--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/bcftools_plugin_split_vep.xml	Sat Jul 23 13:49:21 2022 +0000
@@ -0,0 +1,112 @@
+<?xml version='1.0' encoding='utf-8'?>
+<tool name="bcftools @EXECUTABLE@" id="bcftools_plugin_@PLUGIN_ID@" version="@TOOL_VERSION@">
+    <description>plugin Extracts fields from structured annotations such as INFO/CSQ</description>
+    <macros>
+        <token name="@EXECUTABLE@">split-vep</token>
+        <token name="@PLUGIN_ID@">split_vep</token>
+        <import>macros.xml</import>
+    </macros>
+    <expand macro="bio_tools" />
+    <expand macro="requirements" />
+    <expand macro="version_command" />
+    <command detect_errors="aggressive"><![CDATA[
+@PREPARE_ENV@
+@PREPARE_INPUT_FILE@
+#set $section = $sec_restrict
+@PREPARE_TARGETS_FILE@
+@PREPARE_REGIONS_FILE@
+
+bcftools plugin @EXECUTABLE@
+## VCF input section
+#set $section = $sec_restrict
+@INCLUDE@
+@EXCLUDE@
+@REGIONS@
+@TARGETS@
+
+@OUTPUT_TYPE@
+
+## Primary Input/Outputs
+@INPUT_FILE@
+## Plugin options
+## ToDo: Parameters not wrapped yet: -A, -f (not for BCF/VCF output!), -l, -S, -x
+-a '$a'
+-c '$c'
+$d
+#if $p:
+    -p '$p'
+#end if
+#if $s:
+    -s '$s'
+#end if
+> '$output_file'
+]]>
+    </command>
+    <inputs>
+        <expand macro="macro_input" />
+        <param argument="-a" type="text" value="CSQ" label="Select INFO annotation to parse" help="Usually, annotations are located in the CSQ, ANN or EFF INFO field, though any arbitrary tag may be entered here." />
+        <param argument="-c" type="text" label="Enter fields to be extracted, listed either as indexes or names" help="The default type of the new annotation is String but can be also set to Integer/Int or Float/Real by adding ':type' to the field name or index. Examples can be found in the tool help." />
+        <param argument="-d" type="boolean" label="Enable Output per transcript/allele consequences on a new line rather rather than as comma-separated fields on a single line" truevalue="-d" falsevalue="" />
+        <param argument="-p" type="text" optional="true" label="Enter prefix of INFO annotations to be created after splitting the CSQ string (optional)" />
+        <param argument="-s" type="text" optional="true" label="Select transcripts to extract by type and/or consequence (optional)" help="Argument has the form TR:CSQ. TR = transcript:   worst,primary,all (default: all). CSQ = consequence: any,missense,missense+,etc (default: any). Examples can be found in the tool help." />
+        
+        <section name="sec_restrict" expanded="false" title="Restrict to">
+            <expand macro="macro_restrict" />
+            <expand macro="macro_restrict" type="target" label_type="Target" />
+            <expand macro="macro_include" />
+            <expand macro="macro_exclude" />
+        </section>
+        <expand macro="macro_select_output_type" />
+    </inputs>
+    <outputs>
+        <expand macro="macro_vcf_output" />
+    </outputs>
+    <tests>
+        <test>
+            <param name="input_file" ftype="vcf" value="plugin2.vcf" />
+            <param name="a" value="ANN" />
+            <param name="c" value="IMPACT,gnomAD_AF:Float" />
+            <param name="p" value="NW_" />
+            <param name="s" value="worst" />
+            <param name="output_type" value="v" />
+            <output name="output_file" ftype="vcf">
+                <assert_contents>
+                    <has_line_matching expression="##INFO=&lt;ID=NW_IMPACT,.+" />
+                    <has_line_matching expression="##INFO=&lt;ID=NW_gnomAD_AF,.+" />
+                    <has_line_matching expression=".+NW_IMPACT=MODERATE;NW_gnomAD_AF=0\.08.+" />
+                    <has_line_matching expression=".+NW_IMPACT=LOW;NW_gnomAD_AF=0\.9443.+" />
+                    <has_line_matching expression=".+NW_IMPACT=MODIFIER;NW_gnomAD_AF=\..+" />
+                </assert_contents>
+            </output>
+        </test>
+    </tests>
+    <help><![CDATA[
+=====================================
+ bcftools @EXECUTABLE@ plugin
+=====================================
+
+This plugin allows to extract fields from structured annotations such as ``INFO/CSQ`` created by bcftools/csq or VEP. These fields are then added to the VCF as new ``INFO`` fields.
+
+Examples::
+
+   # Extract Consequence, IMPACT and gene SYMBOL of the most severe consequence into
+   # INFO annotations starting with the prefix "vep". For brevity, the columns can
+   # be given also as 0-based indexes
+   bcftools +split-vep -c Consequence,IMPACT,SYMBOL -s worst -p vep file.vcf.gz
+   bcftools +split-vep -c 1-3 -s worst -p vep file.vcf.gz
+
+   # Extract gnomAD_AF subfield into a new INFO/gnomAD_AF annotation of Type=Float so that
+   # numeric filtering can be used.
+   bcftools +split-vep -c gnomAD_AF:Float file.vcf.gz -i 'gnomAD_AF<0.001'
+
+   # Similar to above, but add the annotation only if the consequence severity is missense
+   # or equivalent.
+   bcftools +split-vep -c gnomAD_AF:Float -s :missense file.vcf.gz
+
+@REGIONS_HELP@
+@TARGETS_HELP@
+@EXPRESSIONS_HELP@
+
+    ]]></help>
+    <expand macro="citations" />
+</tool>