annotate cufflinks_wrapper.py @ 6:9aab29e159a7 draft

Convert tool to use $GALAXY_SLOTS if available.
author Nate Coraor <nate@bx.psu.edu>
date Thu, 16 Jan 2014 13:14:05 -0500
parents da11bfc10e81
children 5346d5eea8b1
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
0
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
1 #!/usr/bin/env python
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
2
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
3 # Supports Cufflinks versions 1.3 and newer.
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
4
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
5 import optparse, os, shutil, subprocess, sys, tempfile
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
6 from galaxy import eggs
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
7 from galaxy.datatypes.util.gff_util import parse_gff_attributes, gff_attributes_to_str
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
8
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
9 def stop_err( msg ):
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
10 sys.stderr.write( "%s\n" % msg )
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
11 sys.exit()
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
12
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
13 def __main__():
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
14 #Parse Command Line
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
15 parser = optparse.OptionParser()
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
16 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.' )
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
17 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.' )
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
18 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.' )
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
19 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.' )
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
20 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%.' )
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
21 parser.add_option( '-p', '--num-threads', dest='num_threads', help='Use this many threads to align reads. The default is 1.' )
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
22 parser.add_option( '-m', '--inner-mean-dist', dest='inner_mean_dist', help='This is the expected (mean) inner distance between mate pairs. \
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
23 For, example, for paired end runs with fragments selected at 300bp, \
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
24 where each end is 50bp, you should set -r to be 200. The default is 45bp.')
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
25 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.' )
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
26 parser.add_option( '-g', '--GTF-guide', dest='GTFguide', help='use reference transcript annotation to guide assembly' )
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
27 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')
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
28
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
29 # Normalization options.
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
30 parser.add_option( "-N", "--quartile-normalization", dest="do_normalization", action="store_true" )
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
31 parser.add_option( "--no-effective-length-correction", dest="no_effective_length_correction", action="store_true" )
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
32
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
33 # Wrapper / Galaxy options.
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
34 parser.add_option( '-A', '--assembled-isoforms-output', dest='assembled_isoforms_output_file', help='Assembled isoforms output file; formate is GTF.' )
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
35
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
36 # Advanced Options:
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
37 parser.add_option( '--num-importance-samples', dest='num_importance_samples', help='Sets the number of importance samples generated for each locus during abundance estimation. Default: 1000' )
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
38 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' )
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
39
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
40 # Bias correction options.
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
41 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.')
2
da11bfc10e81 Update to the new data table specification.
Dave Bouvier <dave@bx.psu.edu>
parents: 0
diff changeset
42 parser.add_option( '', '--index', dest='index', help='The path of the reference genome' )
0
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
43 parser.add_option( '', '--ref_file', dest='ref_file', help='The reference dataset from the history' )
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
44
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
45 # Global model.
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
46 parser.add_option( '', '--global_model', dest='global_model_file', help='Global model used for computing on local data' )
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
47
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
48 (options, args) = parser.parse_args()
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
49
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
50 # output version # of tool
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
51 try:
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
52 tmp = tempfile.NamedTemporaryFile().name
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
53 tmp_stdout = open( tmp, 'wb' )
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
54 proc = subprocess.Popen( args='cufflinks --no-update-check 2>&1', shell=True, stdout=tmp_stdout )
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
55 tmp_stdout.close()
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
56 returncode = proc.wait()
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
57 stdout = None
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
58 for line in open( tmp_stdout.name, 'rb' ):
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
59 if line.lower().find( 'cufflinks v' ) >= 0:
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
60 stdout = line.strip()
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
61 break
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
62 if stdout:
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
63 sys.stdout.write( '%s\n' % stdout )
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
64 else:
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
65 raise Exception
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
66 except:
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
67 sys.stdout.write( 'Could not determine Cufflinks version\n' )
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
68
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
69 # If doing bias correction, set/link to sequence file.
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
70 if options.do_bias_correction:
2
da11bfc10e81 Update to the new data table specification.
Dave Bouvier <dave@bx.psu.edu>
parents: 0
diff changeset
71 if options.ref_file:
0
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
72 # Sequence data from history.
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
73 # Create symbolic link to ref_file so that index will be created in working directory.
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
74 seq_path = "ref.fa"
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
75 os.symlink( options.ref_file, seq_path )
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
76 else:
2
da11bfc10e81 Update to the new data table specification.
Dave Bouvier <dave@bx.psu.edu>
parents: 0
diff changeset
77 if not os.path.exists( options.index ):
da11bfc10e81 Update to the new data table specification.
Dave Bouvier <dave@bx.psu.edu>
parents: 0
diff changeset
78 stop_err( 'Reference genome %s not present, request it by reporting this error.' % options.index )
da11bfc10e81 Update to the new data table specification.
Dave Bouvier <dave@bx.psu.edu>
parents: 0
diff changeset
79 seq_path = options.index
da11bfc10e81 Update to the new data table specification.
Dave Bouvier <dave@bx.psu.edu>
parents: 0
diff changeset
80
0
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
81 # Build command.
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
82
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
83 # Base; always use quiet mode to avoid problems with storing log output.
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
84 cmd = "cufflinks -q --no-update-check"
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
85
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
86 # Add options.
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
87 if options.inner_dist_std_dev:
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
88 cmd += ( " -s %i" % int ( options.inner_dist_std_dev ) )
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
89 if options.max_intron_len:
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
90 cmd += ( " -I %i" % int ( options.max_intron_len ) )
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
91 if options.min_isoform_fraction:
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
92 cmd += ( " -F %f" % float ( options.min_isoform_fraction ) )
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
93 if options.pre_mrna_fraction:
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
94 cmd += ( " -j %f" % float ( options.pre_mrna_fraction ) )
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
95 if options.num_threads:
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
96 cmd += ( " -p %i" % int ( options.num_threads ) )
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
97 if options.inner_mean_dist:
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
98 cmd += ( " -m %i" % int ( options.inner_mean_dist ) )
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
99 if options.GTF:
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
100 cmd += ( " -G %s" % options.GTF )
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
101 if options.GTFguide:
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
102 cmd += ( " -g %s" % options.GTFguide )
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
103 if options.multi_read_correct:
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
104 cmd += ( " -u" )
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
105 if options.num_importance_samples:
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
106 cmd += ( " --num-importance-samples %i" % int ( options.num_importance_samples ) )
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
107 if options.max_mle_iterations:
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
108 cmd += ( " --max-mle-iterations %i" % int ( options.max_mle_iterations ) )
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
109 if options.do_normalization:
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
110 cmd += ( " -N" )
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
111 if options.do_bias_correction:
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
112 cmd += ( " -b %s" % seq_path )
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
113 if options.no_effective_length_correction:
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
114 cmd += ( " --no-effective-length-correction" )
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
115
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
116 # Debugging.
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
117 print cmd
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
118
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
119 # Add input files.
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
120 cmd += " " + options.input
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
121
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
122 #
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
123 # Run command and handle output.
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
124 #
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
125 try:
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
126 #
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
127 # Run command.
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
128 #
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
129 tmp_name = tempfile.NamedTemporaryFile( dir="." ).name
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
130 tmp_stderr = open( tmp_name, 'wb' )
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
131 proc = subprocess.Popen( args=cmd, shell=True, stderr=tmp_stderr.fileno() )
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
132 returncode = proc.wait()
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
133 tmp_stderr.close()
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
134
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
135 # Error checking.
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
136 if returncode != 0:
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
137 raise Exception, "return code = %i" % returncode
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
138
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
139 #
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
140 # Handle output.
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
141 #
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
142
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
143 # Read standard error to get total map/upper quartile mass.
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
144 total_map_mass = -1
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
145 tmp_stderr = open( tmp_name, 'r' )
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
146 for line in tmp_stderr:
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
147 if line.lower().find( "map mass" ) >= 0 or line.lower().find( "upper quartile" ) >= 0:
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
148 total_map_mass = float( line.split(":")[1].strip() )
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
149 break
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
150 tmp_stderr.close()
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
151
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
152 #
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
153 # If there's a global model provided, use model's total map mass
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
154 # to adjust FPKM + confidence intervals.
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
155 #
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
156 if options.global_model_file:
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
157 # Global model is simply total map mass from original run.
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
158 global_model_file = open( options.global_model_file, 'r' )
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
159 global_model_total_map_mass = float( global_model_file.readline() )
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
160 global_model_file.close()
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
161
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
162 # Ratio of global model's total map mass to original run's map mass is
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
163 # factor used to adjust FPKM.
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
164 fpkm_map_mass_ratio = total_map_mass / global_model_total_map_mass
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
165
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
166 # Update FPKM values in transcripts.gtf file.
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
167 transcripts_file = open( "transcripts.gtf", 'r' )
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
168 tmp_transcripts = tempfile.NamedTemporaryFile( dir="." ).name
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
169 new_transcripts_file = open( tmp_transcripts, 'w' )
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
170 for line in transcripts_file:
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
171 fields = line.split( '\t' )
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
172 attrs = parse_gff_attributes( fields[8] )
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
173 attrs[ "FPKM" ] = str( float( attrs[ "FPKM" ] ) * fpkm_map_mass_ratio )
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
174 attrs[ "conf_lo" ] = str( float( attrs[ "conf_lo" ] ) * fpkm_map_mass_ratio )
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
175 attrs[ "conf_hi" ] = str( float( attrs[ "conf_hi" ] ) * fpkm_map_mass_ratio )
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
176 fields[8] = gff_attributes_to_str( attrs, "GTF" )
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
177 new_transcripts_file.write( "%s\n" % '\t'.join( fields ) )
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
178 transcripts_file.close()
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
179 new_transcripts_file.close()
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
180 shutil.copyfile( tmp_transcripts, "transcripts.gtf" )
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
181
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
182 # TODO: update expression files as well.
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
183
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
184 # Set outputs. Transcript and gene expression handled by wrapper directives.
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
185 shutil.copyfile( "transcripts.gtf" , options.assembled_isoforms_output_file )
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
186 if total_map_mass > -1:
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
187 f = open( "global_model.txt", 'w' )
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
188 f.write( "%f\n" % total_map_mass )
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
189 f.close()
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
190 except Exception, e:
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
191 # Read stderr so that it can be reported:
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
192 tmp_stderr = open( tmp_name, 'rb' )
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
193 stderr = ''
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
194 buffsize = 1048576
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
195 try:
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
196 while True:
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
197 stderr += tmp_stderr.read( buffsize )
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
198 if not stderr or len( stderr ) % buffsize != 0:
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
199 break
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
200 except OverflowError:
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
201 pass
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
202 tmp_stderr.close()
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
203
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
204 stop_err( 'Error running cufflinks.\n%s\n%s' % ( str( e ), stderr ) )
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
205
b50aacc8ae49 Uploaded tool tarball.
devteam
parents:
diff changeset
206 if __name__=="__main__": __main__()