comparison bowtie_wrapper.py @ 5:306077e393d4 draft

planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/bowtie_wrappers commit b2e1043bf4db38be490fec298a1829f8e4a1c48e

4:df86f29bedee

#!/usr/bin/env python

"""
Runs Bowtie on single-end or paired-end data.
For use with Bowtie v. 0.12.7

usage: bowtie_wrapper.py [options]
    -t, --threads=t: The number of threads to run
    -o, --output=o: The output file
    --output_unmapped_reads=: File name for unmapped reads (single-end)
    --output_unmapped_reads_l=: File name for unmapped reads (left, paired-end)
    --output_unmapped_reads_r=: File name for unmapped reads (right, paired-end)
    --output_suppressed_reads=: File name for suppressed reads because of max setting (single-end)
    --output_suppressed_reads_l=: File name for suppressed reads because of max setting (left, paired-end)
    --output_suppressed_reads_r=: File name for suppressed reads because of max setting (right, paired-end)
    -i, --input1=i: The (forward or single-end) reads file in Sanger FASTQ format
    -I, --input2=I: The reverse reads file in Sanger FASTQ format
    -4, --dataType=4: The type of data (SOLiD or Solexa)
    -2, --paired=2: Whether the data is single- or paired-end
    -g, --genomeSource=g: The type of reference provided

    parser.add_option( '', '--output_unmapped_reads_l', dest='output_unmapped_reads_l', help='File name for unmapped reads (left, paired-end)' )
    parser.add_option( '', '--output_unmapped_reads_r', dest='output_unmapped_reads_r', help='File name for unmapped reads (right, paired-end)' )
    parser.add_option( '', '--output_suppressed_reads', dest='output_suppressed_reads', help='File name for suppressed reads because of max setting (single-end)' )
    parser.add_option( '', '--output_suppressed_reads_l', dest='output_suppressed_reads_l', help='File name for suppressed reads because of max setting (left, paired-end)' )
    parser.add_option( '', '--output_suppressed_reads_r', dest='output_suppressed_reads_r', help='File name for suppressed reads because of max setting (right, paired-end)' )
    parser.add_option( '-4', '--dataType', dest='dataType', help='The type of data (SOLiD or Solexa)' )
    parser.add_option( '-i', '--input1', dest='input1', help='The (forward or single-end) reads file in Sanger FASTQ format' )
    parser.add_option( '-I', '--input2', dest='input2', help='The reverse reads file in Sanger FASTQ format' )
    parser.add_option( '-2', '--paired', dest='paired', help='Whether the data is single- or paired-end' )
    parser.add_option( '-g', '--genomeSource', dest='genomeSource', help='The type of reference provided' )

            else:
                cmd2 = 'bowtie %s %s %s > %s' % ( aligning_cmds, ref_file_name, options.input1, options.output )
            # align
            tmp = tempfile.NamedTemporaryFile( dir=tmp_index_dir ).name
            tmp_stderr = open( tmp, 'wb' )
            proc = subprocess.Popen( args=cmd2, shell=True, cwd=tmp_index_dir, stderr=tmp_stderr.fileno() )
            returncode = proc.wait()
            tmp_stderr.close()
            # get stderr, allowing for case where it's very large
            tmp_stderr = open( tmp, 'rb' )
            stderr = ''

            except OverflowError:
                pass
            tmp_stderr.close()
            if returncode != 0:
                raise Exception, stderr
            # get suppressed and unmapped reads output files in place if appropriate
            if options.paired == 'paired' and tmp_suppressed_file_name and \
                               options.output_suppressed_reads_l and options.output_suppressed_reads_r:
                try:
                    left = tmp_suppressed_file_name.replace( '.fastq', '_1.fastq' )

5:306077e393d4

#!/usr/bin/env python

"""
Runs Bowtie on single-end or paired-end data.

usage: bowtie_wrapper.py [options]
    -t, --threads=t: The number of threads to run
    -o, --output=o: The output file
    --output_unmapped_reads=: File name for unmapped reads (single-end)
    --output_unmapped_reads_l=: File name for unmapped reads (left, paired-end)
    --output_unmapped_reads_r=: File name for unmapped reads (right, paired-end)
    --output_suppressed_reads=: File name for suppressed reads because of max setting (single-end)
    --output_suppressed_reads_l=: File name for suppressed reads because of max setting (left, paired-end)
    --output_suppressed_reads_r=: File name for suppressed reads because of max setting (right, paired-end)
    --output_mapping_stats=: File name for mapping statistics (output on stderr by bowtie)
    -i, --input1=i: The (forward or single-end) reads file in Sanger FASTQ format
    -I, --input2=I: The reverse reads file in Sanger FASTQ format
    -4, --dataType=4: The type of data (SOLiD or Solexa)
    -2, --paired=2: Whether the data is single- or paired-end
    -g, --genomeSource=g: The type of reference provided

    parser.add_option( '', '--output_unmapped_reads_l', dest='output_unmapped_reads_l', help='File name for unmapped reads (left, paired-end)' )
    parser.add_option( '', '--output_unmapped_reads_r', dest='output_unmapped_reads_r', help='File name for unmapped reads (right, paired-end)' )
    parser.add_option( '', '--output_suppressed_reads', dest='output_suppressed_reads', help='File name for suppressed reads because of max setting (single-end)' )
    parser.add_option( '', '--output_suppressed_reads_l', dest='output_suppressed_reads_l', help='File name for suppressed reads because of max setting (left, paired-end)' )
    parser.add_option( '', '--output_suppressed_reads_r', dest='output_suppressed_reads_r', help='File name for suppressed reads because of max setting (right, paired-end)' )
    parser.add_option( '', '--output_mapping_stats', dest='output_mapping_stats', help='File for mapping statistics (i.e. stderr from bowtie)' )
    parser.add_option( '-4', '--dataType', dest='dataType', help='The type of data (SOLiD or Solexa)' )
    parser.add_option( '-i', '--input1', dest='input1', help='The (forward or single-end) reads file in Sanger FASTQ format' )
    parser.add_option( '-I', '--input2', dest='input2', help='The reverse reads file in Sanger FASTQ format' )
    parser.add_option( '-2', '--paired', dest='paired', help='Whether the data is single- or paired-end' )
    parser.add_option( '-g', '--genomeSource', dest='genomeSource', help='The type of reference provided' )

            else:
                cmd2 = 'bowtie %s %s %s > %s' % ( aligning_cmds, ref_file_name, options.input1, options.output )
            # align
            tmp = tempfile.NamedTemporaryFile( dir=tmp_index_dir ).name
            tmp_stderr = open( tmp, 'wb' )
            proc = subprocess.Popen( args=cmd2, shell=True, cwd=tmp_index_dir, stdout=sys.stdout, stderr=tmp_stderr.fileno() )
            returncode = proc.wait()
            tmp_stderr.close()
            # get stderr, allowing for case where it's very large
            tmp_stderr = open( tmp, 'rb' )
            stderr = ''

            except OverflowError:
                pass
            tmp_stderr.close()
            if returncode != 0:
                raise Exception, stderr
            elif options.output_mapping_stats is not None:
                # Write stderr (containing the mapping statistics) to a named file
                with open(options.output_mapping_stats, 'w') as mapping_stats:
                    mapping_stats.write( stderr )
            # get suppressed and unmapped reads output files in place if appropriate
            if options.paired == 'paired' and tmp_suppressed_file_name and \
                               options.output_suppressed_reads_l and options.output_suppressed_reads_r:
                try:
                    left = tmp_suppressed_file_name.replace( '.fastq', '_1.fastq' )