comparison cufflinks_wrapper.py @ 5:261425bba55d draft

corrected syntax error in wrapper.py

4:03fdfb596475

    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%.' )
    parser.add_option( '-p', '--num-threads', dest='num_threads', help='Use this many threads to align reads. The default is 1.' )
    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.' )
    parser.add_option ("--compatible-hits-norm",dest='compatible_hits_norm',help='Count hits compatible with reference RNAs only')
    parser.add_option( '-g', '--GTF-guide', dest='GTFguide', help='use reference transcript annotation to guide assembly' )
    parser.add_option("--3-overhang-tolerance",dest='3_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.')
    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.')
    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.')
    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')
    
    # Normalization options.

    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 \
                                                                                read or another transcript is mappable to/compatible with it. The default is 8 bp based on the default bowtie/TopHat parameters.' )
    parser.add_option( '--max-bundle-length', dest='max_bundle_length', help='Maximum genomic length of a given bundle" help="Default: 3,500,000bp' )
    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' )
    parser.add_option( '--min-intron-length', dest='min_intron_length', help='Minimal allowed intron size. Default: 50' )
    parser.add_option( '--trim-3-avgcov-thresh', dest='trim_3_avgcov_thresh', help='Minimum average coverage required to attempt 3prime trimming. Default: 10' )
    parser.add_option( '--trim-3-dropoff-frac', dest='trim_3_dropoff_frac', help='The fraction of average coverage below which to trim the 3prime end of an assembled transcript. Default: 0.1' )


    # Bias correction options.
    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.')
    parser.add_option( '', '--index', dest='index', help='The path of the reference genome' )

        cmd += ( " -G %s" % options.GTF )
    if options.compatible_hits_norm:
	cmd += ( " --compatible-hits-norm" )
    if options.GTFguide:
        cmd += ( " -g %s" % options.GTFguide )
	cmd += ( " --3-overhang-tolerance %i" % int ( options.3_overhang_tolerance ) )
	cmd += ( " --intron-overhang-tolerance %i" % int ( options.intron_overhang_tolerance ) )
    if options.no_faux_reads:
	cmd += ( " --no-faux-reads" )
    if options.multi_read_correct:
        cmd += ( " -u" )

	cmd += ( " --max-bundle-length %i" % int ( options.max_bundle_length ) ) 
    if options.max_bundle_frags:
	cmd += ( " --max-bundle-frags %i" % int ( options.max_bundle_frags ) )
    if options.min_intron_length:
	cmd += ( " --min-intron-length %i" % int ( options.min_intron_length ) )
    if options.trim_3_avgcov_thresh:
	cmd += ( " --trim-3-avgcov-thresh %i" % int ( options.trim_3_avgcov_thresh ) ) 
    if options.trim_3_dropoff_frac:
	cmd += ( " --trim-3-dropoff-frac %f" % float ( options.trim_3_dropoff_frac ) ) 

    if options.do_bias_correction:
        cmd += ( " -b %s" % seq_path )
    if options.no_effective_length_correction:
        cmd += ( " --no-effective-length-correction" )

5:261425bba55d

    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%.' )
    parser.add_option( '-p', '--num-threads', dest='num_threads', help='Use this many threads to align reads. The default is 1.' )
    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.' )
    parser.add_option ("--compatible-hits-norm",dest='compatible_hits_norm',help='Count hits compatible with reference RNAs only')
    parser.add_option( '-g', '--GTF-guide', dest='GTFguide', help='use reference transcript annotation to guide assembly' )
    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.')
    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.')
    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.')
    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')
    
    # Normalization options.

    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 \
                                                                                read or another transcript is mappable to/compatible with it. The default is 8 bp based on the default bowtie/TopHat parameters.' )
    parser.add_option( '--max-bundle-length', dest='max_bundle_length', help='Maximum genomic length of a given bundle" help="Default: 3,500,000bp' )
    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' )
    parser.add_option( '--min-intron-length', dest='min_intron_length', help='Minimal allowed intron size. Default: 50' )
    parser.add_option( '--trim-3-avgcov-thresh', dest='trim_three_avgcov_thresh', help='Minimum average coverage required to attempt 3prime trimming. Default: 10' )
    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' )


    # Bias correction options.
    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.')
    parser.add_option( '', '--index', dest='index', help='The path of the reference genome' )

        cmd += ( " -G %s" % options.GTF )
    if options.compatible_hits_norm:
	cmd += ( " --compatible-hits-norm" )
    if options.GTFguide:
        cmd += ( " -g %s" % options.GTFguide )
	cmd += ( " --3-overhang-tolerance %i" % int ( options.three_overhang_tolerance ) )
	cmd += ( " --intron-overhang-tolerance %i" % int ( options.intron_overhang_tolerance ) )
    if options.no_faux_reads:
	cmd += ( " --no-faux-reads" )
    if options.multi_read_correct:
        cmd += ( " -u" )

	cmd += ( " --max-bundle-length %i" % int ( options.max_bundle_length ) ) 
    if options.max_bundle_frags:
	cmd += ( " --max-bundle-frags %i" % int ( options.max_bundle_frags ) )
    if options.min_intron_length:
	cmd += ( " --min-intron-length %i" % int ( options.min_intron_length ) )
    if options.trim_three_avgcov_thresh:
	cmd += ( " --trim-3-avgcov-thresh %i" % int ( options.trim_three_avgcov_thresh ) ) 
    if options.trim_three_dropoff_frac:
	cmd += ( " --trim-3-dropoff-frac %f" % float ( options.trim_three_dropoff_frac ) ) 

    if options.do_bias_correction:
        cmd += ( " -b %s" % seq_path )
    if options.no_effective_length_correction:
        cmd += ( " --no-effective-length-correction" )