diff picard_CollectRnaSeqMetrics.xml @ 129:03ed36a962af draft

Uploaded

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/picard_CollectRnaSeqMetrics.xml	Wed Feb 26 02:10:19 2014 -0500
@@ -0,0 +1,98 @@
+<tool name="CollectRnaSeqMetrics" id="picard_CollectRnaSeqMetrics" version="1.106.0">
+<description>Collect RNA-Seq Metrics</description>
+<requirements><requirement type="package" version="1.106.0">picard</requirement></requirements>
+   <command interpreter="python">
+      picard_wrapper.py -i "${input_file}" -d "${html_file.files_path}" -t "${html_file}"
+    -n "${out_prefix}" --tmpdir "${__new_file_path__}" --assumesorted ${ASSUME_SORTED}
+    --refflat ${REF_FLAT}
+    #if $identify_ribosomal.opt == "yes"
+    	--ribosomalintervals ${identify_ribosomal.RIBOSOMAL_INTERVALS}
+    #end if
+    --malevel "${malevel}"
+    --minlength ${MINIMUM_LENGTH}
+    --strandspecificity ${STRAND_SPECIFICITY}
+    --rrnafragmentpercentage ${RRNA_FRAGMENT_PERCENTAGE}
+    #for $i in $IGNORE_SEQUENCES
+        --ignoreseq "${i.IGNORE_SEQUENCE}"
+    #end for 
+    -j "\$JAVA_JAR_PATH/CollectRnaSeqMetrics.jar"
+  </command>
+    
+  <stdio>
+    <exit_code range="0" level="warning" description="Tool finished correctly" />
+  </stdio>
+   
+  <inputs>
+  	<param format="sam" name="input_file" type="data" label="Input SAM file." help="" />
+  
+      <param format="data" name="REF_FLAT" type="data" label="Gene annotations in refFlat form. Format described here: http://genome.ucsc.edu/goldenPath/gbdDescriptionsOld.html#RefFlat Required." help="" />
+      
+    <conditional name="identify_ribosomal">
+      <param name="opt" type="select" label="Identify ribosomal bases" help="If 'no' is selected, no bases will be identified as being ribosomal.">
+        <option value="no">no</option>
+        <option value="yes">yes</option>
+      </param>
+      <when value="no" />
+      <when value="yes">
+        <param format="data" name="RIBOSOMAL_INTERVALS" type="data" label="Location of rRNA sequences in genome, in interval_list format. If not specified no bases will be identified as being ribosomal. Format described here: http://picard.sourceforge.net/javadoc/net/sf/picard/util/IntervalList.html Default value: null." help="" />
+       </when>
+    </conditional>      
+      
+      <param name="STRAND_SPECIFICITY" type="select" label="For strand-specific library prep." help="For unpaired reads, use FIRST_READ_TRANSCRIPTION_STRAND if the reads are expected to be on the transcription strand. {NONE, FIRST_READ_TRANSCRIPTION_STRAND, SECOND_READ_TRANSCRIPTION_STRAND}">
+            <option value="NONE" selected="True">None</option>
+            <option value="FIRST_READ_TRANSCRIPTION_STRAND">FIRST_READ_TRANSCRIPTION_STRAND</option>
+            <option value="SECOND_READ_TRANSCRIPTION_STRAND">SECOND_READ_TRANSCRIPTION_STRAND</option>
+      </param>
+      
+      <param name="MINIMUM_LENGTH" type="text" value="500" label="When calculating coverage based values (e.g. CV of coverage) only use transcripts of this length or greater." help="" />
+      
+     <repeat name="IGNORE_SEQUENCES" title="Ignore Sequences">
+      <param name="IGNORE_SEQUENCE" label="Ignore Sequence" type="text" help="If a read maps to a sequence specified with this option, all the bases in the read are counted as ignored bases." />
+    </repeat>
+      
+      <param name="RRNA_FRAGMENT_PERCENTAGE" type="text" value="0.8" label="This percentage of the length of a fragment must overlap one of the ribosomal intervals for a read or read pair by this must in order to be considered rRNA." help="" />
+      
+      <param name="malevel" value="0" type="select" multiple="true"  label="Metric Accumulation Level"
+      help="Level(s) at which metrics will be accumulated">
+      <option value="ALL_READS" selected="true">All reads (default)</option>
+      <option value="SAMPLE" default="true">Sample</option>
+      <option value="LIBRARY" default="true">Library</option>
+      <option value="READ_GROUP" default="true">Read group</option>
+     </param>      
+      
+      <param  checked="True" truevalue="true" falsevalue="false" name="ASSUME_SORTED" type="boolean" label="If true (default), then the sort order in the header file will be ignored." />
+  </inputs>
+  <outputs>
+    		<data format="html" name="html_file"  label="${out_prefix}.html"/>
+  </outputs>
+  <tests>
+  <test>
+    
+    </test>
+  </tests>
+  <help>
+Picard documentation says:
+ 
+  
+CollectRnaSeqMetrics
+
+Documentation: http://picard.sourceforge.net/command-line-overview.shtml#CollectRnaSeqMetrics
+Program to collect metrics about the alignment of RNA to various functional classes of loci in the genome: coding, intronic, UTR, intergenic, ribosomal. Also determines strand-specificity for strand-specific libraries.
+Option	Description
+REF_FLAT=File	Gene annotations in refFlat form. Format described here: http://genome.ucsc.edu/goldenPath/gbdDescriptionsOld.html#RefFlat Required.
+RIBOSOMAL_INTERVALS=File	Location of rRNA sequences in genome, in interval_list format. If not specified no bases will be identified as being ribosomal. Format described here: http://picard.sourceforge.net/javadoc/net/sf/picard/util/IntervalList.html Default value: null.
+STRAND_SPECIFICITY=StrandSpecificity	For strand-specific library prep. For unpaired reads, use FIRST_READ_TRANSCRIPTION_STRAND if the reads are expected to be on the transcription strand. Required. Possible values: {NONE, FIRST_READ_TRANSCRIPTION_STRAND, SECOND_READ_TRANSCRIPTION_STRAND}
+MINIMUM_LENGTH=Integer	When calculating coverage based values (e.g. CV of coverage) only use transcripts of this length or greater. Default value: 500. This option can be set to 'null' to clear the default value.
+CHART_OUTPUT=File	The PDF file to write out a plot of normalized position vs. coverage. Default value: null.
+IGNORE_SEQUENCE=String	If a read maps to a sequence specified with this option, all the bases in the read are counted as ignored bases. These reads are not counted as This option may be specified 0 or more times.
+RRNA_FRAGMENT_PERCENTAGE=Double	This percentage of the length of a fragment must overlap one of the ribosomal intervals for a read or read pair by this must in order to be considered rRNA. Default value: 0.8. This option can be set to 'null' to clear the default value.
+METRIC_ACCUMULATION_LEVEL=MetricAccumulationLevel	The level(s) at which to accumulate metrics. Possible values: {ALL_READS, SAMPLE, LIBRARY, READ_GROUP} This option may be specified 0 or more times. This option can be set to 'null' to clear the default list.
+INPUT=File	Input SAM or BAM file. Required.
+OUTPUT=File	File to write the output to. Required.
+REFERENCE_SEQUENCE=File	Reference sequence fasta Default value: null.
+ASSUME_SORTED=Boolean	If true (default), then the sort order in the header file will be ignored. Default value: true. This option can be set to 'null' to clear the default value. Possible values: {true, false}
+STOP_AFTER=Long	Stop after processing N reads, mainly for debugging. Default value: 0. This option can be set to 'null' to clear the default value. 
+
+ 
+  </help>
+</tool>