view mut2read.xml @ 11:84a1a3f70407 draft

planemo upload for repository commit ee4a8e6cf290e6c8a4d55f9cd2839d60ab3b11c8
author mheinzl
date Mon, 15 Feb 2021 21:53:24 +0000
parents 11a2a34f8a2b
children d21960b45a6b
line wrap: on
line source

<?xml version="1.0" encoding="UTF-8"?>
<tool id="mut2read" name="DCS mutations to tags/reads:" version="2.0.1" profile="19.01">
    <description>Extracts all tags that carry a mutation in the duplex consensus sequence (DCS)</description>
    <expand macro="requirements"/>
        ln -s '$file2' bam_input.bam &&
        ln -s '${file2.metadata.bam_index}' bam_input.bam.bai &&
        python '$__tool_directory__/' 
        --mutFile '$file1'
        --bamFile bam_input.bam
        --familiesFile '$file3'
        --outputFastq '$output_fastq' 
        --outputJson '$output_json'
        <param name="file1" type="data" format="vcf" label="DCS Mutation File" optional="false" help="VCF file with DCS mutations. See Help section below for a detailed explanation."/>
        <param name="file2" type="data" format="bam" label="DCS BAM File" optional="false" help="BAM file with aligned DCS reads."/>
        <param name="file3" type="data" format="tabular" label="Aligned Families File" optional="false" help="TABULAR file with aligned families."/>
        <data name="output_fastq" format="fastq" label="${} on ${on_string}: FASTQ"/>
        <data name="output_json" format="json" label="${} on ${on_string}: JSON"/>
            <param name="file1" value="FreeBayes_test.vcf"/>
            <param name="file2" value="DCS_test.bam"/>
            <param name="file3" value="Aligned_Families_test.tabular"/>
            <output name="output_fastq" file="Interesting_Reads_test.fastq"/>
            <output name="output_json" file="tag_count_dict_test.json" lines_diff="2"/>
    <help> <![CDATA[
**What it does**

Takes a VCF file with mutations, a BAM file of aligned DCS reads, and a 
tabular file with aligned families as input and prints all tags of reads that 
carry a mutation to a user specified output file and creates a fastq file of 
reads of tags with a mutation.


**Dataset 1:** VCF file with duplex consesus sequence (DCS) mutations. E.g. 
generated by the `FreeBayes variant caller <>`_.

**Dataset 2:** BAM file of aligned DCS reads. This file can be obtained by the 
tool `Map with BWA-MEM <>`_.

**Dataset 3:** Tabular file with reads as produced by the 
**Du Novo: Align families** tool of the `Du Novo Analysis Pipeline 


The output is a json file containing dictonaries of the tags of reads containing mutations 
in the DCS and a fastq file of all reads of these tags.

    <expand macro="citation" />