Mercurial > repos > jjohnson > gmap
changeset 4:f49f5a460c74
GSNAP - add and refine param options for gmap v 2011-10-16
author | Jim Johnson <jj@umn.edu> |
---|---|
date | Tue, 08 Nov 2011 13:02:32 -0600 |
parents | 72ab00e732c3 |
children | f4b4c1712e39 |
files | gmap/gmap_indices.loc.sample gmap/gsnap.xml tool-data/gmap_indices.loc.sample |
diffstat | 3 files changed, 247 insertions(+), 71 deletions(-) [+] |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/gmap/gmap_indices.loc.sample Tue Nov 08 13:02:32 2011 -0600 @@ -0,0 +1,10 @@ +#This is a sample file distributed with Galaxy that enables tools +#to use a directory of GMAPDB indexed sequences data files. You will need +#to create these data files using gmap_build and then create a gmap_indices.loc file +#similar to this one (store it in this directory) that points to +#the directories in which those files are stored. The gmap_indices.loc +#file has this format (white space characters are TAB characters): +# +#<unique_build_id> <dbkey> <display_name> <kmers> <map,map> <snp,snp> <file_base_path> +#hg18 hg18 hg18 (cmet atoi) 12,13,14,15 splicesites,introns snps /depot/data2/galaxy/gmap/hg18 +#hg19 hg19 hg19 (cmet atoi) 12,13,14,15 splicesites,introns,snps snps,dbsnp /depot/data2/galaxy/gmap/hg19
--- a/gmap/gsnap.xml Fri Oct 21 12:11:45 2011 -0500 +++ b/gmap/gsnap.xml Tue Nov 08 13:02:32 2011 -0600 @@ -40,8 +40,11 @@ -V $refGenomeSource.use_snps.snpindex.extra_files_path -v $refGenomeSource.use_snps.snpindex.metadata.snps_name #end if #end if - #if $mode.__str__ != '': - --mode=$mode + #if $refGenomeSource.mode.__str__ != '': + --mode=$refGenomeSource.mode + #end if + #if $mapq_unique_score.__str__ != '': + --mapq-unique-score=$mapq_unique_score #end if #if $computation.options == "advanced": #if $computation.max_mismatches.__str__ != '': @@ -76,6 +79,16 @@ #if $computation.adapter_strip.__str__ != '': --adapter-strip=$computation.adapter_strip #end if + #if $computation.trim_mismatch_score.__str__ != '': + --trim-mismatch-score=$computation.trim_mismatch_score + #end if + ## TODO - do we need these options (Is it tally XOR runlength?): + ## --tallydir= --use-tally=tally + ## --runlengthdir --use-runlength=runlength + #if $computation.use_tally != None and len($computation.use_tally.__str__) > 0: + ##--tallydir $os.path.dirname($computation.use_tally) --use-tally $os.path.basename($computation.use_tally) + --use-tally=$computation.use_tally + #end if ## gmap options #if $computation.gmap_mode.__str__ != '' and $computation.gmap_mode.__str__ != 'None': --gmap-mode='$computation.gmap_mode' @@ -155,9 +168,22 @@ #end if $result.creads_complement #end if - ## TODO - do we need these options (Is it tally XOR runlength?): - ## --tallydir= --use-tally=tally - ## --runlengthdir --use-runlength=runlength + #if $results.split_output == 'yes': + --split-output=gsnap_out + #if $results.fails.choice == 'nofails': + --nofails + #elif $results.fails.choice == 'failsonly': + --failsonly + #end if + $results.fails_as_input + #else + #if $results.fails.choice == 'nofails': + --nofails + #elif $results.fails.choice == 'failsonly': + --failsonly + $results.fails.fails_as_input + #end if + #end if #if $seq.format == "gsnap_fasta": $seq.circularinput $seq.gsnap #else if $seq.format == "fastq": @@ -173,7 +199,7 @@ #if $seq.filter_chastity.__str__ != 'off': --filter-chastity=$seq.filter_chastity #end if - #if $seq.paired.ispaired.__str__ == "yes": + #if $seq.paired.ispaired.__str__ == 'yes': #if $seq.paired.pairmax_dna.__str__ != '': --pairmax-dna=$seq.paired.pairmax_dna #end if @@ -185,10 +211,14 @@ $seq.fastq #end if #end if - #if $split_output == True + #if $results.split_output == 'yes': 2> $gsnap_stderr - #else - 2> $gsnap_stderr > $results + #else: + #if $results.fails.choice.__str__ == 'failsonly' and $results.fails.fails_as_input.__str__ != '': + 2> $gsnap_stderr > $gsnap_fq + #else + 2> $gsnap_stderr > $gsnap_out + #end if #end if </command> @@ -197,12 +227,15 @@ <conditional name="seq"> <param name="format" type="select" label="<H2>Input Sequences</H2>Select the input format" help=""> <option value="fastq">Fastq</option> + <!-- + <option value="goby">Goby compact-reads</option> + --> <option value="gsnap_fasta">GNSAP fasta</option> </param> <when value="fastq"> <param name="fastq" type="data" format="fastq" label="Select a fastq dataset" /> <conditional name="paired"> - <param name="ispaired" type="boolean" truevalue="yes" falsevalue="no" checked="false" label="Paired Reads"/> + <param name="ispaired" type="boolean" truevalue="yes" falsevalue="no" checked="false" label="Use Paired Reads?"/> <when value="no"/> <when value="yes"> <param name="fastq" type="data" format="fastq" label="Select the paired reads reverse dataset" /> @@ -216,8 +249,8 @@ </when> </conditional> <param name="barcode_length" type="integer" value="" optional="true" label="Amount of barcode to remove from start of read (default 0)" /> - <param name="fastq_id_start" type="integer" value="" optional="true" label="Starting field of identifier in FASTQ header, space-delimited, starting from 1" /> - <param name="fastq_id_end" type="integer" value="" optional="true" label="Ending field of identifier in FASTQ header, space-delimited, starting from 1" + <param name="fastq_id_start" type="integer" value="" optional="true" label="Starting field of identifier in FASTQ header, whitespace-delimited, starting from 1" /> + <param name="fastq_id_end" type="integer" value="" optional="true" label="Ending field of identifier in FASTQ header, whitespace-delimited, starting from 1" help="Examples: <br>@HWUSI-EAS100R:6:73:941:1973#0/1 <br> . start=1, end=1 (default) => identifier is HWUSI-EAS100R:6:73:941:1973#0/1 @@ -238,19 +271,19 @@ <option value="both">both - a 'Y' is required on both ends of a paired-end read or the only end of a single-end read</option> </param> </when> + <!-- + <when value="goby"> + </when> + --> <when value="gsnap_fasta"> <param name="gsnap" type="data" format="fasta" label="Select a single-end dataset" help="GSNAP fasta must have the sequence entirely on one line, a second line is interpreted as the paired-end sequence"/> <param name="circularinput" type="boolean" checked="false" truevalue="--circular-input=true" falsevalue="" label="Circular-end data (paired reads are on same strand)"/> </when> + </conditional> - - <param name="mode" type="select" label="Alignment mode" help="Assumes cmetindex and atoiindex were run on the gmap datatbase."> - <option value="">standard</option> - <option value="cmet-stranded">cmet-stranded for bisulfite-treated DNA reads (tolerance to C-to-T changes)</option> - <option value="cmet-nonstranded">cmet-nonstranded for bisulfite-treated DNA reads (tolerance to C-to-T changes)</option> - <option value="atoi-stranded">atoi-stranded for RNA-editing tolerance (A-to-G changes)</option> - <option value="atoi-nonstranded">atoi-nonstranded for RNA-editing tolerance (A-to-G changes)</option> - </param> + <param name="mapq_unique_score" type="integer" value="" optional="true" label="MAPQ score threshold" + help="For multiple results, consider as a unique result if only one of the results has a MAPQ score equal or greater than this + (if not selected, then reports all multiple results, up to npaths)" /> <!-- GMAPDB for alignment --> <conditional name="refGenomeSource"> @@ -282,8 +315,16 @@ </options> </param> + <param name="mode" type="select" label="Alignment mode" help="Assumes cmetindex and atoiindex were run on the gmap datatbase."> + <option value="">standard</option> + <option value="cmet-stranded">cmet-stranded for bisulfite-treated DNA reads (tolerance to C-to-T changes)</option> + <option value="cmet-nonstranded">cmet-nonstranded for bisulfite-treated DNA reads (tolerance to C-to-T changes)</option> + <option value="atoi-stranded">atoi-stranded for RNA-editing tolerance (A-to-G changes)</option> + <option value="atoi-nonstranded">atoi-nonstranded for RNA-editing tolerance (A-to-G changes)</option> + </param> + <conditional name="use_splicing"> - <param name="src" type="select" label="Known Splicesite and Introns" + <param name="src" type="select" label="<HR>Known Splicesite and Introns" help="Look for splicing involving known sites or known introns at short or long distances See README instructions for the distinction between known sites and known introns"> <option value="none" selected="true">None</option> @@ -310,7 +351,7 @@ </conditional> <conditional name="use_snps"> - <param name="src" type="select" label="Known SNPs" help="for SNP tolerant alignments"> + <param name="src" type="select" label="<HR>Known SNPs" help="for SNP tolerant alignments"> <option value="none" selected="true">None</option> <option value="gmapdb">From the GMAP Database</option> <option value="history">A SNP Index in your history</option> @@ -344,8 +385,16 @@ </options> </param> + <param name="mode" type="select" label="Alignment mode" help="Assumes cmetindex and atoiindex were run on the gmap datatbase."> + <option value="">standard</option> + <option value="cmet-stranded">cmet-stranded for bisulfite-treated DNA reads (tolerance to C-to-T changes)</option> + <option value="cmet-nonstranded">cmet-nonstranded for bisulfite-treated DNA reads (tolerance to C-to-T changes)</option> + <option value="atoi-stranded">atoi-stranded for RNA-editing tolerance (A-to-G changes)</option> + <option value="atoi-nonstranded">atoi-nonstranded for RNA-editing tolerance (A-to-G changes)</option> + </param> + <conditional name="use_splicing"> - <param name="src" type="select" label="Known Splicesite and Introns" + <param name="src" type="select" label="<HR>Known Splicesite and Introns" help="Look for splicing involving known sites or known introns at short or long distances See README instructions for the distinction between known sites and known introns"> <option value="none" selected="true">None</option> @@ -367,7 +416,7 @@ </conditional> <conditional name="use_snps"> - <param name="src" type="select" label="Known SNPs" help="for SNP tolerant alignments"> + <param name="src" type="select" label="<HR>Known SNPs" help="for SNP tolerant alignments"> <option value="none" selected="true">None</option> <option value="gmapdb">From the GMAP Database</option> <option value="history">A SNP Index in your history</option> @@ -426,12 +475,26 @@ </param> <param name="trim_mismatch_score" type="integer" value="" optional="true" label="Score to use for mismatches when trimming at ends (default is -3)" help="to turn off trimming, specify 0"/> + <param name="use_tally" type="data" format="tally.iit" optional="true" metadata_name="dbkey" label="Select a tally IIT file to resolve concordant multiple results" + help="generated by gsnap_tally and iit_store"/> + + <!-- + tallydir=STRING Directory for tally IIT file to resolve concordant multiple results (default is + location of genome index files specified using -D and -d). Note: can + just give full path name to use-tally instead. + use-tally=STRING Use this tally IIT file to resolve concordant multiple results + runlengthdir=STRING Directory for runlength IIT file to resolve concordant multiple results (default is + location of genome index files specified using -D and -d). Note: can + just give full path name to use-runlength instead. + use-runlength=STRING Use this runlength IIT file to resolve concordant multiple results + --> <!-- Options for GMAP alignment within GSNAP --> - <param name="gmap_mode" type="select" multiple="true" optional="true" label="Cases to use GMAP for complex alignments containing multiple splices or indels" help=""> - <option value="pairsearch">pairsearch</option> - <option value="terminal">terminal</option> - <option value="improve">improve</option> + <param name="gmap_mode" type="select" multiple="true" optional="true" display="checkboxes" label="Cases to use GMAP for complex alignments containing multiple splices or indels" + help="Default: pairsearch,terminal,improve"> + <option value="pairsearch" selected="true">pairsearch</option> + <option value="terminal" selected="true">terminal</option> + <option value="improve" selected="true">improve</option> </param> <param name="trigger_score_for_gmap" type="integer" value="" optional="true" label="GMAP pairsearch threshold (default 5)" help="Try GMAP pairsearch on nearby genomic regions if best score (the total of both ends if paired-end) exceeds this value (default 5)" /> @@ -456,16 +519,22 @@ <when value="default"/> <when value="advanced"> <!-- Splicing options for RNA-Seq --> - <!-- use-splices This should be either a select list from the gmapdb maps or a data type using splicesdir and use-splices --> + <!-- use-splicing This should be either a select list from the gmapdb maps or a data type using splicesdir and use-splicing --> <!-- Neither novel splicing (-N) nor known splicing (-s) turned on => assume reads are DNA-Seq (genomic) --> <param name="novelsplicing" type="boolean" checked="false" truevalue="--novelsplicing=1" falsevalue="" label="Look for novel splicing "/> <param name="localsplicedist" type="integer" value="" optional="true" label="Definition of local novel splicing event (default 200000)"/> <param name="local_splice_penalty" type="integer" value="" optional="true" label="Penalty for a local splice (default 0). Counts against mismatches allowed"/> - <param name="distant_splice_penalty" type="integer" value="" optional="true" label="Penalty for a distant splice (default 3). Counts against mismatches allowed"/> - <param name="local_splice_endlength" type="integer" value="" optional="true" label="Minimum length at end required for local spliced alignments (default 15, min is 14)"/> - <param name="distant_splice_endlength" type="integer" value="" optional="true" label="Minimum length at end required for distant spliced alignments (default 16, min is 14)"/> - <param name="shortend_splice_endlength" type="integer" value="" optional="true" label="Minimum length at end required for distant spliced alignments (default 16, min is 14)"/> + <param name="distant_splice_penalty" type="integer" value="" optional="true" label="Penalty for a distant splice (default 3). Counts against mismatches allowed" + help="A distant splice is one where the intron length exceeds the value of localsplicedist or is an + inversion, scramble, or translocation between two different chromosomes. Counts against mismatches allowed"/> + <param name="distant_splice_endlength" type="integer" value="" optional="true" label="Minimum length at end required for distant spliced alignments" + help="(default 16, min is the kmer length)"/> + <param name="shortend_splice_endlength" type="integer" value="" optional="true" label="Minimum length at end required for short-end spliced alignments" + help="(default 2, but unless known splice sites are provided, GSNAP may still need the end length to be the value of kmer size to find a given splice"/> <param name="distant_splice_identity" type="float" value="" optional="true" label="Minimum identity at end required for distant spliced alignments (default 0.95)"/> + <param name="antistranded_penalty" type="integer" value="" optional="true" label="Penalty for antistranded splicing when using stranded RNA-Seq protocols" + help="A positive value, such as 1, expects antisense on the first read and sense on the second read. + Default is 0, which treats sense and antisense equally well"/> </when> </conditional> @@ -489,10 +558,13 @@ <conditional name="result"> <param name="format" type="select" label="Select the output format" help=""> <option value="sam">SAM</option> + <!-- goby should only be an option if the input is in goby format <option value="goby">Goby</option> + --> <option value="gsnap">GSNAP default output</option> </param> - <when value="gsnap"/> + <when value="gsnap"> + </when> <when value="sam"> <param name="no_sam_headers" type="boolean" truevalue="--no-sam-headers" falsevalue="" checked="false" label="Do not print headers beginning with '@'"/> <param name="read_group_id" type="text" value="" optional="true" label="Value to put into read-group id (RG-ID) field"/> @@ -501,80 +573,184 @@ <param name="read_group_platform" type="text" value="" optional="true" label="Value to put into read-group library platform (RG-PL) field"/> <param name="quality_shift" type="integer" value="" optional="true" label="Shift FASTQ quality scores by this amount in SAM output (default -31)"/> </when> + <!-- <when value="goby"> <param name="goby_output" type="text" value="" label="Basename for Goby output files"/> <param name="creads_window_start" type="integer" value="" optional="true" label="Compact reads window start (default: 0=start of file)"/> <param name="creads_window_end" type="integer" value="" optional="true" label="Compact reads window end (default: 0=end of file)"/> - <param name="creads_complement" type="boolean" truevalue="--creads-complement" falsevalue="" checked="false" label="Complement read sequences (without reversing)"/> + <param name="creads_complement" type="boolean" truevalue="-\-creads-complement" falsevalue="" checked="false" label="Complement read sequences (without reversing)"/> + </when> + --> + </conditional> + <!-- TODO combine fails and split_output --> + + <conditional name="results"> + <param name="split_output" type="select" label="<HR>Split outputs" + help="Separate outputs for: nomapping, halfmapping_uniq, halfmapping_mult, unpaired_uniq, unpaired_mult, paired_uniq, paired_mult, concordant_uniq, and concordant_mult results"> + <option value="no">no</option> + <option value="yes">yes</option> + </param> + <when value="no"> + <conditional name="fails"> + <param name="choice" type="select" label="How to deal with fails" help=""> + <option value="default">default - include them in results</option> + <option value="nofails">nofails - exclude fails from results</option> + <option value="failsonly">failsonly - only output failing results</option> + </param> + <when value="default"/> + <when value="nofails"/> + <when value="failsonly"> + <param name="fails_as_input" type="boolean" truevalue="--fails-as-input" falsevalue="" checked="false" label="Print completely failed alignments as input FASTA or FASTQ format" + help=""/> + </when> + </conditional> + </when> + <when value="yes"> + <conditional name="fails"> + <param name="choice" type="select" label="How to deal with fails" help=""> + <option value="default">default - include them in results</option> + <option value="nofails">nofails - exclude fails from results</option> + <option value="failsonly">failsonly - only output failing results</option> + </param> + <when value="default"/> + <when value="nofails"/> + <when value="failsonly"/> + </conditional> + <param name="fails_as_input" type="boolean" truevalue="--fails-as-input" falsevalue="" checked="false" label="Print completely failed alignments as input FASTA or FASTQ format" + help=""/> </when> </conditional> - <param name="split_output" type="boolean" truevalue="--split-output=gsnap_out" falsevalue="" checked="false" label="Separate outputs" - help="Separate outputs for: nomapping, halfmapping_uniq, halfmapping_mult, unpaired_uniq, unpaired_mult, paired_uniq, paired_mult, concordant_uniq, and concordant_mult results"/> + </inputs> <outputs> - <data format="txt" name="gsnap_stderr" label="${tool.name} on ${on_string}: stderr"/> - <data format="txt" name="results" label="${tool.name} on ${on_string} ${result.format}" > - <filter>(split_output == False)</filter> + <data format="txt" name="gsnap_stderr" label="${tool.name} on ${on_string}: gsnap.log"/> + + <data format="txt" name="gsnap_out" label="${tool.name} on ${on_string} ${result.format}" > + <filter>(results['split_output'] == 'no' and (results['fails']['choice'] != 'failsonly' or results['fails']['fails_as_input'] == False))</filter> <change_format> <when input="result['format']" value="sam" format="sam"/> + <when input="result['format']" value="gsnap" format="gsnap"/> </change_format> </data> + + <data format="fastq" name="gsnap_fq" label="${tool.name} on ${on_string} fails.fq" > + <filter>(results['split_output'] == 'no' and results['fails']['choice'] == 'failsonly' and results['fails']['fails_as_input'] == True)</filter> + </data> + <!-- nomapping, halfmapping_uniq, halfmapping_mult, unpaired_uniq, unpaired_mult, paired_uniq, paired_mult, concordant_uniq, concordant_mult --> - <data format="txt" name="concordant_mult" label="${tool.name} on ${on_string} uniq.${result.format}" from_work_dir="gsnap_out.concordant_mult"> - <filter>(split_output == True)</filter> + + <data format="txt" name="unpaired_mult" label="${tool.name} on ${on_string} unpaired_mult.${result.format}" from_work_dir="gsnap_out.unpaired_mult"> + <filter>(results['split_output'] == 'yes')</filter> <change_format> <when input="result['format']" value="sam" format="sam"/> + <when input="result['format']" value="gsnap" format="gsnap"/> </change_format> </data> - <data format="txt" name="concordant_uniq" label="${tool.name} on ${on_string} uniq.${result.format}" from_work_dir="gsnap_out.concordant_uniq"> - <filter>(split_output == True)</filter> + <data format="txt" name="unpaired_uniq" label="${tool.name} on ${on_string} unpaired_uniq.${result.format}" from_work_dir="gsnap_out.unpaired_uniq"> + <filter>(results['split_output'] == 'yes')</filter> <change_format> <when input="result['format']" value="sam" format="sam"/> + <when input="result['format']" value="gsnap" format="gsnap"/> </change_format> </data> - <data format="txt" name="paired_mult" label="${tool.name} on ${on_string} uniq.${result.format}" from_work_dir="gsnap_out.paired_mult"> - <filter>(split_output == True)</filter> + <data format="txt" name="unpaired_transloc" label="${tool.name} on ${on_string} unpaired_transloc.${result.format}" from_work_dir="gsnap_out.unpaired_transloc"> + <filter>(results['split_output'] == 'yes')</filter> <change_format> <when input="result['format']" value="sam" format="sam"/> + <when input="result['format']" value="gsnap" format="gsnap"/> </change_format> </data> - <data format="txt" name="paired_uniq" label="${tool.name} on ${on_string} uniq.${result.format}" from_work_dir="gsnap_out.paired_uniq"> - <filter>(split_output == True)</filter> + <data format="txt" name="halfmapping_mult" label="${tool.name} on ${on_string} halfmapping_mult.${result.format}" from_work_dir="gsnap_out.halfmapping_mult"> + <filter>(results['split_output'] == 'yes' and seq['format'] == 'fastq' and seq['paired']['ispaired'] == True)</filter> <change_format> <when input="result['format']" value="sam" format="sam"/> + <when input="result['format']" value="gsnap" format="gsnap"/> + </change_format> + </data> + <data format="txt" name="halfmapping_uniq" label="${tool.name} on ${on_string} halfmapping_uniq.${result.format}" from_work_dir="gsnap_out.halfmapping_uniq"> + <filter>(results['split_output'] == 'yes' and seq['format'] == 'fastq' and seq['paired']['ispaired'] == True)</filter> + <change_format> + <when input="result['format']" value="sam" format="sam"/> + <when input="result['format']" value="gsnap" format="gsnap"/> </change_format> </data> - <data format="txt" name="unpaired_mult" label="${tool.name} on ${on_string} uniq.${result.format}" from_work_dir="gsnap_out.unpaired_mult"> - <filter>(split_output == True)</filter> + <data format="txt" name="halfmapping_transloc" label="${tool.name} on ${on_string} halfmapping_transloc.${result.format}" from_work_dir="gsnap_out.halfmapping_transloc"> + <filter>(results['split_output'] == 'yes' and seq['format'] == 'fastq' and seq['paired']['ispaired'] == True)</filter> + <change_format> + <when input="result['format']" value="sam" format="sam"/> + <when input="result['format']" value="gsnap" format="gsnap"/> + </change_format> + </data> + <data format="txt" name="paired_mult" label="${tool.name} on ${on_string} paired_mult.${result.format}" from_work_dir="gsnap_out.paired_mult"> + <filter>(results['split_output'] == 'yes' and seq['format'] == 'fastq' and seq['paired']['ispaired'] == True)</filter> <change_format> <when input="result['format']" value="sam" format="sam"/> + <when input="result['format']" value="gsnap" format="gsnap"/> </change_format> </data> - <data format="txt" name="unpaired_uniq" label="${tool.name} on ${on_string} uniq.${result.format}" from_work_dir="gsnap_out.unpaired_uniq"> - <filter>(split_output == True)</filter> + <data format="txt" name="paired_uniq" label="${tool.name} on ${on_string} paired_uniq.${result.format}" from_work_dir="gsnap_out.paired_uniq"> + <filter>(results['split_output'] == 'yes' and seq['format'] == 'fastq' and seq['paired']['ispaired'] == True)</filter> <change_format> <when input="result['format']" value="sam" format="sam"/> + <when input="result['format']" value="gsnap" format="gsnap"/> + </change_format> + </data> + <data format="txt" name="paired_transloc" label="${tool.name} on ${on_string} paired_transloc.${result.format}" from_work_dir="gsnap_out.paired_transloc"> + <filter>(results['split_output'] == 'yes' and seq['format'] == 'fastq' and seq['paired']['ispaired'] == True)</filter> + <change_format> + <when input="result['format']" value="sam" format="sam"/> + <when input="result['format']" value="gsnap" format="gsnap"/> </change_format> </data> - <data format="txt" name="halfmapping_mult" label="${tool.name} on ${on_string} uniq.${result.format}" from_work_dir="gsnap_out.halfmapping_mult"> - <filter>(split_output == True)</filter> + + <data format="txt" name="concordant_mult" label="${tool.name} on ${on_string} concordant_mult.${result.format}" from_work_dir="gsnap_out.concordant_mult"> + <filter>(results['split_output'] == 'yes' and seq['format'] == 'fastq' and seq['paired']['ispaired'] == True)</filter> <change_format> <when input="result['format']" value="sam" format="sam"/> + <when input="result['format']" value="gsnap" format="gsnap"/> + </change_format> + </data> + <data format="txt" name="concordant_uniq" label="${tool.name} on ${on_string} concordant_uniq.${result.format}" from_work_dir="gsnap_out.concordant_uniq"> + <filter>(results['split_output'] == 'yes' and seq['format'] == 'fastq' and seq['paired']['ispaired'] == True)</filter> + <change_format> + <when input="result['format']" value="sam" format="sam"/> + <when input="result['format']" value="gsnap" format="gsnap"/> + </change_format> + </data> + <data format="txt" name="concordant_transloc" label="${tool.name} on ${on_string} concordant_transloc.${result.format}" from_work_dir="gsnap_out.concordant_transloc"> + <filter>(results['split_output'] == 'yes' and seq['format'] == 'fastq' and seq['paired']['ispaired'] == True)</filter> + <change_format> + <when input="result['format']" value="sam" format="sam"/> + <when input="result['format']" value="gsnap" format="gsnap"/> </change_format> </data> - <data format="txt" name="halfmapping_uniq" label="${tool.name} on ${on_string} uniq.${result.format}" from_work_dir="gsnap_out.halfmapping_uniq"> - <filter>(split_output == True)</filter> + + <data format="txt" name="nomapping" label="${tool.name} on ${on_string} nomapping.${result.format}" from_work_dir="gsnap_out.nomapping"> + <filter>(results['split_output'] == 'yes' and results['fails_as_input'] == False)</filter> <change_format> <when input="result['format']" value="sam" format="sam"/> + <when input="result['format']" value="gsnap" format="gsnap"/> </change_format> </data> - <data format="txt" name="nomapping" label="${tool.name} on ${on_string} uniq.${result.format}" from_work_dir="gsnap_out.nomapping"> - <filter>(split_output == True)</filter> - <change_format> - <when input="result['format']" value="sam" format="sam"/> - </change_format> + + <data format="fastq" name="nomapping_fq" label="${tool.name} on ${on_string} nomapping.fq" from_work_dir="gsnap_out.nomapping.fq"> + <filter>(results['split_output'] == 'yes' and seq['format'] == 'fastq' and seq['paired']['ispaired'] == False)</filter> + </data> + + <data format="fastq" name="nomapping_1_fq" label="${tool.name} on ${on_string} nomapping.1.fq" from_work_dir="gsnap_out.nomapping.1.fq"> + <filter>(results['split_output'] == 'yes' and seq['format'] == 'fastq' and seq['paired']['ispaired'] == True)</filter> </data> + <data format="fastq" name="nomapping_2_fq" label="${tool.name} on ${on_string} nomapping.2.fq" from_work_dir="gsnap_out.nomapping.2.fq"> + <filter>(results['split_output'] == 'yes' and seq['format'] == 'fastq' and seq['paired']['ispaired'] == True)</filter> + </data> + + <!-- Will problay need wrapper code to generate composite datatype for goby alignment + <data format="gobyalignment" name="goby_alignment" label="${tool.name} on ${on_string} uniq.${result.format}" from_work_dir="gsnap_out.nomapping"> + <filter>result['format'] == 'goby'</filter> + </data> + --> + </outputs> <tests> </tests>
--- a/tool-data/gmap_indices.loc.sample Fri Oct 21 12:11:45 2011 -0500 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,10 +0,0 @@ -#This is a sample file distributed with Galaxy that enables tools -#to use a directory of GMAPDB indexed sequences data files. You will need -#to create these data files using gmap_build and then create a gmap_indices.loc file -#similar to this one (store it in this directory) that points to -#the directories in which those files are stored. The gmap_indices.loc -#file has this format (white space characters are TAB characters): -# -#<unique_build_id> <dbkey> <display_name> <kmers> <map,map> <snp,snp> <file_base_path> -#hg18 hg18 hg18 (cmet atoi) 12,13,14,15 splicesites,introns snps /depot/data2/galaxy/gmap/hg18 -#hg19 hg19 hg19 (cmet atoi) 12,13,14,15 splicesites,introns,snps snps,dbsnp /depot/data2/galaxy/gmap/hg19