Python Bunch.combine_data_queue方法代码示例

# 需要导入模块: from galaxy.util.bunch import Bunch [as 别名]
# 或者: from galaxy.util.bunch.Bunch import combine_data_queue [as 别名]

#.........这里部分代码省略.........
                    coverage_max = options.coverage_max
                set_options += '--filter=coverage:%s..%s ' % ( coverage_min, coverage_max )
            elif options.filter == 'nmatch':
                set_options += '--filter=nmatch:%s% ' % options.nmatch_min
            elif options.filter == 'nmismatch':
                set_options += '--filter=nmismatch:0..%s ' % options.nmismatch_max
    # Handle --strand
    set_options += '--strand=%s ' % options.strand
    # Handle --ambiguous
    if options.ambiguous not in [ "no" ]:
        set_options += '--ambiguous=%s ' % options.ambiguous
    # Handle --shortcuts_for_yasra
    if options.shortcuts_for_yasra not in [ 'none' ]:
        set_options += '--%s ' % ( options.shortcuts_for_yasra )
    # Specify input2 and add [fullnames] modifier if output format is diffs
    if options.format == 'diffs':
        input2 = '%s[fullnames]' % options.input2
    else:
        input2 = options.input2
    if options.format == 'tabular':
        # Change output format to general if it's tabular and add field names for tabular output
        format = 'general-'
        tabular_fields = ':score,name1,strand1,size1,start1,zstart1,end1,length1,text1,name2,strand2,size2,start2,zstart2,end2,start2+,zstart2+,end2+,length2,text2,diff,cigar,identity,coverage,gaprate,diagonal,shingle'
    elif options.format == 'sam':
        # We currently need to keep headers.
        format = 'sam'
        tabular_fields = ''
    else:
        format = options.format
        tabular_fields = ''
    # Set up our queues
    threads = int( options.threads )
    lastz_job_queue = LastzJobQueue( threads, slots=SLOTS )
    combine_data_queue = CombineDataQueue( options.output )
    if str( options.ref_source ) in [ 'history', 'self' ]:
        # Reference is a fasta dataset from the history or the dataset containing the target sequence itself,
        # so split job across the number of sequences in the dataset ( this could be a HUGE number ).
        try:
            # Ensure there is at least 1 sequence in the dataset ( this may not be necessary ).
            error_msg = "The reference dataset is missing metadata.  Click the pencil icon in the history item and 'auto-detect' the metadata attributes."
            ref_sequences = int( options.ref_sequences )
            if ref_sequences < 1:
                stop_queues( lastz_job_queue, combine_data_queue )
                stop_err( error_msg )
        except:
            stop_queues( lastz_job_queue, combine_data_queue )
            stop_err( error_msg )
        seqs = 0
        fasta_reader = FastaReader( open( options.input1 ) )
        while True:
            # Read the next sequence from the reference dataset
            seq = fasta_reader.next()
            if not seq:
                break
            seqs += 1
            # Create a temporary file to contain the current sequence as input to lastz
            tmp_in_fd, tmp_in_name = tempfile.mkstemp( suffix='.in' )
            tmp_in = os.fdopen( tmp_in_fd, 'wb' )
            # Write the current sequence to the temporary input file
            tmp_in.write( '>%s\n%s\n' % ( seq.name, seq.text ) )
            tmp_in.close()
            # Create a 2nd temporary file to contain the output from lastz execution on the current sequence
            tmp_out_fd, tmp_out_name = tempfile.mkstemp( suffix='.out' )
            os.close( tmp_out_fd )
            # Generate the command line for calling lastz on the current sequence
            command = 'lastz %s%s %s %s --format=%s%s > %s' % ( tmp_in_name, ref_name, input2, set_options, format, tabular_fields, tmp_out_name )

# 需要导入模块: from galaxy.util.bunch import Bunch [as 别名]
# 或者: from galaxy.util.bunch.Bunch import combine_data_queue [as 别名]
def __main__():
    #Parse Command Line
    parser = optparse.OptionParser()
    parser.add_option( '', '--ref_name', dest='ref_name', help='The reference name to change all output matches to' )
    parser.add_option( '', '--ref_source', dest='ref_source', help='Whether the reference is cached or from the history' )
    parser.add_option( '', '--ref_sequences', dest='ref_sequences', help='Number of sequences in the reference dataset' )
    parser.add_option( '', '--source_select', dest='source_select', help='Whether to used pre-set or cached reference file' )
    parser.add_option( '', '--input1', dest='input1', help='The name of the reference file if using history or reference base name if using cached' )
    parser.add_option( '', '--input2', dest='input2', help='The reads file to align' )
    parser.add_option( '', '--pre_set_options', dest='pre_set_options', help='Which of the pre set options to use, if using pre-sets' )
    parser.add_option( '', '--strand', dest='strand', help='Which strand of the read to search, if specifying all parameters' )
    parser.add_option( '', '--seed', dest='seed', help='Seeding settings, if specifying all parameters' )
    parser.add_option( '', '--transition', dest='transition', help='Number of transitions to allow in each seed hit, if specifying all parameters' )
    parser.add_option( '', '--gfextend', dest='gfextend', help='Whether to perform gap-free extension of seed hits to HSPs (high scoring segment pairs), if specifying all parameters' )
    parser.add_option( '', '--chain', dest='chain', help='Whether to perform chaining of HSPs, if specifying all parameters' )
    parser.add_option( '', '--O', dest='O', help='Gap opening penalty, if specifying all parameters' )
    parser.add_option( '', '--E', dest='E', help='Gap extension penalty, if specifying all parameters' )
    parser.add_option( '', '--X', dest='X', help='X-drop threshold, if specifying all parameters' )
    parser.add_option( '', '--Y', dest='Y', help='Y-drop threshold, if specifying all parameters' )
    parser.add_option( '', '--K', dest='K', help='Threshold for HSPs, if specifying all parameters' )
    parser.add_option( '', '--L', dest='L', help='Threshold for gapped alignments, if specifying all parameters' )
    parser.add_option( '', '--entropy', dest='entropy', help='Whether to involve entropy when filtering HSPs, if specifying all parameters' )
    parser.add_option( '', '--identity_min', dest='identity_min', help="Minimum identity (don't report matches under this identity)" )
    parser.add_option( '', '--identity_max', dest='identity_max', help="Maximum identity (don't report matches above this identity)" )
    parser.add_option( '', '--coverage', dest='coverage', help="The minimum coverage value (don't report matches covering less than this)" )
    parser.add_option( '', '--unmask', dest='unmask', help='Whether to convert lowercase bases to uppercase' )
    parser.add_option( '', '--out_format', dest='format', help='The format of the output file (sam, diffs, or tabular (general))' )
    parser.add_option( '', '--output', dest='output', help='The output file' )
    parser.add_option( '', '--lastzSeqsFileDir', dest='lastzSeqsFileDir', help='Directory of local lastz_seqs.loc file' )
    ( options, args ) = parser.parse_args()

    # output version # of tool
    try:
        tmp = tempfile.NamedTemporaryFile().name
        tmp_stdout = open( tmp, 'wb' )
        proc = subprocess.Popen( args='lastz -v', shell=True, stdout=tmp_stdout )
        tmp_stdout.close()
        returncode = proc.wait()
        stdout = None
        for line in open( tmp_stdout.name, 'rb' ):
            if line.lower().find( 'version' ) >= 0:
                stdout = line.strip()
                break
        if stdout:
            sys.stdout.write( '%s\n' % stdout )
        else:
            raise Exception
    except:
        sys.stdout.write( 'Could not determine Lastz version\n' )

    if options.unmask == 'yes':
        unmask = '[unmask]'
    else:
        unmask = ''
    if options.ref_name:
        ref_name = '[nickname=%s]' % options.ref_name
    else:
        ref_name = ''
    # Prepare for commonly-used preset options
    if options.source_select == 'pre_set':
        set_options = '--%s' % options.pre_set_options
    # Prepare for user-specified options
    else:
        set_options = '--%s --%s --gapped --strand=%s --seed=%s --%s O=%s E=%s X=%s Y=%s K=%s L=%s --%s' % \
                    ( options.gfextend, options.chain, options.strand, options.seed, options.transition,
                      options.O, options.E, options.X, options.Y, options.K, options.L, options.entropy )
    # Specify input2 and add [fullnames] modifier if output format is diffs
    if options.format == 'diffs':
        input2 = '%s[fullnames]' % options.input2
    else:
        input2 = options.input2
    if options.format == 'tabular':
        # Change output format to general if it's tabular and add field names for tabular output
        format = 'general-'
        tabular_fields = ':score,name1,strand1,size1,start1,zstart1,end1,length1,text1,name2,strand2,size2,start2,zstart2,end2,start2+,zstart2+,end2+,length2,text2,diff,cigar,identity,coverage,gaprate,diagonal,shingle'
    elif options.format == 'sam':
        # We currently ALWAYS suppress SAM headers.
        format = 'sam-'
        tabular_fields = ''
    else:
        format = options.format
        tabular_fields = ''

    # Set up our queues
    lastz_job_queue = LastzJobQueue( WORKERS, slots=SLOTS )
    combine_data_queue = CombineDataQueue( options.output )

    if options.ref_source == 'history':
        # Reference is a fasta dataset from the history, so split job across
        # the number of sequences in the dataset ( this could be a HUGE number )
        try:
            # Ensure there is at least 1 sequence in the dataset ( this may not be necessary ).
            error_msg = "The reference dataset is missing metadata, click the pencil icon in the history item and 'auto-detect' the metadata attributes."
            ref_sequences = int( options.ref_sequences )
            if ref_sequences < 1:
                stop_queues( lastz_job_queue, combine_data_queue )
                stop_err( error_msg )
        except:
            stop_queues( lastz_job_queue, combine_data_queue )
            stop_err( error_msg )
#.........这里部分代码省略.........