Mercurial > repos > elixir-it > somaticsniper

changeset 0:70999d19997f draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded
author elixir-it
date Mon, 02 Jul 2018 11:16:55 -0400
parents
children 2ff18e84c946
files somatic_sniper.xml test-data/sniper_results.vcf test-data/sniper_test_normal.bam test-data/sniper_test_tumoral.bam
diffstat 4 files changed, 142 insertions(+), 0 deletions(-) [+]
line wrap: on
line diff
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/somatic_sniper.xml	Mon Jul 02 11:16:55 2018 -0400
@@ -0,0 +1,122 @@
+<tool id="somatic_sniper" name="SomaticSniper" version="1.0">
+  <description>identify single nucleotide positions that are different between tumor and normal</description>
+  <requirements>
+    <requirement type="package" version="1.0.5.0">somatic-sniper</requirement>	
+  </requirements> 
+  <command detect_errors="aggressive"><![CDATA[
+
+  ## SYMLINK BAM FILES ALONGSIDE INDEX FILES
+  ln -s $normal normal.bam;
+  ln -s $normal.metadata.bam_index normal.bam.bai;
+  ln -s $tumor tumor.bam;
+  ln -s $tumor.metadata.bam_index tumor.bam.bai;
+
+  #if $interval:
+
+  for i in \$(cut -f1 $interval); do
+
+  #end if
+
+	
+  ## BUILD SOMATICSNIPER COMMAND LINE 
+  \$CONDA_DEFAULT_ENV/bin/bam-somaticsniper
+    -F vcf
+    -q $advancedsettings.q
+    -Q $advancedsettings.Q
+    -T $advancedsettings.T
+    -N $advancedsettings.N
+    -r $advancedsettings.r
+    -n $advancedsettings.n
+    -t $advancedsettings.t
+    $advancedsettings.L 
+    $advancedsettings.G 
+    $advancedsettings.p
+
+    #if $ref.ref_options == "cached"
+      -f ${ref.index.fields.path}
+    #else
+      -f ${ref.ownFile}
+    #end if
+
+    #if $interval:
+    
+    <(samtools view -b tumor.bam \$i)
+    <(samtools view -b normal.bam \$i)
+    
+    #else:
+      tumor.bam
+      normal.bam
+
+    #end if
+
+    #if $interval:
+      tmp_\$i.txt
+    #else:
+      $variants
+    #end if
+    ;
+
+    #if $interval:
+
+      done;
+    
+      for i in \$(cut -f1 $interval); do
+      
+      if [ \$i == \$(cut -f1 $interval | head -n1) ] ; then
+        cat tmp_\$i.txt > $variants;
+      else
+        grep -v ^#.* tmp_\$i.txt >> $variants;
+      fi ;
+
+      done;  
+
+    #end if
+
+
+
+    ]]></command>
+	<inputs>
+		<conditional name="ref">
+			<param name="ref_options" type="select" label="Choose the source for the reference genome">
+				<option value="cached" selected="True">Use a built-in genome</option>
+				<option value="history">Use a genome from the history</option>
+			</param>
+			<when value="cached">
+				<param name="index" type="select" label="Reference Genome File" >
+					<options from_data_table="all_fasta" />
+				</param>
+      			</when>
+      			<when value="history">
+        			<param format="fasta" name="ownFile" type="data" metadata_name="dbkey" label="Reference Genome File" />
+      			</when>
+		</conditional>
+		<param format="bam" name="normal" type="data" label="Normal Alignment File" />
+		<param format="bam" name="tumor" type="data" label="Tumour Alignment File" />
+                <param type="data" format="txt" optional="true" name="interval" label="Specify Inteval"/>
+		<section name="advancedsettings" title="Advanced Settings" expanded="False" >
+			<param name="q" type="integer" value="0" label="Minimum read mapping quality"/>
+			<param name="Q" type="integer" value="15" label="Minimum somatic variant quality score"/>
+			<param name="T" type="float" value="0.850000" label="theta in maq consensus calling model (for -c/-g) [0.850000]"/>
+			<param name="N" type="integer" value="2" label="Ploidy (number of haplotypes)"/>
+			<param name="r" type="float" value="0.001000" label="Prior probability for differences between haplotypes"/>
+			<param name="n" type="text" value="NORMAL" label="Normal sample ID"/>
+			<param name="t" type="text" value="TUMOR" label="Tumour sample ID"/>
+  			<param name="L" type="boolean" truevalue="-L" falsevalue="" checked="true" label="Exclude LOH variants from output" />
+  			<param name="G" type="boolean"  truevalue="-G" falsevalue="" checked="true" label="Exclude gain of reference variants from output" />
+  			<param name="p" type="boolean"  truevalue="-p" falsevalue="" checked="true" label="Disable priors in somatic calculation (improved sensitivity for solid tumours)" />
+		</section>
+	</inputs>
+	<outputs>
+		<data name="variants" format="vcf" label="SomaticSniper SNVs" />
+	</outputs>
+	<tests>
+                <test>
+                  <param name="normal" file="sniper_test_normal.bam" />
+                  <param name="tumor" file="sniper_test_tumoral.bam" />
+                  <output name="variants" file="sniper_results.vcf" />
+                </test>
+        </tests>
+	<help>
+		http://gmt.genome.wustl.edu/packages/somatic-sniper/
+	</help>
+</tool>
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/sniper_results.vcf	Mon Jul 02 11:16:55 2018 -0400
@@ -0,0 +1,20 @@
+##fileformat=VCFv4.1
+##fileDate=20180622
+##phasing=none
+##reference=file:///export/gatkhg38pl/GRCh38.d1.vd1.fa
+##FORMAT=<ID=GT,Number=1,Type=String,Description="Genotype">
+##FORMAT=<ID=IGT,Number=1,Type=String,Description="Genotype when called independently (only filled if called in joint prior mode)">
+##FORMAT=<ID=DP,Number=1,Type=Integer,Description="Total read depth">
+##FORMAT=<ID=DP4,Number=4,Type=Integer,Description="# high-quality ref-forward bases, ref-reverse, alt-forward and alt-reverse bases">
+##FORMAT=<ID=BCOUNT,Number=4,Type=Integer,Description="Occurrence count for each base at this site (A,C,G,T)">
+##FORMAT=<ID=GQ,Number=1,Type=Integer,Description="Genotype quality">
+##FORMAT=<ID=JGQ,Number=1,Type=Integer,Description="Joint genotype quality (only filled if called in join prior mode)">
+##FORMAT=<ID=VAQ,Number=1,Type=Integer,Description="Variant allele quality">
+##FORMAT=<ID=BQ,Number=.,Type=Integer,Description="Average base quality">
+##FORMAT=<ID=MQ,Number=1,Type=Integer,Description="Average mapping quality across all reads">
+##FORMAT=<ID=AMQ,Number=.,Type=Integer,Description="Average mapping quality for each allele present in the genotype">
+##FORMAT=<ID=SS,Number=1,Type=Integer,Description="Variant status relative to non-adjacent Normal, 0=wildtype,1=germline,2=somatic,3=LOH,4=unknown">
+##FORMAT=<ID=SSC,Number=1,Type=Integer,Description="Somatic Score">
+#CHROM	POS	ID	REF	ALT	QUAL	FILTER	INFO	FORMAT	NORMAL	TUMOR
+chr22	22714396	.	G	A	.	.	.	GT:IGT:DP:DP4:BCOUNT:GQ:JGQ:VAQ:BQ:MQ:AMQ:SS:SSC	0/0:0/0:15:0,15,0,0:0,0,15,0:72:.:0:30:60:60:0:.	0/1:0/1:41:0,28,0,13:13,0,28,0:59:.:59:30,31:60:60,60:2:45
+chr22	22714411	.	T	C	.	.	.	GT:IGT:DP:DP4:BCOUNT:GQ:JGQ:VAQ:BQ:MQ:AMQ:SS:SSC	0/0:0/0:9:0,9,0,0:0,0,0,9:54:.:0:30:60:60:0:.	0/1:0/1:28:0,22,0,6:0,6,0,22:32:.:32:32,31:60:60,60:2:27
Binary file test-data/sniper_test_normal.bam has changed
Binary file test-data/sniper_test_tumoral.bam has changed