diff cpt_promote_qualifiers/promote_qualifier.xml @ 0:6f4c46313117 draft default tip

Uploaded
author cpt
date Fri, 17 Jun 2022 13:05:11 +0000
parents
children
line wrap: on
line diff
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/cpt_promote_qualifiers/promote_qualifier.xml	Fri Jun 17 13:05:11 2022 +0000
@@ -0,0 +1,67 @@
+<?xml version="1.0"?>
+<tool id="edu.tamu.cpt.gff3.promote_qualifiers" name="Promote Qualifers" version="20.0.0">
+  <description>Promote a child feature's qualifier into the parent feature</description>
+  <macros>
+    <import>macros.xml</import>
+	<import>cpt-macros.xml</import>
+  </macros>
+  <expand macro="requirements"/>
+  <command detect_errors="aggressive"><![CDATA[
+python $__tool_directory__/promote_qualifier.py
+@INPUT_GFF@
+$parent
+$child
+$qualifier
+> $output]]></command>
+  <inputs>
+    <expand macro="gff3_input" />
+    <param label="Parent Feature Type" name="parent" type="text" help="e.g. gene, mRNA, exon" />
+    <param label="Child Feature Type" name="child" type="text" help="e.g. mRNA, exon, CDS" />
+    <param label="Qualifer to Promote" name="qualifier" type="text" help="e.g. Name, Product, Notes" />
+  </inputs>
+  <outputs>
+    <data format="gff3" name="output" />
+  </outputs>
+  <tests>
+      <test>
+          <param name="gff3_data" value="promote_qualifiers_in.gff3" />
+          <param name="parent" value="gene" />
+          <param name="child" value="mRNA" />
+          <param name="qualifier" value="Name" />
+          <output name="output" file="promote_qualifiers_out.gff3" />
+      </test>
+  </tests>
+  <help><![CDATA[
+**What it does**
+
+Allows you to copy a specified qualifier value from a child feature into a parent feature, most likely to copy the Name from an mRNA into a gene. 
+
+For example, for a *Parent Feature Type* of "gene", *Child Feature Type* of "mRNA", and *Qualifier to Promote* of "Name" the following gff will be changed (spacing for emphasis):
+
+*Before*::
+
+  NC_049846.1	.	gene	630	1182	.	+	.	ID=8942304a;date_last_modified=2020-09-25;   Name=NC_049846.1.gene_1   ;date_creation=2020-09-25
+  NC_049846.1	.	mRNA	630	1182	.	+	.	Parent=8942304a;ID=536ddf54;   Name=Gene_1_Name   ;date_creation=2020-09-25
+
+*After*::
+
+  NC_049846.1	.	gene	630	1182	.	+	.	ID=8942304a;date_last_modified=2020-09-25;   Name=Gene_1_Name   ;date_creation=2020-09-25
+  NC_049846.1	.	mRNA	630	1182	.	+	.	Parent=8942304a;ID=536ddf54;   Name=Gene_1_Name   ;date_creation=2020-09-25
+
+.. class:: infomark 
+
+**Notes**::
+
+  - If the qualifier is already present in the parent, it will be overwritten with the child's value. 
+  - If there are multiple child features of the specified type under the same parent, the value from the first child. This action is strand aware. 
+    - For positive strand features it will select the child with the smaller start coordinate. 
+    - For negative strand it will select the child with the largest end coordinate.
+
+.. class:: warningmark 
+
+**Warning**::
+
+  You should likely never run this to promote the "ID" qualifier as this will break the gff3 hierarchy structure and cause parsing failures downstream. 
+]]></help>
+		<expand macro="citations-clm" />
+</tool>