Mercurial > repos > fubar > rgrnastar_203e

changeset 0:f13499e0de61 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Initial commit
author fubar
date Fri, 09 Aug 2013 04:31:52 -0400
parents
children 88448bbbab2c
files prepStar.sh rg_rnaStar.xml tool-data/rnastar_indices.loc.sample tool_data_table_conf.xml.sample tool_dependencies.xml
diffstat 5 files changed, 276 insertions(+), 0 deletions(-) [+]
line wrap: on
line diff
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/prepStar.sh	Fri Aug 09 04:31:52 2013 -0400
@@ -0,0 +1,12 @@
+# automate their generation f
+# from existing fasta genomes
+INDEXROOT=/data/ucsc
+# fix that
+for genome in hg19 hg18 mm9 mm10 rn4 rn5
+do
+  TARGET=${INDEXROOT}/${genome}/rnastar
+  mkdir -p $TARGET
+  cd $TARGET
+  STAR --runMode genomeGenerate --genomeDir $TARGET --genomeFastaFiles ${TARGET}/$genome.fa --runThreadN 4
+done
+
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/rg_rnaStar.xml	Fri Aug 09 04:31:52 2013 -0400
@@ -0,0 +1,217 @@
+<tool id="rna_star" name="RNA-STAR" version="0.2">
+    <description>Gapped-read mapper for RNA-seq data</description>
+    <requirements>
+        <requirement type="package">star</requirement>
+    <requirement type="package">samtools</requirement>
+    </requirements>
+    <command>
+    ##
+    ## Run STAR.
+    ##
+
+        STAR
+    ## Can adjust this as appropriate for the system.
+    --genomeLoad NoSharedMemory
+
+    --genomeDir ${refGenomeSource.index.fields.path} 
+    --readFilesIn $input1 
+    #if $singlePaired.sPaired == "paired"
+            $singlePaired.input2
+        #end if
+
+        --runThreadN 4
+
+    ## Parameters.
+    #if $params.settingsType == "full":
+        --chimSegmentMin $params.chim_segment_min
+        --chimScoreMin $params.chim_score_min
+    #end if
+
+    ## Needed to generate SAM tags for Cufflinks tools.
+    --outSAMstrandField intronMotif
+
+    ;
+
+    ##
+    ## BAM conversion.
+    ##
+
+    ## Convert aligned reads.
+    samtools view -Shb Aligned.out.sam | samtools sort - Aligned.out
+
+    ## Convert chimeric reads.
+    #if $params.settingsType == "full" and $params.chim_segment_min > 0:
+        ; samtools view -Shb Chimeric.out.sam | samtools sort - Chimeric.out
+    #end if
+    </command>
+
+    <stdio>
+        <regex match=".*" source="both" level="warning" description="generic stdout/err chatter"/>
+    </stdio>
+
+    <inputs>
+        <param name="jobName" type="text" size="120" 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>
+           </sanitizer>
+        </param>
+        <!-- FASTQ input(s) and options specifically for paired-end data. -->
+        <conditional name="singlePaired">
+            <param name="sPaired" type="select" label="Single ended or mate-pair ended reads in this library?">
+              <option value="single" selected="true">Single-end</option>
+              <option value="paired">Paired-end</option>
+            </param>
+            <when value="single">
+                <param format="fastqsanger,fastq,fasta" name="input1" type="data" label="RNA-Seq FASTQ file" help="Nucleotide-space: Must have Sanger-scaled quality values with ASCII offset 33"/>
+            </when>
+            <when value="paired">
+                <param format="fastqsanger,fastq,fasta" name="input1" type="data" label="RNA-Seq FASTQ file, forward reads" help="Nucleotide-space: Must have Sanger-scaled quality values with ASCII offset 33" />
+                <param format="fastqsanger,fastq,fasta" name="input2" type="data" label="RNA-Seq FASTQ file, reverse reads" help="Nucleotide-space: Must have Sanger-scaled quality values with ASCII offset 33" />
+            </when>
+        </conditional>
+
+        <!-- Genome source. -->
+        <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="history">Use one from the history</option>
+            </param>
+            <when value="indexed">
+            <param name="index" type="select" label="Select a reference genome">
+                <options from_data_table="rnastar_indexes">
+                    <filter type="sort_by" column="2"/>
+                    <validator type="no_options" message="No indexes are available for the selected input dataset"/>
+                </options>
+            </param>
+            </when>
+            <when value="history">
+                <param name="ownFile" type="data" format="fasta" metadata_name="dbkey" label="Select the reference genome" />
+            </when>
+        </conditional>
+
+        <!-- Parameter settings. -->
+        <conditional name="params">
+            <param name="settingsType" type="select" label="Settings to use" help="You can use the default settings or set custom values for any STAR parameter.">
+                <option value="preSet" selected="true">Use Defaults</option>
+                <option value="full">Full parameter list</option>
+            </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>
+        </conditional>
+    </inputs>
+
+    <outputs>
+       <data format="txt" name="output_log" label="${on_string}_{jobName}.log" from_work_dir="Log.final.out"/>
+       <data format="interval" name="chimeric_junctions" label="${on_string}_{jobName}_starchimjunc.bed" from_work_dir="Chimeric.out.junction">
+          <filter>(params['settingsType'] == 'full' and params['chim_segment_min'] > 0)</filter>
+          <actions>
+             <conditional name="refGenomeSource.genomeSource">
+             <when value="indexed">
+               <action type="metadata" name="dbkey">
+                <option type="from_data_table" name="star_indexes" column="1" offset="0">
+                 <filter type="param_value" column="0" value="#" compare="startswith" keep="False"/>
+                  <filter type="param_value" ref="refGenomeSource.index" column="0"/>
+                </option>
+               </action>
+             </when>
+             <when value="history">
+               <action type="metadata" name="dbkey">
+                 <option type="from_param" name="refGenomeSource.ownFile" param_attribute="dbkey" />
+               </action>
+             </when>
+             </conditional>
+          </actions>
+       </data>
+       <data format="bam" name="chimeric_reads" label="${on_string}_{jobName}_starmappedchim.bam" 
+                    from_work_dir="Chimeric.out.bam">
+         <filter>(params['settingsType'] == 'full' and params['chim_segment_min'] > 0)</filter>
+          <actions>
+             <conditional name="refGenomeSource.genomeSource">
+             <when value="indexed">
+               <action type="metadata" name="dbkey">
+                <option type="from_data_table" name="star_indexes" column="1" offset="0">
+                 <filter type="param_value" column="0" value="#" compare="startswith" keep="False"/>
+                  <filter type="param_value" ref="refGenomeSource.index" column="0"/>
+                </option>
+               </action>
+             </when>
+             <when value="history">
+               <action type="metadata" name="dbkey">
+                 <option type="from_param" name="refGenomeSource.ownFile" param_attribute="dbkey" />
+               </action>
+             </when>
+             </conditional>
+          </actions>
+        </data>
+        <data format="interval" name="splice_junctions" label="${on_string}_{jobName}_starsplicejunct.bed" 
+                   from_work_dir="SJ.out.tab">
+          <actions>
+             <conditional name="refGenomeSource.genomeSource">
+             <when value="indexed">
+               <action type="metadata" name="dbkey">
+                <option type="from_data_table" name="star_indexes" column="1" offset="0">
+                 <filter type="param_value" column="0" value="#" compare="startswith" keep="False"/>
+                  <filter type="param_value" ref="refGenomeSource.index" column="0"/>
+                </option>
+               </action>
+             </when>
+             <when value="history">
+               <action type="metadata" name="dbkey">
+                 <option type="from_param" name="refGenomeSource.ownFile" param_attribute="dbkey" />
+               </action>
+             </when>
+             </conditional>
+          </actions>
+        </data>
+        <data format="bam" name="mapped_reads" label="${on_string}_{jobName}_starmapped.bam" 
+                    from_work_dir="Aligned.out.bam">
+          <actions>
+             <conditional name="refGenomeSource.genomeSource">
+             <when value="indexed">
+               <action type="metadata" name="dbkey">
+                <option type="from_data_table" name="star_indexes" column="1" offset="0">
+                 <filter type="param_value" column="0" value="#" compare="startswith" keep="False"/>
+                  <filter type="param_value" ref="refGenomeSource.index" column="0"/>
+                </option>
+               </action>
+             </when>
+             <when value="history">
+               <action type="metadata" name="dbkey">
+                 <option type="from_param" name="refGenomeSource.ownFile" param_attribute="dbkey" />
+               </action>
+             </when>
+             </conditional>
+          </actions>
+        </data>
+    </outputs>
+<help>
+    
+**Attributions**
+Note that each component has its own license. Good luck with figuring out your obligations.
+
+rna_star - see the web site at rna_star_
+
+For details, please see the rna_starMS_
+"STAR: ultrafast universal RNA-seq aligner"
+A. Dobin et al, Bioinformatics 2012; doi: 10.1093/bioinformatics/bts635
+
+Galaxy_ (that's what you are using right now!) for gluing everything together 
+
+Most of the work for this wrapper XML is Jeremy Goecks' original STAR_ wrapper 
+
+Minor tweaks to output names to suit our downstream purposes, toolshed automated dependencies and odds and ends of other code and documentation comprising this tool was written by Ross Lazarus and
+that part is licensed_ the same way as other rgenetics artefacts
+
+.. _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_starMS: http://bioinformatics.oxfordjournals.org/content/29/1/15.full
+.. _Galaxy: http://getgalaxy.org
+
+</help>
+</tool>
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/tool-data/rnastar_indices.loc.sample	Fri Aug 09 04:31:52 2013 -0400
@@ -0,0 +1,16 @@
+#This is a sample file distributed with Galaxy that enables tools
+#to use a directory of rna-star indexed sequences data files. You will
+#need to create these data files and then create a bowtie_indices.loc
+#file similar to this one (store it in this directory) that points to
+#the directories in which those files are stored. The bowtie2_indices.loc
+#file has this format (longer white space characters are TAB characters):
+#
+#<unique_build_id>   <dbkey>   <display_name>   <file_base_path>
+#
+hg19	hg19	hg19 full	/data/ucsc/hg19/rnastar
+hg18	hg18	hg18 full	/data/ucsc/hg18/rnastar
+mm9	mm9	mm9 full	/data/ucsc/mm9/rnastar
+mm10	mm10	mm10 full	/data/ucsc/mm10/rnastar
+rn4	rn4	rn4 full	/data/ucsc/rn4/rnastar
+rn5	rn5	rn5 full	/data/ucsc/rn5/rnastar
+
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/tool_data_table_conf.xml.sample	Fri Aug 09 04:31:52 2013 -0400
@@ -0,0 +1,7 @@
+<!-- Use the file tool_data_table_conf.xml.oldlocstyle if you don't want to update your loc files as changed in revision 4550:535d276c92bc-->
+<tables>
+    <table name="rnastar_indexes" comment_char="#">
+        <columns>value, dbkey, name, path</columns>
+        <file path="tool-data/rnastar_indices.loc" />
+    </table>
+</tables>
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/tool_dependencies.xml	Fri Aug 09 04:31:52 2013 -0400
@@ -0,0 +1,24 @@
+<?xml version="1.0"?>
+<tool_dependency>
+    <package name="rnastar" version="2.3.0e">
+        <install version="1.0">
+            <actions>
+                <action type="make_directory">$INSTALL_DIR</action>
+                <action type="make_directory">$INSTALL_DIR/bin</action>
+                <action type="download_by_url">https://rna-star.googlecode.com/files/STAR_2.3.0e.tgz</action>
+                <action type="shell_command">make</action>
+                <action type="move_file">
+                    <source>STAR</source>
+                    <destination>$INSTALL_DIR/bin</destination>
+                </action>
+                <action type="set_environment">
+                    <environment_variable name="PATH" action="prepend_to">$INSTALL_DIR/bin</environment_variable>
+                </action>
+            </actions>
+        </install>
+        <readme>
+Installs the STAR binary for rnastar - see https://code.google.com/p/rna-star/
+        </readme>
+    </package>
+</tool_dependency>
+