changeset 1:eb60bf61a2b7

first commit
author nilesh
date Wed, 17 Jul 2013 12:39:36 -0500
parents c11fe2766a0c
children a4e511091a2f
files all_fasta.loc.sample muTect.xml tool_data_table_conf.xml.sample tool_dependencies.xml
diffstat 4 files changed, 139 insertions(+), 0 deletions(-) [+]
line wrap: on
line diff
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/all_fasta.loc.sample	Wed Jul 17 12:39:36 2013 -0500
@@ -0,0 +1,18 @@
+#This file lists the locations and dbkeys of all the fasta files
+#under the "genome" directory (a directory that contains a directory
+#for each build). The script extract_fasta.py will generate the file
+#all_fasta.loc. This file has the format (white space characters are
+#TAB characters):
+#
+#<unique_build_id>   <dbkey>   <display_name>   <file_path>
+#
+#So, all_fasta.loc could look something like this:
+#
+#apiMel3     apiMel3   Honeybee (Apis mellifera): apiMel3     /path/to/genome/apiMel3/apiMel3.fa
+#hg19canon   hg19      Human (Homo sapiens): hg19 Canonical   /path/to/genome/hg19/hg19canon.fa
+#hg19full    hg19      Human (Homo sapiens): hg19 Full        /path/to/genome/hg19/hg19full.fa
+#
+#Your all_fasta.loc file should contain an entry for each individual
+#fasta file. So there will be multiple fasta files for each build,
+#such as with hg19 above.
+#
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/muTect.xml	Wed Jul 17 12:39:36 2013 -0500
@@ -0,0 +1,107 @@
+<tool id="muTect" name="muTect" version="1.0.0">
+  <description>identify somatic point mutations</description>
+  <requirements>
+  		<requirement type="set_environment">MUTECTPATH</requirement>
+  </requirements>
+  <command interpreter="java">
+  	-Xmx2g -jar \$MUTECTPATH/muTect-1.1.1.jar
+  	--analysis_type MuTect
+  	--reference_sequence $reference
+  	#if ($cosmic.has_cosmic):
+  		--cosmic $cosmic.cosmicfile
+  	#end if
+	--dbsnp $dbsnp
+	#if str($intervals) != "" 
+  		--intervals $intervals
+  	#end if
+  	#if str($intervals) == "" and str($intervalfile) != "" 
+  		--intervals $intervalfile
+  	#end if
+	--input_file:normal $normal
+	--input_file:tumor $tumor
+	--out call_stats.txt
+	--coverage_file coverage.wig.txt	
+  </command>
+
+  <inputs>
+  	<param name="reference" type="data" format="bed, fasta" label="Select a reference genome">
+	</param>
+  	<param name="dbsnp" type="data" format="vcf" label="dbsnp.vcf file" />
+  	<param name="intervals" type="text" label="Intervals to process" help="In format 'chr1:1500-2500; chr2:2500-3500', separated by semicolons" optional="true"/>
+  	<param name="intervalfile" type="data" format="txt" label="Intervals to process (.txt file)" help="'chr1:1500-2500', one entry per line" optional="true"/>
+  	<param name="normal" type="bam" label="Normal BAM file"/>
+  	<param name="tumor" type="bam" label="Tumor BAM file"/>	
+    <conditional name="cosmic">
+		<param name="has_cosmic" type="boolean" label="Cosmic vcf file available for specimen" value="false" />
+		<when value="true">
+			<param name="cosmicfile" type="data" format="vcf" label="Cosmic vcf file"/>
+		</when>
+	</conditional>
+    	
+    	
+  </inputs>
+  
+  <outputs>
+	<data format="txt" name="callstats" label="Detailed caller output" from_work_dir="call_stats.txt"/>
+	<data format="txt" name="coverage" label="Filename for coverage output" from_work_dir="coverage.wig.txt"/>
+  	</data>
+  </outputs>
+  	
+  <help> 
+
+.. class:: infomark
+
+**License**
+
+TmuTect Revision: 44830
+GATK Revision: 2.1-202-g2fe6a31
+Copyright (c) 2012 The Broad Institute
+Please view our documentation at http://www.broadinstitute.org/gsa/wiki
+For support, please view our support site at http://getsatisfaction.com/gsa
+
+**What it does**
+
+MuTect is a method developed at the Broad Institute for the reliable 
+and accurate identification of somatic point mutations in next generation 
+sequencing data of cancer genomes.
+
+
+
+**Input**
+
+Reference Genome:
+
+	Fasta file of ref gnome
+
+Normal Sample:
+
+	bam normal sample
+
+Tumor Sample:
+
+	bam tumor sample
+
+
+Intervals:
+
+	A list of genomic intervals over which to operate.
+	
+
+
+**Output**
+
+Caller Output: 
+	
+	Detailed caller output
+
+Coverage Output:
+	
+	write out coverage in WIGGLE format to this file
+
+
+  </help>
+</tool>
+
+
+
+
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/tool_data_table_conf.xml.sample	Wed Jul 17 12:39:36 2013 -0500
@@ -0,0 +1,8 @@
+<!-- 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>
+    <!-- Locations of all fasta files under genome directory -->
+    <table name="all_fasta" comment_char="#">
+        <columns>value, dbkey, name, path</columns>
+        <file path="all_fasta.loc" />
+    </table>
+</tables>
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/tool_dependencies.xml	Wed Jul 17 12:39:36 2013 -0500
@@ -0,0 +1,6 @@
+<?xml version="1.0"?>
+<tool_dependency>
+    <set_environment version="1.0">
+        <environment_variable name="MUTECTPATH" action="set_to">$REPOSITORY_INSTALL_DIR</environment_variable>
+    </set_environment>
+</tool_dependency>