Mercurial > repos > jjohnson > gmap
diff gmap/gsnap.xml @ 2:52da588232b0
Add datatypes for maps and snpindex, add iit_store and snpindex tools, update GMAP and GSNAP to use these.
| author | Jim Johnson <jj@umn.edu> |
|---|---|
| date | Fri, 21 Oct 2011 11:38:55 -0500 |
| parents | d58d272914e7 |
| children | f49f5a460c74 |
line wrap: on
line diff
--- a/gmap/gsnap.xml Tue Oct 18 11:51:15 2011 -0500 +++ b/gmap/gsnap.xml Fri Oct 21 11:38:55 2011 -0500 @@ -2,31 +2,43 @@ <description>Genomic Short-read Nucleotide Alignment Program</description> <requirements> <requirement type="binary">gsnap</requirement> + <!-- proposed tag for added datatype dependencies --> + <requirement type="datatype">gmapdb</requirement> + <requirement type="datatype">gmapsnpindex</requirement> + <requirement type="datatype">splicesites.iit</requirement> + <requirement type="datatype">introns.iit</requirement> </requirements> <version_string>gsnap --version</version_string> <command> #import os.path, re gsnap --nthreads="4" --ordered - #if $refGenomeSource.genomeSource == "history": - --gseg=$refGenomeSource.ownFile - #elif $refGenomeSource.genomeSource == "gmapdb": + #if $refGenomeSource.genomeSource == "gmapdb": #set $gmapdb = $os.listdir($refGenomeSource.gmapdb.extra_files_path)[0] - --dir=$refGenomeSource.gmapdb.extra_files_path --db=$gmapdb - #if $refGenomeSource.kmer != None and len($refGenomeSource.kmer.__str__) == 2: - --kmer=$refGenomeSource.kmer - #end if - #if $refGenomeSource.splicemap != None and len($refGenomeSource.splicemap.__str__) == 2: - --use-splices=$refGenomeSource.splicemap - #end if - #if $refGenomeSource.snpindex != None and len($refGenomeSource.snpindex.__str__) == 2: - --use-snps=$refGenomeSource.snpindex - #end if + --dir=$refGenomeSource.gmapdb.extra_files_path --db=$refGenomeSource.gmapdb.metadata.db_name #else: --dir=$os.path.dirname($refGenomeSource.gmapindex.value) --db=$os.path.basename($refGenomeSource.gmapindex.value) - #if $refGenomeSource.kmer != None and len($refGenomeSource.kmer.__str__) == 2: - --kmer=$refGenomeSource.kmer + #end if + #if $refGenomeSource.kmer != None and len($refGenomeSource.kmer.__str__) == 2: + --kmer=$refGenomeSource.kmer + #end if + #if $refGenomeSource.use_splicing.src == 'gmapdb': + #if $refGenomeSource.use_splicing.splicemap != None and len($refGenomeSource.use_splicing.splicemap.__str__) > 0: + -s $refGenomeSource.use_splicing.splicemap.value #end if + #elif $refGenomeSource.use_splicing.src == 'history': + #if $refGenomeSource.use_splicing.splicemap != None and len($refGenomeSource.use_splicing.splicemap.__str__) > 0: + -S $os.path.dirname($refGenomeSource.use_splicing.splicemap) -s $os.path.basename($refGenomeSource.use_splicing.splicemap) + #end if + #end if + #if $refGenomeSource.use_snps.src == 'gmapdb': + #if $refGenomeSource.use_snps.snpindex != None and len($refGenomeSource.use_snps.snpindex.__str__) > 0: + -v $refGenomeSource.use_snps.snpindex.value + #end if + #elif $refGenomeSource.use_snps.src == 'history': + #if $refGenomeSource.use_snps.snpindex != None and len($refGenomeSource.use_snps.snpindex.__str__) > 0: + -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 @@ -181,86 +193,9 @@ </command> <inputs> - <conditional name="refGenomeSource"> - <param name="genomeSource" type="select" label="Will you select a reference genome from your history or use a built-in index?" help="Built-ins were indexed using default options"> - <option value="indexed">Use a built-in index</option> - <option value="gmapdb">Use gmapdb from the history</option> - <option value="history">Use one from the history</option> - </param> - <when value="indexed"> - <param name="gmapindex" type="select" label="Select a reference genome" help="if your genome of interest is not listed - contact Galaxy team"> - <options from_file="gmap_indices.loc"> - <column name="uid" index="0" /> - <column name="dbkey" index="1" /> - <column name="name" index="2" /> - <column name="kmers" index="3" /> - <column name="maps" index="4" /> - <column name="snps" index="5" /> - <column name="value" index="6" /> - </options> - </param> - - <param name="kmer" type="select" data_ref="gmapindex" label="kmer size" help="Defaults to highest available kmer size"> - <options from_file="gmap_indices.loc"> - <column name="name" index="3"/> - <column name="value" index="3"/> - <filter type="param_value" ref="gmapindex" column="6"/> - <filter type="multiple_splitter" column="3" separator=","/> - <filter type="add_value" name="" value=""/> - <filter type="sort_by" column="3"/> - </options> - </param> - - <param name="splicemap" type="select" data_ref="gmapindex" label="Use map for splicing involving known sites or known introns" help=""> - <options from_file="gmap_indices.loc"> - <column name="name" index="4"/> - <column name="value" index="4"/> - <filter type="param_value" ref="gmapindex" column="6"/> - <filter type="multiple_splitter" column="4" separator=","/> - <filter type="add_value" name="" value=""/> - <filter type="sort_by" column="4"/> - </options> - </param> - - <param name="snpindex" type="select" data_ref="gmapindex" label="Use database containing known SNPs" help=""> - <options from_file="gmap_indices.loc"> - <column name="name" index="5"/> - <column name="value" index="5"/> - <filter type="param_value" ref="gmapindex" column="6"/> - <filter type="multiple_splitter" column="5" separator=","/> - <filter type="add_value" name="" value=""/> - <filter type="sort_by" column="5"/> - </options> - </param> - </when> - <when value="gmapdb"> - <param name="gmapdb" type="data" format="gmapdb" metadata_name="dbkey" label="Select a gmapdb" - help="A GMAP database built with GMAP Build"/> - <param name="kmer" type="select" data_ref="gmapdb" label="kmer size" help="Defaults to highest available kmer size"> - <options> - <filter type="data_meta" ref="gmapdb" key="kmers" multiple="True" separator=","/> - </options> - </param> - <param name="splicemap" type="select" data_ref="gmapdb" label="Use map for splicing involving known sites or known introns" help=""> - <options> - <filter type="data_meta" ref="gmapdb" key="maps" multiple="True"/> - </options> - </param> - <param name="snpindex" type="select" data_ref="gmapdb" label="Use database containing known SNPs" help=""> - <options> - <filter type="data_meta" ref="gmapdb" key="snps" multiple="True" separator=","/> - </options> - </param> - - </when> - <when value="history"> - <param name="ownFile" type="data" format="fasta" metadata_name="dbkey" label="Select the reference genome" - help="Fasta containing genomic DNA sequence"/> - </when> - </conditional> <!-- Input data --> <conditional name="seq"> - <param name="format" type="select" label="Select the input format" help=""> + <param name="format" type="select" label="<H2>Input Sequences</H2>Select the input format" help=""> <option value="fastq">Fastq</option> <option value="gsnap_fasta">GNSAP fasta</option> </param> @@ -308,6 +243,7 @@ <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> @@ -315,9 +251,147 @@ <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> + + <!-- GMAPDB for alignment --> + <conditional name="refGenomeSource"> + <param name="genomeSource" type="select" label="<HR><H2>Align To</H2>Will you select a reference genome from your history or use a built-in index?" help="Built-ins were indexed using default options"> + <option value="indexed">Use a built-in index</option> + <option value="gmapdb">Use a gmapdb from your history</option> + </param> + <when value="indexed"> + <param name="gmapindex" type="select" label="Select a reference genome" help="if your genome of interest is not listed - contact Galaxy team"> + <options from_file="gmap_indices.loc"> + <column name="uid" index="0" /> + <column name="dbkey" index="1" /> + <column name="name" index="2" /> + <column name="kmers" index="3" /> + <column name="maps" index="4" /> + <column name="snps" index="5" /> + <column name="value" index="6" /> + </options> + </param> + + <param name="kmer" type="select" data_ref="gmapindex" label="kmer size" help="Defaults to highest available kmer size"> + <options from_file="gmap_indices.loc"> + <column name="name" index="3"/> + <column name="value" index="3"/> + <filter type="param_value" ref="gmapindex" column="6"/> + <filter type="multiple_splitter" column="3" separator=","/> + <filter type="add_value" name="" value=""/> + <filter type="sort_by" column="3"/> + </options> + </param> + + <conditional name="use_splicing"> + <param name="src" type="select" label="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> + <option value="gmapdb">From the GMAP Database</option> + <option value="history">A Map in your history</option> + </param> + <when value="none"/> + <when value="history"> + <param name="splicemap" type="data" format="splicesites.iit,introns.iit" metadata_name="dbkey" label="Select a splicesite map" + help="built with GMAP IIT"/> + </when> + <when value="gmapdb"> + <param name="splicemap" type="select" data_ref="gmapindex" label="Use map for splicing involving known sites or known introns" help=""> + <options from_file="gmap_indices.loc"> + <column name="name" index="4"/> + <column name="value" index="4"/> + <filter type="param_value" ref="gmapindex" column="6"/> + <filter type="multiple_splitter" column="4" separator=","/> + <filter type="add_value" name="" value=""/> + <filter type="sort_by" column="4"/> + </options> + </param> + </when> + </conditional> + + <conditional name="use_snps"> + <param name="src" type="select" label="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> + </param> + <when value="none"/> + <when value="history"> + <param name="snpindex" type="data" format="gmapsnpindex" metadata_name="dbkey" label="Select a snpindex" + help="built with GMAP SNP Index"/> + </when> + <when value="gmapdb"> + <param name="snpindex" type="select" data_ref="gmapindex" label="Use database containing known SNPs" help=""> + <options from_file="gmap_indices.loc"> + <column name="name" index="5"/> + <column name="value" index="5"/> + <filter type="param_value" ref="gmapindex" column="6"/> + <filter type="multiple_splitter" column="5" separator=","/> + <filter type="add_value" name="" value=""/> + <filter type="sort_by" column="5"/> + </options> + </param> + </when> + </conditional> + + </when> + <when value="gmapdb"> + <param name="gmapdb" type="data" format="gmapdb" metadata_name="dbkey" label="Select a gmapdb" + help="A GMAP database built with GMAP Build"/> + <param name="kmer" type="select" data_ref="gmapdb" label="kmer size" help="Defaults to highest available kmer size"> + <options> + <filter type="data_meta" ref="gmapdb" key="kmers" multiple="True" separator=","/> + </options> + </param> + + <conditional name="use_splicing"> + <param name="src" type="select" label="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> + <option value="gmapdb">From the GMAP Database</option> + <option value="history">A Map in your history</option> + </param> + <when value="none"/> + <when value="history"> + <param name="splicemap" type="data" format="splicesites.iit,introns.iit" metadata_name="dbkey" label="Select a splicesite map" + help="built with GMAP IIT"/> + </when> + <when value="gmapdb"> + <param name="splicemap" type="select" data_ref="gmapdb" label="Use map for splicing involving known sites or known introns" help=""> + <options> + <filter type="data_meta" ref="gmapdb" key="maps" multiple="True"/> + </options> + </param> + </when> + </conditional> + + <conditional name="use_snps"> + <param name="src" type="select" label="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> + </param> + <when value="none"/> + <when value="history"> + <param name="snpindex" type="data" format="gmapsnpindex" metadata_name="dbkey" label="Select a snpindex" + help="built with GMAP SNP Index"/> + </when> + <when value="gmapdb"> + <param name="snpindex" type="select" data_ref="gmapdb" label="Use database containing known SNPs" help=""> + <options> + <filter type="data_meta" ref="gmapdb" key="snps" multiple="True" separator=","/> + </options> + </param> + </when> + </conditional> + + </when> + </conditional> + <!-- Computation options --> <conditional name="computation"> - <param name="options" type="select" label="Computational Settings" help=""> + <param name="options" type="select" label="<HR>Computational Settings" help=""> <option value="default">Use default settings</option> <option value="advanced">Set Computation Options</option> </param> @@ -352,8 +426,7 @@ </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"/> - <!-- use-snps This should be either a select list from the gmapdb maps or a data type using snpsdir and use-snps --> - <param name="use_snps" type="text" value="" optional="true" label="SNP database Name for SNP tolearnce" help="Use database containing known SNPs (built previously using snpindex) for tolerance to SNPs"/> + <!-- 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> @@ -376,7 +449,7 @@ </conditional> <conditional name="splicing"> - <param name="options" type="select" label="Splicing options for RNA-Seq" help=""> + <param name="options" type="select" label="<HR>Splicing options for RNA-Seq" help=""> <option value="default">Use default settings</option> <option value="advanced">Set Splicing Options</option> </param> @@ -384,7 +457,7 @@ <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 --> - <param name="use_splices" type="text" value="" optional="true" label="Known splicesites or 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"/> + <!-- 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"/> @@ -398,7 +471,7 @@ <!-- Output data --> <conditional name="output"> - <param name="options" type="select" label="Output options for RNA-Seq" help=""> + <param name="options" type="select" label="<HR><H2>Output</H2>Output options for RNA-Seq" help=""> <option value="default">Use default settings</option> <option value="advanced">Set Output Options</option> </param> @@ -439,7 +512,7 @@ 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 ${on_string}: log"/> + <data format="txt" name="gsnap_stderr" label="${tool.name} on ${on_string}: stderr"/> <data format="txt" name="results" label="${tool.name} on ${on_string} ${result.format}" > <filter>(split_output == False)</filter> <change_format>