changeset 1:bc685d13b637 draft

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/rgrnastar commit 97a064489364118d108b0dd2cfb4d9bc53080837
author iuc
date Thu, 19 Nov 2015 05:34:06 -0500
parents b2326241bb09
children ace9f5a2b40f
files rg_rnaStar.xml test-data/rnastar_test2.log test-data/rnastar_test2_mapped_reads.bam test-data/rnastar_test2_splicejunctions.bed tool-data/rnastar_index.loc.sample
diffstat 4 files changed, 92 insertions(+), 27 deletions(-) [+]
line wrap: on
line diff
--- a/rg_rnaStar.xml	Mon May 18 13:34:13 2015 -0400
+++ b/rg_rnaStar.xml	Thu Nov 19 05:34:06 2015 -0500
@@ -1,14 +1,17 @@
-<tool id="rna_star" name="rnastar" version="2.4.0d">
+<tool id="rna_star" name="RNA STAR" version="2.4.0d">
     <description>Gapped-read mapper for RNA-seq data</description>
     <requirements>
         <requirement type="package" version="2.4.0d">rnastar</requirement>
         <requirement type="package" version="0.1.19">samtools</requirement>
     </requirements>
     <stdio>
+        <regex match="EXITING: FATAL INPUT ERROR:" source="both" level="fatal"/>
+        <regex match="EXITING: fatal error trying to allocate genome arrays, exception thrown: std::bad_alloc" source="both" level="fatal"/>
+        <regex match="\[sam_read1\] missing header\? Abort!" source="both" level="fatal"/>
         <regex match=".*" source="both" level="warning" description="Some stderr/stdout text"/>
     </stdio>
 
-    <command>
+    <command><![CDATA[
     ##
     ## Run STAR.
     ##
@@ -34,10 +37,13 @@
     #if str($singlePaired.sPaired) == "paired"
             $singlePaired.input2
     #end if
-        --runThreadN 4
+        --runThreadN \${GALAXY_SLOTS:-4}
     #if str($params.settingsType) == "full":
         --chimSegmentMin $params.chim_segment_min
         --chimScoreMin $params.chim_score_min
+        --seedSearchStartLmax $params.seed_search_start_l_max
+        --alignSJDBoverhangMin $params.align_sjdb_overhang_min
+        --outFilterScoreMinOverLread $params.out_filter_score_min_over_l_read
     #end if
 
     ## may or may not need to generate SAM tags and handle non-canonicals for Cufflinks tools.
@@ -49,16 +55,16 @@
     ##
 
     ## Convert aligned reads.
-    samtools view -Shb Aligned.out.sam | samtools sort - AlignedSorted 2&gt;/dev/null
+    samtools view -Shb Aligned.out.sam | samtools sort - AlignedSorted 2>/dev/null
 
     ## Convert chimeric reads.
     #if str($params.settingsType) == "full" and $params.chim_segment_min > 0:
-        ; samtools view -Shb Chimeric.out.sam | samtools sort - ChimericSorted 2&gt;/dev/null
+        ; samtools view -Shb Chimeric.out.sam | samtools sort - ChimericSorted 2>/dev/null
     #end if
-    </command>
+    ]]></command>
 
     <inputs>
-        <param name="jobName" type="text" size="120" value="rna-star run" label="Job narrative (added to output names)"
+        <param name="jobName" type="text" value="rna-star run" label="Job narrative (added to output names)"
           help="Only letters, numbers and underscores (_) will be retained in this field">
            <sanitizer invalid_char="">
               <valid initial="string.letters,string.digits"><add value="_" /> </valid>
@@ -109,7 +115,7 @@
               <option value="--outSAMstrandField intronMotif" selected="true">Add XS for cufflinks</option>
               <option value="">No XS added to sam output</option>
             </param>
-            <param name="outFilterIntronMotifs" type="select" label="Canonical junction preparation for unstranded data">
+            <param name="outFilterIntronMotifs" type="select" label="Canonical junction preparation for unstranded data (--outFilterIntronMotifs)">
               <option value="">No special handling - all non-canonical junctions passed through</option>
               <option value="--outFilterIntronMotifs RemoveNoncanonical" selected="true">Remove all non-canonical junctions for eg cufflinks</option>
               <option value="--outFilterIntronMotifs RemoveNoncanonicalUnannotated">Remove only unannotated non-canonical junctions for eg cufflinks</option>
@@ -122,10 +128,12 @@
             </param>
             <when value="preSet" />
             <!-- Full/advanced params. -->
-            <when value="full">
-            <param name="chim_segment_min" type="integer" min="0" value="0" label="Minimum chimeric segment length" />
-            <param name="chim_score_min" type="integer" min="0" value="0" label="Minimum total (summed) score of the chimeric segments" />
-
+            <when value="full">        
+                <param name="chim_segment_min" type="integer" min="0" value="0" label="Minimum chimeric segment length (--chimSegmentMin)" />
+                <param name="chim_score_min" type="integer" min="0" value="0" label="Minimum total (summed) score of the chimeric segments (--chimScoreMin)" />
+                <param name="seed_search_start_l_max" type="integer" min="0" value="50" label="Defines the search start point through the read - the read is split into pieces no longer than this value (--seedSearchStartLmax)" />
+                <param name="align_sjdb_overhang_min" type="integer" value="1" label="Minimum overhang for annotated junctions (--alignSJDBoverhangMin)" />
+                <param name="out_filter_score_min_over_l_read" type="float" value="0.66" label="OutFilterScoreMin normalized to read length; sum of mates’ lengths for paired-end reads (--outFilterScoreMinOverLread)" />
             </when>
         </conditional>
     </inputs>
@@ -216,21 +224,43 @@
     </outputs>
     <tests>
         <test>
- <param name='input1' value='tophat_in2.fastqsanger' ftype='fastqsanger' />
- <param name='jobName' value='rnastar_test' />
- <param name='genomeSource' value='history' />
- <param name='ownFile' value='tophat_test.fa' />
- <param name='sPaired' value='single' />
- <param name='outSAMattributes' value='--outSAMattributes All' />
- <param name='outSAMstrandField' value='--outSAMstrandField intronMotif' />
- <param name='outFilterIntronMotifs' value='--outFilterIntronMotifs RemoveNoncanonical' />
- <output name='output_log' file='rnastar_test.log' compare='diff' lines_diff = '10'/>
- <output name='splice_junctions' file="rnastar_test_splicejunctions.bed" compare="sim_size" delta="200"/>
- <output name='mapped_reads' file="rnastar_test_mapped_reads.bam" compare="sim_size" delta="200" />
+            <param name='input1' value='tophat_in2.fastqsanger' ftype='fastqsanger' />
+            <param name='jobName' value='rnastar_test' />
+            <param name='genomeSource' value='history' />
+            <param name='ownFile' value='tophat_test.fa' />
+            <param name='sPaired' value='single' />
+            <param name='outSAMattributes' value='--outSAMattributes All' />
+            <param name='outSAMstrandField' value='--outSAMstrandField intronMotif' />
+            <param name='outFilterIntronMotifs' value='--outFilterIntronMotifs RemoveNoncanonical' />
+            
+            <output name='output_log' file='rnastar_test.log' compare='diff' lines_diff = '10'/>
+            <output name='splice_junctions' file="rnastar_test_splicejunctions.bed"/>
+            <output name='mapped_reads' file="rnastar_test_mapped_reads.bam" compare="sim_size" delta="200" />
+        </test>
+        <test>
+            <param name='input1' value='tophat_in2.fastqsanger' ftype='fastqsanger' />
+            <param name='jobName' value='rnastar_test' />
+            <param name='genomeSource' value='history' />
+            <param name='ownFile' value='tophat_test.fa' />
+            <param name='sPaired' value='single' />
+            <param name='outSAMattributes' value='--outSAMattributes All' />
+            <param name='outSAMstrandField' value='--outSAMstrandField intronMotif' />
+            <param name='outFilterIntronMotifs' value='--outFilterIntronMotifs RemoveNoncanonical' />
+            
+            <param name="settingsType" value="full" />
+
+            <param name="chim_segment_min" value="0" />
+            <param name="chim_score_min" value="0" />
+            <param name="seed_search_start_l_max" value="25" />
+            <param name="align_sjdb_overhang_min" value="3" />
+            <param name="out_filter_score_min_over_l_read" value="0.9" />
+
+            <output name='output_log' file='rnastar_test2.log' compare='diff' lines_diff = '10'/>
+            <output name='splice_junctions' file="rnastar_test2_splicejunctions.bed"/>
+            <output name='mapped_reads' file="rnastar_test2_mapped_reads.bam" compare="sim_size" delta="200" />
         </test>
     </tests>
 <help>
-
 **What it does**
 Runs the rna star gapped aligner. Suited to paired or single end rna-seq.
 
@@ -291,7 +321,9 @@
 
 **Attributions**
 
-Note that each component has its own license. Good luck with figuring out your obligations.
+Note that each component has its own license:
+ - RNA STAR: GPLv3
+ - samtools: MIT/Expat License
 
 rna_star - see the web site at rna_star_
 
@@ -309,13 +341,13 @@
 
 .. _STAR: https://bitbucket.org/jgoecks/jeremys-code/raw/fa1930a689b8e2f6b59cc1706e5ba0ed8ad357be/galaxy/tool-wrappers/star.xml
 .. _licensed: http://creativecommons.org/licenses/by-nc-nd/3.0/
-.. _rna_star: http://code.google.com/p/rna-star/
+.. _rna_star: https://github.com/alexdobin/STAR
 .. _rna_starMS: http://bioinformatics.oxfordjournals.org/content/29/1/15.full
 .. _Galaxy: http://getgalaxy.org
 
 </help>
 <citations>
-    <citation type="doi">doi: 10.1093/bioinformatics/bts635</citation>
+    <citation type="doi">10.1093/bioinformatics/bts635</citation>
 </citations>
 </tool>
 
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/rnastar_test2.log	Thu Nov 19 05:34:06 2015 -0500
@@ -0,0 +1,31 @@
+                                 Started job on |	Jul 23 12:00:42
+                             Started mapping on |	Jul 23 12:00:42
+                                    Finished on |	Jul 23 12:00:43
+       Mapping speed, Million of reads per hour |	0.36
+
+                          Number of input reads |	100
+                      Average input read length |	75
+                                    UNIQUE READS:
+                   Uniquely mapped reads number |	89
+                        Uniquely mapped reads % |	89.00%
+                          Average mapped length |	74.80
+                       Number of splices: Total |	47
+            Number of splices: Annotated (sjdb) |	0
+                       Number of splices: GT/AG |	47
+                       Number of splices: GC/AG |	0
+                       Number of splices: AT/AC |	0
+               Number of splices: Non-canonical |	0
+                      Mismatch rate per base, % |	1.73%
+                         Deletion rate per base |	0.00%
+                        Deletion average length |	0.00
+                        Insertion rate per base |	0.00%
+                       Insertion average length |	0.00
+                             MULTI-MAPPING READS:
+        Number of reads mapped to multiple loci |	1
+             % of reads mapped to multiple loci |	1.00%
+        Number of reads mapped to too many loci |	0
+             % of reads mapped to too many loci |	0.00%
+                                  UNMAPPED READS:
+       % of reads unmapped: too many mismatches |	0.00%
+                 % of reads unmapped: too short |	10.00%
+                     % of reads unmapped: other |	0.00%
Binary file test-data/rnastar_test2_mapped_reads.bam has changed
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/rnastar_test2_splicejunctions.bed	Thu Nov 19 05:34:06 2015 -0500
@@ -0,0 +1,2 @@
+test_chromosome	251	350	1	1	0	23	0	33
+test_chromosome	401	500	1	1	0	24	0	36