Mercurial > repos > devteam > cufflinks

comparison cufflinks_wrapper.py @ 10:83bec71c5c9f draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tool_collections/cufflinks/cufflinks commit eb18f691975ef9539b5ebd4f118343c8ad967a1f
author devteam
date Tue, 07 Feb 2017 18:39:22 -0500
parents a1ea9af8d5f4
children e04dbae2abe0
comparison
equal deleted inserted replaced
9:a1ea9af8d5f4 10:83bec71c5c9f
4 import os 4 import os
5 import shutil 5 import shutil
6 import subprocess 6 import subprocess
7 import sys 7 import sys
8 import tempfile 8 import tempfile
9 from galaxy.datatypes.util.gff_util import parse_gff_attributes, gff_attributes_to_str 9
10 10 from galaxy.datatypes.util.gff_util import gff_attributes_to_str, parse_gff_attributes
11 11
12 def stop_err( msg ): 12
13 sys.exit( "%s\n" % msg ) 13 def stop_err(msg):
14 sys.exit("%s\n" % msg)
14 15
15 16
16 def __main__(): 17 def __main__():
17 #Parse Command Line
18 parser = optparse.OptionParser() 18 parser = optparse.OptionParser()
19 parser.add_option( '-1', '--input', dest='input', help=' file of RNA-Seq read alignments in the SAM format. SAM is a standard short read alignment, that allows aligners to attach custom tags to individual alignments, and Cufflinks requires that the alignments you supply have some of these tags. Please see Input formats for more details.' ) 19 parser.add_option('-1', '--input', dest='input', help=' file of RNA-Seq read alignments in the SAM format. SAM is a standard short read alignment, that allows aligners to attach custom tags to individual alignments, and Cufflinks requires that the alignments you supply have some of these tags. Please see Input formats for more details.')
20 parser.add_option( '-I', '--max-intron-length', dest='max_intron_len', help='The minimum intron length. Cufflinks will not report transcripts with introns longer than this, and will ignore SAM alignments with REF_SKIP CIGAR operations longer than this. The default is 300,000.' ) 20 parser.add_option('-I', '--max-intron-length', dest='max_intron_len', help='The minimum intron length. Cufflinks will not report transcripts with introns longer than this, and will ignore SAM alignments with REF_SKIP CIGAR operations longer than this. The default is 300,000.')
21 parser.add_option( '-F', '--min-isoform-fraction', dest='min_isoform_fraction', help='After calculating isoform abundance for a gene, Cufflinks filters out transcripts that it believes are very low abundance, because isoforms expressed at extremely low levels often cannot reliably be assembled, and may even be artifacts of incompletely spliced precursors of processed transcripts. This parameter is also used to filter out introns that have far fewer spliced alignments supporting them. The default is 0.05, or 5% of the most abundant isoform (the major isoform) of the gene.' ) 21 parser.add_option('-F', '--min-isoform-fraction', dest='min_isoform_fraction', help='After calculating isoform abundance for a gene, Cufflinks filters out transcripts that it believes are very low abundance, because isoforms expressed at extremely low levels often cannot reliably be assembled, and may even be artifacts of incompletely spliced precursors of processed transcripts. This parameter is also used to filter out introns that have far fewer spliced alignments supporting them. The default is 0.05, or 5% of the most abundant isoform (the major isoform) of the gene.')
22 parser.add_option( '-j', '--pre-mrna-fraction', dest='pre_mrna_fraction', help='Some RNA-Seq protocols produce a significant amount of reads that originate from incompletely spliced transcripts, and these reads can confound the assembly of fully spliced mRNAs. Cufflinks uses this parameter to filter out alignments that lie within the intronic intervals implied by the spliced alignments. The minimum depth of coverage in the intronic region covered by the alignment is divided by the number of spliced reads, and if the result is lower than this parameter value, the intronic alignments are ignored. The default is 5%.' ) 22 parser.add_option('-j', '--pre-mrna-fraction', dest='pre_mrna_fraction', help='Some RNA-Seq protocols produce a significant amount of reads that originate from incompletely spliced transcripts, and these reads can confound the assembly of fully spliced mRNAs. Cufflinks uses this parameter to filter out alignments that lie within the intronic intervals implied by the spliced alignments. The minimum depth of coverage in the intronic region covered by the alignment is divided by the number of spliced reads, and if the result is lower than this parameter value, the intronic alignments are ignored. The default is 5%.')
23 parser.add_option( '-p', '--num-threads', dest='num_threads', help='Use this many threads to align reads. The default is 1.' ) 23 parser.add_option('-p', '--num-threads', dest='num_threads', help='Use this many threads to align reads. The default is 1.')
24 parser.add_option( '-G', '--GTF', dest='GTF', help='Tells Cufflinks to use the supplied reference annotation to estimate isoform expression. It will not assemble novel transcripts, and the program will ignore alignments not structurally compatible with any reference transcript.' ) 24 parser.add_option('-G', '--GTF', dest='GTF', help='Tells Cufflinks to use the supplied reference annotation to estimate isoform expression. It will not assemble novel transcripts, and the program will ignore alignments not structurally compatible with any reference transcript.')
25 parser.add_option("--compatible-hits-norm", dest='compatible_hits_norm', action="store_true", help='Count hits compatible with reference RNAs only') 25 parser.add_option("--compatible-hits-norm", dest='compatible_hits_norm', action="store_true", help='Count hits compatible with reference RNAs only')
26 parser.add_option( '-g', '--GTF-guide', dest='GTFguide', help='use reference transcript annotation to guide assembly' ) 26 parser.add_option('-g', '--GTF-guide', dest='GTFguide', help='use reference transcript annotation to guide assembly')
27 parser.add_option("--3-overhang-tolerance", dest='three_overhang_tolerance', help='The number of bp allowed to overhang the 3prime end of a reference transcript when determining if an assembled transcript should be merged with it (ie, the assembled transcript is not novel). The default is 600 bp.') 27 parser.add_option("--3-overhang-tolerance", dest='three_overhang_tolerance', help='The number of bp allowed to overhang the 3prime end of a reference transcript when determining if an assembled transcript should be merged with it (ie, the assembled transcript is not novel). The default is 600 bp.')
28 parser.add_option("--intron-overhang-tolerance", dest='intron_overhang_tolerance', help='The number of bp allowed to enter the intron of a reference transcript when determining if an assembled transcript should be merged with it (ie, the assembled transcript is not novel). The default is 50 bp.') 28 parser.add_option("--intron-overhang-tolerance", dest='intron_overhang_tolerance', help='The number of bp allowed to enter the intron of a reference transcript when determining if an assembled transcript should be merged with it (ie, the assembled transcript is not novel). The default is 50 bp.')
29 parser.add_option("--no-faux-reads", dest='no_faux_reads', help='This option disables tiling of the reference transcripts with faux reads. Use this if you only want to use sequencing reads in assembly but do not want to output assembled transcripts that lay within reference transcripts. All reference transcripts in the input annotation will also be included in the output.') 29 parser.add_option("--no-faux-reads", dest='no_faux_reads', help='This option disables tiling of the reference transcripts with faux reads. Use this if you only want to use sequencing reads in assembly but do not want to output assembled transcripts that lay within reference transcripts. All reference transcripts in the input annotation will also be included in the output.')
30 parser.add_option( '-u', '--multi-read-correct', dest='multi_read_correct', action="store_true", help='Tells Cufflinks to do an initial estimation procedure to more accurately weight reads mapping to multiple locations in the genome') 30 parser.add_option('-u', '--multi-read-correct', dest='multi_read_correct', action="store_true", help='Tells Cufflinks to do an initial estimation procedure to more accurately weight reads mapping to multiple locations in the genome')
31 31
32 # Normalization options. 32 # Normalization options.
33 parser.add_option( "--no-effective-length-correction", dest="no_effective_length_correction", action="store_true" ) 33 parser.add_option("--no-effective-length-correction", dest="no_effective_length_correction", action="store_true")
34 parser.add_option( "--no-length-correction", dest="no_length_correction", action="store_true" ) 34 parser.add_option("--no-length-correction", dest="no_length_correction", action="store_true")
35 35
36 # Wrapper / Galaxy options. 36 # Wrapper / Galaxy options.
37 parser.add_option( '-A', '--assembled-isoforms-output', dest='assembled_isoforms_output_file', help='Assembled isoforms output file; formate is GTF.' ) 37 parser.add_option('-A', '--assembled-isoforms-output', dest='assembled_isoforms_output_file', help='Assembled isoforms output file; formate is GTF.')
38 38
39 # Advanced Options: 39 # Advanced Options:
40 parser.add_option( "--library-type", dest="library_type", help=' library prep used for input reads, default fr-unstranded') 40 parser.add_option("--library-type", dest="library_type", help=' library prep used for input reads, default fr-unstranded')
41 parser.add_option( '-M', '--mask-file', dest='mask_file', help='Tells Cufflinks to ignore all reads that could have come from transcripts in this GTF file. \ 41 parser.add_option('-M', '--mask-file', dest='mask_file', help='Tells Cufflinks to ignore all reads that could have come from transcripts in this GTF file. \
42 We recommend including any annotated rRNA, mitochondrial transcripts other abundant transcripts \ 42 We recommend including any annotated rRNA, mitochondrial transcripts other abundant transcripts \
43 you wish to ignore in your analysis in this file. Due to variable efficiency of mRNA enrichment \ 43 you wish to ignore in your analysis in this file. Due to variable efficiency of mRNA enrichment \
44 methods and rRNA depletion kits, masking these transcripts often improves the overall robustness \ 44 methods and rRNA depletion kits, masking these transcripts often improves the overall robustness \
45 of transcript abundance estimates.') 45 of transcript abundance estimates.')
46 parser.add_option( '-m', '--inner-mean-dist', dest='inner_mean_dist', help='This is the expected (mean) inner distance between mate pairs. \ 46 parser.add_option('-m', '--inner-mean-dist', dest='inner_mean_dist', help='This is the expected (mean) inner distance between mate pairs. \
47 For, example, for paired end runs with fragments selected at 300bp, \ 47 For, example, for paired end runs with fragments selected at 300bp, \
48 where each end is 50bp, you should set -r to be 200. The default is 45bp.') # cufflinks: --frag-len-mean 48 where each end is 50bp, you should set -r to be 200. The default is 45bp.') # cufflinks: --frag-len-mean
49 49
50 parser.add_option( '-s', '--inner-dist-std-dev', dest='inner_dist_std_dev', help='The standard deviation for the distribution on inner distances between mate pairs. The default is 20bp.' ) # cufflinks: --frag-len-std-dev 50 parser.add_option('-s', '--inner-dist-std-dev', dest='inner_dist_std_dev', help='The standard deviation for the distribution on inner distances between mate pairs. The default is 20bp.') # cufflinks: --frag-len-std-dev
51 parser.add_option( '--max-mle-iterations', dest='max_mle_iterations', help='Sets the number of iterations allowed during maximum likelihood estimation of abundances. Default: 5000' ) 51 parser.add_option('--max-mle-iterations', dest='max_mle_iterations', help='Sets the number of iterations allowed during maximum likelihood estimation of abundances. Default: 5000')
52 parser.add_option( '--junc-alpha', dest='junc_alpha', help='Alpha value for the binomial test used during false positive spliced alignment filtration. Default: 0.001' ) 52 parser.add_option('--junc-alpha', dest='junc_alpha', help='Alpha value for the binomial test used during false positive spliced alignment filtration. Default: 0.001')
53 parser.add_option( '--small-anchor-fraction', dest='small_anchor_fraction', help='Spliced reads with less than this percent of their length on each side of\ 53 parser.add_option('--small-anchor-fraction', dest='small_anchor_fraction', help='Spliced reads with less than this percent of their length on each side of\
54 the junction are considered suspicious and are candidates for filtering prior to assembly. Default: 0.09.' ) 54 the junction are considered suspicious and are candidates for filtering prior to assembly. Default: 0.09.')
55 parser.add_option( '--overhang-tolerance', dest='overhang_tolerance', help='The number of bp allowed to enter the intron of a transcript when determining if a \ 55 parser.add_option('--overhang-tolerance', dest='overhang_tolerance', help='The number of bp allowed to enter the intron of a transcript when determining if a \
56 read or another transcript is mappable to/compatible with it. The default is 8 bp based on the default bowtie/TopHat parameters.' ) 56 read or another transcript is mappable to/compatible with it. The default is 8 bp based on the default bowtie/TopHat parameters.')
57 parser.add_option( '--max-bundle-length', dest='max_bundle_length', help='Maximum genomic length of a given bundle" help="Default: 3,500,000bp' ) 57 parser.add_option('--max-bundle-length', dest='max_bundle_length', help='Maximum genomic length of a given bundle" help="Default: 3,500,000bp')
58 parser.add_option( '--max-bundle-frags', dest='max_bundle_frags', help='Sets the maximum number of fragments a locus may have before being skipped. Skipped loci are listed in skipped.gtf. Default: 1,000,000' ) 58 parser.add_option('--max-bundle-frags', dest='max_bundle_frags', help='Sets the maximum number of fragments a locus may have before being skipped. Skipped loci are listed in skipped.gtf. Default: 1,000,000')
59 parser.add_option( '--min-intron-length', dest='min_intron_length', help='Minimal allowed intron size. Default: 50' ) 59 parser.add_option('--min-intron-length', dest='min_intron_length', help='Minimal allowed intron size. Default: 50')
60 parser.add_option( '--trim-3-avgcov-thresh', dest='trim_three_avgcov_thresh', help='Minimum average coverage required to attempt 3prime trimming. Default: 10' ) 60 parser.add_option('--trim-3-avgcov-thresh', dest='trim_three_avgcov_thresh', help='Minimum average coverage required to attempt 3prime trimming. Default: 10')
61 parser.add_option( '--trim-3-dropoff-frac', dest='trim_three_dropoff_frac', help='The fraction of average coverage below which to trim the 3prime end of an assembled transcript. Default: 0.1' ) 61 parser.add_option('--trim-3-dropoff-frac', dest='trim_three_dropoff_frac', help='The fraction of average coverage below which to trim the 3prime end of an assembled transcript. Default: 0.1')
62 62
63 # Bias correction options. 63 # Bias correction options.
64 parser.add_option( '-b', dest='do_bias_correction', action="store_true", help='Providing Cufflinks with a multifasta file via this option instructs it to run our new bias detection and correction algorithm which can significantly improve accuracy of transcript abundance estimates.') 64 parser.add_option('-b', dest='do_bias_correction', action="store_true", help='Providing Cufflinks with a multifasta file via this option instructs it to run our new bias detection and correction algorithm which can significantly improve accuracy of transcript abundance estimates.')
65 parser.add_option( '', '--index', dest='index', help='The path of the reference genome' ) 65 parser.add_option('', '--index', dest='index', help='The path of the reference genome')
66 parser.add_option( '', '--ref_file', dest='ref_file', help='The reference dataset from the history' ) 66 parser.add_option('', '--ref_file', dest='ref_file', help='The reference dataset from the history')
67 67
68 # Global model (for trackster). 68 # Global model (for trackster).
69 parser.add_option( '', '--global_model', dest='global_model_file', help='Global model used for computing on local data' ) 69 parser.add_option('', '--global_model', dest='global_model_file', help='Global model used for computing on local data')
70 70
71 (options, args) = parser.parse_args() 71 (options, args) = parser.parse_args()
72 72
73 # output version # of tool 73 # output version # of tool
74 try: 74 try:
75 tmp = tempfile.NamedTemporaryFile().name 75 with tempfile.NamedTemporaryFile() as tmp_stdout:
76 tmp_stdout = open( tmp, 'wb' ) 76 returncode = subprocess.call(args='cufflinks --no-update-check 2>&1', stdout=tmp_stdout, shell=True)
77 proc = subprocess.Popen( args='cufflinks --no-update-check 2>&1', shell=True, stdout=tmp_stdout ) 77 stdout = None
78 tmp_stdout.close() 78 with open(tmp_stdout.name) as tmp_stdout2:
79 returncode = proc.wait() 79 for line in tmp_stdout2:
80 stdout = None 80 if line.lower().find('cufflinks v') >= 0:
81 for line in open( tmp_stdout.name, 'rb' ): 81 stdout = line.strip()
82 if line.lower().find( 'cufflinks v' ) >= 0: 82 break
83 stdout = line.strip()
84 break
85 if stdout: 83 if stdout:
86 sys.stdout.write( '%s\n' % stdout ) 84 sys.stdout.write('%s\n' % stdout)
87 else: 85 else:
88 raise Exception 86 raise Exception
89 except: 87 except:
90 sys.stdout.write( 'Could not determine Cufflinks version\n' ) 88 sys.stdout.write('Could not determine Cufflinks version\n')
91 89
92 # If doing bias correction, set/link to sequence file. 90 # If doing bias correction, set/link to sequence file.
93 if options.do_bias_correction: 91 if options.do_bias_correction:
94 if options.ref_file: 92 if options.ref_file:
95 # Sequence data from history. 93 # Sequence data from history.
96 # Create symbolic link to ref_file so that index will be created in working directory. 94 # Create symbolic link to ref_file so that index will be created in working directory.
97 seq_path = "ref.fa" 95 seq_path = "ref.fa"
98 os.symlink( options.ref_file, seq_path ) 96 os.symlink(options.ref_file, seq_path)
99 else: 97 else:
100 if not os.path.exists( options.index ): 98 if not os.path.exists(options.index):
101 stop_err( 'Reference genome %s not present, request it by reporting this error.' % options.index ) 99 stop_err('Reference genome %s not present, request it by reporting this error.' % options.index)
102 seq_path = options.index 100 seq_path = options.index
103 101
104 # Build command. 102 # Build command.
105 103
106 # Base; always use quiet mode to avoid problems with storing log output. 104 # Base; always use quiet mode to avoid problems with storing log output.
107 cmd = "cufflinks -q --no-update-check" 105 cmd = "cufflinks -q --no-update-check"
108 106
109 # Add options. 107 # Add options.
110 if options.max_intron_len: 108 if options.max_intron_len:
111 cmd += ( " -I %i" % int( options.max_intron_len ) ) 109 cmd += (" -I %i" % int(options.max_intron_len))
112 if options.min_isoform_fraction: 110 if options.min_isoform_fraction:
113 cmd += ( " -F %f" % float( options.min_isoform_fraction ) ) 111 cmd += (" -F %f" % float(options.min_isoform_fraction))
114 if options.pre_mrna_fraction: 112 if options.pre_mrna_fraction:
115 cmd += ( " -j %f" % float( options.pre_mrna_fraction ) ) 113 cmd += (" -j %f" % float(options.pre_mrna_fraction))
116 if options.num_threads: 114 if options.num_threads:
117 cmd += ( " -p %i" % int( options.num_threads ) ) 115 cmd += (" -p %i" % int(options.num_threads))
118 if options.GTF: 116 if options.GTF:
119 cmd += ( " -G %s" % options.GTF ) 117 cmd += (" -G %s" % options.GTF)
120 if options.compatible_hits_norm: 118 if options.compatible_hits_norm:
121 cmd += ( " --compatible-hits-norm" ) 119 cmd += (" --compatible-hits-norm")
122 if options.GTFguide: 120 if options.GTFguide:
123 cmd += ( " -g %s" % options.GTFguide ) 121 cmd += (" -g %s" % options.GTFguide)
124 cmd += ( " --3-overhang-tolerance %i" % int( options.three_overhang_tolerance ) ) 122 cmd += (" --3-overhang-tolerance %i" % int(options.three_overhang_tolerance))
125 cmd += ( " --intron-overhang-tolerance %i" % int( options.intron_overhang_tolerance ) ) 123 cmd += (" --intron-overhang-tolerance %i" % int(options.intron_overhang_tolerance))
126 if options.no_faux_reads: 124 if options.no_faux_reads:
127 cmd += ( " --no-faux-reads" ) 125 cmd += (" --no-faux-reads")
128 if options.multi_read_correct: 126 if options.multi_read_correct:
129 cmd += ( " -u" ) 127 cmd += (" -u")
130 128
131 if options.library_type and options.library_type != 'auto': 129 if options.library_type and options.library_type != 'auto':
132 cmd += ( " --library-type %s" % options.library_type) 130 cmd += (" --library-type %s" % options.library_type)
133 if options.mask_file: 131 if options.mask_file:
134 cmd += ( " --mask-file %s" % options.mask_file ) 132 cmd += (" --mask-file %s" % options.mask_file)
135 if options.inner_mean_dist: 133 if options.inner_mean_dist:
136 cmd += ( " -m %i" % int( options.inner_mean_dist ) ) 134 cmd += (" -m %i" % int(options.inner_mean_dist))
137 if options.inner_dist_std_dev: 135 if options.inner_dist_std_dev:
138 cmd += ( " -s %i" % int( options.inner_dist_std_dev ) ) 136 cmd += (" -s %i" % int(options.inner_dist_std_dev))
139 if options.max_mle_iterations: 137 if options.max_mle_iterations:
140 cmd += ( " --max-mle-iterations %i" % int( options.max_mle_iterations ) ) 138 cmd += (" --max-mle-iterations %i" % int(options.max_mle_iterations))
141 if options.junc_alpha: 139 if options.junc_alpha:
142 cmd += ( " --junc-alpha %f" % float( options.junc_alpha) ) 140 cmd += (" --junc-alpha %f" % float(options.junc_alpha))
143 if options.small_anchor_fraction: 141 if options.small_anchor_fraction:
144 cmd += ( " --small-anchor-fraction %f" % float(options.small_anchor_fraction ) ) 142 cmd += (" --small-anchor-fraction %f" % float(options.small_anchor_fraction))
145 if options.overhang_tolerance: 143 if options.overhang_tolerance:
146 cmd += ( " --overhang-tolerance %i" % int( options.overhang_tolerance ) ) 144 cmd += (" --overhang-tolerance %i" % int(options.overhang_tolerance))
147 if options.max_bundle_length: 145 if options.max_bundle_length:
148 cmd += ( " --max-bundle-length %i" % int( options.max_bundle_length ) ) 146 cmd += (" --max-bundle-length %i" % int(options.max_bundle_length))
149 if options.max_bundle_frags: 147 if options.max_bundle_frags:
150 cmd += ( " --max-bundle-frags %i" % int( options.max_bundle_frags ) ) 148 cmd += (" --max-bundle-frags %i" % int(options.max_bundle_frags))
151 if options.min_intron_length: 149 if options.min_intron_length:
152 cmd += ( " --min-intron-length %i" % int( options.min_intron_length ) ) 150 cmd += (" --min-intron-length %i" % int(options.min_intron_length))
153 if options.trim_three_avgcov_thresh: 151 if options.trim_three_avgcov_thresh:
154 cmd += ( " --trim-3-avgcov-thresh %i" % int( options.trim_three_avgcov_thresh ) ) 152 cmd += (" --trim-3-avgcov-thresh %i" % int(options.trim_three_avgcov_thresh))
155 if options.trim_three_dropoff_frac: 153 if options.trim_three_dropoff_frac:
156 cmd += ( " --trim-3-dropoff-frac %f" % float( options.trim_three_dropoff_frac ) ) 154 cmd += (" --trim-3-dropoff-frac %f" % float(options.trim_three_dropoff_frac))
157 155
158 if options.do_bias_correction: 156 if options.do_bias_correction:
159 cmd += ( " -b %s" % seq_path ) 157 cmd += (" -b %s" % seq_path)
160 if options.no_effective_length_correction: 158 if options.no_effective_length_correction:
161 cmd += ( " --no-effective-length-correction" ) 159 cmd += (" --no-effective-length-correction")
162 if options.no_length_correction: 160 if options.no_length_correction:
163 cmd += ( " --no-length-correction" ) 161 cmd += (" --no-length-correction")
164 162
165 # Add input files. 163 # Add input files.
166 cmd += " " + options.input 164 cmd += " " + options.input
167 165
168 # Debugging.
169 print cmd
170
171 #
172 # Run command and handle output. 166 # Run command and handle output.
173 #
174 try: 167 try:
175 #
176 # Run command. 168 # Run command.
177 # 169 with tempfile.NamedTemporaryFile(dir=".") as tmp_stderr:
178 tmp_name = tempfile.NamedTemporaryFile( dir="." ).name 170 returncode = subprocess.call(args=cmd, stderr=tmp_stderr, shell=True)
179 tmp_stderr = open( tmp_name, 'wb' ) 171
180 proc = subprocess.Popen( args=cmd, shell=True, stderr=tmp_stderr.fileno() ) 172 # Error checking.
181 returncode = proc.wait() 173 if returncode != 0:
182 tmp_stderr.close() 174 # Get stderr, allowing for case where it's very large.
183 175 buffsize = 1048576
184 # Error checking. 176 stderr = ''
185 if returncode != 0: 177 with open(tmp_stderr.name) as tmp_stderr2:
186 raise Exception("return code = %i" % returncode) 178 try:
187 179 while True:
188 # 180 stderr += tmp_stderr2.read(buffsize)
189 # Handle output. 181 if not stderr or len(stderr) % buffsize != 0:
190 # 182 break
191 183 except OverflowError:
192 # Read standard error to get total map/upper quartile mass. 184 pass
193 total_map_mass = -1 185 raise Exception(stderr)
194 tmp_stderr = open( tmp_name, 'r' ) 186
195 for line in tmp_stderr: 187 # Read standard error to get total map/upper quartile mass.
196 if line.lower().find( "map mass" ) >= 0 or line.lower().find( "upper quartile" ) >= 0: 188 total_map_mass = -1
197 total_map_mass = float( line.split(":")[1].strip() ) 189 with open(tmp_stderr.name, 'r') as tmp_stderr2:
198 break 190 for line in tmp_stderr2:
199 tmp_stderr.close() 191 if line.lower().find("map mass") >= 0 or line.lower().find("upper quartile") >= 0:
200 192 total_map_mass = float(line.split(":")[1].strip())
201 # 193 break
194
202 # If there's a global model provided, use model's total map mass 195 # If there's a global model provided, use model's total map mass
203 # to adjust FPKM + confidence intervals. 196 # to adjust FPKM + confidence intervals.
204 #
205 if options.global_model_file: 197 if options.global_model_file:
206 # Global model is simply total map mass from original run. 198 # Global model is simply total map mass from original run.
207 global_model_file = open( options.global_model_file, 'r' ) 199 with open(options.global_model_file, 'r') as global_model_file:
208 global_model_total_map_mass = float( global_model_file.readline() ) 200 global_model_total_map_mass = float(global_model_file.readline())
209 global_model_file.close()
210 201
211 # Ratio of global model's total map mass to original run's map mass is 202 # Ratio of global model's total map mass to original run's map mass is
212 # factor used to adjust FPKM. 203 # factor used to adjust FPKM.
213 fpkm_map_mass_ratio = total_map_mass / global_model_total_map_mass 204 fpkm_map_mass_ratio = total_map_mass / global_model_total_map_mass
214 205
215 # Update FPKM values in transcripts.gtf file. 206 # Update FPKM values in transcripts.gtf file.
216 transcripts_file = open( "transcripts.gtf", 'r' ) 207 with open("transcripts.gtf", 'r') as transcripts_file:
217 tmp_transcripts = tempfile.NamedTemporaryFile( dir="." ).name 208 with tempfile.NamedTemporaryFile(dir=".", delete=False) as new_transcripts_file:
218 new_transcripts_file = open( tmp_transcripts, 'w' ) 209 for line in transcripts_file:
219 for line in transcripts_file: 210 fields = line.split('\t')
220 fields = line.split( '\t' ) 211 attrs = parse_gff_attributes(fields[8])
221 attrs = parse_gff_attributes( fields[8] ) 212 attrs["FPKM"] = str(float(attrs["FPKM"]) * fpkm_map_mass_ratio)
222 attrs[ "FPKM" ] = str( float( attrs[ "FPKM" ] ) * fpkm_map_mass_ratio ) 213 attrs["conf_lo"] = str(float(attrs["conf_lo"]) * fpkm_map_mass_ratio)
223 attrs[ "conf_lo" ] = str( float( attrs[ "conf_lo" ] ) * fpkm_map_mass_ratio ) 214 attrs["conf_hi"] = str(float(attrs["conf_hi"]) * fpkm_map_mass_ratio)
224 attrs[ "conf_hi" ] = str( float( attrs[ "conf_hi" ] ) * fpkm_map_mass_ratio ) 215 fields[8] = gff_attributes_to_str(attrs, "GTF")
225 fields[8] = gff_attributes_to_str( attrs, "GTF" ) 216 new_transcripts_file.write("%s\n" % '\t'.join(fields))
226 new_transcripts_file.write( "%s\n" % '\t'.join( fields ) ) 217 shutil.move(new_transcripts_file.name, "transcripts.gtf")
227 transcripts_file.close()
228 new_transcripts_file.close()
229 shutil.copyfile( tmp_transcripts, "transcripts.gtf" )
230 218
231 # TODO: update expression files as well. 219 # TODO: update expression files as well.
232 220
233 # Set outputs. Transcript and gene expression handled by wrapper directives. 221 # Set outputs. Transcript and gene expression handled by wrapper directives.
234 shutil.copyfile( "transcripts.gtf", options.assembled_isoforms_output_file ) 222 shutil.move("transcripts.gtf", options.assembled_isoforms_output_file)
235 if total_map_mass > -1: 223 if total_map_mass > -1:
236 f = open( "global_model.txt", 'w' ) 224 with open("global_model.txt", 'w') as f:
237 f.write( "%f\n" % total_map_mass ) 225 f.write("%f\n" % total_map_mass)
238 f.close() 226 except Exception as e:
239 except Exception, e: 227 stop_err('Error running cufflinks: %s' % e)
240 # Read stderr so that it can be reported: 228
241 tmp_stderr = open( tmp_name, 'rb' )
242 stderr = ''
243 buffsize = 1048576
244 try:
245 while True:
246 stderr += tmp_stderr.read( buffsize )
247 if not stderr or len( stderr ) % buffsize != 0:
248 break
249 except OverflowError:
250 pass
251 tmp_stderr.close()
252 stop_err( 'Error running cufflinks.\n%s\n%s' % ( str( e ), stderr ) )
253 229
254 if __name__ == "__main__": 230 if __name__ == "__main__":
255 __main__() 231 __main__()