Mercurial > repos > jjohnson > gmap
changeset 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 | 30d42bb409b8 |
| children | 72ab00e732c3 |
| files | gmap/README gmap/gmap.xml gmap/gmap_build.xml gmap/gsnap.xml gmap/iit_store.xml gmap/lib/galaxy/datatypes/gmap.py gmap/snpindex.xml |
| diffstat | 7 files changed, 981 insertions(+), 278 deletions(-) [+] |
line wrap: on
line diff
--- a/gmap/README Tue Oct 18 11:51:15 2011 -0500 +++ b/gmap/README Fri Oct 21 11:38:55 2011 -0500 @@ -9,9 +9,16 @@ add to datatypes_conf.xml <!-- Start GMAP Datatypes --> <datatype extension="gmapdb" type="galaxy.datatypes.gmap:GmapDB" display_in_upload="False"/> - <!-- - - + <datatype extension="gmapsnpindex" type="galaxy.datatypes.gmap:GmapSnpIndex" display_in_upload="False"/> + <datatype extension="iit" type="galaxy.datatypes.gmap:IntervalIndexTree" display_in_upload="True"/> + <datatype extension="splicesites.iit" type="galaxy.datatypes.gmap:SpliceSitesIntervalIndexTree" display_in_upload="True"/> + <datatype extension="introns.iit" type="galaxy.datatypes.gmap:IntronsIntervalIndexTree" display_in_upload="True"/> + <datatype extension="snps.iit" type="galaxy.datatypes.gmap:SNPsIntervalIndexTree" display_in_upload="True"/> + <datatype extension="gmap_annotation" type="galaxy.datatypes.gmap:IntervalAnnotation" display_in_upload="False"/> + <datatype extension="gmap_splicesites" type="galaxy.datatypes.gmap:SpliceSiteAnnotation" display_in_upload="True"/> + <datatype extension="gmap_introns" type="galaxy.datatypes.gmap:IntronAnnotation" display_in_upload="True"/> + <datatype extension="gmap_snps" type="galaxy.datatypes.gmap:SNPAnnotation" display_in_upload="True"/> + <!-- End GMAP tools --> Tools: GMAP_Build - create a GmapDB set of index files for a reference sequence and optional set of annotations @@ -19,28 +26,22 @@ GSNAP - align sequences to a reference and detect splicing Add to tool_conf.xml ( probably in the "NGS: Mapping" section ) - <tool file="gmap/gmap_build.xml" /> <tool file="gmap/gmap.xml" /> <tool file="gmap/gsnap.xml" /> + <tool file="gmap/gmap_build.xml" /> + <tool file="gmap/snpindex.xml" /> + <tool file="gmap/iit_store.xml" /> + +Admin built cached gmapdb indexes defined in tool-data/gmap_indices.loc TODO: Add classes to gmap.py - IntervalIndexTree - datatype for the iit_store result - IntervalAnnotation - generic class for gmap annotation formats - SpliceSiteAnnotation - class for gmap splicesite annotation format - IntronAnnotation - class for gmap introns annotation format - SNPAnnotation - class for gmap snp annotation format - GmapIndex - generic class for a gmap index - SnpIndex - an index created by snpindex CmetIndex - an index created by cmetindex AtoiIndex - an index created by atoiindex Possibly add Tools: - iit_store - creates a mapping index .iit from: gtf,gff3,gmapannotation, UCSC refGene table - iit_get - retrieves from .iit store get_genome - retrieves from a gmapdb - snpindex - create a SNPIndex cmetindex - create methylcytosine index atoiindex - create A-to-I RNA editing index
--- a/gmap/gmap.xml Tue Oct 18 11:51:15 2011 -0500 +++ b/gmap/gmap.xml Fri Oct 21 11:38:55 2011 -0500 @@ -1,7 +1,13 @@ <tool id="gmap" name="GMAP" version="2.0.0"> <description>Genomic Mapping and Alignment Program for mRNA and EST sequences</description> <requirements> - <requirement type="binary">gmap</requirement> + <requirement type="binary">gmap</requirement> + <!-- proposed tag for added datatype dependencies --> + <requirement type="datatype">gmapdb</requirement> + <requirement type="datatype">gmap_annotation</requirement> + <requirement type="datatype">gmap_splicesites</requirement> + <requirement type="datatype">gmap_introns</requirement> + <requirement type="datatype">gmap_snps</requirement> </requirements> <version_string>gmap --version</version_string> <command> @@ -113,8 +119,20 @@ #end if </command> <inputs> + <!-- Input data --> + <param name="input" type="data" format="fasta,fastqsanger,fastqillumina" label="<H2>Input Sequences</H2>Select an mRNA or EST dataset to map" /> + <repeat name="inputs" title="addtional mRNA or EST dataset to map"> + <param name="added_input" type="data" format="fasta,fastqsanger,fastqillumina" label=""/> + </repeat> + <param name="quality_protocol" type="select" label="Protocol for input quality scores"> + <option value="">No quality scores</option> + <option value="sanger">Sanger quality scores</option> + <option value="illumina">Illumina quality scores</option> + </param> + + <!-- GMAPDB for mapping --> <conditional name="refGenomeSource"> - <param name="genomeSource" type="select" label="Will you map to a reference genome from your history or use a built-in index?" help="Built-ins were indexed using default options"> + <param name="genomeSource" type="select" label="<HR><H2>Map To</H2>Will you map to 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 a fasta reference sequence from the history</option> @@ -155,8 +173,6 @@ <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="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=","/> @@ -174,18 +190,89 @@ </when> </conditional> - <!-- Input data --> - <param name="input" type="data" format="fasta,fastqsanger,fastqillumina" label="Select an mRNA or EST dataset to map" /> - <repeat name="inputs" title="addtional mRNA or EST dataset to map"> - <param name="added_input" type="data" format="fasta,fastqsanger,fastqillumina" label=""/> - </repeat> - <param name="quality_protocol" type="select" label="Protocol for input quality scores"> - <option value="">No quality scores</option> - <option value="sanger">Sanger quality scores</option> - <option value="illumina">Illumina quality scores</option> - </param> + + <!-- Computation options --> + <conditional name="computation"> + <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> + <when value="default"/> + <when value="advanced"> + <param name="nosplicing" type="boolean" truevalue="--nosplicing" falsevalue="" checked="false" label="Turn off splicing" help="(useful for aligning genomic sequences onto a genome)"/> + <param name="min_intronlength" type="integer" value="9" label="Min length for one internal intron (default 9)." help="Below this size, a genomic gap will be considered a deletion rather than an intron." /> + <param name="intronlength" type="integer" value="1000000" label="Max length for one intron (default 1000000)" /> + <param name="localsplicedist" type="integer" value="200000" label="Max length for known splice sites at ends of sequence (default 200000)" /> + <param name="totallength" type="integer" value="2400000" label="Max total intron length (default 2400000)" /> + <param name="chimera_margin" type="integer" value="40" label="Amount of unaligned sequence that triggers search for a chimera (default is 40, 0 is off)" /> + <param name="direction" type="select" label="cDNA direction"> + <option value="auto">auto</option> + <option value="sense_force">sense_force</option> + <option value="antisense_force">antisense_force</option> + <option value="sense_filter">sense_filter</option> + <option value="antisense_filter">antisense_filter</option> + </param> + <param name="trimendexons" type="integer" value="12" label="Trim end exons with fewer than given number of matches (in nt, default 12)" /> + <param name="cross_species" type="boolean" truevalue="--cross-species" falsevalue="" checked="false" label="Cross-species alignment" help="For cross-species alignments, use a more sensitive search for canonical splicing"/> + + <param name="canonical" type="select" label="Reward for canonical and semi-canonical introns"> + <option value="1">high reward (default)</option> + <option value="0">low reward</option> + <option value="2">low reward for high-identity sequences</option> + </param> + <param name="allow_close_indels" type="select" label="Allow an insertion and deletion close to each other"> + <option value="1" selected="true">yes (default)</option> + <option value="0">no</option> + <option value="2">only for high-quality alignments</option> + </param> + <param name="microexon_spliceprob" type="float" value="0.90" label="Allow microexons only if one of the splice site probabilities is greater than this value (default 0.90)" > + <validator type="in_range" message="slice probability between 0.00 and 1.00" min="0" max="1"/> + </param> + <param name="prunelevel" type="select" label="Pruning level"> + <option value="0">no pruning (default)</option> + <option value="1">poor sequences</option> + <option value="2">repetitive sequences</option> + <option value="3">poor and repetitive sequences</option> + </param> + <!-- could do this as a config file + <param name="chrsubsetfile" type="data" format="fasta" label="User-supplied chromosome subset file" /> + <param name="chrsubset" type="text" label="Chromosome subset to search" /> + --> + </when> + </conditional> + + <!-- Advanced Settings --> + <conditional name="advanced"> + <param name="options" type="select" label="<HR>Advanced Settings" help=""> + <option value="default">Use default settings</option> + <option value="used">Set Options</option> + </param> + <when value="default"/> + <when value="used"> + <param name="nolengths" type="boolean" checked="false" truevalue="--nolengths=true" falsevalue="" label="No intron lengths in alignment"/> + <param name="invertmode" type="select" label=" Mode for alignments to genomic (-) strand" help=""> + <option value="">Don't invert the cDNA (default)</option> + <option value="--invertmode=1">Invert cDNA and print genomic (-) strand</option> + <option value="--invertmode=2">Invert cDNA and print genomic (+) strand</option> + </param> + <param name="introngap" type="integer" value="3" label="Nucleotides to show on each end of intron (default=3)" /> + <param name="wraplength" type="integer" value="50" label="Line Wrap length for alignment (default=50)" /> + <param name="npaths" type="integer" value="-1" optional="true" + label="Maximum number of paths to show. Ignored if negative. If 0, prints two paths if chimera detected, else one." /> + <param name="chimera_overlap" type="integer" value="0" label="Overlap to show, if any, at chimera breakpoint" /> + <param name="tolerant" type="boolean" checked="false" truevalue="--tolerant=true" falsevalue="" + label="Translates cDNA with corrections for frameshifts"/> + <param name="protein" type="select" label="Protein alignment" help=""> + <option value="">default</option> + <option value="--fulllength=true">Assume full-length protein, starting with Met</option> + <option value="--truncate=true">Truncate alignment around full-length protein, Met to Stop</option> + </param> + </when> + </conditional> + + <!-- Output data --> <conditional name="result"> - <param name="format" type="select" label="Select the output format" help=""> + <param name="format" type="select" label="<HR><H2>Output</H2>Select the output format" help=""> <option value="gmap">GMAP default output</option> <option value="summary">Summary of alignments</option> <option value="align">Alignment</option> @@ -246,92 +333,20 @@ </conditional> <!-- name="result" --> <param name="split_output" type="boolean" truevalue="--split-output=gmap_out" falsevalue="" checked="false" label="Separate outputs for nomapping, uniq, mult, and chimera" help="(chimera only when chimera-margin is selected)"/> - - <conditional name="computation"> - <param name="options" type="select" label="Computational Settings" help=""> - <option value="default">Use default settings</option> - <option value="advanced">Set Computation Options</option> - </param> - <when value="default"/> - <when value="advanced"> - <param name="nosplicing" type="boolean" truevalue="--nosplicing" falsevalue="" checked="false" label="Turn off splicing" help="(useful for aligning genomic sequences onto a genome)"/> - <param name="min_intronlength" type="integer" value="9" label="Min length for one internal intron (default 9)." help="Below this size, a genomic gap will be considered a deletion rather than an intron." /> - <param name="intronlength" type="integer" value="1000000" label="Max length for one intron (default 1000000)" /> - <param name="localsplicedist" type="integer" value="200000" label="Max length for known splice sites at ends of sequence (default 200000)" /> - <param name="totallength" type="integer" value="2400000" label="Max total intron length (default 2400000)" /> - <param name="chimera_margin" type="integer" value="40" label="Amount of unaligned sequence that triggers search for a chimera (default is 40, 0 is off)" /> - <param name="direction" type="select" label="cDNA direction"> - <option value="auto">auto</option> - <option value="sense_force">sense_force</option> - <option value="antisense_force">antisense_force</option> - <option value="sense_filter">sense_filter</option> - <option value="antisense_filter">antisense_filter</option> - </param> - <param name="trimendexons" type="integer" value="12" label="Trim end exons with fewer than given number of matches (in nt, default 12)" /> - <param name="cross_species" type="boolean" truevalue="--cross-species" falsevalue="" checked="false" label="Cross-species alignment" help="For cross-species alignments, use a more sensitive search for canonical splicing"/> - - <param name="canonical" type="select" label="Reward for canonical and semi-canonical introns"> - <option value="1">high reward (default)</option> - <option value="0">low reward</option> - <option value="2">low reward for high-identity sequences</option> - </param> - <param name="allow_close_indels" type="select" label="Allow an insertion and deletion close to each other"> - <option value="1" selected="true">yes (default)</option> - <option value="0">no</option> - <option value="2">only for high-quality alignments</option> - </param> - <param name="microexon_spliceprob" type="float" value="0.90" label="Allow microexons only if one of the splice site probabilities is greater than this value (default 0.90)" > - <validator type="in_range" message="slice probability between 0.00 and 1.00" min="0" max="1"/> - </param> - <param name="prunelevel" type="select" label="Pruning level"> - <option value="0">no pruning (default)</option> - <option value="1">poor sequences</option> - <option value="2">repetitive sequences</option> - <option value="3">poor and repetitive sequences</option> - </param> - <!-- could do this as a config file - <param name="chrsubsetfile" type="data" format="fasta" label="User-supplied chromosome subset file" /> - <param name="chrsubset" type="text" label="Chromosome subset to search" /> - --> - </when> - </conditional> - <conditional name="advanced"> - <param name="options" type="select" label="Advanced Settings" help=""> - <option value="default">Use default settings</option> - <option value="used">Set Options</option> - </param> - <when value="default"/> - <when value="used"> - <param name="nolengths" type="boolean" checked="false" truevalue="--nolengths=true" falsevalue="" label="No intron lengths in alignment"/> - <param name="invertmode" type="select" label=" Mode for alignments to genomic (-) strand" help=""> - <option value="">Don't invert the cDNA (default)</option> - <option value="--invertmode=1">Invert cDNA and print genomic (-) strand</option> - <option value="--invertmode=2">Invert cDNA and print genomic (+) strand</option> - </param> - <param name="introngap" type="integer" value="3" label="Nucleotides to show on each end of intron (default=3)" /> - <param name="wraplength" type="integer" value="50" label="Line Wrap length for alignment (default=50)" /> - <param name="npaths" type="integer" value="-1" optional="true" - label="Maximum number of paths to show. Ignored if negative. If 0, prints two paths if chimera detected, else one." /> - <param name="chimera_overlap" type="integer" value="0" label="Overlap to show, if any, at chimera breakpoint" /> - <param name="tolerant" type="boolean" checked="false" truevalue="--tolerant=true" falsevalue="" - label="Translates cDNA with corrections for frameshifts"/> - <param name="protein" type="select" label="Protein alignment" help=""> - <option value="">default</option> - <option value="--fulllength=true">Assume full-length protein, starting with Met</option> - <option value="--truncate=true">Truncate alignment around full-length protein, Met to Stop</option> - </param> - </when> - </conditional> + + <!-- - map=iitfile Map file. If argument is '?' (with the quotes), this lists available map files. - mapexons Map each exon separately - mapboth Report hits from both strands of genome - flanking=INT Show flanking hits (default 0) - print-comment Show comment line for each hit + map=iitfile Map file. If argument is '?' (with the quotes), this lists available map files. + mapexons Map each exon separately + mapboth Report hits from both strands of genome + flanking=INT Show flanking hits (default 0) + print-comment Show comment line for each hit --> + + </inputs> <outputs> - <data format="txt" name="gmap_stderr" label="${tool.name} on ${on_string}: log"/> + <data format="txt" name="gmap_stderr" label="${tool.name} on ${on_string}: stderr"/> <data format="txt" name="output" label="${tool.name} on ${on_string} ${result.format}" > <filter>(split_output == False)</filter> <change_format> @@ -339,10 +354,10 @@ <when input="result['format']" value="gff3_match_cdna" format="gff3"/> <when input="result['format']" value="gff3_match_est" format="gff3"/> <when input="result['format']" value="sam" format="sam"/> - <!-- <when input="result['format']" value="splicesites" format="gmap_splicesites"/> <when input="result['format']" value="introns" format="gmap_introns"/> - --> + <when input="result['format']" value="map_genes" format="gmap_annotation"/> + <when input="result['format']" value="map_exons" format="gmap_annotation"/> </change_format> </data> <data format="txt" name="uniq" label="${tool.name} on ${on_string} uniq.${result.format}" from_work_dir="gmap_out.uniq"> @@ -352,6 +367,10 @@ <when input="result['format']" value="gff3_match_cdna" format="gff3"/> <when input="result['format']" value="gff3_match_est" format="gff3"/> <when input="result['format']" value="sam" format="sam"/> + <when input="result['format']" value="splicesites" format="gmap_splicesites"/> + <when input="result['format']" value="introns" format="gmap_introns"/> + <when input="result['format']" value="map_genes" format="gmap_annotation"/> + <when input="result['format']" value="map_exons" format="gmap_annotation"/> </change_format> </data> <data format="txt" name="transloc" label="${tool.name} on ${on_string} transloc.${result.format}" from_work_dir="gmap_out.transloc"> @@ -361,6 +380,10 @@ <when input="result['format']" value="gff3_match_cdna" format="gff3"/> <when input="result['format']" value="gff3_match_est" format="gff3"/> <when input="result['format']" value="sam" format="sam"/> + <when input="result['format']" value="splicesites" format="gmap_splicesites"/> + <when input="result['format']" value="introns" format="gmap_introns"/> + <when input="result['format']" value="map_genes" format="gmap_annotation"/> + <when input="result['format']" value="map_exons" format="gmap_annotation"/> </change_format> </data> <data format="txt" name="nomapping" label="${tool.name} on ${on_string} nomapping.${result.format}" from_work_dir="gmap_out.nomapping"> @@ -370,6 +393,10 @@ <when input="result['format']" value="gff3_match_cdna" format="gff3"/> <when input="result['format']" value="gff3_match_est" format="gff3"/> <when input="result['format']" value="sam" format="sam"/> + <when input="result['format']" value="splicesites" format="gmap_splicesites"/> + <when input="result['format']" value="introns" format="gmap_introns"/> + <when input="result['format']" value="map_genes" format="gmap_annotation"/> + <when input="result['format']" value="map_exons" format="gmap_annotation"/> </change_format> </data> <data format="txt" name="mult" label="${tool.name} on ${on_string} mult.${result.format}" from_work_dir="gmap_out.mult"> @@ -379,6 +406,10 @@ <when input="result['format']" value="gff3_match_cdna" format="gff3"/> <when input="result['format']" value="gff3_match_est" format="gff3"/> <when input="result['format']" value="sam" format="sam"/> + <when input="result['format']" value="splicesites" format="gmap_splicesites"/> + <when input="result['format']" value="introns" format="gmap_introns"/> + <when input="result['format']" value="map_genes" format="gmap_annotation"/> + <when input="result['format']" value="map_exons" format="gmap_annotation"/> </change_format> </data> </outputs>
--- a/gmap/gmap_build.xml Tue Oct 18 11:51:15 2011 -0500 +++ b/gmap/gmap_build.xml Fri Oct 21 11:38:55 2011 -0500 @@ -1,16 +1,23 @@ <tool id="gmap_build" name="GMAP Build" version="2.0.0"> - <description>a GMAP DB Index</description> + <description>a database genome index for GMAP and GSNAP</description> <requirements> <requirement type="binary">gmap_build</requirement> + <!-- proposed tag for added datatype dependencies --> + <requirement type="datatype">gmapdb</requirement> + <requirement type="datatype">gmap_snps</requirement> </requirements> <version_string>gmap --version</version_string> <command interpreter="command"> /bin/bash $shscript 2>1 1> $output </command> <inputs> - <!-- Input data --> - <param name="input" type="data" format="fasta" label="reference sequence fasta" /> - <param name="refname" type="text" label="reference name" help=""> + <!-- Name for this gmapdb --> + <param name="refname" type="text" label="Name you want to give this gmap database" help=""> <validator type="empty_field" message="A database name is required."/> </param> + <!-- Input data --> + <repeat name="inputs" title="Reference Sequence" min="1"> + <param name="input" type="data" format="fasta" label="reference sequence fasta" /> + </repeat> + <param name="kmer" type="select" multiple="true" force_select="true" label="kmer size" help=""> <option value="12">12</option> <option value="13">13</option> @@ -79,7 +86,6 @@ <!-- <data format="txt" name="log" label="${tool.name} on ${on_string}: log"/> --> - <!-- this should have its own datatype: gmapdb --> <data format="gmapdb" name="output" label="${tool.name} on ${on_string} gmapdb ${refname}" /> </outputs> <configfiles> @@ -89,6 +95,11 @@ #set $gt = chr(62) #set $lt = chr(60) #set $ad = chr(38) +## #set $ref_files = '' +## #for $i in $inputs: + ## #set $ref_files = $ref_files $i.input +## #end for +## echo $ref_files #import os.path #set $gmapdb = $output.extra_files_path #set $mapsdir = $os.path.join($os.path.join($gmapdb,str($refname)), str($refname) + '.maps') @@ -96,7 +107,7 @@ ## export GMAPDB required for cmetindex and atoiindex export GMAPDB=$gmapdb #for $k in $kmer.__str__.split(','): -gmap_build -D $gmapdb -d $refname -s numeric-alpha -k $k $input +gmap_build -D $gmapdb -d $refname -s numeric-alpha -k $k #for i in $inputs# ${i.input}#end for# #end for get-genome -D $gmapdb -d '?' | sed 's/^Available .*/gmap db: /' echo "kmers: " $kmer @@ -116,23 +127,26 @@ cat $splicesite.gff3Genes | gff3_introns | iit_store -o $os.path.join($mapsdir,'introns') #end if #end if +#if $dbsnp.snp_source != 'none' and $dbsnp.snps.__str__ != 'None': #if $dbsnp.snp_source == 'snpTable': -#if $dbsnp.snps.__str__ != 'None': #if $dbsnp.snpsex.__str__ != 'None': cat $dbsnp.snps | dbsnp_iit -w $dbsnp.weight -e $dbsnp.snpsex | iit_store -o $os.path.join($mapsdir,'snps') #else: cat $dbsnp.snps | dbsnp_iit -w $dbsnp.weight | iit_store -o $os.path.join($mapsdir,'snps') #end if +#else: +cat $dbsnp.snps | iit_store -o $os.path.join($mapsdir,'snps') +#end if snpindex -d $refname -v snps -#end if +echo "snpindex" -d $refname -v snps #end if #if $cmetindex.__str__ == 'yes': cmetindex -d $refname -echo "cmetindex" +echo "cmetindex" -d $refname #end if #if $atoiindex.__str__ == 'yes': atoiindex -d $refname -echo "atoiindex" +echo "atoiindex" -d $refname #end if get-genome -D $gmapdb -d $refname -m '?' | sed 's/^Available maps .*/maps: /' </configfile> @@ -146,7 +160,7 @@ **GMAP Build** -GMAP Build creates an index of a genomic sequence for alignments using GMAP_ (Genomic Mapping and Alignment Program for mRNA and EST sequences) and GSNAP_ (Genomic Short-read Nucleotide Alignment Program). +GMAP Build creates an index of a genomic sequence for mapping and alignment using GMAP_ (Genomic Mapping and Alignment Program for mRNA and EST sequences) and GSNAP_ (Genomic Short-read Nucleotide Alignment Program). (GMAP Build uses GMSP commands: gmap_build, iit_store, psl_splicesites, psl_introns, gtf_splicesites, gtf_introns, gff3_splicesites, gff3_introns, dbsnp_iit, snpindex, cmetindex, and atoiindex.) You will want to read the README_
--- 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>
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/gmap/iit_store.xml Fri Oct 21 11:38:55 2011 -0500 @@ -0,0 +1,188 @@ +<tool id="gmap_iit_store" name="GMAP IIT" version="2.0.0"> + <description>Create a map store for known genes or SNPs</description> + <requirements> + <requirement type="binary">iit_store</requirement> + <!-- proposed tag for added datatype dependencies --> + <requirement type="datatype">gmap_annotation</requirement> + <requirement type="datatype">gmap_snps</requirement> + <requirement type="datatype">iit</requirement> + <requirement type="datatype">splicesites.iit</requirement> + <requirement type="datatype">introns.iit</requirement> + <requirement type="datatype">snps.iit</requirement> + </requirements> + <version_string>iit_store --version</version_string> + <command interpreter="command"> /bin/bash $shscript 2> $log </command> + <inputs> + <!-- Input data --> + <conditional name="map"> + <param name="type" type="select" label="Make map for" > + <option value="genes">Introns and Splice sites</option> + <option value="snps">SNPs</option> + <option value="gmap">GMAP Annotation</option> + </param> + <when value="genes"> + <conditional name="src"> + <param name="src_format" type="select" label="Add splice and intron info from" > + <option value="refGeneTable">refGenes table from UCSC table browser</option> + <option value="gtf">GTF</option> + <option value="gff3">GFF3</option> + </param> + <when value="refGeneTable"> + <param name="genes" type="data" format="tabular" label="UCSC refGenes table" help="Example: ftp://hgdownload.cse.ucsc.edu/goldenPath/hg18/database/refGene.txt.gz" /> + <param name="col_skip" type="integer" value="1" label="Columns to skip before the id/name column (default 1)" + help="Note that alignment tracks in UCSC sometimes have an extra column on the left."> + <validator type="in_range" message="The number of colmumns to skip must >= 0." min="0."/> + </param> + </when> + <when value="gtf"> + <param name="genes" type="data" format="gtf" label="Genes as GTF" help="" /> + </when> + <when value="gff3"> + <param name="genes" type="data" format="gff3" label="Genes in GFF3 format" help="" /> + </when> + </conditional> + <param name="maps" type="select" display="checkboxes" multiple="true" force_select="true" label="Add splice and intron info from" > + <option value="splicesites" selected="true">splicesites.iit</option> + <option value="introns" selected="false">introns.iit</option> + </param> + </when> + <when value="snps"> + <conditional name="src"> + <param name="src_format" type="select" label="Add SNP info from" > + <option value="snpTable">UCSC SNP Table</option> + <option value="snpFile">GMAP SNP File</option> + </param> + <when value="snpTable"> + <param name="snps" type="data" format="tabular" label="UCSC SNPs table" help="Example: ftp://hgdownload.cse.ucsc.edu/goldenPath/hg18/database/snp130.txt.gz" /> + <param name="snpsex" type="data" format="tabular" optional="true" label="UCSC SNP Exceptions table" help="Example: ftp://hgdownload.cse.ucsc.edu/goldenPath/hg18/database/snp130Exceptions.txt.gz" /> + <param name="weight" type="select" label="Include SNPs with at least Confidence Level" help=""> + <option value="1" selected="true">1 (High)</option> + <option value="2">2 (Medium)</option> + <option value="3">3 (All)</option> + </param> + </when> + <when value="snpFile"> + <param name="snps" type="data" format="gmap_snps" optional="true" label="GMAP SNPs file" + help="Format (3 columns):<B> + <br>>rs62211261 21:14379270 CG + <br>>rs62211262 21:14379281 CG + </B> + <br>Each line must start with a > character, then be followed by an + identifier (which may have duplicates). Then there should be the + chromosomal coordinate of the SNP. (Coordinates are all 1-based, so + the first character of a chromosome is number 1.) Finally, there + should be the two possible alleles: ( AC AG AT CG CT GT or AN CN GN TN) + <br>These alleles must correspond to the possible nucleotides on the plus strand of the genome. + If the one of these two letters does not match the allele in the reference + sequence, that SNP will be ignored in subsequent processing as a probable error. + The N stands for any other allele." /> + </when> + </conditional> + </when> + <when value="gmap"> + <param name="annotation" type="data" format="gmap_annotation" label="GMAP mapfile" + help="Format (2 or columns): <B> + <br>>label coords optional_tag + <br>optional_annotation (which may be zero, one, or multiple lines) + </B> + <br>Each line must start with a > character, then be followed by an identifier (which may have duplicates). + <br>Then there should be the chromosomal coordinate range. (Coordinates are all 1-based, so the first character of a chromosome is number 1.) + <br>The coords should be of the form + <br> chr:position + <br> chr:startposition..endposition + <br>The term chr:position is equivalent to chr:position..position. + <br>If you want to indicate that the interval is on the minus strand or reverse direction, then endposition may be less than startposition. + " /> + </when> + </conditional> + </inputs> + <outputs> + <data format="txt" name="log" label="${tool.name} on ${on_string}: log"/> + <data format="splicesites.iit" name="splicesites_iit" label="${tool.name} on ${on_string} splicesites.iit"> + <filter>(map['type'] == 'genes' and 'splicesites' in map['maps'])</filter> + </data> + <data format="introns.iit" name="introns_iit" label="${tool.name} on ${on_string} introns.iit"> + <filter>(map['type'] == 'genes' and 'introns' in map['maps'])</filter> + </data> + <data format="snps.iit" name="snps_iit" label="${tool.name} on ${on_string} snps.iit"> + <filter>(map['type'] == 'snps')</filter> + </data> + <data format="iit" name="map_iit" label="${tool.name} on ${on_string} map.iit"> + <filter>(map['type'] == 'gmap')</filter> + </data> + </outputs> + <configfiles> + <configfile name="shscript"> +#!/bin/bash +#set $catcmd = 'gzcat -f' +#set $catcmd = 'cat' +#set $ds = chr(36) +#set $gt = chr(62) +#set $lt = chr(60) +#set $ad = chr(38) +#set $ep = chr(33) +#set $toerr = ''.join([$gt,$ad,'2']) +#import os.path +#if $map.type == 'genes': +if [ $ep -e $map.src.genes ]; then echo "$map.src.genes does not exist" $toerr; exit 1; fi +if [ $ep -s $map.src.genes ]; then echo "$map.src.genes is empty" $toerr; exit 2; fi + #if $map.src.src_format == 'refGeneTable': + #if 'splicesites' in [ $map.maps.__str__ ]: + $catcmd $map.src.genes | psl_splicesites -s $map.src.col_skip | iit_store -o $splicesites_iit + #end if + #if 'introns' in [ $map.maps.__str__ ]: + $catcmd $map.src.genes | psl_introns -s $map.src.col_skip | iit_store -o $introns_iit + #end if + #elif $map.src.src_format == 'gtf': + #if 'splicesites' in [ $map.maps.__str__ ]: + $catcmd $map.src.genes | gtf_splicesites | iit_store -o $splicesites_iit + #end if + #if 'introns' in [ $map.maps.__str__ ]: + $catcmd $map.src.genes | gtf_introns | iit_store -o $introns_iit + #end if + #elif $map.src.src_format == 'gff3': + #if 'splicesites' in [ $map.maps.__str__ ]: + $catcmd $map.src.genes | gff3_splicesites | iit_store -o $splicesites_iit + #end if + #if 'introns' in [ $map.maps.__str__ ]: + $catcmd $map.src.genes | gff3_introns | iit_store -o $introns_iit + #end if + #end if +#elif $map.type == 'snps': +if [ $ep -s $map.src.snps ]; then echo "$map.src.snps is empty" $toerr; exit 2; fi + #if $map.src.snpsex.__str__ != 'None': + $catcmd $map.src.snps | dbsnp_iit -w $map.src.weight -e $map.src.snpsex | iit_store -o $snps_iit + #else: + $catcmd $map.src.snps | dbsnp_iit -w $map.src.weight | iit_store -o $snps_iit + #end if +#else: + $catcmd $map.src.snps | iit_store -o $map_iit +#end if + </configfile> + </configfiles> + + <tests> + </tests> + + <help> + + +**iit_store** + +GMAP IIT creates an Interval Index Tree map of known splice sites, introns, or SNPs (it uses iit_store described in the GMAP documentation). The maps can be used in GMAP_ (Genomic Mapping and Alignment Program for mRNA and EST sequences) and GSNAP_ (Genomic Short-read Nucleotide Alignment Program). Maps are typically used for known splice sites, introns, or SNPs. + +You will want to read the README_ + +Publication_ citation: Thomas D. Wu, Colin K. Watanabe Bioinformatics 2005 21(9):1859-1875; doi:10.1093/bioinformatics/bti310 + +.. _GMAP: http://research-pub.gene.com/gmap/ +.. _GSNAP: http://research-pub.gene.com/gmap/ +.. _README: http://research-pub.gene.com/gmap/src/README +.. _Publication: http://bioinformatics.oxfordjournals.org/cgi/content/full/21/9/1859 + + +**inputs** + + </help> +</tool> +
--- a/gmap/lib/galaxy/datatypes/gmap.py Tue Oct 18 11:51:15 2011 -0500 +++ b/gmap/lib/galaxy/datatypes/gmap.py Fri Oct 21 11:38:55 2011 -0500 @@ -3,7 +3,9 @@ """ import logging import os,os.path,re +import data from data import Text +from galaxy import util from metadata import MetadataElement log = logging.getLogger(__name__) @@ -61,6 +63,7 @@ return dataset.peek except: return "GMAP index file" + def sniff( self, filename ): return False def set_meta( self, dataset, overwrite = True, **kwd ): @@ -113,57 +116,309 @@ dataset.metadata.atoi = True dataset.metadata.kmers = kmers.keys() -## class IntervalIndexTree( Text ): -## """ -## A GMAP Interval Index Tree Map -## created by iit_store -## (/path/to/map)/(mapname).iit -## """ -## MetadataElement( name="map_name", desc="The map name for this index set", default='unknown', set_in_upload=True, readonly=False ) -## file_ext = 'iit' -## is_binary = True -## composite_type = 'auto_primary_file' -## allow_datatype_change = False -## -## class IntervalAnnotation(data.Text): -## """ -## Class describing a GMAP Interval format: -## >label coords optional_tag -## optional_annotation (which may be zero, one, or multiple lines) -## The coords should be of the form: -## chr:position -## chr:startposition..endposition -## """ -## file_ext = 'gmapannotation' -## -## class SpliceSiteAnnotation(IntervalAnnotation): -## file_ext = 'gmapsplicesites' -## """ -## Example: -## >NM_004448.ERBB2.exon1 17:35110090..35110091 donor 6678 -## >NM_004448.ERBB2.exon2 17:35116768..35116769 acceptor 6678 -## >NM_004448.ERBB2.exon2 17:35116920..35116921 donor 1179 -## >NM_004448.ERBB2.exon3 17:35118099..35118100 acceptor 1179 -## >NM_004449.ERG.exon1 21:38955452..38955451 donor 783 -## >NM_004449.ERG.exon2 21:38878740..38878739 acceptor 783 -## >NM_004449.ERG.exon2 21:38878638..38878637 donor 360 -## >NM_004449.ERG.exon3 21:38869542..38869541 acceptor 360 -## """ -## -## class IntronAnnotation(IntervalAnnotation): -## file_ext = 'gmapintrons' -## """ -## Example: -## >NM_004448.ERBB2.intron1 17:35110090..35116769 -## >NM_004448.ERBB2.intron2 17:35116920..35118100 -## >NM_004449.ERG.intron1 21:38955452..38878739 -## >NM_004449.ERG.intron2 21:38878638..38869541 -## """ -## -## class SNPAnnotation(IntervalAnnotation): -## file_ext = 'gmapsnps' -## """ -## Example: -## >rs62211261 21:14379270 CG -## >rs62211262 21:14379281 CG -## """ +class GmapSnpIndex( Text ): + """ + A GMAP SNP index created by snpindex + """ + MetadataElement( name="db_name", desc="The db name for this index set", default='unknown', set_in_upload=True, readonly=True ) + MetadataElement( name="snps_name", default='snps', desc="The name of SNP index", visible=True, no_value='', readonly=True ) + + file_ext = 'gmapsnpindex' + is_binary = True + composite_type = 'auto_primary_file' + allow_datatype_change = False + + def generate_primary_file( self, dataset = None ): + """ + This is called only at upload to write the html file + cannot rename the datasets here - they come with the default unfortunately + """ + return '<html><head></head><body>AutoGenerated Primary File for Composite Dataset</body></html>' + + def regenerate_primary_file(self,dataset): + """ + cannot do this until we are setting metadata + """ + bn = dataset.metadata.db_name + log.info( "GmapDB regenerate_primary_file %s" % (bn)) + rval = ['<html><head><title>GMAPDB %s</title></head><p/><H3>GMAPDB %s</H3><p/>cmet %s<br>atoi %s<H4>Maps:</H4><ul>' % (bn,bn,dataset.metadata.cmet,dataset.metadata.atoi)] + for i,name in enumerate(dataset.metadata.maps): + rval.append( '<li>%s' % name) + rval.append( '</ul></html>' ) + f = file(dataset.file_name,'w') + f.write("\n".join( rval )) + f.write('\n') + f.close() + def set_peek( self, dataset, is_multi_byte=False ): + log.info( "GmapSnpIndex set_peek %s" % (dataset)) + if not dataset.dataset.purged: + dataset.peek = "GMAP SNPindex %s on %s\n" % ( dataset.metadata.snps_name,dataset.metadata.db_name) + dataset.blurb = "GMAP SNPindex %s on %s\n" % ( dataset.metadata.snps_name,dataset.metadata.db_name) + else: + dataset.peek = 'file does not exist' + dataset.blurb = 'file purged from disk' + def display_peek( self, dataset ): + try: + return dataset.peek + except: + return "GMAP SNP index" + + def sniff( self, filename ): + return False + def set_meta( self, dataset, overwrite = True, **kwd ): + """ + Expecting: + extra_files_path/snp_name.iit + extra_files_path/db_name/db_name.ref1[2345]1[2345]3offsetscomp.snp_name + extra_files_path/db_name/db_name.ref1[2345]1[2345]3positions.snp_name + extra_files_path/db_name/db_name.ref1[2345]1[2345]3gammaptrs.snp_name + """ + log.info( "GmapSnpIndex set_meta %s %s" % (dataset,dataset.extra_files_path)) + pat = '(.*)\.(ref((\d\d)(\d\d))?3positions)\.(.+)?' + efp = dataset.extra_files_path + flist = os.listdir(efp) + for i,fname in enumerate(flist): + m = re.match(pat,fname) + if m: + assert len(m.groups()) == 6 + dataset.metadata.db_name = m.groups()[0] + dataset.metadata.snps_name = m.groups()[-1] + + + + +class IntervalIndexTree( Text ): + """ + A GMAP Interval Index Tree Map + created by iit_store + (/path/to/map)/(mapname).iit + """ + file_ext = 'iit' + is_binary = True + +class SpliceSitesIntervalIndexTree( IntervalIndexTree ): + """ + A GMAP Interval Index Tree Map + created by iit_store + """ + file_ext = 'splicesites.iit' + +class IntronsIntervalIndexTree( IntervalIndexTree ): + """ + A GMAP Interval Index Tree Map + created by iit_store + """ + file_ext = 'introns.iit' + +class SNPsIntervalIndexTree( IntervalIndexTree ): + """ + A GMAP Interval Index Tree Map + created by iit_store + """ + file_ext = 'snps.iit' + +class IntervalAnnotation( Text ): + """ + Class describing a GMAP Interval format: + >label coords optional_tag + optional_annotation (which may be zero, one, or multiple lines) + The coords should be of the form: + chr:position + chr:startposition..endposition + """ + file_ext = 'gmap_annotation' + """Add metadata elements""" + MetadataElement( name="annotations", default=0, desc="Number of interval annotations", readonly=True, optional=True, visible=False, no_value=0 ) + + def set_meta( self, dataset, **kwd ): + """ + Set the number of annotations and the number of data lines in dataset. + """ + data_lines = 0 + annotations = 0 + for line in file( dataset.file_name ): + line = line.strip() + if line and line.startswith( '>' ): + annotations += 1 + data_lines +=1 + else: + data_lines += 1 + dataset.metadata.data_lines = data_lines + dataset.metadata.annotations = annotations + def set_peek( self, dataset, is_multi_byte=False ): + if not dataset.dataset.purged: + dataset.peek = data.get_file_peek( dataset.file_name, is_multi_byte=is_multi_byte ) + if dataset.metadata.annotations: + dataset.blurb = "%s annotations" % util.commaify( str( dataset.metadata.annotations ) ) + else: + dataset.blurb = data.nice_size( dataset.get_size() ) + else: + dataset.peek = 'file does not exist' + dataset.blurb = 'file purged from disk' + + def sniff( self, filename ): + """ + Determines whether the file is a gmap annotation file + Format: + >label coords optional_tag + optional_annotation (which may be zero, one, or multiple lines) + For example, the label may be an EST accession, with the coords + representing its genomic position. Labels may be duplicated if + necessary. + The coords should be of the form + chr:position + chr:startposition..endposition + The term "chr:position" is equivalent to "chr:position..position". If + you want to indicate that the interval is on the minus strand or + reverse direction, then <endposition> may be less than <startposition>. + """ + try: + pat = '>(\S+)\s((\S+):(\d+)(\.\.(\d+))?(\s.(.+))?$' #>label chr:position[..endposition][ optional_tag] + fh = open( filename ) + count = 0 + while True and count < 10: + line = fh.readline() + if not line: + break #EOF + line = line.strip() + if line: #first non-empty line + if line.startswith( '>' ): + count += 1 + if re.match(pat,line) == None: # Failed to match + return False + finally: + fh.close() + return False + +class SpliceSiteAnnotation(IntervalAnnotation): + file_ext = 'gmap_splicesites' + """ + Example: + >NM_004448.ERBB2.exon1 17:35110090..35110091 donor 6678 + >NM_004448.ERBB2.exon2 17:35116768..35116769 acceptor 6678 + >NM_004448.ERBB2.exon2 17:35116920..35116921 donor 1179 + >NM_004448.ERBB2.exon3 17:35118099..35118100 acceptor 1179 + >NM_004449.ERG.exon1 21:38955452..38955451 donor 783 + >NM_004449.ERG.exon2 21:38878740..38878739 acceptor 783 + >NM_004449.ERG.exon2 21:38878638..38878637 donor 360 + >NM_004449.ERG.exon3 21:38869542..38869541 acceptor 360 + Each line must start with a ">" character, then be followed by an + identifier, which may have duplicates and can have any format, with + the gene name or exon number shown here only as a suggestion. Then + there should be the chromosomal coordinates which straddle the + exon-intron boundary, so one coordinate is on the exon and one is on + the intron. (Coordinates are all 1-based, so the first character of a + chromosome is number 1.) Finally, there should be the splice type: + "donor" or "acceptor". You may optionally store the intron distance + at the end. GSNAP can use this intron distance, if it is longer than + its value for --localsplicedist, to look for long introns at that + splice site. The same splice site may have different intron distances + in the database; GSNAP will use the longest intron distance reported + in searching for long introns. + """ + def sniff( self, filename ): # TODO + """ + Determines whether the file is a gmap splice site annotation file + """ + try: + pat = '>(\S+\.intron\d+)\s((\S+):(\d+)\.\.(\d+))\s(donor|acceptor)(\s(\d+))?$' #>label chr:position..position donor|acceptor[ intron_dist] + fh = open( filename ) + count = 0 + while True and count < 10: + line = fh.readline() + if not line: + break #EOF + line = line.strip() + if line: #first non-empty line + count += 1 + if re.match(pat,line) == None: # Failed to match + return False + finally: + fh.close() + return False + +class IntronAnnotation(IntervalAnnotation): + file_ext = 'gmap_introns' + """ + Example: + >NM_004448.ERBB2.intron1 17:35110090..35116769 + >NM_004448.ERBB2.intron2 17:35116920..35118100 + >NM_004449.ERG.intron1 21:38955452..38878739 + >NM_004449.ERG.intron2 21:38878638..38869541 + The coordinates are 1-based, and specify the exon coordinates + surrounding the intron, with the first coordinate being from the donor + exon and the second one being from the acceptor exon. + """ + def sniff( self, filename ): # TODO + """ + Determines whether the file is a gmap Intron annotation file + """ + try: + pat = '>(\S+\.intron\d+)\s((\S+):(\d+)\.\.(\d+)(\s(.)+)?$' #>label chr:position + fh = open( filename ) + count = 0 + while True and count < 10: + line = fh.readline() + if not line: + break #EOF + line = line.strip() + if line: #first non-empty line + count += 1 + if re.match(pat,line) == None: # Failed to match + return False + finally: + fh.close() + return False + +class SNPAnnotation(IntervalAnnotation): + file_ext = 'gmap_snps' + """ + Example: + >rs62211261 21:14379270 CG + >rs62211262 21:14379281 AT + >rs62211263 21:14379298 WN + Each line must start with a ">" character, then be followed by an + identifier (which may have duplicates). Then there should be the + chromosomal coordinate of the SNP. (Coordinates are all 1-based, so + the first character of a chromosome is number 1.) Finally, there + should be the two possible alleles. (Previous versions required that + these be in alphabetical order: "AC", "AG", "AT", "CG", "CT", or "GT", + but that is no longer a requirement.) These alleles must correspond + to the possible nucleotides on the plus strand of the genome. If the + one of these two letters does not match the allele in the reference + sequence, that SNP will be ignored in subsequent processing as a + probable error. + + GSNAP also supports the idea of a wildcard SNP. A wildcard SNP allows + all nucleotides to match at that position, not just a given reference + and alternate allele. It is essentially as if an "N" were recorded at + that genomic location, although the index files still keep track of + the reference allele. To indicate that a position has a wildcard SNP, + you can indicate the genotype as "WN", where "W" is the reference + allele. Another indication of a wildcard SNP is to provide two + separate lines at that position with the genotypes "WX" and "WY", + where "W" is the reference allele and "X" and "Y" are two different + alternate alleles. + """ + def sniff( self, filename ): + """ + Determines whether the file is a gmap SNP annotation file + """ + try: + pat = '>(\S+)\s((\S+):(\d+)\s([TACGW][TACGN])$' #>label chr:position ATCG + fh = open( filename ) + count = 0 + while True and count < 10: + line = fh.readline() + if not line: + break #EOF + line = line.strip() + if line: #first non-empty line + count += 1 + if re.match(pat,line) == None: # Failed to match + return False + finally: + fh.close() + return False + +
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/gmap/snpindex.xml Fri Oct 21 11:38:55 2011 -0500 @@ -0,0 +1,141 @@ +<tool id="gmap_snpindex" name="GMAP SNP Index" version="2.0.0"> + <description>build index files for known SNPs</description> + <requirements> + <requirement type="binary">snpindex</requirement> + <!-- proposed tag for added datatype dependencies --> + <requirement type="datatype">gmapsnpindex</requirement> + <requirement type="datatype">gmapdb</requirement> + <requirement type="datatype">gmap_snps</requirement> + <requirement type="datatype">snps.iit</requirement> + </requirements> + <version_string>snpindex --version</version_string> + <command interpreter="command"> /bin/bash $shscript 2>1 1> $output </command> + <inputs> + <conditional name="refGenomeSource"> + <param name="genomeSource" type="select" label="Will you map to 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> + </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> + </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"/> + </when> + </conditional> + <conditional name="dbsnp"> + <param name="snp_source" type="select" label="Add SNP info from" > + <option value="snpTable">UCSC SNP Table</option> + <option value="snpFile">GMAP SNP File</option> + <option value="snpIIT">"GMAP SNPs map from GMAP iit store</option> + </param> + <when value="snpTable"> + <param name="snps" type="data" format="tabular" label="UCSC SNPs table" help="Example: ftp://hgdownload.cse.ucsc.edu/goldenPath/hg18/database/snp130.txt.gz" /> + <param name="snpsex" type="data" format="tabular" optional="true" label="UCSC SNP Exceptions table" help="Example: ftp://hgdownload.cse.ucsc.edu/goldenPath/hg18/database/snp130Exceptions.txt.gz" /> + <param name="weight" type="select" label="Include SNPs with at least Confidence Level" help=""> + <option value="1" selected="true">1 (High)</option> + <option value="2">2 (Medium)</option> + <option value="3">3 (All)</option> + </param> + </when> + <when value="snpFile"> + <param name="snps" type="data" format="gmap_snps" label="GMAP SNPs file" + help="Format (3 columns): + <br>>rs62211261 21:14379270 CG + <br>>rs62211262 21:14379281 CG + <br>Each line must start with a > character, then be followed by an + identifier (which may have duplicates). Then there should be the + chromosomal coordinate of the SNP. (Coordinates are all 1-based, so + the first character of a chromosome is number 1.) Finally, there + should be the two possible alleles: ( AC AG AT CG CT GT or AN CN GN TN) + <br>These alleles must correspond to the possible nucleotides on the plus strand of the genome. + If the one of these two letters does not match the allele in the reference + sequence, that SNP will be ignored in subsequent processing as a probable error. + The N stands for any other allele." /> + </when> + <when value="snpIIT"> + <param name="snpIIT" type="data" format="snps.iit" label="GMAP SNPs map" help="Created by: GMAP iit store" /> + </when> + </conditional> + <param name="snps_name" type="text" value="snps" label="Name for this SNP index" help="no white space characters"> + </param> + </inputs> + <outputs> + <!-- + <data format="txt" name="log" label="${tool.name} on ${on_string}: log"/> + --> + <data format="gmapsnpindex" name="output" label="${tool.name} on ${on_string} snpindex" /> + </outputs> + <configfiles> + <configfile name="shscript"> +#!/bin/bash +#set $ds = chr(36) +#set $gt = chr(62) +#set $lt = chr(60) +#set $ad = chr(38) +#import os.path +#if $refGenomeSource.genomeSource == "gmapdb": +#set $gmapdb = $refGenomeSource.gmapdb.extra_files_path +#set $refname = $refGenomeSource.gmapdb.metadata.db_name +#else: +#set $gmapdb = $os.path.dirname($refGenomeSource.gmapindex.value) +$refname = $os.path.basename($refGenomeSource.gmapindex.value) +#end if +#set $gmapsnpdir = $output.extra_files_path +mkdir -p $gmapsnpdir +#set $snpsname = $snps_name.__str__ +#set $snpsiit = '.'.join([$snpsname,'iit']) +#set $pathsnps = $os.path.join($gmapsnpdir,$snpsname) +#set $pathsnpsiit = $os.path.join($gmapsnpdir,$snpsiit) +#if $dbsnp.snp_source != 'none' and $dbsnp.snps.__str__ != 'None': +#if $dbsnp.snp_source == 'snpTable': +#if $dbsnp.snpsex.__str__ != 'None': +cat $dbsnp.snps | dbsnp_iit -w $dbsnp.weight -e $dbsnp.snpsex | iit_store -o $pathsnps +#else: +cat $dbsnp.snps | dbsnp_iit -w $dbsnp.weight | iit_store -o $pathsnps +#end if +#elif $dbsnp.snp_source == 'snpFile': +cat $dbsnp.snps | iit_store -o $pathsnps +#elif $dbsnp.snp_source == 'snpIIT': +cat $dbsnp.snps > $pathsnpsiit +#end if +snpindex -D $gmapdb -d $refname -V $output.extra_files_path -v $snpsname $pathsnpsiit +echo snpindex -D $gmapdb -d $refname -V $output.extra_files_path -v $snpsname $pathsnpsiit +#end if + </configfile> + </configfiles> + + <tests> + </tests> + + <help> + + +**GMAP SNP Index** + +GMAP SNP Index (snpindex in the GMAP documentaion) creates an index for known SNPs allowing for SNP tolerant mapping and alignment when using GMAP_ (Genomic Mapping and Alignment Program for mRNA and EST sequences) and GSNAP_ (Genomic Short-read Nucleotide Alignment Program). + +You will want to read the README_ + +Publication_ citation: Thomas D. Wu, Colin K. Watanabe Bioinformatics 2005 21(9):1859-1875; doi:10.1093/bioinformatics/bti310 + +.. _GMAP: http://research-pub.gene.com/gmap/ +.. _GSNAP: http://research-pub.gene.com/gmap/ +.. _README: http://research-pub.gene.com/gmap/src/README +.. _Publication: http://bioinformatics.oxfordjournals.org/cgi/content/full/21/9/1859 + + + </help> +</tool> +