Mercurial > repos > saskia-hiltemann > virtual_normal_analysis

changeset 2:885ba15c2564 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded
author saskia-hiltemann
date Mon, 03 Aug 2015 05:45:16 -0400
parents 1c6710924e80
children ac09a5aaed0b
files JunctionDiff-vs-background.sh JunctionDiff-vs-background.xml README.txt TV-vs-background.sh TV-vs-background.xml tool-data/virtual_normal_correction.loc.sample vcf2lv.sh vcf2lv.xml
diffstat 8 files changed, 80 insertions(+), 57 deletions(-) [+]
line wrap: on
line diff
--- a/JunctionDiff-vs-background.sh	Mon Aug 03 05:03:16 2015 -0400
+++ b/JunctionDiff-vs-background.sh	Mon Aug 03 05:45:16 2015 -0400
@@ -20,7 +20,7 @@
 		--scoreThresholdA) 		scoreThresholdA=$2;shift;;  
 		--scoreThresholdB) 		scoreThresholdB=$2;shift;;  
 		--distance) 			distance=$2;shift;;  
-		--minlength) 			minlength=$2;shift;;		
+		--minlength) 			minlength=$2;shift;;  
         -h)        		shift;;
 		--)        		shift;break;;
         -*)        		usage;;
--- a/JunctionDiff-vs-background.xml	Mon Aug 03 05:03:16 2015 -0400
+++ b/JunctionDiff-vs-background.xml	Mon Aug 03 05:45:16 2015 -0400
@@ -1,4 +1,4 @@
-<tool id="t-vs-vnormal_junctions" name="Virtual Normal Correction SVs" version="1.6">
+<tool id="t-vs-vnormal_junctions" name="Virtual Normal Correction SVs" version="1.8">
 	<description> Filter SVs based on presence in VN set </description>
 	
 	<requirements>		
@@ -9,32 +9,31 @@
 	JunctionDiff-vs-background.sh 
 		--variants $variants 
 		--reference ${reference.fields.reference_crr_cgatools} 
-		#if $virtnorm.VNset == "diversity"
-			--VN_junctions ${reference.fields.VN_genomes_junctionfile_list} 
-		#else
-			--VN_junctions ${reference.fields.VN_genomes_junctionfile_list_1000G} 
-		#end if
+		--VN_junctions ${reference.fields.VN_genomes_junctionfile_list}${VNset}
 		--cgatools_binary cgatools
 		--outputfile_filtered $output_filtered 
 		--scoreThresholdA $scoreThresholdA 
 		--scoreThresholdB $scoreThresholdB 
 		--distance $distance 
-		--minlength $minlength					
+		--minlength $minlength			
 	</command>
 	
 	<inputs>
+		<param name="variants" type="data" format="tabular" label="CG Junctions file"/>	
+		
 		<!--select build-->
 		<param name="reference" type="select" label="Select Build">
 			<options from_data_table="virtual_normal_correction" />
-			<filter type="data_meta" ref="variants" key="dbkey" column="0" />
 		</param>
-		<conditional name="virtnorm" >
-		<param name="VNset" type="select" label="Select Virtual Normal set to use" help="1000Genomes set can only be used for hg19 samples">
-			<option value="diversity" selected="true"> CG Diversity Panel and trios (54 Genomes) (hg18/hg19) </option>
-			<option value="thousand" > CG 1000G project genomes (433 Genomes) (hg19 only) </option>
+
+		<param name="VNset" type="select" label="Select Virtual Normal set to use" help="1000Genomes set can only be used for hg19 samples, for hg18 54 genomes will be used.">
+			<option value="46_diversity.txt" > CG Diversity Panel (46 Genomes) </option>
+			<option value="433_1000g.txt" > CG 1000G project genomes (433 Genomes) (hg19 only) </option>
+			<option value="479_diversity_1000g.txt" > Diversity and 1000G (479 genomes) (hg19 only) </option>
+                        <option value="10_tutorial.txt" > Small VN for tutorial (10 Genomes) </option>
 		</param>
-		</conditional>
-		<param name="variants" type="data" format="tabular" label="CG Junctions file"/>
+		
+			
 		<param name="scoreThresholdA" type="text" value="10" label="scoreThreshold" help="The minimum number of discordant mate pair alignments supporting the junction from input genome"/>
 		<param name="scoreThresholdB" type="text" value="10" label="scoreThreshold" help="The minimum number of discordant mate pair alignments supporting the junction from background genomes"/>
 		<param name="distance" type="text" value="200" label="Maximum distance between coordinates of potentially compatible junctions."/>		
@@ -48,9 +47,9 @@
 
   <outputs>
        <data format="tabular" name="output_filtered" label="${fname} Filtered junctions for ${tool.name} on  ${on_string}"/>		
-       <data format="tabular" name="output_report" from_work_dir= "output_reports.tsv" label="${fname} report for ${tool.name} on  ${on_string}">
-       	<filter> report == "Y" </filter>
-       </data>			  
+	   <data format="tabular" name="output_report" from_work_dir= "output_reports.tsv" label="${fname} report for ${tool.name} on  ${on_string}">
+		   <filter> report == "Y" </filter>
+	   </data>	
   </outputs>
 
 	<help> 
--- a/README.txt	Mon Aug 03 05:03:16 2015 -0400
+++ b/README.txt	Mon Aug 03 05:45:16 2015 -0400
@@ -7,7 +7,7 @@
    - change "/path/to/hg18.crr" to the location of the Complete Genomics reference crr file on your system
      (can be downloaded from ftp://ftp.completegenomics.com/ReferenceFiles/ )
      
-   - change "/path/to/VN_genomes_varfiles_hg18.txt" to the location of the file containing the locations of all the Complete Genomics
+   - change "/path/to/VN_genomes_varfiles_lists_hg18" to the location of the directory containing files with the locations of all the Complete Genomics
      varfiles to be used as a virtual normal. This file should contain 1 file location per line, e.g.
      
 	    /path/to/normal-varfile-1
@@ -20,10 +20,44 @@
 		/path/to/normal-varfile-8
    			...
    			
-   	 Varfiles can be in compressed or uncompressed form. For example, Complete Genomics' Diversity panel can be used.
+   - edit the tool xml file to offer sets of virtual normals
+
+	[..]
+		<!-- edit these options to reflect sets of normal you have available. The values must name files within the directories specified in data_table_conf.xml file -->
+		<param name="VNset" type="select" label="Select Virtual Normal set to use" help="1000Genomes set can only be used for hg19 samples, for hg18 54 genomes will be used.">
+			<option value="46_diversity.txt" > CG Diversity Panel and trios (54 Genomes) </option>
+			<option value="433_1000g.txt" > CG 1000G project genomes (433 Genomes) (hg19 only) </option>
+			<option value="479_diversity_1000g.txt" > Diversity and 1000G (479 genomes) (hg19 only) </option>
+                        <option value="10_tutorial.txt" > Small VN for tutorial (10 Genomes) </option>
+		</param>
+	[..]
+
+	the values indicate files expected to be at the location configured in the loc file, 
+
+
+     So if your .loc file looks like this:
+
+
+		#loc file for annovar tool
+
+		# <columns>value, dbkey, name, VN_genomes_varfiles_list, VN_genomes_junctionfile_list, reference_crr_cgatools</columns>
+
+		hg18	hg18	Virtual Normal hg18	/path/to/VN_genomes_varfiles_lists_hg18	/path/to/VN_genomes_junctionfiles_lists_hg18	/path/to/hg18.crr
+		hg19	hg19	Virtual_Normal hg19	/path/to/VN_genomes_varfiles_lists_hg19	/path/to/VN_genomes_junctionfiles_lists_hg19	/path/to/hg19.crr
+
+     And your xml file like the example above, then the tool expects the following files to exist:
+		 /path/to/VN_genomes/varfiles_list_hg18/46_diversity.txt 	
+     		 /path/to/VN_genomes/varfiles_list_hg18/433_1000g.txt
+		etc
+     and containing a 1-per-line list of locations of the varfiles of the normal genomes.
+
+
+ 
+
+     Varfiles can be in compressed or uncompressed form. For example, Complete Genomics' Diversity panel can be used.
      (can be downloaded from ftp://ftp2.completegenomics.com/)		
    
-   - change	"/path/to/VN_genomes_junctionfiles_hg18.txt" to the location of the file containing the locations of all the Complete Genomics
+   - change	"/path/to/VN_genomes_junctionfiles_lists_hg18" to the location of the file containing the locations of all the Complete Genomics
      junctionfiles to be used as a virtual normal. This file should contain 1 file location per line.  For example, Complete Genomics' 
 	 Diversity panel can be used. (can be downloaded from ftp://ftp2.completegenomics.com/)
      
--- a/TV-vs-background.sh	Mon Aug 03 05:03:16 2015 -0400
+++ b/TV-vs-background.sh	Mon Aug 03 05:45:16 2015 -0400
@@ -26,6 +26,8 @@
 done
 
 # replace newline chars with spaces for input to testvariants
+echo "varfiles list: $VN_varfiles_list"
+
 tr '\n' ' ' < $VN_varfiles_list > VN_varfiles.txt
 
 
@@ -137,3 +139,4 @@
 
 
 
+
--- a/TV-vs-background.xml	Mon Aug 03 05:03:16 2015 -0400
+++ b/TV-vs-background.xml	Mon Aug 03 05:45:16 2015 -0400
@@ -1,4 +1,4 @@
-<tool id="t-vs-vnormal" name="Virtual Normal Correction SmallVars" version="1.6">
+<tool id="t-vs-vnormal" name="Virtual Normal Correction SmallVars" version="1.7">
 	<description> Filter small variants based on presence in Virtual Normal set  </description>
 
 	<requirements>		
@@ -9,15 +9,11 @@
 	TV-vs-background.sh 
 		--variants $variants
 		--reference ${reference.fields.reference_crr_cgatools}
-		#if $virtnorm.VNset == "diversity":
-			--VN_varfiles ${reference.fields.VN_genomes_varfiles_list} 
-		#else
-			--VN_varfiles ${reference.fields.VN_genomes_varfiles_list_1000G} 
-		#end if
+		--VN_varfiles "${reference.fields.VN_genomes_varfiles_list}${VNset}"
 		--threshold $threshold
-                --thresholdhc $thresholdhc
+		--thresholdhc $thresholdhc
 		--outputfile_all $output_all
-		--outputfile_filtered $output_filtered		
+		--outputfile_filtered $output_filtered
 	</command>
 	
 	<inputs>
@@ -25,34 +21,26 @@
 		<!--select build-->
 		<param name="reference" type="select" label="Select Build">
 			<options from_data_table="virtual_normal_correction" />
-			<filter type="data_meta" ref="variants" key="dbkey" column="0" />
 		</param>
-		<conditional name="virtnorm" >
+		
+		<!-- edit these options to reflect sets of normal you have available. The values must name files within the directories specified in data_table_conf.xml file -->
 		<param name="VNset" type="select" label="Select Virtual Normal set to use" help="1000Genomes set can only be used for hg19 samples, for hg18 54 genomes will be used.">
-			<option value="diversity" > CG Diversity Panel and trios (54 Genomes) </option>
-			<option value="thousand" > CG 1000G project genomes (433 Genomes) (hg19 only) </option>
-		</param> 
-		</conditional>
-				
-		<param name="threshold" type="text" value="1" label="Threshold: Filter variants if present in at least this number of the background genomes"/>
-                <param name="thresholdhc" type="text" value="10" label="High Confidence Threshold: Label a somatic variant as high-confidence if locus was fully called in at least this many normal genomes" help="Please adjust according to number of normals used and desired stringency. "/>
+			<option value="46_diversity.txt" > CG Diversity Panel and trios (54 Genomes) </option>
+			<option value="433_1000g.txt" > CG 1000G project genomes (433 Genomes) (hg19 only) </option>
+			<option value="479_diversity_1000g.txt" > Diversity and 1000G (479 genomes) (hg19 only) </option>
+                        <option value="10_tutorial.txt" > Small VN for tutorial (10 Genomes) </option>
+		</param>
+					
+		<param name="threshold" type="text" value="1" label="Filter out variants present in at least this number of the virtual normal genomes"/>
+        <param name="thresholdhc" type="text" value="10" label="High Confidence Threshold: Label a somatic variant as high-confidence if locus was fully called in at least this many normal genomes" help="Please adjust according to number of normals used and desired stringency. "/>
 		<param name="fname" type="text" value="" label="Prefix for your output file" help="Optional. For example sample name."/>
-		<!--<param name="debug" type="select" label="individual level annotations?" help="get a columns per normal sample whether variant was present (only available for fully public normal samples)">
-			<option value="N" > No  </option>
-			<option value="Y" > Yes </option>
-		</param>
-                -->
 	</inputs>
 
   <outputs>
-    <data format="tabular" name="output_all" label="${fname} All variants for ${tool.name} on ${on_string}"/>		
-    <data format="tabular" name="output_filtered" label="${fname} Filtered variants for ${tool.name} on  ${on_string}"/>
-    <data format="tabular" name="output_filtered_highconf" label="${fname} High Confidence Filtered variants for ${tool.name} on  ${on_string}" from_work_dir="output_filtered_highconf.tsv"/>
-    <!--<data format="tabular" name="output_filtered" label="${fname} Filtered variants for ${tool.name} on  ${on_string}"/>
-	<data format="tabular" name="output_expanded" from_work_dir="output_expanded" label="${fname} expanded annotation for ${tool.name} on  ${on_string}">
-		<filter> $debug == "Y" </filter>
-	</data>	
-    -->
+    <data format="tabular" name="output_all" label="All variants for ${tool.name} on ${on_string}"/>		
+    <data format="tabular" name="output_filtered" label="Filtered variants for ${tool.name} on  ${on_string}"/>	
+	<data format="tabular" name="output_filtered_highconf" label="${fname} High Confidence Filtered variants for ${tool.name} on  ${on_string}" from_work_dir="output_filtered_highconf.tsv"/>
+
   </outputs>
 
 	<help> 
--- a/tool-data/virtual_normal_correction.loc.sample	Mon Aug 03 05:03:16 2015 -0400
+++ b/tool-data/virtual_normal_correction.loc.sample	Mon Aug 03 05:45:16 2015 -0400
@@ -2,5 +2,5 @@
 
 # <columns>value, dbkey, name, VN_genomes_varfiles_list, VN_genomes_junctionfile_list, reference_crr_cgatools</columns>
 
-hg18	hg18	Virtual Normal hg18	/mnt/galaxyIndices/VirtualNormal/VN_genomes_varfiles_hg18.txt	/mnt/galaxyIndices/VirtualNormal/VN_genomes_junctionfiles_hg18.txt	/mnt/galaxyIndices/cgatools/build36.crr
-hg19	hg19	Virtual Normal hg19	/mnt/galaxyIndices/VirtualNormal/VN_genomes_varfiles_hg19.txt	/mnt/galaxyIndices/VirtualNormal/VN_genomes_junctionfiles_hg19.txt	/mnt/galaxyIndices/cgatools/build37.crr
+#hg18	hg18	Virtual Normal hg18	/path/to/VN_genomes_varfiles_lists_hg18	/path/to/VN_genomes_junctionfiles_lists_hg18	/path/to/hg18.crr
+#hg19	hg19	Virtual_Normal hg19	/path/to/VN_genomes_varfiles_lists_hg19	/path/to/VN_genomes_junctionfiles_lists_hg19	/path/to/hg19.crr
--- a/vcf2lv.sh	Mon Aug 03 05:03:16 2015 -0400
+++ b/vcf2lv.sh	Mon Aug 03 05:45:16 2015 -0400
@@ -19,7 +19,7 @@
 		count=0;
 		
 		#output new header
-		print "variantId", "chromosome", "begin", "end", "varType", "reference", "alleleSeq", "xRef"
+		print "variantId", "chromosome", "begin", "end", "varType", "reference", "alleleSeq"
 	}{
 
 		if(substr($0,1,1)!="#" && $5 != "."){ #skip header or nonvariant entries (period in ALT column)
@@ -85,8 +85,7 @@
 		
 				#print output variant(s)
 		
-				if(chromosome != "chrM")
-					print count, chromosome, start, end, varType, reference, alleleSeq, ""
+				print count, chromosome, start, end, varType, reference, alleleSeq
 			
 				count+=1
 			}
--- a/vcf2lv.xml	Mon Aug 03 05:03:16 2015 -0400
+++ b/vcf2lv.xml	Mon Aug 03 05:45:16 2015 -0400
@@ -1,5 +1,5 @@
 <tool id="vcf2lv" name="VCF-2-VariantList" version="1">
- 	<description> virtual normal preprocessing - convert VCF file to CG-compatible variant list </description>
+ 	<description> convert VCF file to CG-compatible variant list </description>
   
   	<command interpreter="bash"> 
   		vcf2lv.sh $vcffile $outputfile