diff vcfallelicprimitives.xml @ 0:3f4fefbc52c8 draft

Uploaded

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/vcfallelicprimitives.xml	Thu Mar 19 12:23:24 2015 -0400
@@ -0,0 +1,62 @@
+<?xml version="1.0" encoding="utf-8"?>
+<tool id="vcfallelicprimitives" name="VcfAllelicPrimitives:" version="0.0.3">
+    <description>Split alleleic primitives (gaps or mismatches) into multiple VCF lines</description>
+    <macros>
+        <import>macros.xml</import>
+    </macros>
+    <expand macro="requirements"></expand>
+    <expand macro="stdio" />
+    <command>
+        cat "${input}" | vcfallelicprimitives 
+            ${m_option} 
+            -t "${t_option}"
+	    -L "${max_length}" 
+            $keep_info 
+            $keep_geno > "${out_file1}"
+    </command>
+    <inputs>
+        <param format="vcf" name="input" type="data" label="Select VCF dataset"/>
+        <param name="m_option" type="boolean" checked="false" truevalue="--use-mnps" falsevalue="" label="Retain MNPs as separate events" help="--use-mnps option"/>
+        <param name="t_option" size="20" type="text" value="Split primitives" label="Tag records which are split apart of a complex allele with this flag. " help="--tag-parsed option"/>
+	<param name="max_length" type="integer" size="4" value="200" label="Do not manipulate records in which either the ALT or REF is longer than (bp)" help="--max-length option"/>
+        <param name="keep_info" type="boolean" truevalue="--keep-info" falsevalue="" checked="False" 
+            label="Maintain site and allele-level annotations when decomposing" 
+            help="Note that in many cases, such as multisample VCFs, these won't be valid post-decomposition.  For biallelic loci in single-sample VCFs, they should be usable with caution. (--keep-info)"/>
+        <param name="keep_geno" type="boolean" truevalue="--keep-geno" falsevalue="" checked="False" 
+            label="Maintain genotype-level annotations when decomposing" 
+            help="Similar caution should be used for this as for --keep-info. (--keep-geno)"/>
+    </inputs>
+    <outputs>
+        <data format="vcf" name="out_file1" label="${tool.name} on ${on_string}" />
+    </outputs>
+    <tests>
+        <test>
+            <param name="input" value="vcflib.vcf"/>
+            <output name="out_file1" file="vcfallelicprimitives-test1.vcf"/>
+        </test>
+    </tests>
+    <help>
+
+If multiple alleleic primitives (gaps or mismatches) are specified in a single VCF record, this tools splits the record into multiple lines, but drops all INFO fields.  
+"Pure" MNPs are split into multiple SNPs unless the -m flag is provided. 
+Genotypes are phased where complex alleles have been decomposed, provided genotypes in the input.
+
+The options are::
+
+    -m, --use-mnps          Retain MNPs as separate events (default: false).
+    -t, --tag-parsed FLAG   Tag records which are split apart of a complex allele with this flag.
+    -L, --max-length LEN    Do not manipulate records in which either the ALT or
+                            REF is longer than LEN (default: 200).
+    -k, --keep-info         Maintain site and allele-level annotations when decomposing.
+                            Note that in many cases, such as multisample VCFs, these won't
+                            be valid post-decomposition.  For biallelic loci in single-sample
+                            VCFs, they should be usable with caution.
+    -g, --keep-geno         Maintain genotype-level annotations when decomposing.  Similar
+                            caution should be used for this as for --keep-info.
+
+----
+
+Vcfallelicprimitives @IS_PART_OF_VCFLIB@
+    </help>
+    <expand macro="citations" />
+</tool>