Repository 'gmap'
hg clone https://toolshed.g2.bx.psu.edu/repos/jjohnson/gmap

Changeset 8:a89fec682254 (2011-12-08)
Previous changeset 7:561503a442f0 (2011-11-08) Next changeset 9:7f032685214b (2011-12-08)
Commit message:
gmap/gsnap updated to version 2011-11-30
modified:
gmap.xml
gmap_build.xml
gsnap.xml
iit_store.xml
snpindex.xml
b
diff -r 561503a442f0 -r a89fec682254 gmap.xml
--- a/gmap.xml Tue Nov 08 13:26:41 2011 -0600
+++ b/gmap.xml Thu Dec 08 11:00:46 2011 -0600
b
b'@@ -1,13 +1,7 @@\n-<tool id="gmap" name="GMAP" version="2.0.0">\n+<tool id="gmap" name="GMAP" version="2.0.1">\n   <description>Genomic Mapping and Alignment Program for mRNA and EST sequences</description>\n   <requirements>\n     <requirement type="binary">gmap</requirement>\n-    <!-- proposed tag for added datatype dependencies -->\n-    <requirement type="datatype">gmapdb</requirement>\n-    <requirement type="datatype">gmap_annotation</requirement>\n-    <requirement type="datatype">gmap_splicesites</requirement>\n-    <requirement type="datatype">gmap_introns</requirement>\n-    <requirement type="datatype">gmap_snps</requirement>\n   </requirements>\n   <version_string>gmap --version</version_string>\n   <command>\n@@ -49,9 +43,11 @@\n     #elif $result.format == "sam":\n       --format=$result.sam_paired_read\n       $result.no_sam_headers \n+      #* Removed in gmap version 2011-11-30\n       #if len($result.noncanonical_splices.__str__) > 0\n          --noncanonical-splices=$result.noncanonical_splices\n       #end if\n+      *#\n       #if len($result.read_group_id.__str__) > 0\n          --read-group-id=$result.read_group_id\n       #end if\n@@ -70,35 +66,50 @@\n     #if $computation.options == "advanced":\n       $computation.nosplicing\n       $computation.cross_species\n-      --min-intronlength=$computation.min_intronlength\n-      --intronlength=$computation.intronlength\n-      --localsplicedist=$computation.localsplicedist\n-      --totallength=$computation.totallength\n-      --trimendexons=$computation.trimendexons\n+      #if len($computation.min_intronlength.__str__) > 0\n+        --min-intronlength=$computation.min_intronlength\n+      #end if\n+      #if len($computation.intronlength.__str__) > 0\n+        --intronlength=$computation.intronlength\n+      #end if\n+      #if len($computation.localsplicedist.__str__) > 0\n+        --localsplicedist=$computation.localsplicedist\n+      #end if\n+      #if len($computation.totallength.__str__) > 0\n+        --totallength=$computation.totallength\n+      #end if\n+      #if len($computation.trimendexons.__str__) > 0\n+        --trimendexons=$computation.trimendexons\n+      #end if\n       --direction=$computation.direction\n       --canonical-mode=$computation.canonical\n       --prunelevel=$computation.prunelevel\n       --allow-close-indels=$computation.allow_close_indels\n-      --microexon-spliceprob=$computation.microexon_spliceprob\n-      #if int($computation.chimera_margin) >= 0:\n+      #if len($computation.microexon_spliceprob.__str__) >= 0:\n+        --microexon-spliceprob=$computation.microexon_spliceprob\n+      #end if\n+      #if len($computation.chimera_margin.__str__) >= 0:\n         --chimera-margin=$computation.chimera_margin\n       #end if\n     #end if\n     #if $advanced.options == "used":\n-      #if int($advanced.npaths) >= 0:\n+      #if len($advanced.npaths.__str__) > 0:\n         --npaths=$advanced.npaths\n       #end if\n-      #if int($advanced.chimera_overlap) > 0:\n+      #if len($advanced.suboptimal_score.__str__) > 0:\n+        --suboptimal-score=$advanced.suboptimal_score\n+      #end if\n+      #if len($advanced.chimera_overlap.__str__) > 0:\n         --chimera_overlap=$advanced.chimera_overlap\n       #end if\n       $advanced.protein\n       $advanced.tolerant\n       $advanced.nolengths\n       $advanced.invertmode\n-      #if int($advanced.introngap) > 0:\n+      #if len($advanced.introngap.__str__) > 0:\n         --introngap=$advanced.introngap\n       #end if\n-      #if int($advanced.wraplength) > 0:\n+      #if len($advanced.wraplength.__str__) > 0:\n         --wraplength=$advanced.wraplength\n       #end if\n     #end if\n@@ -200,11 +211,22 @@\n       <when value="default"/>\n       <when value="advanced">\n        <param name="nosplicing" type="boolean" truevalue="--nosplicing" falsevalue="" checked="false" label="Turn off splicing" help="(useful for aligning genomic sequences onto a genome)"/>\n-       <param name="min_intronlength" type="integer" value="9" label="Min length for one internal intron '..b'essage="slice probability between 0.00 and 1.00" min="0" max="1"/> \n        </param>\n        <param name="prunelevel"  type="select" label="Pruning level">\t\n@@ -255,11 +280,24 @@\n         <option value="--invertmode=1">Invert cDNA and print genomic (-) strand</option>\n         <option value="--invertmode=2">Invert cDNA and print genomic (+) strand</option>\n        </param>\n-       <param name="introngap" type="integer" value="3" label="Nucleotides to show on each end of intron (default=3)" />\t\n-       <param name="wraplength" type="integer" value="50" label="Line Wrap length for alignment (default=50)" />\t\n-       <param name="npaths" type="integer" value="-1" optional="true"\n-              label="Maximum number of paths to show.  Ignored if negative.  If 0, prints two paths if chimera detected, else one." />\t\n-       <param name="chimera_overlap" type="integer" value="0" label="Overlap to show, if any, at chimera breakpoint" />\t\n+       <param name="introngap" type="integer" value="" optional="true" label="Nucleotides to show on each end of intron (default=3)">\t\n+         <validator type="in_range" message="introngap must be positive" min="0" />\n+       </param>\n+       <param name="wraplength" type="integer" value="" optional="true" label="Line Wrap length for alignment (default=50)">\t\n+         <validator type="in_range" message="wraplength must be positive" min="1" />\n+       </param>\n+       <param name="npaths" type="integer" value="" optional="true"\n+              label="Maximum number of paths to show.  Ignored if negative.  If 0, prints two paths if chimera detected, else one." >\t\n+         <validator type="in_range" message="npaths must be positive" min="0" />\n+       </param>\n+       <param name="suboptimal_score" type="integer" value="" optional="true"\n+              label="Report only paths whose score is within this value of the best path"\n+              help="By default the program prints all paths found." >\t\n+         <validator type="in_range" message="suboptimal_score must be positive" min="0" />\n+       </param>\n+       <param name="chimera_overlap" type="integer" value="" optional="true" label="Overlap to show, if any, at chimera breakpoint (default 0)" >\t\n+                <validator type="in_range" message="chimera_overlap must be positive" min="0" />\n+       </param>\n        <param name="tolerant" type="boolean" checked="false" truevalue="--tolerant=true" falsevalue="" \n               label="Translates cDNA with corrections for frameshifts"/>\n        <param name="protein" type="select" label="Protein alignment" help="">\n@@ -294,10 +332,10 @@\n       <option value="coords">coords in table format</option>\n       <option value="sam" selected="true">SAM format</option>\n     </param>\n-      <when value="gmap"/>\n+      <when value="gmap">\n+      </when>\n       <when value="summary"/>\n       <when value="align">\n-\n       </when>\n       <when value="continuous">\n       </when>\n@@ -320,11 +358,13 @@\n       <when value="sam">\n         <param name="sam_paired_read" type="boolean" truevalue="sampe" falsevalue="samse" checked="false" label="SAM paired reads"/>\n         <param name="no_sam_headers" type="boolean" truevalue="--no-sam-headers" falsevalue="" checked="false" label="Do not print headers beginning with \'@\'"/>\n+        <!--  Removed in gmap version 2011-11-30\n         <param name="noncanonical_splices" type="select" label="Print non-canonical genomic gaps greater than 20 nt in CIGAR string as STRING.">\n           <option value="">Use default</option>\n           <option value="N">N</option>\n           <option value="D">D</option>\n         </param>\n+        -->\n         <param name="read_group_id" type="text" value="" label="Value to put into read-group id (RG-ID) field"/>\n         <param name="read_group_name" type="text" value="" label="Value to put into read-group name (RG-SM) field"/>\n         <param name="read_group_library" type="text" value="" label="Value to put into read-group library (RG-LB) field"/>\n'
b
diff -r 561503a442f0 -r a89fec682254 gmap_build.xml
--- a/gmap_build.xml Tue Nov 08 13:26:41 2011 -0600
+++ b/gmap_build.xml Thu Dec 08 11:00:46 2011 -0600
b
@@ -2,9 +2,6 @@
   <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>
b
diff -r 561503a442f0 -r a89fec682254 gsnap.xml
--- a/gsnap.xml Tue Nov 08 13:26:41 2011 -0600
+++ b/gsnap.xml Thu Dec 08 11:00:46 2011 -0600
b
b'@@ -1,12 +1,7 @@\n-<tool id="gsnap" name="GSNAP" version="2.0.0">\n+<tool id="gsnap" name="GSNAP" version="2.0.1">\n   <description>Genomic Short-read Nucleotide Alignment Program</description>\n   <requirements>\n       <requirement type="binary">gsnap</requirement>\n-      <!-- proposed tag for added datatype dependencies -->\n-      <requirement type="datatype">gmapdb</requirement>\n-      <requirement type="datatype">gmapsnpindex</requirement>\n-      <requirement type="datatype">splicesites.iit</requirement>\n-      <requirement type="datatype">introns.iit</requirement>\n   </requirements>\n   <version_string>gsnap --version</version_string>\n   <command>\n@@ -25,10 +20,16 @@\n     #if $refGenomeSource.use_splicing.src == \'gmapdb\':\n       #if $refGenomeSource.use_splicing.splicemap != None and len($refGenomeSource.use_splicing.splicemap.__str__) > 0:\n         -s $refGenomeSource.use_splicing.splicemap.value\n+        #if $computation.trim_mismatch_score.__str__ == \'0\':\n+          $ambig_splice_noclip\n+        #end if\n       #end if\n     #elif $refGenomeSource.use_splicing.src == \'history\':\n       #if $refGenomeSource.use_splicing.splicemap != None and len($refGenomeSource.use_splicing.splicemap.__str__) > 0:\n         -S $os.path.dirname($refGenomeSource.use_splicing.splicemap) -s $os.path.basename($refGenomeSource.use_splicing.splicemap)\n+        #if $computation.trim_mismatch_score.__str__ == \'0\':\n+          $ambig_splice_noclip\n+        #end if\n       #end if\n     #end if\n     #if $refGenomeSource.use_snps.src == \'gmapdb\':\n@@ -43,9 +44,11 @@\n     #if $refGenomeSource.mode.__str__ != \'\':\n       --mode=$refGenomeSource.mode\n     #end if\n+    #* ## No longer in options as of version 2011-11-30\n     #if $mapq_unique_score.__str__ != \'\':\n       --mapq-unique-score=$mapq_unique_score\n     #end if\n+    *#\n     #if $computation.options == "advanced":\n       #if $computation.max_mismatches.__str__ != \'\':\n         --max-mismatches=$computation.max_mismatches\n@@ -82,6 +85,9 @@\n       #if $computation.trim_mismatch_score.__str__ != \'\':\n         --trim-mismatch-score=$computation.trim_mismatch_score\n       #end if\n+      #if $computation.trim_indel_score.__str__ != \'\':\n+        --trim-indel-score=$computation.trim_indel_score\n+      #end if\n       ## TODO - do we need these options (Is it tally XOR runlength?):\n       ## --tallydir=  --use-tally=tally\n       ## --runlengthdir  --use-runlength=runlength\n@@ -206,6 +212,12 @@\n         #if $seq.paired.pairmax_rna.__str__ != \'\':\n           --pairmax-rna=$seq.paired.pairmax_rna\n         #end if\n+        #if $seq.paired.pairexpect.__str__ != \'\':\n+          --pairexpect=$seq.paired.pairexpect\n+        #end if\n+        #if $seq.paired.pairdev.__str__ != \'\':\n+          --pairdev=$seq.paired.pairdev\n+        #end if\n         $seq.fastq $seq.paired.fastq\n       #else\n         $seq.fastq\n@@ -245,7 +257,11 @@\n               <option value="FF">fwd-fwd, same strand</option>\n             </param>\n             <param name="pairmax_dna"  type="integer" value="" optional="true" label="Max total genomic length for DNA-Seq paired reads, or other reads without splicing (default 1000)." help="Used if no splice file is provided and novelsplicing is off."/>\n-            <param name="pairmax_rna"  type="integer" value="" optional="true" label="Max total genomic length for RNA-Seq paired reads, or other reads that could have a splice (default 200000)." help="Used novelspliceing is specified or a splice file is provided.  Should probably match the value for localsplicedist."/>\n+            <param name="pairmax_rna"  type="integer" value="" optional="true" label="Max total genomic length for RNA-Seq paired reads, or other reads that could have a splice (default 200000)." help="Used when novel splicing is specified or a splice file is provided.  Should probably match the value for localsplicedist."/>\n+            <param name="pairexpect"  type="integer" value="" optional="true" label="Expected paired-end length" \n+             '..b' splicing at ends of the read, do not clip at the splice site, but extend instead into the intron.  \n+                    This flag makes sense only if you are trying to eliminate all soft clipping with --trim-mismatch-score=0"/>\n           </when>\n           <when value="gmapdb">\n             <param name="splicemap" type="select"  data_ref="gmapdb" label="Use map for splicing involving known sites or known introns" help="">\n@@ -412,6 +433,9 @@\n                 <filter type="data_meta" ref="gmapdb" key="maps" multiple="True"/>\n               </options>\n             </param>\n+            <param name="ambig_splice_noclip"  type="boolean" checked="false" truevalue="--ambig-splice-noclip" falsevalue="" label="Do not clip at ambiguous splice sites"\n+              help="For ambiguous known splicing at ends of the read, do not clip at the splice site, but extend instead into the intron.  \n+                    This flag makes sense only if you are trying to eliminate all soft clipping with --trim-mismatch-score=0"/>\n           </when>\n         </conditional>\n \n@@ -457,8 +481,12 @@\n          </param>\n          <param name="query_unk_mismatch" type="boolean" checked="false" truevalue="--query-unk-mismatch=1" falsevalue="" label="Count unknown (N) characters in the query as a mismatch"/>\n          <param name="genome_unk_mismatch" type="boolean" checked="true" truevalue="" falsevalue="--genome-unk-mismatch=0" label="Count unknown (N) characters in the genome as a mismatch"/>\n-         <param name="terminal_threshold"  type="integer" value="" optional="true" label="Threshold for searching for a terminal alignment (default 3)" \n-                help="(from one end of the read to the best possible position at the other end).  To turn off terminal alignments, set this to a high value." />\n+         <param name="terminal_threshold"  type="integer" value="" optional="true" label="Threshold for searching for a terminal alignment (default 2)" \n+                help="(from one end of the read to the best possible position at the other end).   For example, if this value is 2, then if GSNAP finds an exact or\n+                                   1-mismatch alignment, it will not try to find a terminal alignment.\n+                                   Note that this default value may not be low enough if you want to\n+                                   obtain terminal alignments for very short reads, although such reads\n+                                   probably don\'t have enough specificity for terminal alignments anyway." />\n          <param name="indel_penalty"  type="integer" value="" optional="true" label="Penalty for an indel (default 2)" \n                 help="Counts against mismatches allowed.  To find indels, make indel-penalty less than or equal to max-mismatches.  A value &lt; 2 can lead to false positives at read ends" />\n          <param name="indel_endlength"  type="integer" value="" optional="true" label="Minimum length at end required for indel alignments (default 4)" />\n@@ -474,7 +502,9 @@\n            <option value="off">off</option>\n          </param>\n          <param name="trim_mismatch_score" type="integer" value="" optional="true" label="Score to use for mismatches when trimming at ends (default is -3)" \n-                help="to turn off trimming, specify 0"/>\n+                help="to turn off trimming, specify 0 (Warning: turning trimming off will give false positive mismatches at the ends of reads)"/>\n+         <param name="trim_indel_score" type="integer" value="" optional="true" label="Score to use for indels when trimming at ends (default is -4)" \n+                help="to turn off trimming, specify 0 (Warning: turning trimming off will give false positive indels at the ends of reads)"/>\n          <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" \n               help="generated by gsnap_tally and iit_store"/>\n \n'
b
diff -r 561503a442f0 -r a89fec682254 iit_store.xml
--- a/iit_store.xml Tue Nov 08 13:26:41 2011 -0600
+++ b/iit_store.xml Thu Dec 08 11:00:46 2011 -0600
b
@@ -2,13 +2,6 @@
   <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>
b
diff -r 561503a442f0 -r a89fec682254 snpindex.xml
--- a/snpindex.xml Tue Nov 08 13:26:41 2011 -0600
+++ b/snpindex.xml Thu Dec 08 11:00:46 2011 -0600
b
@@ -2,11 +2,6 @@
   <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>