Mercurial > repos > iuc > data_manager_star_index_builder

changeset 11:d63c1442407f draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/data_managers/data_manager_star_index_builder commit 096286097ed5cdf189a1b68c3fc34d10f4142e54
author iuc
date Sun, 16 Apr 2023 08:31:33 +0000
parents a225487bf618
children 71c994a11f71
files data_manager/macros.xml data_manager_conf.xml
diffstat 2 files changed, 36 insertions(+), 23 deletions(-) [+]
line wrap: on
line diff
--- a/data_manager/macros.xml	Fri Feb 17 20:00:58 2023 +0000
+++ b/data_manager/macros.xml	Sun Apr 16 08:31:33 2023 +0000
@@ -5,7 +5,7 @@
     the index versions in sync, but you should manually update @IDX_VERSION_SUFFIX@ -->
     <!-- STAR version to be used -->
     <token name="@TOOL_VERSION@">2.7.10b</token>
-    <token name="@VERSION_SUFFIX@">0</token>
+    <token name="@VERSION_SUFFIX@">3</token>
     <token name="@PROFILE@">21.01</token>
     <!-- STAR index version compatible with this version of STAR
     This is the STAR version that introduced the index structure expected
@@ -64,23 +64,26 @@
     </xml>
     <xml name="dbKeyActions">
         <actions>
-            <conditional name="refGenomeSource.geneSource">
-                <when value="indexed">
-                    <action type="metadata" name="dbkey">
-                        <option type="from_data_table" name="@IDX_DATA_TABLE@" column="1" offset="0">
-                            <filter type="param_value" column="0" value="#" compare="startswith" keep="False"/>
-                            <filter type="param_value" ref="refGenomeSource.GTFconditional.genomeDir" column="0"/>
-                        </option>
-                    </action>
-                </when>
-                <when value="history">
-                    <action type="metadata" name="dbkey">
-                        <option type="from_param" name="refGenomeSource.genomeFastaFiles" param_attribute="dbkey" />
-                    </action>
-                </when>
-            </conditional>
+            <expand macro="dbKeyAction"/>
         </actions>
     </xml>
+    <xml name="dbKeyAction">
+        <conditional name="refGenomeSource.geneSource">
+            <when value="indexed">
+                <action type="metadata" name="dbkey">
+                    <option type="from_data_table" name="@IDX_DATA_TABLE@" column="1" offset="0">
+                        <filter type="param_value" column="0" value="#" compare="startswith" keep="False"/>
+                        <filter type="param_value" ref="refGenomeSource.GTFconditional.genomeDir" column="0"/>
+                    </option>
+                </action>
+            </when>
+            <when value="history">
+                <action type="metadata" name="dbkey">
+                    <option type="from_param" name="refGenomeSource.genomeFastaFiles" param_attribute="dbkey" />
+                </action>
+            </when>
+        </conditional>
+    </xml>
     <token name="@TEMPINDEX@"><![CDATA[
     ## Create temporary index for custom reference
     #if str($refGenomeSource.geneSource) == 'history':
@@ -219,7 +222,7 @@
         </conditional>
     </xml>
     <xml name="umidedup_options">
-        <option value="1MM_All" selected="true">Collapse all UMIs with 1 mismatch distance to each other</option>
+        <option value="1MM_All" selected="true">Collapse all UMIs with 1 mismatch distance to each other (1MM_All)</option>
         <option value="1MM_Directional_UMItools" >Directional method from the UMI-tool</option>
         <option value="1MM_Directional" >Directional with stringent UMI deduplication</option>
     </xml>
@@ -231,12 +234,12 @@
     </xml>
     <xml name="cb_match_wl_common">
         <option value="Exact" >Exact</option>
-        <option value="1MM" >Single match</option>
+        <option value="1MM" >Single match (1MM)</option>
     </xml>
     <xml name="cb_match_wl_cellranger">
-        <option value="1MM_multi" selected="true" >Multiple matches (CellRanger 2)</option>
-        <option value="1MM_multi_pseudocounts" >Multiple matches (CellRanger 3)</option>
-        <option value="1MM_multi_Nbase_pseudocounts" >Multimatching to WL is allowed for CBs with N-bases (CellRanger 3)</option>
+        <option value="1MM_multi" selected="true" >Multiple matches (CellRanger 2, 1MM_multi)</option>
+        <option value="1MM_multi_pseudocounts" >Multiple matches (CellRanger 3, 1MM_multi_pseudocounts)</option>
+        <option value="1MM_multi_Nbase_pseudocounts" >Multimatching to WL is allowed for CBs with N-bases (CellRanger 3, 1MM_multi_Nbase_pseudocounts)</option>
     </xml>
     <xml name="solo_adapter_params">
         <param argument="--soloAdapterSequence" type="text" value="-" label="Adapter sequence to anchor barcodes." >
@@ -278,6 +281,7 @@
     <xml name="outCountActions">
         <actions>
             <action name="column_names" type="metadata" default="GeneID,Counts_unstrand,Counts_firstStrand,Counts_secondStrand" />
+            <expand macro="dbKeyAction"/>
         </actions>
     </xml>
     <xml name="outWig">
@@ -305,7 +309,7 @@
             <option value="read_5p">signal from only 5’ of the 1st read</option>
             <option value="read2">signal from only 2nd read</option>
         </param>
-        <param argument="--outWigStrand" type="boolean" truevalue="Stranded" falsevalue="Unstranded" checked="true" label="collapse strands (unstranded coverage)" help="By default, the strands are separated."/>
+        <param argument="--outWigStrand" type="boolean" truevalue="Stranded" falsevalue="Unstranded" checked="true" label="Generate a coverage for each strand (stranded coverage)"/>
         <param argument="--outWigReferencesPrefix" type="text" value="-" label="prefix matching reference name" help="For example, set 'chr' if you mapped on an ensembl genome but you want to display on UCSC"/>
         <param argument="--outWigNorm" type="boolean" truevalue="RPM" falsevalue="None" checked="true" label="Normalize coverage to million of mapped reads (RPM)"/>
     </xml>
@@ -397,4 +401,13 @@
             <when value="-" />
         </conditional>
     </xml>
+    <xml name="outSAMmapqUnique">
+        <!-- MAPQ 255 is the default in STAR (coming from tophat behaviour and compatibility for Cufflinks) but it is a problematic value
+        - according to SAM/BAM specs it means "undefined".
+        - Using 255 as the max mapq causes problem with modern downstream tools like mutect2: https://sites.duke.edu/workblog/2021/08/18/star-rnaseq-gatk-mutect2/ and 60 has become an inofficial replacement for 255. -->
+        <param argument="--outSAMmapqUnique" type="integer" value="60" min="0" max="255"
+        label="MAPQ value for unique mappers"
+        help="STAR bases the mapping quality scores of alignment records in its BAM output on the number of alternative mappings for the read. If a read maps to multiple locations on the reference genome, the following MAPQ scoring scheme is
+used: >=5 mappings => MAPQ=0; 3-4 mappings => MAPQ=1; 2 mappings => MAPQ=3. This setting lets you control the MAPQ used for reads mapped to a single location. Set to 255 for compatibility with Cufflink (default in STAR) but keep to 60 for modern downstream tools like mutect2." />
+    </xml>
 </macros>
--- a/data_manager_conf.xml	Fri Feb 17 20:00:58 2023 +0000
+++ b/data_manager_conf.xml	Sun Apr 16 08:31:33 2023 +0000
@@ -1,6 +1,6 @@
 <?xml version="1.0"?>
 <data_managers>
-    <data_manager tool_file="data_manager/rna_star_index_builder.xml" id="rna_star_index_builder" version="0.0.7">
+    <data_manager tool_file="data_manager/rna_star_index_builder.xml" id="rna_star_index_builder">
         <data_table name="rnastar_index2x_versioned">
             <output>
                 <column name="value" />