comparison cuffdiff_wrapper.py @ 2:fdf01b3c1841

Update to new cuffdiff wrapper, add cuffdb_info.txt to cummerbund html output

1:ebb9a992508d

    setattr(parser.values, option.dest, labels)

def stop_err( msg ):
    sys.stderr.write( "%s\n" % msg )
    sys.exit()
    
# Copied from sam_to_bam.py:
def check_seq_file( dbkey, cached_seqs_pointer_file ):
    seq_path = ''
    for line in open( cached_seqs_pointer_file ):

                                                                                For, example, for paired end runs with fragments selected at 300bp, \
                                                                                where each end is 50bp, you should set -r to be 200. The default is 45bp.')
    parser.add_option( '-c', '--min-alignment-count', dest='min_alignment_count', help='The minimum number of alignments in a locus for needed to conduct significance testing on changes in that locus observed between samples. If no testing is performed, changes in the locus are deemed not signficant, and the locus\' observed changes don\'t contribute to correction for multiple testing. The default is 1,000 fragment alignments (up to 2,000 paired reads).' )
    parser.add_option( '--FDR', dest='FDR', help='The allowed false discovery rate. The default is 0.05.' )
    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')

    # Advanced Options:	
    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' )
    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' )
    

    parser.add_option( "--tss_groups_read_group_tracking_output", dest="tss_groups_read_group_tracking_output", default=None )
    parser.add_option( "--isoforms_exp_output", dest="isoforms_exp_output" )
    parser.add_option( "--genes_exp_output", dest="genes_exp_output" )
    parser.add_option( "--tss_groups_exp_output", dest="tss_groups_exp_output" )
    parser.add_option( "--cds_exp_fpkm_tracking_output", dest="cds_exp_fpkm_tracking_output" )
    parser.add_option( "--isoforms_count_tracking_output", dest="isoforms_count_tracking_output" )
    parser.add_option( "--genes_count_tracking_output", dest="genes_count_tracking_output" )
    parser.add_option( "--cds_count_tracking_output", dest="cds_count_tracking_output" )
    parser.add_option( "--tss_groups_count_tracking_output", dest="tss_groups_count_tracking_output" )
    parser.add_option( "--splicing_diff_output", dest="splicing_diff_output" )
    parser.add_option( "--cds_diff_output", dest="cds_diff_output" )
    parser.add_option( "--promoters_diff_output", dest="promoters_diff_output" )
    parser.add_option( "--run_info_output", dest="run_info_output" )
    parser.add_option( "--read_groups_info_output", dest="read_groups_info_output" )
    parser.add_option( "--cuffdatadir", dest="cuffdatadir", default=None)
    parser.add_option( "--cummeRbund_db_output", dest="cummeRbund_db_output", default=None)

    tmp_output_dir = tempfile.mkdtemp()
    cuffdatadir = options.cuffdatadir if options.cuffdatadir else tmp_output_dir
    if not os.path.exists( cuffdatadir ):
        os.makedirs( cuffdatadir )
    
    
    # If doing bias correction, set/link to sequence file.
    if options.do_bias_correction:
        if options.ref_file != 'None':
            # Sequence data from history.
            # Create symbolic link to ref_file so that index will be created in working directory.

    
    # Base; always use quiet mode to avoid problems with storing log output.
    cmd = "cuffdiff --no-update-check -q"
    
    # Add options.
    if options.inner_dist_std_dev:
        cmd += ( " -s %i" % int ( options.inner_dist_std_dev ) )
    if options.num_threads:
        cmd += ( " -p %i" % int ( options.num_threads ) )
    if options.inner_mean_dist:

    # Add inputs.
    # For replicate analysis: group1_rep1,group1_rep2 groupN_rep1,groupN_rep2
    if options.groups:
        cmd += " --labels "
        for label in options.labels:
            cmd += label + ","
        cmd = cmd[:-1]

        cmd += " " + options.inputA + " "

        for group in options.groups:

2:fdf01b3c1841

    setattr(parser.values, option.dest, labels)

def stop_err( msg ):
    sys.stderr.write( "%s\n" % msg )
    sys.exit(1)
    
# Copied from sam_to_bam.py:
def check_seq_file( dbkey, cached_seqs_pointer_file ):
    seq_path = ''
    for line in open( cached_seqs_pointer_file ):

                                                                                For, example, for paired end runs with fragments selected at 300bp, \
                                                                                where each end is 50bp, you should set -r to be 200. The default is 45bp.')
    parser.add_option( '-c', '--min-alignment-count', dest='min_alignment_count', help='The minimum number of alignments in a locus for needed to conduct significance testing on changes in that locus observed between samples. If no testing is performed, changes in the locus are deemed not signficant, and the locus\' observed changes don\'t contribute to correction for multiple testing. The default is 1,000 fragment alignments (up to 2,000 paired reads).' )
    parser.add_option( '--FDR', dest='FDR', help='The allowed false discovery rate. The default is 0.05.' )
    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')
    parser.add_option( '--library-norm-method', dest='library_norm_method' )
    parser.add_option( '--dispersion-method', dest='dispersion_method' )

    # Advanced Options:	
    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' )
    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' )
    

    parser.add_option( "--tss_groups_read_group_tracking_output", dest="tss_groups_read_group_tracking_output", default=None )
    parser.add_option( "--isoforms_exp_output", dest="isoforms_exp_output" )
    parser.add_option( "--genes_exp_output", dest="genes_exp_output" )
    parser.add_option( "--tss_groups_exp_output", dest="tss_groups_exp_output" )
    parser.add_option( "--cds_exp_fpkm_tracking_output", dest="cds_exp_fpkm_tracking_output" )
    parser.add_option( "--cds_diff_output", dest="cds_diff_output" )
    parser.add_option( "--isoforms_count_tracking_output", dest="isoforms_count_tracking_output" )
    parser.add_option( "--genes_count_tracking_output", dest="genes_count_tracking_output" )
    parser.add_option( "--cds_count_tracking_output", dest="cds_count_tracking_output" )
    parser.add_option( "--tss_groups_count_tracking_output", dest="tss_groups_count_tracking_output" )
    parser.add_option( "--splicing_diff_output", dest="splicing_diff_output" )
    parser.add_option( "--promoters_diff_output", dest="promoters_diff_output" )
    parser.add_option( "--run_info_output", dest="run_info_output" )
    parser.add_option( "--read_groups_info_output", dest="read_groups_info_output" )
    parser.add_option( "--cuffdatadir", dest="cuffdatadir", default=None)
    parser.add_option( "--cummeRbund_db_output", dest="cummeRbund_db_output", default=None)

    tmp_output_dir = tempfile.mkdtemp()
    cuffdatadir = options.cuffdatadir if options.cuffdatadir else tmp_output_dir
    if not os.path.exists( cuffdatadir ):
        os.makedirs( cuffdatadir )
    
    # If doing bias correction, set/link to sequence file.
    if options.do_bias_correction:
        if options.ref_file != 'None':
            # Sequence data from history.
            # Create symbolic link to ref_file so that index will be created in working directory.

    
    # Base; always use quiet mode to avoid problems with storing log output.
    cmd = "cuffdiff --no-update-check -q"
    
    # Add options.
    if options.library_norm_method:
        cmd += ( " --library-norm-method %s" % options.library_norm_method )
    if options.dispersion_method:
        cmd += ( " --dispersion-method %s" % options.dispersion_method )
    if options.inner_dist_std_dev:
        cmd += ( " -s %i" % int ( options.inner_dist_std_dev ) )
    if options.num_threads:
        cmd += ( " -p %i" % int ( options.num_threads ) )
    if options.inner_mean_dist:

    # Add inputs.
    # For replicate analysis: group1_rep1,group1_rep2 groupN_rep1,groupN_rep2
    if options.groups:
        cmd += " --labels "
        for label in options.labels:
            cmd += '"%s",' % label
        cmd = cmd[:-1]

        cmd += " " + options.inputA + " "

        for group in options.groups: