comparison bowtie_wrapper.py @ 4:df86f29bedee draft

planemo upload commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty

3:9ca609a2a421

    -L, --trimL=L: Trim n bases from low-quality (right) end of each read before alignment
    -m, --mismatchSeed=m: Maximum number of mismatches permitted in the seed
    -M, --mismatchQual=M: Maximum permitted total of quality values at mismatched read positions
    -l, --seedLen=l: Seed length
    -n, --rounding=n: Whether or not to round to the nearest 10 and saturating at 30
    -P, --maqSoapAlign=P: Choose MAQ- or SOAP-like alignment policy
    -w, --tryHard=: Whether or not to try as hard as possible to find valid alignments when they exist
    -v, --valAlign=v: Report up to n valid arguments per read
    -V, --allValAligns=V: Whether or not to report all valid alignments per read
    -G, --suppressAlign=G: Suppress all alignments for a read if more than n reportable alignments exist
    -b, --best=b: Whether or not to make Bowtie guarantee that reported singleton alignments are 'best' in terms of stratum and in terms of the quality values at the mismatched positions
    -B, --maxBacktracks=B: Maximum number of backtracks permitted when aligning a read
    -R, --strata=R: Whether or not to report only those alignments that fall in the best stratum if many valid alignments exist and are reportable
    -j, --minInsert=j: Minimum insert size for valid paired-end alignments

    -z, --ioffrate=z: How many rows get marked during annotation of some or all of the Burrows-Wheeler rows
    -W, --iftab=W: The size of the lookup table used to calculate an initial Burrows-Wheeler range with respect to the first n characters of the query
    -X, --intoa=X: Whether or not to convert Ns in the reference sequence to As
    -N, --iendian=N: Endianness to use when serializing integers to the index file
    -Z, --iseed=Z: Seed for the pseudorandom number generator
    -c, --icutoff=c: Number of first bases of the reference sequence to index
    -x, --indexSettings=x: Whether or not indexing options are to be set
    -H, --suppressHeader=H: Suppress header
    --do_not_build_index: Flag to specify that provided file is already indexed and to just use 'as is'
"""

    parser.add_option( '-L', '--trimL', dest='trimL', help='Trim n bases from low-quality (right) end of each read before alignment' )
    parser.add_option( '-m', '--mismatchSeed', dest='mismatchSeed', help='Maximum number of mismatches permitted in the seed' )
    parser.add_option( '-M', '--mismatchQual', dest='mismatchQual', help='Maximum permitted total of quality values at mismatched read positions' )
    parser.add_option( '-l', '--seedLen', dest='seedLen', help='Seed length' )
    parser.add_option( '-n', '--rounding', dest='rounding', help='Whether or not to round to the nearest 10 and saturating at 30' )
    parser.add_option( '-P', '--maqSoapAlign', dest='maqSoapAlign', help='Choose MAQ- or SOAP-like alignment policy' )
    parser.add_option( '-w', '--tryHard', dest='tryHard', help='Whether or not to try as hard as possible to find valid alignments when they exist' )
    parser.add_option( '-v', '--valAlign', dest='valAlign', help='Report up to n valid arguments per read' )
    parser.add_option( '-V', '--allValAligns', dest='allValAligns', help='Whether or not to report all valid alignments per read' )
    parser.add_option( '-G', '--suppressAlign', dest='suppressAlign', help='Suppress all alignments for a read if more than n reportable alignments exist' )
    parser.add_option( '-b', '--best', dest='best', help="Whether or not to make Bowtie guarantee that reported singleton alignments are 'best' in terms of stratum and in terms of the quality values at the mismatched positions" )
    parser.add_option( '-B', '--maxBacktracks', dest='maxBacktracks', help='Maximum number of backtracks permitted when aligning a read' )
    parser.add_option( '-R', '--strata', dest='strata', help='Whether or not to report only those alignments that fall in the best stratum if many valid alignments exist and are reportable' )
    parser.add_option( '-j', '--minInsert', dest='minInsert', help='Minimum insert size for valid paired-end alignments' )

    parser.add_option( '-z', '--ioffrate', dest='ioffrate', help='How many rows get marked during annotation of some or all of the Burrows-Wheeler rows' )
    parser.add_option( '-W', '--iftab', dest='iftab', help='The size of the lookup table used to calculate an initial Burrows-Wheeler range with respect to the first n characters of the query' )
    parser.add_option( '-X', '--intoa', dest='intoa', help='Whether or not to convert Ns in the reference sequence to As' )
    parser.add_option( '-N', '--iendian', dest='iendian', help='Endianness to use when serializing integers to the index file' )
    parser.add_option( '-Z', '--iseed', dest='iseed', help='Seed for the pseudorandom number generator' )
    parser.add_option( '-c', '--icutoff', dest='icutoff', help='Number of first bases of the reference sequence to index' )
    parser.add_option( '-x', '--indexSettings', dest='index_settings', help='Whether or not indexing options are to be set' )
    parser.add_option( '-H', '--suppressHeader', dest='suppressHeader', help='Suppress header' )
    parser.add_option( '--galaxy_input_format', dest='galaxy_input_format', default="fastqsanger", help='galaxy input format' )
    parser.add_option( '--do_not_build_index', dest='do_not_build_index', action="store_true", default=False, help='Flag to specify that provided file is already indexed, use as is' )
    (options, args) = parser.parse_args()
    stdout = ''

    # make temp directory for placement of indices and copy reference file there if necessary
    tmp_index_dir = tempfile.mkdtemp()
    # get type of data (solid or solexa)

            try:
                if options.iautoB and options.iautoB == 'set':
                    iautoB = '--noauto'
                else:
                    iautoB = ''
                if options. ipacked and options.ipacked == 'packed':
                    ipacked = '--packed'
                else:
                    ipacked = ''
                if options.ibmax and int( options.ibmax ) >= 1:
                    ibmax = '--bmax %s' % options.ibmax 
                else:
                    ibmax = ''
                if options.ibmaxdivn and int( options.ibmaxdivn ) >= 0:
                    ibmaxdivn = '--bmaxdivn %s' % options.ibmaxdivn
                else:
                    ibmaxdivn = ''
                if options.idcv and int( options.idcv ) > 0:
                    idcv = '--dcv %s' % options.idcv
                else:
                    idcv = ''
                if options.inodc and options.inodc == 'nodc':
                    inodc = '--nodc'

                    inodc = ''
                if options.inoref and options.inoref == 'noref':
                    inoref = '--noref'
                else:
                    inoref = ''
                if options.iftab and int( options.iftab ) >= 0:
                    iftab = '--ftabchars %s' % options.iftab
                else:
                    iftab = ''
                if options.intoa and options.intoa == 'yes':
                    intoa = '--ntoa'

                    iendian = '--little'
                if options.iseed and int( options.iseed ) > 0:
                    iseed = '--seed %s' % options.iseed
                else:
                    iseed = ''
                if options.icutoff and int( options.icutoff ) > 0:
                    icutoff = '--cutoff %s' % options.icutoff
                else:
                    icutoff = ''
                indexing_cmds = '%s %s %s %s %s %s %s --offrate %s %s %s %s %s %s %s' % \
                                ( iautoB, ipacked, ibmax, ibmaxdivn, idcv, inodc, 
                                  inoref, options.ioffrate, iftab, intoa, iendian, 
                                  iseed, icutoff, colorspace )
            except ValueError, e:
                # clean up temp dir
                if os.path.exists( tmp_index_dir ):
                    shutil.rmtree( tmp_index_dir )
                stop_err( "Something is wrong with the indexing parameters and the indexing and alignment could not be run. Make sure you don't have any non-numeric values where they should be numeric.\n" + str( e ) )

                trimH = ''
            if options.trimL and int( options.trimL ) > 0:
                trimL = '-3 %s' % options.trimL
            else:
                trimL = ''
            if options.maqSoapAlign != '-1' and int( options.maqSoapAlign ) >= 0:
                maqSoapAlign = '-v %s' % options.maqSoapAlign
            else:
                maqSoapAlign = ''
            if options.mismatchSeed and (options.mismatchSeed == '0' or options.mismatchSeed == '1' \
                        or options.mismatchSeed == '2' or options.mismatchSeed == '3'):
                mismatchSeed = '-n %s' % options.mismatchSeed
            else:
                mismatchSeed = ''
            if options.mismatchQual and int( options.mismatchQual ) >= 0:
                mismatchQual = '-e %s' % options.mismatchQual
            else:
                mismatchQual = ''
            if options.seedLen and int( options.seedLen ) >= 5:
                seedLen = '-l %s' % options.seedLen

            else:
                keepends = ''
            aligning_cmds = '-q %s %s -p %s -S %s %s %s %s %s %s %s %s %s %s %s %s ' \
                            '%s %s %s %s %s %s %s %s %s %s %s %s %s %s %s %s %s %s ' % \
                            ( maxInsert, mateOrient, options.threads, suppressHeader,
                              colorspace, skip, alignLimit, trimH, trimL, maqSoapAlign,
                              mismatchSeed, mismatchQual, seedLen, rounding, minInsert, 
                              maxAlignAttempt, forwardAlign, reverseAlign, maxBacktracks,
                              tryHard, valAlign, allValAligns, suppressAlign, best,
                              strata, offrate, seed, snpphred, snpfrac, keepends,
                              output_unmapped_reads, output_suppressed_reads,
                              quality_score_encoding )

        if os.path.exists( tmp_index_dir ):
            shutil.rmtree( tmp_index_dir )
    stdout += 'Sequence file aligned.\n'
    sys.stdout.write( stdout )

if __name__=="__main__": __main__()

4:df86f29bedee

    -L, --trimL=L: Trim n bases from low-quality (right) end of each read before alignment
    -m, --mismatchSeed=m: Maximum number of mismatches permitted in the seed
    -M, --mismatchQual=M: Maximum permitted total of quality values at mismatched read positions
    -l, --seedLen=l: Seed length
    -n, --rounding=n: Whether or not to round to the nearest 10 and saturating at 30
    -P, --maxMismatches=P: Maximum number of mismatches for -v alignment mode
    -w, --tryHard=: Whether or not to try as hard as possible to find valid alignments when they exist
    -V, --allValAligns=V: Whether or not to report all valid alignments per read or pair
    -v, --valAlign=v: Report up to n valid alignments per read or pair
    -G, --suppressAlign=G: Suppress all alignments for a read if more than n reportable alignments exist
    -b, --best=b: Whether or not to make Bowtie guarantee that reported singleton alignments are 'best' in terms of stratum and in terms of the quality values at the mismatched positions
    -B, --maxBacktracks=B: Maximum number of backtracks permitted when aligning a read
    -R, --strata=R: Whether or not to report only those alignments that fall in the best stratum if many valid alignments exist and are reportable
    -j, --minInsert=j: Minimum insert size for valid paired-end alignments

    -z, --ioffrate=z: How many rows get marked during annotation of some or all of the Burrows-Wheeler rows
    -W, --iftab=W: The size of the lookup table used to calculate an initial Burrows-Wheeler range with respect to the first n characters of the query
    -X, --intoa=X: Whether or not to convert Ns in the reference sequence to As
    -N, --iendian=N: Endianness to use when serializing integers to the index file
    -Z, --iseed=Z: Seed for the pseudorandom number generator
    -x, --indexSettings=x: Whether or not indexing options are to be set
    -H, --suppressHeader=H: Suppress header
    --do_not_build_index: Flag to specify that provided file is already indexed and to just use 'as is'
"""

    parser.add_option( '-L', '--trimL', dest='trimL', help='Trim n bases from low-quality (right) end of each read before alignment' )
    parser.add_option( '-m', '--mismatchSeed', dest='mismatchSeed', help='Maximum number of mismatches permitted in the seed' )
    parser.add_option( '-M', '--mismatchQual', dest='mismatchQual', help='Maximum permitted total of quality values at mismatched read positions' )
    parser.add_option( '-l', '--seedLen', dest='seedLen', help='Seed length' )
    parser.add_option( '-n', '--rounding', dest='rounding', help='Whether or not to round to the nearest 10 and saturating at 30' )
    parser.add_option( '-P', '--maxMismatches', dest='maxMismatches', help='Maximum number of mismatches for -v alignment mode' )
    parser.add_option( '-w', '--tryHard', dest='tryHard', help='Whether or not to try as hard as possible to find valid alignments when they exist' )
    parser.add_option( '-V', '--allValAligns', dest='allValAligns', help='Whether or not to report all valid alignments per read or pair' )
    parser.add_option( '-v', '--valAlign', dest='valAlign', help='Report up to n valid alignments per read or pair' )
    parser.add_option( '-G', '--suppressAlign', dest='suppressAlign', help='Suppress all alignments for a read if more than n reportable alignments exist' )
    parser.add_option( '-b', '--best', dest='best', help="Whether or not to make Bowtie guarantee that reported singleton alignments are 'best' in terms of stratum and in terms of the quality values at the mismatched positions" )
    parser.add_option( '-B', '--maxBacktracks', dest='maxBacktracks', help='Maximum number of backtracks permitted when aligning a read' )
    parser.add_option( '-R', '--strata', dest='strata', help='Whether or not to report only those alignments that fall in the best stratum if many valid alignments exist and are reportable' )
    parser.add_option( '-j', '--minInsert', dest='minInsert', help='Minimum insert size for valid paired-end alignments' )

    parser.add_option( '-z', '--ioffrate', dest='ioffrate', help='How many rows get marked during annotation of some or all of the Burrows-Wheeler rows' )
    parser.add_option( '-W', '--iftab', dest='iftab', help='The size of the lookup table used to calculate an initial Burrows-Wheeler range with respect to the first n characters of the query' )
    parser.add_option( '-X', '--intoa', dest='intoa', help='Whether or not to convert Ns in the reference sequence to As' )
    parser.add_option( '-N', '--iendian', dest='iendian', help='Endianness to use when serializing integers to the index file' )
    parser.add_option( '-Z', '--iseed', dest='iseed', help='Seed for the pseudorandom number generator' )
    parser.add_option( '-x', '--indexSettings', dest='index_settings', help='Whether or not indexing options are to be set' )
    parser.add_option( '-H', '--suppressHeader', dest='suppressHeader', help='Suppress header' )
    parser.add_option( '--galaxy_input_format', dest='galaxy_input_format', default="fastqsanger", help='galaxy input format' )
    parser.add_option( '--do_not_build_index', dest='do_not_build_index', action="store_true", default=False, help='Flag to specify that provided file is already indexed, use as is' )
    (options, args) = parser.parse_args()
    if options.mismatchSeed and options.maxMismatches:
        parser.error("options --mismatchSeed and --maxMismatches are mutually exclusive")
    stdout = ''

    # make temp directory for placement of indices and copy reference file there if necessary
    tmp_index_dir = tempfile.mkdtemp()
    # get type of data (solid or solexa)

            try:
                if options.iautoB and options.iautoB == 'set':
                    iautoB = '--noauto'
                else:
                    iautoB = ''
                if options.ipacked and options.ipacked == 'packed':
                    ipacked = '--packed'
                else:
                    ipacked = ''
                if options.ibmax and int( options.ibmax ) >= 1:
                    ibmax = '--bmax %s' % options.ibmax
                else:
                    ibmax = ''
                if options.ibmaxdivn and int( options.ibmaxdivn ) >= 0:
                    ibmaxdivn = '--bmaxdivn %s' % options.ibmaxdivn
                else:
                    ibmaxdivn = ''
                if options.idcv and int( options.idcv ) >= 3:
                    idcv = '--dcv %s' % options.idcv
                else:
                    idcv = ''
                if options.inodc and options.inodc == 'nodc':
                    inodc = '--nodc'

                    inodc = ''
                if options.inoref and options.inoref == 'noref':
                    inoref = '--noref'
                else:
                    inoref = ''
                if options.iftab and int( options.iftab ) >= 1:
                    iftab = '--ftabchars %s' % options.iftab
                else:
                    iftab = ''
                if options.intoa and options.intoa == 'yes':
                    intoa = '--ntoa'

                    iendian = '--little'
                if options.iseed and int( options.iseed ) > 0:
                    iseed = '--seed %s' % options.iseed
                else:
                    iseed = ''
                indexing_cmds = '%s %s %s %s %s %s %s --offrate %s %s %s %s %s %s' % \
                                ( iautoB, ipacked, ibmax, ibmaxdivn, idcv, inodc,
                                  inoref, options.ioffrate, iftab, intoa, iendian,
                                  iseed, colorspace )
            except ValueError, e:
                # clean up temp dir
                if os.path.exists( tmp_index_dir ):
                    shutil.rmtree( tmp_index_dir )
                stop_err( "Something is wrong with the indexing parameters and the indexing and alignment could not be run. Make sure you don't have any non-numeric values where they should be numeric.\n" + str( e ) )

                trimH = ''
            if options.trimL and int( options.trimL ) > 0:
                trimL = '-3 %s' % options.trimL
            else:
                trimL = ''
            if options.maxMismatches and (options.maxMismatches == '0' or options.maxMismatches == '1' \
                        or options.maxMismatches == '2' or options.maxMismatches == '3'):
                maxMismatches = '-v %s' % options.maxMismatches
            else:
                maxMismatches = ''
            if options.mismatchSeed and (options.mismatchSeed == '0' or options.mismatchSeed == '1' \
                        or options.mismatchSeed == '2' or options.mismatchSeed == '3'):
                mismatchSeed = '-n %s' % options.mismatchSeed
            else:
                mismatchSeed = ''
            if options.mismatchQual and int( options.mismatchQual ) >= 1:
                mismatchQual = '-e %s' % options.mismatchQual
            else:
                mismatchQual = ''
            if options.seedLen and int( options.seedLen ) >= 5:
                seedLen = '-l %s' % options.seedLen

            else:
                keepends = ''
            aligning_cmds = '-q %s %s -p %s -S %s %s %s %s %s %s %s %s %s %s %s %s ' \
                            '%s %s %s %s %s %s %s %s %s %s %s %s %s %s %s %s %s %s ' % \
                            ( maxInsert, mateOrient, options.threads, suppressHeader,
                              colorspace, skip, alignLimit, trimH, trimL, maxMismatches,
                              mismatchSeed, mismatchQual, seedLen, rounding, minInsert,
                              maxAlignAttempt, forwardAlign, reverseAlign, maxBacktracks,
                              tryHard, valAlign, allValAligns, suppressAlign, best,
                              strata, offrate, seed, snpphred, snpfrac, keepends,
                              output_unmapped_reads, output_suppressed_reads,
                              quality_score_encoding )

        if os.path.exists( tmp_index_dir ):
            shutil.rmtree( tmp_index_dir )
    stdout += 'Sequence file aligned.\n'
    sys.stdout.write( stdout )

if __name__ == "__main__":
    __main__()