Mercurial > repos > anton > vcfrandomsample

changeset 0:81b9a3179670

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Imported from capsule None
author anton
date Wed, 11 Jun 2014 17:11:37 -0400
parents
children a67b14d368a4
files test-data/vcflib.vcf test-data/vcfrandomsample-test1.vcf tool_dependencies.xml vcfrandomsample.xml
diffstat 4 files changed, 116 insertions(+), 0 deletions(-) [+]
line wrap: on
line diff
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/vcflib.vcf	Wed Jun 11 17:11:37 2014 -0400
@@ -0,0 +1,31 @@
+##fileformat=VCFv4.0
+##fileDate=20090805
+##source=myImputationProgramV3.1
+##reference=1000GenomesPilot-NCBI36
+##phasing=partial
+##INFO=<ID=NS,Number=1,Type=Integer,Description="Number of Samples With Data">
+##INFO=<ID=AN,Number=1,Type=Integer,Description="Total number of alleles in called genotypes">
+##INFO=<ID=AC,Number=.,Type=Integer,Description="Allele count in genotypes, for each ALT allele, in the same order as listed">
+##INFO=<ID=DP,Number=1,Type=Integer,Description="Total Depth">
+##INFO=<ID=AF,Number=.,Type=Float,Description="Allele Frequency">
+##INFO=<ID=AA,Number=1,Type=String,Description="Ancestral Allele">
+##INFO=<ID=DB,Number=0,Type=Flag,Description="dbSNP membership, build 129">
+##INFO=<ID=H2,Number=0,Type=Flag,Description="HapMap2 membership">
+##FILTER=<ID=q10,Description="Quality below 10">
+##FILTER=<ID=s50,Description="Less than 50% of samples have data">
+##FORMAT=<ID=GT,Number=1,Type=String,Description="Genotype">
+##FORMAT=<ID=GQ,Number=1,Type=Integer,Description="Genotype Quality">
+##FORMAT=<ID=DP,Number=1,Type=Integer,Description="Read Depth">
+##FORMAT=<ID=HQ,Number=2,Type=Integer,Description="Haplotype Quality">
+##ALT=<ID=DEL:ME:ALU,Description="Deletion of ALU element">
+##ALT=<ID=CNV,Description="Copy number variable region">
+#CHROM	POS	ID	REF	ALT	QUAL	FILTER	INFO	FORMAT	NA00001	NA00002	NA00003
+19	111	.	A	C	9.6	.	.	GT:HQ	0|0:10,10	0|0:10,10	0/1:3,3
+19	112	.	A	G	10	.	.	GT:HQ	0|0:10,10	0|0:10,10	0/1:3,3
+20	14370	rs6054257	G	A	29	PASS	NS=3;DP=14;AF=0.5;DB;H2	GT:GQ:DP:HQ	0|0:48:1:51,51	1|0:48:8:51,51	1/1:43:5:.,.
+20	17330	.	T	A	3	q10	NS=3;DP=11;AF=0.017	GT:GQ:DP:HQ	0|0:49:3:58,50	0|1:3:5:65,3	0/0:41:3:.,.
+20	1110696	rs6040355	A	G,T	67	PASS	NS=2;DP=10;AF=0.333,0.667;AA=T;DB	GT:GQ:DP:HQ	1|2:21:6:23,27	2|1:2:0:18,2	2/2:35:4:.,.
+20	1230237	.	T	.	47	PASS	NS=3;DP=13;AA=T	GT:GQ:DP:HQ	0|0:54:.:56,60	0|0:48:4:51,51	0/0:61:2:.,.
+20	1234567	microsat1	G	GA,GAC	50	PASS	NS=3;DP=9;AA=G;AN=6;AC=3,1	GT:GQ:DP	0/1:.:4	0/2:17:2	1/1:40:3
+20	1235237	.	T	.	.	.	.	GT	0/0	0|0	./.
+X	10	rsTest	AC	A,ATG	10	PASS	.	GT	0	0/1	0|2
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/vcfrandomsample-test1.vcf	Wed Jun 11 17:11:37 2014 -0400
@@ -0,0 +1,26 @@
+##fileformat=VCFv4.0
+##fileDate=20090805
+##source=myImputationProgramV3.1
+##reference=1000GenomesPilot-NCBI36
+##phasing=partial
+##INFO=<ID=NS,Number=1,Type=Integer,Description="Number of Samples With Data">
+##INFO=<ID=AN,Number=1,Type=Integer,Description="Total number of alleles in called genotypes">
+##INFO=<ID=AC,Number=.,Type=Integer,Description="Allele count in genotypes, for each ALT allele, in the same order as listed">
+##INFO=<ID=DP,Number=1,Type=Integer,Description="Total Depth">
+##INFO=<ID=AF,Number=.,Type=Float,Description="Allele Frequency">
+##INFO=<ID=AA,Number=1,Type=String,Description="Ancestral Allele">
+##INFO=<ID=DB,Number=0,Type=Flag,Description="dbSNP membership, build 129">
+##INFO=<ID=H2,Number=0,Type=Flag,Description="HapMap2 membership">
+##FILTER=<ID=q10,Description="Quality below 10">
+##FILTER=<ID=s50,Description="Less than 50% of samples have data">
+##FORMAT=<ID=GT,Number=1,Type=String,Description="Genotype">
+##FORMAT=<ID=GQ,Number=1,Type=Integer,Description="Genotype Quality">
+##FORMAT=<ID=DP,Number=1,Type=Integer,Description="Read Depth">
+##FORMAT=<ID=HQ,Number=2,Type=Integer,Description="Haplotype Quality">
+##ALT=<ID=DEL:ME:ALU,Description="Deletion of ALU element">
+##ALT=<ID=CNV,Description="Copy number variable region">
+##sampling="random sampling using vcfrandomsample -p 1 -r 0.2 /space/anton/galaxy-central/database/files/000/dataset_1.dat using random seed 1"
+#CHROM	POS	ID	REF	ALT	QUAL	FILTER	INFO	FORMAT	NA00001	NA00002	NA00003
+20	1110696	rs6040355	A	G,T	67	PASS	AA=T;AF=0.333,0.667;DP=10;NS=2;DB	GT:GQ:DP:HQ	1|2:21:6:23,27	2|1:2:0:18,2	2/2:35:4:.,.
+20	1230237	.	T	.	47	PASS	AA=T;DP=13;NS=3	GT:GQ:DP:HQ	0|0:54:.:56,60	0|0:48:4:51,51	0/0:61:2:.,.
+X	10	rsTest	AC	A,ATG	10	PASS	.	GT	0	0/1	0|2
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/tool_dependencies.xml	Wed Jun 11 17:11:37 2014 -0400
@@ -0,0 +1,6 @@
+<?xml version="1.0"?>
+<tool_dependency>
+  <package name="vcflib" version="586c5ae5d57a38dae6b32ea831fb1f7cfa14c9bd">
+      <repository changeset_revision="7949cc09120a" name="package_vcflib" owner="anton" toolshed="http://toolshed.g2.bx.psu.edu" />
+    </package>
+</tool_dependency>
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/vcfrandomsample.xml	Wed Jun 11 17:11:37 2014 -0400
@@ -0,0 +1,53 @@
+<tool id="vcfrandomsample" name="VCFrandomSample:" version="0.0.1">
+<requirements>
+    <requirement type="package" version="586c5ae5d57a38dae6b32ea831fb1f7cfa14c9bd">vcflib</requirement>
+</requirements>
+  <description>Randomly sample sites from VCF dataset</description>
+  <command>
+
+    #if $adv_options.adv_options_selector == True:
+        vcfrandomsample -s "${adv_options.scale_by}" -p ${random_seed} -r ${rate} "${vcf_input}" > "${out_file1}"
+    #else:
+        vcfrandomsample -p ${random_seed} -r ${rate} "${vcf_input}" > "${out_file1}" 
+    #end if                                                                      
+  </command>
+  <inputs>
+    <param format="vcf" name="vcf_input" type="data" label="Select random sites from"/>
+    <param name="rate" type="float" value="0.1" label="base sampling probability per locus" help="-r, --rate"/>
+    <param name="random_seed" type="integer" value="17823618326" label="use this random seed" help="-p, --random-seed; use this to make results reproducible" />
+    <conditional name="adv_options">
+      <param name="adv_options_selector" type="boolean" truevalue="use_adv_controls" label="Advanced controls" help="Allows you to specify options that are not listed above"/>
+      <when value="use_adv_controls">
+	<param name="scale_by" type="text" value="AF" label="scale sampling likelihood by this INFO field" help="-s, --scale-by; this only works for Float info fields such as AF" />
+      </when>
+      </conditional>
+  </inputs>
+  <outputs>
+    <data format="vcf" name="out_file1" />
+  </outputs>
+  <tests>
+    <test>
+      <param name="vcf_input" value="vcflib.vcf"/>
+      <param name="rate" value="0.2" />
+      <param name="random_seed" value="1" />
+      <param name="adv_options_selector" value="False" />
+      <output name="out_file1" file="vcfrandomsample-test1.vcf" lines_diff="2" />
+    </test>
+    </tests>
+  <help>
+
+Randomly sample sites from an input VCF file. Scale the sampling probability by the field specified by --scale-by (see advanced controls).  This may be
+used to provide uniform sampling across allele frequencies, for instance (AF field in this case).
+
+Options::
+
+    -r, --rate RATE      base sampling probability per locus
+    -s, --scale-by KEY   scale sampling likelihood by this Float info field
+    -p, --random-seed N  use this random seed
+
+----
+
+Vcfrandomsample is a part of VCFlib toolkit developed by Erik Garrison (https://github.com/ekg/vcflib).                                                                                                                                 
+
+</help>
+</tool>