Mercurial > repos > yufei-luo > bwa_0_7_5
changeset 0:839e36b39c3f draft
Uploaded
| author | yufei-luo |
|---|---|
| date | Mon, 12 Aug 2013 08:44:05 -0400 |
| parents | |
| children | 53987fecf8c7 |
| files | bwa_0_7_5/README bwa_0_7_5/bwa_0_7_5.py bwa_0_7_5/bwa_0_7_5.xml bwa_0_7_5/tool-data/bwa_index.loc |
| diffstat | 4 files changed, 500 insertions(+), 0 deletions(-) [+] |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/bwa_0_7_5/README Mon Aug 12 08:44:05 2013 -0400 @@ -0,0 +1,4 @@ +This tool is just a wrapper of bwa for the 0.7.5 version. +Only for BWA-MEM usage. + +If you have problems with wrapper files, please contact me: luoyufei@gmail.com
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/bwa_0_7_5/bwa_0_7_5.py Mon Aug 12 08:44:05 2013 -0400 @@ -0,0 +1,272 @@ +#!/usr/bin/env python +## yufei.luo@gustave.roussy 22/07/2013 + +""" +Runs BWA on single-end or paired-end data. +Produces a SAM file containing the mappings. +Works with BWA version 0.7.5. +NOTICE: In this wrapper, we only use 'mem' for mapping step. + +usage: bwa_0_7_5.py [args] + +See below for args +""" + +import optparse, os, shutil, subprocess, sys, tempfile +import argparse + +def stop_err( msg ): + sys.stderr.write( '%s\n' % msg ) + sys.exit() + +def check_is_double_encoded( fastq ): + # check that first read is bases, not one base followed by numbers + bases = [ 'A', 'C', 'G', 'T', 'a', 'c', 'g', 't', 'N' ] + nums = [ '0', '1', '2', '3' ] + for line in file( fastq, 'rb'): + if not line.strip() or line.startswith( '@' ): + continue + if len( [ b for b in line.strip() if b in nums ] ) > 0: + return False + elif line.strip()[0] in bases and len( [ b for b in line.strip() if b in bases ] ) == len( line.strip() ): + return True + else: + raise Exception, 'First line in first read does not appear to be a valid FASTQ read in either base-space or color-space' + raise Exception, 'There is no non-comment and non-blank line in your FASTQ file' + +def __main__(): + + descr = "bwa_0_7_5.py: version 1.0. Map the reads(long length) against the genome reference with BWA MEM. \n" + descr += "Usage: BWA mem -t thread -R groupInfo refSequence read.R1.fastq (read.R2.fastq) > out.sam" + parser = argparse.ArgumentParser(description=descr) + parser.add_argument( '-t', '--threads', default=1, help='The number of threads to use [1]' ) + parser.add_argument( '--color-space', default=False, help='If the input files are SOLiD format' ) + parser.add_argument( '--ref', help='The reference genome to use or index' ) + parser.add_argument( '-f', '--fastq', help='The (forward) fastq file to use for the mapping' ) + parser.add_argument( '-F', '--rfastq', help='The reverse fastq file to use for mapping if paired-end data' ) + parser.add_argument( '-u', '--output', help='The file to save the output (SAM format)' ) + parser.add_argument( '-g', '--genAlignType', help='The type of pairing (single or paired)' ) + parser.add_argument( '--params', help='Parameter setting to use (pre_set or full)' ) + parser.add_argument( '-s', '--fileSource', help='Whether to use a previously indexed reference sequence or one form history (indexed or history)' ) + parser.add_argument( '-D', '--dbkey', help='Dbkey for reference genome' ) + + parser.add_argument( '-k', '--minEditDistSeed', default=19, type=int, help='Minimum edit distance to the seed [19]' ) + parser.add_argument( '-w', '--bandWidth', default=100, type=int, help='Band width for banded alignment [100]' ) + parser.add_argument( '-d', '--offDiagonal', default=100, type=int, help='off-diagonal X-dropoff [100]' ) + parser.add_argument( '-r', '--internalSeeds', default=1.5, type=float, help='look for internal seeds inside a seed longer than {-k} * FLOAT [1.5]' ) + parser.add_argument( '-c', '--seedsOccurrence', default=10000, type=int, help='skip seeds with more than INT occurrences [10000]' ) + parser.add_argument( '-S', '--mateRescue', default=False, help='skip mate rescue' ) + parser.add_argument( '-P', '--skipPairing', default=False, help='skpe pairing, mate rescue performed unless -S also in use' ) + parser.add_argument( '-A', '--seqMatch', default=1, type=int, help='score of a sequence match' ) + parser.add_argument( '-B', '--mismatch', default=4,type=int, help='penalty for a mismatch' ) + parser.add_argument( '-O', '--gapOpen', default=6, type=int, help='gap open penalty' ) + parser.add_argument( '-E', '--gapExtension', default=None, help='gap extension penalty; a gap of size k cost {-O} + {-E}*k [1]' ) + parser.add_argument( '-L', '--clipping', default=5, type=int, help='penalty for clipping [5]' ) + parser.add_argument( '-U', '--unpairedReadpair', default=17, type=int, help='penalty for an unpaired read pair [17]' ) + parser.add_argument( '-p', '--interPairEnd', default=False, help='first query file consists of interleaved paired-end sequences' ) + parser.add_argument( '--rgid', help='Read group identifier' ) + parser.add_argument( '--rgsm', help='Sample' ) + parser.add_argument( '--rgpl', choices=[ 'CAPILLARY', 'LS454', 'ILLUMINA', 'SOLID', 'HELICOS', 'IONTORRENT' and 'PACBIO' ], help='Platform/technology used to produce the reads' ) + parser.add_argument( '--rglb', help='Library name' ) + parser.add_argument( '--rgpu', help='Platform unit (e.g. flowcell-barcode.lane for Illumina or slide for SOLiD)' ) + parser.add_argument( '--rgcn', help='Sequencing center that produced the read' ) + parser.add_argument( '--rgds', help='Description' ) + parser.add_argument( '--rgdt', help='Date that run was produced (ISO8601 format date or date/time, like YYYY-MM-DD)' ) + parser.add_argument( '--rgfo', help='Flow order' ) + parser.add_argument( '--rgks', help='The array of nucleotide bases that correspond to the key sequence of each read' ) + parser.add_argument( '--rgpg', help='Programs used for processing the read group' ) + parser.add_argument( '--rgpi', help='Predicted median insert size' ) + parser.add_argument( '-T', '--minScore', default=30, type=int, help='minimum score to output [30]' ) + parser.add_argument( '-M', '--mark', default=False, help='mark shorter split hits as secondary (for Picard/GATK compatibility)' ) + args = parser.parse_args() + + + # output version # of tool + try: + tmp = tempfile.NamedTemporaryFile().name + tmp_stdout = open( tmp, 'wb' ) + proc = subprocess.Popen( args='bwa 2>&1', 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( 'BWA %s\n' % stdout ) + else: + raise Exception + except: + sys.stdout.write( 'Could not determine BWA version\n' ) + + # check for color space fastq that's not double-encoded and exit if appropriate +# if args.color_space: +# if not check_is_double_encoded( args.fastq ): +# stop_err( 'Your file must be double-encoded (it must be converted from "numbers" to "bases"). See the help section for details' ) +# if args.genAlignType == 'paired': +# if not check_is_double_encoded( args.rfastq ): +# stop_err( 'Your reverse reads file must also be double-encoded (it must be converted from "numbers" to "bases"). See the help section for details' ) + + fastq = args.fastq + if args.rfastq: + rfastq = args.rfastq + + # set color space variable +# if args.color_space: +# color_space = '-c' +# else: +# color_space = '' + + # make temp directory for placement of indices + tmp_index_dir = tempfile.mkdtemp() + tmp_dir = tempfile.mkdtemp() + # index if necessary + if args.fileSource == 'history' and not args.do_not_build_index: + ref_file = tempfile.NamedTemporaryFile( dir=tmp_index_dir ) + ref_file_name = ref_file.name + ref_file.close() + os.symlink( args.ref, ref_file_name ) + # determine which indexing algorithm to use, based on size + try: + size = os.stat( args.ref ).st_size + if size <= 2**30: + indexingAlg = 'is' + else: + indexingAlg = 'bwtsw' + except: + indexingAlg = 'is' + #indexing_cmds = '%s -a %s' % ( color_space, indexingAlg ) + indexing_cmds = '-a %s' % indexingAlg + cmd1 = 'bwa index %s %s' % ( indexing_cmds, 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 dirs + if os.path.exists( tmp_index_dir ): + shutil.rmtree( tmp_index_dir ) + if os.path.exists( tmp_dir ): + shutil.rmtree( tmp_dir ) + stop_err( 'Error indexing reference sequence. ' + str( e ) ) + else: + ref_file_name = args.ref + # if args.illumina13qual: + # illumina_quals = "-I" + # else: + # illumina_quals = "" + + # set up aligning and generate aligning command args + start_cmds = '-t %s ' % args.threads + if args.params == 'pre_set': + # aligning_cmds = '-t %s %s %s' % ( args.threads, color_space, illumina_quals ) + #start_cmds = '-t %s ' % args.threads + end_cmds = ' ' + print start_cmds, end_cmds + + else: + end_cmds = '-k %s -w %s -d %s -r %s -c %s -A %s -B %s -O %s -L %s -U %s -T %s ' % (args.minEditDistSeed, args.bandWidth, args.offDiagonal, args.internalSeeds, args.seedsOccurrence, args.seqMatch, args.mismatch, args.gapOpen, args.clipping, args.unpairedReadpair, args.minScore) + if args.mateRescue: + end_cmds += '-S ' + if args.skipPairing: + end_cmds += '-P ' + else: + if args.skipPairing: + print "Option Error and will not be considered, you should also choose 'skip mate rescue -S' option! " + if args.gapExtension != None: + end_cmds += '-E %s ' % args.gapExtension + + if args.rgid: + if not args.rglb or not args.rgpl or not args.rgsm or not args.rglb: + stop_err( 'If you want to specify read groups, you must include the ID, LB, PL, and SM tags.' ) + # readGroup = '@RG\tID:%s\tLB:%s\tPL:%s\tSM:%s' % ( args.rgid, args.rglb, args.rgpl, args.rgsm ) + readGroup = '@RG\tID:%s\tLB:%s\tPL:%s\tSM:%s' % ( args.rgid, args.rglb, args.rgpl, args.rgsm ) + if args.rgpu: + readGroup += '\tPU:%s' % args.rgpu + if args.rgcn: + readGroup += '\tCN:%s' % args.rgcn + if args.rgds: + readGroup += '\tDS:%s' % args.rgds + if args.rgdt: + readGroup += '\tDT:%s' % args.rgdt + if args.rgfo: + readGroup += '\tFO:%s' % args.rgfo + if args.rgks: + readGroup += '\tKS:%s' % args.rgks + if args.rgpg: + readGroup += '\tPG:%s' % args.rgpg + if args.rgpi: + readGroup += '\tPI:%s' % args.rgpi + end_cmds += ' -R "%s" ' % readGroup + + if args.interPairEnd: + end_cmds += '-p %s ' % args.interPairEnd + if args.mark: + end_cmds += '-M ' + + + if args.genAlignType == 'paired': + cmd = 'bwa mem %s %s %s %s %s > %s' % ( start_cmds, ref_file_name, fastq, rfastq, end_cmds, args.output ) + else: + cmd = 'bwa mem %s %s %s > %s' % ( start_cmds, ref_file_name, fastq, end_cmds, args.output ) + + # perform alignments + buffsize = 1048576 + try: + # need to nest try-except in try-finally to handle 2.4 + try: + try: + tmp = tempfile.NamedTemporaryFile( dir=tmp_dir ).name + tmp_stderr = open( tmp, 'wb' ) + print "The cmd is %s" % cmd + proc = subprocess.Popen( args=cmd, shell=True, cwd=tmp_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 = '' + 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: + raise Exception, 'Error generating alignments. ' + str( e ) + + # check that there are results in the output file + if os.path.getsize( args.output ) > 0: + sys.stdout.write( 'BWA run on %s-end data' % args.genAlignType ) + else: + raise Exception, 'The output file is empty. You may simply have no matches, or there may be an error with your input file or settings.' + except Exception, e: + stop_err( 'The alignment failed.\n' + str( e ) ) + finally: + # clean up temp dir + if os.path.exists( tmp_index_dir ): + shutil.rmtree( tmp_index_dir ) + if os.path.exists( tmp_dir ): + shutil.rmtree( tmp_dir ) + +if __name__=="__main__": __main__()
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/bwa_0_7_5/bwa_0_7_5.xml Mon Aug 12 08:44:05 2013 -0400 @@ -0,0 +1,186 @@ +<tool id="bwa_0_7_5" name="Map with BWA (Version 0.7.5)" version="0.7.5"> + <requirements> + <requirement type="package" version="0.7.5">bwa</requirement> + </requirements> + <description>This new version BWA (0.7.5) use 'mem' algorithm for mapping, dosen't need 'aln', 'samse', 'sampe' and picard AddOrReplace anymore.</description> + <parallelism method="basic"></parallelism> + <command interpreter="python"> + bwa_0_7_5.py + --threads="1" + --fileSource="${genomeSource.refGenomeSource}" + #if $genomeSource.refGenomeSource == "history": + ##build index on the fly + --ref="${genomeSource.ownFile}" + --dbkey="${dbkey}" + #else: + ##use precomputed indexes + --ref="${genomeSource.indices.fields.path}" + #end if + + ## input file(s) + --fastq="${paired.fastq}" + #if $paired.sPaired == "paired": + --rfastq="${paired.rfastq}" + #end if + + ## output file + --output="${output}" + + ## run parameters + --genAlignType="${paired.sPaired}" + --params="${params.source_select}" + #if $params.source_select != "pre_set": + --minEditDistSeed="${params.minEditDistSeed}" + --bandWidth="${params.bandWidth}" + --offDiagonal="${params.offDiagonal}" + --internalSeeds="${params.internalSeeds}" + --seedsOccurrence="${params.seedsOccurrence}" + --mateRescue="${params.mateRescue}" + --skipPairing="${params.skipPairing}" + --seqMatch="${params.seqMatch}" + --mismatch="${params.mismatch}" + --gapOpen="${params.gapOpen}" + --gapExtension="${params.gapExtension}" + --clipping="${params.clipping}" + --unpairedReadpair="${params.unpairedReadpair}" + --interPairEnd="${params.interPairEnd}" + --minScore="${params.minScore}" + --mark="${params.mark}" + + #if $params.readGroup.specReadGroup == "yes" + --rgid="${params.readGroup.rgid}" + --rgsm="${params.readGroup.rgsm}" + --rgpl="${params.readGroup.rgpl}" + --rglb="${params.readGroup.rglb}" + --rgpu="${params.readGroup.rgpu}" + --rgcn="${params.readGroup.rgcn}" + --rgds="${params.readGroup.rgds}" + --rgdt="${params.readGroup.rgdt}" + --rgfo="${params.readGroup.rgfo}" + --rgks="${params.readGroup.rgks}" + --rgpg="${params.readGroup.rgpg}" + --rgpi="${params.readGroup.rgpi}" + #end if + #end if + </command> + + <inputs> + <conditional name="genomeSource"> + <param name="refGenomeSource" type="select" label="Will you select a reference genome from your history or use a built-in index?"> + <option value="indexed">Use a built-in index</option> + <option value="history">Use one from the history</option> + </param> + <when value="indexed"> + <param name="indices" type="select" label="Select a reference genome"> + <options from_data_table="bwa_indexes"> + <filter type="sort_by" column="2" /> + <validator type="no_options" message="No indexes are available" /> + </options> + </param> + </when> + <when value="history"> + <param name="ownFile" type="data" format="fasta" metadata_name="dbkey" label="Select a reference from history" /> + </when> + </conditional> + <conditional name="paired"> + <param name="sPaired" type="select" label="Is this library mate-paired?"> + <option value="single">Single-end</option> + <option value="paired">Paired-end</option> + </param> + <when value="single"> + <param name="fastq" type="data" format="fastqsanger,fastqillumina" label="FASTQ file" help="FASTQ with either Sanger-scaled quality values (fastqsanger) or Illumina-scaled quality values (fastqillumina)" /> + </when> + <when value="paired"> + <param name="fastq" type="data" format="fastqsanger,fastqillumina" label="Forward FASTQ file" help="FASTQ with either Sanger-scaled quality values (fastqsanger) or Illumina-scaled quality values (fastqillumina)" /> + <param name="rfastq" type="data" format="fastqsanger,fastqillumina" label="Reverse FASTQ file" help="FASTQ with either Sanger-scaled quality values (fastqsanger) or Illumina-scaled quality values (fastqillumina)" /> + </when> + </conditional> + <conditional name="params"> + <param name="source_select" type="select" label="BWA settings to use" help="For most mapping needs use Commonly Used settings. If you want full control use Full Parameter List"> + <option value="pre_set">Commonly Used</option> + <option value="full">Full Parameter List</option> + </param> + <when value="pre_set" /> + <when value="full"> + <param name="minEditDistSeed" type="integer" value="19" label="Minimum seed length" /> + <param name="bandWidth" type="integer" value="100" label="Band width for banded alignment" /> + <param name="offDiagonal" type="integer" value="100" label="off-diagonal X-dropoff" /> + <param name="internalSeeds" type="float" value="1.5" label="look for internal seeds inside a seed longer than {-k} * FLOAT [1.5]" /> + <param name="seedsOccurrence" type="integer" value="10000" label="skip seeds with more than INT occurrences" /> + <param name="mateRescue" type="boolean" truevalue="True" falsevalue="False" checked="False" label="skip seeds with more than INT occurrences" /> + <param name="skipPairing" type="boolean" truevalue="True" falsevalue="False" checked="False" label="skpe pairing, mate rescue performed unless -S also in use" /> + <param name="seqMatch" type="integer" value="1" label="score of a sequence match" /> + <param name="mismatch" type="integer" value="4" label="penalty for a mismatch" /> + <param name="gapOpen" type="integer" value="6" label="gap open penalty" /> + <param name="gapExtension" type="text" value="None" label="gap extension penalty; a gap of size k cost {-O} + {-E}*k [1]" /> + <param name="clipping" type="integer" value="5" label="penalty for clipping" /> + <param name="unpairedReadpair" type="integer" value="17" label="penalty for an unpaired read pair" /> + <param name="interPairEnd" type="boolean" truevalue="True" falsevalue="False" checked="False" label="first query file consists of interleaved paired-end sequences" /> + <param name="minScore" type="integer" value="30" label="minimum score to output" /> + <param name="mark" type="boolean" truevalue="True" falsevalue="False" checked="False" label="mark shorter split hits as secondary (for Picard/GATK compatibility)" /> + + <conditional name="readGroup"> + <param name="specReadGroup" type="select" label="Specify the read group for this file? (samse/sampe -r)"> + <option value="yes">Yes</option> + <option value="no" selected="True">No</option> + </param> + <when value="yes"> + <param name="rgid" type="text" size="25" label="[Essential]Read group identifier (ID). Each @RG line must have a unique ID. The value of ID is used in the RG +tags of alignment records. Must be unique among all read groups in header section." help="Required if RG specified. Read group +IDs may be modified when merging SAM files in order to handle collisions." /> + <param name="rgpl" type="text" size="25" label="[Essential]Platform/technology used to produce the reads (PL)" help="Required if RG specified. Valid values : CAPILLARY, LS454, ILLUMINA, +SOLID, HELICOS, IONTORRENT and PACBIO" /> + <param name="rglb" type="text" size="25" label="[Essential]Library name (LB)" help="Required if RG specified" /> + <param name="rgsm" type="text" size="25" label="[Essential]Sample (SM)" help="Required if RG specified. Use pool name where a pool is being sequenced" /> + <param name="rgpu" type="text" size="25" label="Platform unit (PU)" help="Optional. Unique identifier (e.g. flowcell-barcode.lane for Illumina or slide for SOLiD)" /> + <param name="rgcn" type="text" size="25" label="Sequencing center that produced the read (CN)" help="Optional" /> + <param name="rgds" type="text" size="25" label="Description (DS)" help="Optional" /> + <param name="rgdt" type="text" size="25" label="Date that run was produced (DT)" help="Optional. ISO8601 format date or date/time, like YYYY-MM-DD" /> + <param name="rgfo" type="text" size="25" label="Flow order (FO). The array of nucleotide bases that correspond to the nucleotides used for each +flow of each read." help="Optional. Multi-base flows are encoded in IUPAC format, and non-nucleotide flows by +various other characters. Format : /\*|[ACMGRSVTWYHKDBN]+/" /> + <param name="rgks" type="text" size="25" label="The array of nucleotide bases that correspond to the key sequence of each read (KS)" help="Optional" /> + <param name="rgpg" type="text" size="25" label="Programs used for processing the read group (PG)" help="Optional" /> + <param name="rgpi" type="text" size="25" label="Predicted median insert size (PI)" help="Optional" /> + </when> + <when value="no" /> + </conditional> + </when> + </conditional> + </inputs> + + <outputs> + <data format="sam" name="output" label="${tool.name} on ${on_string}: mapped reads"> + <actions> + <conditional name="genomeSource.refGenomeSource"> + <when value="indexed"> + <action type="metadata" name="dbkey"> + <option type="from_data_table" name="bwa_indexes" column="1"> + <filter type="param_value" column="0" value="#" compare="startswith" keep="False"/> + <filter type="param_value" ref="genomeSource.indices" column="0"/> + </option> + </action> + </when> + <when value="history"> + <action type="metadata" name="dbkey"> + <option type="from_param" name="genomeSource.ownFile" param_attribute="dbkey" /> + </action> + </when> + </conditional> + </actions> + </data> + </outputs> + + <tests> + <test> + </test> + <test> + </test> + <test> + </test> + </tests> + + +</tool> + +
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/bwa_0_7_5/tool-data/bwa_index.loc Mon Aug 12 08:44:05 2013 -0400 @@ -0,0 +1,38 @@ +#This is a sample file distributed with Galaxy that enables tools +#to use a directory of BWA indexed sequences data files. You will need +#to create these data files and then create a bwa_index.loc file +#similar to this one (store it in this directory) that points to +#the directories in which those files are stored. The bwa_index.loc +#file has this format (longer white space characters are TAB characters): +# +#<unique_build_id> <dbkey> <display_name> <file_path> +# +#So, for example, if you had phiX indexed stored in +#/depot/data2/galaxy/phiX/base/, +#then the bwa_index.loc entry would look like this: +# +#phiX174 phiX phiX Pretty /depot/data2/galaxy/phiX/base/phiX.fa +# +#and your /depot/data2/galaxy/phiX/base/ directory +#would contain phiX.fa.* files: +# +#-rw-r--r-- 1 james universe 830134 2005-09-13 10:12 phiX.fa.amb +#-rw-r--r-- 1 james universe 527388 2005-09-13 10:12 phiX.fa.ann +#-rw-r--r-- 1 james universe 269808 2005-09-13 10:12 phiX.fa.bwt +#...etc... +# +#Your bwa_index.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: +# +#phiX174 phiX phiX174 /depot/data2/galaxy/phiX/base/phiX.fa +#hg18canon hg18 hg18 Canonical /depot/data2/galaxy/hg18/base/hg18canon.fa +#hg18full hg18 hg18 Full /depot/data2/galaxy/hg18/base/hg18full.fa +#/orig/path/hg19.fa hg19 hg19 /depot/data2/galaxy/hg19/base/hg19.fa +#...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. +#