# HG changeset patch # User qfab # Date 1395279316 14400 # Node ID c9d76b53903a844e5b34f48f9379cc1f14f5263a Uploaded diff -r 000000000000 -r c9d76b53903a bowtie_for_fasta-254d8bd5d21a/bowtie_for_fasta_wrapper.py --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/bowtie_for_fasta-254d8bd5d21a/bowtie_for_fasta_wrapper.py Wed Mar 19 21:35:16 2014 -0400 @@ -0,0 +1,324 @@ +#!/usr/bin/env python + +import optparse, os, shutil, subprocess, sys, tempfile + +#Allow more than Sanger encoded variants +DEFAULT_ASCII_ENCODING = '--phred33-quals' +GALAXY_FORMAT_TO_QUALITY_SCORE_ENCODING_ARG = { 'fastqsanger':'--phred33-quals', 'fastqillumina':'--phred64-quals', 'fastqsolexa':'--solexa-quals' } +#FIXME: Integer quality scores are supported only when the '--integer-quals' argument is specified to bowtie; this is not currently able to be set in the tool/wrapper/config + +def stop_err( msg ): + sys.stderr.write( '%s\n' % msg ) + sys.exit() + +def __main__(): + #Parse Command Line + parser = optparse.OptionParser() + parser.add_option( '-t', '--threads', dest='threads', help='The number of threads to run' ) + parser.add_option( '-i', '--input1', dest='input1', help='The (forward or single-end) reads file in Sanger FASTQ format' ) + parser.add_option( '-4', '--dataType', dest='dataType', help='The type of data (SOLiD or Solexa)' ) + parser.add_option( '-g', '--genomeSource', dest='genomeSource', help='The type of reference provided' ) + parser.add_option( '-r', '--ref', dest='ref', help='The reference genome to use or index' ) + parser.add_option( '-s', '--skip', dest='skip', help='Skip the first n reads' ) + parser.add_option( '-a', '--alignLimit', dest='alignLimit', help='Only align the first n reads' ) + parser.add_option( '-T', '--trimH', dest='trimH', help='Trim n bases from high-quality (left) end of each read before alignment' ) + 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( '--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' ) + parser.add_option( '-x', '--indexSettings', dest='index_settings', help='Whether or not indexing options are to be set' ) + parser.add_option( '-F', '--offrate', dest='offrate', help='Override the offrate of the index to n' ) + parser.add_option( '-u', '--iautoB', dest='iautoB', help='Automatic or specified behavior' ) + parser.add_option( '-K', '--ipacked', dest='ipacked', help='Whether or not to use a packed representation for DNA strings' ) + parser.add_option( '-Q', '--ibmax', dest='ibmax', help='Maximum number of suffixes allowed in a block' ) + parser.add_option( '-Y', '--ibmaxdivn', dest='ibmaxdivn', help='Maximum number of suffixes allowed in a block as a fraction of the length of the reference' ) + parser.add_option( '-D', '--idcv', dest='idcv', help='The period for the difference-cover sample' ) + parser.add_option( '-U', '--inodc', dest='inodc', help='Whether or not to disable the use of the difference-cover sample' ) + parser.add_option( '-y', '--inoref', dest='inoref', help='Whether or not to build the part of the reference index used only in paired-end alignment' ) + 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') + parser.add_option( '-C', '--params', dest='params', help='Whether to use default or specified parameters' ) + parser.add_option( '-O', '--seed', dest='seed', help='Seed for pseudo-random number generator' ) + parser.add_option( '-S', '-S', dest='samformat', help='The output format' ) + parser.add_option( '-o', '--output', dest='output', help='The output file' ) + parser.add_option( '--galaxy_input_format', dest='galaxy_input_format', default="fasta", help='galaxy input format' ) + (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) + if options.dataType == 'solid': + colorspace = '-C' + else: + colorspace = '' + + # get type of data (solid or solexa) + if options.samformat == 'true': + format = '-S' + else: + format = '' + + # index if necessary + if options.genomeSource == 'history' and not options.do_not_build_index: + # set up commands + if options.index_settings =='indexPreSet': + indexing_cmds = '%s' % colorspace + else: + 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' + else: + 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' + else: + intoa = '' + if options.iendian and options.iendian == 'big': + iendian = '--big' + else: + 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 ) ) + ref_file = tempfile.NamedTemporaryFile( dir=tmp_index_dir ) + ref_file_name = ref_file.name + ref_file.close() + os.symlink( options.ref, ref_file_name ) + + cmd1 = 'bowtie-build %s -f %s %s' % ( indexing_cmds, ref_file_name, ref_file_name ) + + try: + tmp = tempfile.NamedTemporaryFile( dir=tmp_index_dir ).name + tmp_stderr = open( tmp, 'wb' ) + proc = subprocess.Popen( args=cmd1, 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 = '' + buffsize = 1048576 + try: + while True: + stderr += tmp_stderr.read( buffsize ) + if not stderr or len( stderr ) % buffsize != 0: + break + except OverflowError: + pass + tmp_stderr.close() + if returncode != 0: + raise Exception, stderr + except Exception, e: + # clean up temp dir + if os.path.exists( tmp_index_dir ): + shutil.rmtree( tmp_index_dir ) + stop_err( 'Error indexing reference sequence\n' + str( e ) ) + stdout += 'File indexed. ' + else: + + ref_file_name = options.ref + # set up aligning and generate aligning command options + # automatically set threads in both cases + tmp_suppressed_file_name = None + tmp_unmapped_file_name = None + quality_score_encoding = GALAXY_FORMAT_TO_QUALITY_SCORE_ENCODING_ARG.get( options.galaxy_input_format, DEFAULT_ASCII_ENCODING ) + + try: + 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 = '' + print "seedLen is %s" % options.seedLen + if options.seedLen and int( options.seedLen ) >= 5: + print "seedLen1 is %s" % options.seedLen + seedLen = '-l %s' % options.seedLen + else: + print "seedLen2 is %s" % options.seedLen + seedLen = '' + if options.valAlign and int( options.valAlign ) >= 0: + valAlign = '-k %s' % options.valAlign + else: + valAlign = '' + if options.suppressAlign and int( options.suppressAlign ) >= 0: + suppressAlign = '-m %s' % options.suppressAlign + else: + suppressAlign = '' + except ValueError, e: + # clean up temp dir + if os.path.exists( tmp_index_dir ): + shutil.rmtree( tmp_index_dir ) + stop_err( 'Something is wrong \n' + str( e ) ) + if options.params: + aligning_cmds = '-f -p %s -S %s %s %s %s %s %s ' % \ + (options.threads, mismatchSeed,mismatchQual,seedLen,valAlign,suppressAlign, + quality_score_encoding ) + else: + try: + if options.skip and int( options.skip ) > 0: + skip = '-s %s' % options.skip + else: + skip = '' + if options.alignLimit and int( options.alignLimit ) >= 0: + alignLimit = '-u %s' % options.alignLimit + else: + alignLimit = '' + if options.trimH and int( options.trimH ) > 0: + trimH = '-5 %s' % options.trimH + else: + trimH = '' + if options.trimL and int( options.trimL ) > 0: + trimL = '-3 %s' % options.trimL + else: + trimL = '' + if int(options.maqSoapAlign) != '-1' and int(options.maqSoapAlign) >= '0': + maqSoapAlign = '-v %s' % options.maqSoapAlign + else: + maqSoapAlign = '' + if options.rounding == 'noRound': + rounding = '--nomaqround' + else: + rounding = '' + if options.maxBacktracks and int( options.maxBacktracks ) > 0 and \ + ( options.mismatchSeed == '2' or options.mismatchSeed == '3' ): + maxBacktracks = '--maxbts %s' % options.maxBacktracks + else: + maxBacktracks = '' + if options.tryHard == 'doTryHard': + tryHard = '-y' + else: + tryHard = '' + if options.valAlign and int( options.valAlign ) >= 0: + valAlign = '-k %s' % options.valAlign + else: + valAlign = '' + if options.allValAligns == 'doAllValAligns': + allValAligns = '-a' + else: + allValAligns = '' + if options.best == 'doBest': + best = '--best' + else: + best = '' + if options.strata == 'doStrata': + strata = '--strata' + else: + strata = '' + if options.offrate and int( options.offrate ) >= 0: + offrate = '-o %s' % options.offrate + else: + offrate = '' + if options.seed and int( options.seed ) > 0: + seed = '--seed %s' % options.seed + else: + iseed = '' + aligning_cmds = '-f -p %s %s %s %s %s %s %s %s %s %s %s %s ' \ + '%s %s %s %s %s %s %s %s' % \ + ( options.threads, skip, alignLimit, + trimH, trimL, maqSoapAlign,mismatchSeed, mismatchQual, seedLen, rounding, + maxBacktracks,tryHard, valAlign, allValAligns, suppressAlign, best, + strata, offrate,seed, quality_score_encoding ) + 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 alignment parameters and the alignment could not be run\n' + str( e ) ) + + # have to nest try-except in try-finally to handle 2.4 + try: + # prepare actual mapping commands + cmd2 = 'bowtie %s %s %s > %s' % ( aligning_cmds, ref_file_name, options.input1, options.output) + print(cmd2) + # 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 = '' + buffsize = 1048576 + try: + while True: + stderr += tmp_stderr.read( buffsize ) + if not stderr or len( stderr ) % buffsize != 0: + break + except OverflowError: + pass + tmp_stderr.close() + if returncode != 0: + raise Exception, stderr + # check that there are results in the output file + if os.path.getsize( options.output ) == 0: + raise Exception, 'The output file is empty, there may be an error with your input file or settings.' + except Exception, e: + stop_err( 'Error aligning sequence. ' + str( e ) ) + finally: + # clean up temp dir + 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__() diff -r 000000000000 -r c9d76b53903a bowtie_for_fasta-254d8bd5d21a/bowtie_for_fasta_wrapper.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/bowtie_for_fasta-254d8bd5d21a/bowtie_for_fasta_wrapper.xml Wed Mar 19 21:35:16 2014 -0400 @@ -0,0 +1,248 @@ + + + bowtie + + Fasta File + + + bowtie_for_fasta_wrapper.py + ## Hackish setting of number of threads + --threads="4" + ## Output + #if str( $outformat) == "sam": + -S "true" + --output "${samoutput}" + #else: + -S "false" + --output "${taboutput}" + #end if + + +## #if $output_unmapped_reads_l +## --output_unmapped_reads="${output_unmapped_reads_l}" +## #end if +## #if $output_suppressed_reads_l +## --output_suppressed_reads="${output_suppressed_reads_l}" +## #end if +## --galaxy_input_format="${singlePaired.sInput1.ext}" + ## Inputs + --dataType="solexa" ##this indicates that nucleotide base space is used in the wrapper +## --suppressHeader="${suppressHeader}" + --genomeSource="${refGenomeSource.genomeSource}" + #if $refGenomeSource.genomeSource == "history": + ##index already exists + #if $refGenomeSource.ownFile.extension.startswith( 'bowtie_' ): + ##user previously built + --ref="${refGenomeSource.ownFile.extra_files_path}/${refGenomeSource.ownFile.metadata.base_name}" + --do_not_build_index + #else: + ##build index on the fly + --ref="${refGenomeSource.ownFile}" + --indexSettings="${refGenomeSource.indexParams.indexSettings}" + #if $refGenomeSource.indexParams.indexSettings == "indexFull": + --iautoB="${refGenomeSource.indexParams.autoBehavior.autoB}" + #if $refGenomeSource.indexParams.autoBehavior.autoB == "set": + --ipacked="${refGenomeSource.indexParams.autoBehavior.packed}" + --ibmax="${refGenomeSource.indexParams.autoBehavior.bmax}" + --ibmaxdivn="${refGenomeSource.indexParams.autoBehavior.bmaxdivn}" + --idcv="${refGenomeSource.indexParams.autoBehavior.dcv}" + #end if + --inodc="${refGenomeSource.indexParams.nodc}" + --inoref="${refGenomeSource.indexParams.noref}" + --ioffrate="${refGenomeSource.indexParams.offrate}" + --iftab="${refGenomeSource.indexParams.ftab}" + --intoa="${refGenomeSource.indexParams.ntoa}" + --iendian="${refGenomeSource.indexParams.endian}" + --iseed="${refGenomeSource.indexParams.seed}" + --icutoff="${refGenomeSource.indexParams.cutoff}" + #end if + #end if + #else + ##use pre-built index + --ref="${refGenomeSource.index.fields.path}" + #end if + --input1="${sInput1}" + --params="${Params.sSettingsType}" + --mismatchQual="${sMismatchQual}" + --mismatchSeed="${sMismatchSeed}" + --seedLen="${sSeedLen}" + --suppressAlign="${sSuppressAlign}" + --valAlign="${sValAlign}" + #unless $Params.sSettingsType: + --skip="${Params.sSkip}" + --alignLimit="${Params.sAlignLimit}" + --trimH="${Params.sTrimH}" + --trimL="${Params.sTrimL}" + --rounding="${Params.sRounding}" + --maqSoapAlign="${Params.sMaqSoapAlign}" + --tryHard="${Params.sTryHard}" + --best="${Params.sBestOption.sBest}" + #if $Params.sBestOption.sBest == "doBest": + --maxBacktracks="${Params.sBestOption.sdMaxBacktracks}" + --strata="${Params.sBestOption.sdStrata}" + #else: + --maxBacktracks="${Params.sBestOption.snMaxBacktracks}" + #end if + --offrate="${Params.sOffrate}" + --seed="${Params.sSeed}" + #end unless + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + outformat == "sam" + + + + + + + + + + + + + + + + outformat == "tab" + + + + + + + + + + + + + + diff -r 000000000000 -r c9d76b53903a bowtie_for_fasta-254d8bd5d21a/bowtie_indices.loc.sample --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/bowtie_for_fasta-254d8bd5d21a/bowtie_indices.loc.sample Wed Mar 19 21:35:16 2014 -0400 @@ -0,0 +1,37 @@ +#This is a sample file distributed with Galaxy that enables tools +#to use a directory of Bowtie indexed sequences data files. You will +#need to create these data files and then create a bowtie_indices.loc +#file similar to this one (store it in this directory) that points to +#the directories in which those files are stored. The bowtie_indices.loc +#file has this format (longer white space characters are TAB characters): +# +# +# +#So, for example, if you had hg18 indexed stored in +#/depot/data2/galaxy/bowtie/hg18/, +#then the bowtie_indices.loc entry would look like this: +# +#hg18 hg18 hg18 /depot/data2/galaxy/bowtie/hg18/hg18 +# +#and your /depot/data2/galaxy/bowtie/hg18/ directory +#would contain hg18.*.ebwt files: +# +#-rw-r--r-- 1 james universe 830134 2005-09-13 10:12 hg18.1.ebwt +#-rw-r--r-- 1 james universe 527388 2005-09-13 10:12 hg18.2.ebwt +#-rw-r--r-- 1 james universe 269808 2005-09-13 10:12 hg18.3.ebwt +#...etc... +# +#Your bowtie_indices.loc file should include an entry per line for each +#index set you have stored. The "file" in the path does not actually +#exist, but it is the prefix for the actual index files. For example: +# +#hg18canon hg18 hg18 Canonical /depot/data2/galaxy/bowtie/hg18/hg18canon +#hg18full hg18 hg18 Full /depot/data2/galaxy/bowtie/hg18/hg18full +#/orig/path/hg19 hg19 hg19 /depot/data2/galaxy/bowtie/hg19/hg19 +#...etc... +# +#Note that for backwards compatibility with workflows, the unique ID of +#an entry must be the path that was in the original loc file, because that +#is the value stored in the workflow for that parameter. That is why the +#hg19 entry above looks odd. New genomes can be better-looking. +# diff -r 000000000000 -r c9d76b53903a bowtie_for_fasta-254d8bd5d21a/tool_data_table_conf.xml.sample --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/bowtie_for_fasta-254d8bd5d21a/tool_data_table_conf.xml.sample Wed Mar 19 21:35:16 2014 -0400 @@ -0,0 +1,8 @@ + + + + + value, dbkey, name, path + +
+
diff -r 000000000000 -r c9d76b53903a bowtie_for_fasta-254d8bd5d21a/tool_dependencies.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/bowtie_for_fasta-254d8bd5d21a/tool_dependencies.xml Wed Mar 19 21:35:16 2014 -0400 @@ -0,0 +1,4 @@ + + + +