1.2.0, despite documentation to the contrary. (Fixed in version 1.3.1)
|
|
|
241 # need to warn user of this fact
|
|
|
242 #sys.stdout.write( "Max insertion length and max deletion length options don't work in Tophat v1.2.0\n" )
|
|
|
243
|
|
|
244 # Search type options.
|
|
|
245 if options.coverage_search:
|
|
|
246 opts += '--coverage-search --min-coverage-intron %s --max-coverage-intron %s ' % ( options.min_coverage_intron, options.max_coverage_intron )
|
|
|
247 else:
|
|
|
248 opts += '--no-coverage-search '
|
|
|
249 if options.closure_search:
|
|
|
250 opts += '--closure-search --min-closure-exon %s --min-closure-intron %s --max-closure-intron %s ' % ( options.min_closure_exon, options.min_closure_intron, options.max_closure_intron )
|
|
|
251 else:
|
|
|
252 opts += '--no-closure-search '
|
|
|
253 if options.microexon_search:
|
|
|
254 opts += '--microexon-search '
|
|
|
255 if options.single_paired == 'paired':
|
|
|
256 opts += '--mate-std-dev %s ' % options.mate_std_dev
|
|
|
257 if options.initial_read_mismatches:
|
|
|
258 opts += '--initial-read-mismatches %d ' % int( options.initial_read_mismatches )
|
|
|
259 if options.seg_mismatches:
|
|
|
260 opts += '--segment-mismatches %d ' % int( options.seg_mismatches )
|
|
|
261 if options.seg_length:
|
|
|
262 opts += '--segment-length %d ' % int( options.seg_length )
|
|
|
263 if options.min_segment_intron:
|
|
|
264 opts += '--min-segment-intron %d ' % int( options.min_segment_intron )
|
|
|
265 if options.max_segment_intron:
|
|
|
266 opts += '--max-segment-intron %d ' % int( options.max_segment_intron )
|
|
|
267 if options.own_file:
|
|
|
268 cmd = cmd % ( opts, index_paths[0], input_files ) #here to add paired end file
|
|
|
269 else:
|
|
|
270 cmd = cmd % ( opts, index_paths[i], input_files ) #here to add paired end file
|
|
|
271 except Exception, e:
|
|
|
272 # Clean up temp dirs
|
|
|
273 if os.path.exists( tmp_index_dir ):
|
|
|
274 shutil.rmtree( tmp_index_dir )
|
|
|
275 stop_err( 'Something is wrong with the alignment parameters and the alignment could not be run\n' + str( e ) )
|
|
|
276
|
|
|
277 cmds.append(cmd)
|
|
|
278
|
|
|
279 # Run the command line for each file.
|
|
|
280 for i in range(len(cmds)):
|
|
|
281 try:
|
|
|
282 tmp_out = tempfile.NamedTemporaryFile().name
|
|
|
283 tmp_files.append(tmp_out)
|
|
|
284 tmp_stdout = open( tmp_out, 'wb' )
|
|
|
285 tmp_err = tempfile.NamedTemporaryFile().name
|
|
|
286 tmp_files.append(tmp_err)
|
|
|
287 tmp_stderr = open( tmp_err, 'wb' )
|
|
|
288 proc = subprocess.Popen( args=cmds[i], shell=True, cwd=".", stdout=tmp_stdout, stderr=tmp_stderr )
|
|
|
289 returncode = proc.wait()
|
|
|
290 tmp_stderr.close()
|
|
|
291 # get stderr, allowing for case where it's very large
|
|
|
292 tmp_stderr = open( tmp_err, 'rb' )
|
|
|
293 stderr = ''
|
|
|
294 buffsize = 1048576
|
|
|
295 try:
|
|
|
296 while True:
|
|
|
297 stderr += tmp_stderr.read( buffsize )
|
|
|
298 if not stderr or len( stderr ) % buffsize != 0:
|
|
|
299 break
|
|
|
300 except OverflowError:
|
|
|
301 pass
|
|
|
302 tmp_stdout.close()
|
|
|
303 tmp_stderr.close()
|
|
|
304 if returncode != 0:
|
|
|
305 raise Exception, stderr
|
|
|
306
|
|
|
307 # Copy output files from tmp directory to specified files.
|
|
|
308 #shutil.copyfile( os.path.join( "tophat_out", "junctions.bed" ), junctions_outputNames[i] )
|
|
|
309 shutil.copyfile( os.path.join( "tophat_out", "accepted_hits.bam" ), accepted_hits_outputNames[i] )
|
|
|
310 # TODO: look for errors in program output.
|
|
|
311 except Exception, e:
|
|
|
312 stop_err( 'Error in tophat:\n' + str( e ) )
|
|
|
313
|
|
|
314 if options.outputTar != None:
|
|
|
315 toTar(options.outputTar, accepted_hits_outputNames)
|
|
|
316
|
|
|
317
|
|
|
318 # Clean up temp dirs
|
|
|
319 for tmp_index_dir in tmp_index_dirs:
|
|
|
320 if os.path.exists( tmp_index_dir ):
|
|
|
321 shutil.rmtree( tmp_index_dir )
|
|
|
322
|
|
|
323 for tmp in tmp_files:
|
|
|
324 os.remove(tmp)
|
|
|
325
|
|
|
326
|
|
|
327 if __name__=="__main__": __main__()
|
