view ChipSeqRatioDef.xml @ 23:36c418bca8b2 draft

planemo upload commit 20bdf879b52796d3fb251a20807191ff02084d3c-dirty
author petr-novak
date Wed, 02 Aug 2023 11:50:25 +0000
parents 58807b35777a
children 53dc6aef5441
line wrap: on
line source

<tool id="chip_seq_ratio_1" name="ChIP-Seq Mapper" version="1.1.1.3">
  <stdio>
    <exit_code range="1:" level="fatal" description="Error"/>
  </stdio>
    <description></description>
    <requirements>
      <requirement type="package">r-base64enc</requirement>
      <requirement type="package">r-r2html</requirement>
      <requirement type="package">blast</requirement>
      <!-- <requirement type="package">chip_seq_ration</requirement> -->
    </requirements>
    <required_files>
        <include type="literal" path="ChipSeqRatioAnalysis.py"/>
        <include type="literal" path="ChipSeqRatioAnalysis.R"/>
    </required_files>
    <command>
	python '$__tool_directory__'/ChipSeqRatioAnalysis.py
	--ChipSeq=${ChipFile}
	--InputSeq=${InputFile}
	--Contigs=${ContigFile}
	--output=${OutputFile}
	--html=${ReportFile}
	--max_cl=${MaxCl}
  --bitscore=$bitscore
  --nproc=16
    </command>

    <inputs>
        <param name="ChipFile" label="Chip reads" type="data" format="fasta" help="Reads in FASTA format"/> 
	<param name="InputFile" label="Input reads" type="data" format="fasta" help="Reads in FASTA format"/>
	<param name="ContigFile" label="Reference - contig sequences" type="data" format="fasta"
	       help="Contigs from RepeatExplorer clustering (the file &quot;contigs.fasta&quot;)"/> 
	<param name="MaxCl" label="Number of top clusters to be shown in graph" type="integer" value="200"/>   
	<param name="bitscore" label="Bit score threshold" type="integer" value="50" help="Similarity hits with lower bit score will not be used for ChIP/Input ratio calculation"/>   
    </inputs>
    <outputs>
    	<data name="OutputFile" format="tabular"
            label="csv table from ChIP-Seq-Mapper on datasets ${InputFile.hid} (Input) ${ChipFile.hid} (ChIP) and ${ContigFile.hid} (reference)"/>

	    <data name="ReportFile" format="html"
            label="HTML report from ChIP-Seq-Mapper on datasets ${InputFile.hid} (Input) ${ChipFile.hid} (ChIP) and ${ContigFile.hid} (reference)"/> 
    </outputs>

    <help>
**What it does**

The ChIP-seq Mapper evaluates the enrichment of repetitive sequences in sequencing data from chromatin 
immunoprecipitation experiments, using repeats identified by RepeatExplorer as the reference. The tool 
performs BLASTN similarity search of the read sequences to the reference, 
and the reads producing hits that passed the user-specified similarity threshold are assigned to the 
repeat clusters. The assignment is made to the cluster that produced the best similarity hit, and every 
read is assigned to only a single cluster. Following read mapping, the numbers of reads from the 
INPUT and ChIP samples are evaluated, and ChIP/INPUT ratios of the normalized read counts are reported 
for individual clusters.
ChIP and INPUT reads should be of uniform lengths of at least 40 nt. The bit score threshold value should be
adjusted based on the length of the analyzed reads (the value equal to the read length is recommended for a start). 
This method was first used in (`Neumann et al. 2012`__) for
identification of repetitive sequences associated with centromeres:


`PLoS Genet. Epub 2012 Jun 21. Stretching the rules: monocentric chromosomes with multiple centromere domains. Neumann P, Navrátilová A, Schroeder-Reiter E, Koblížková A, Steinbauerová V, Chocholová E, Novák P, Wanner G, Macas J.`__.

.. __: http://journals.plos.org/plosgenetics/article?id=10.1371/journal.pgen.1002777
.. __: http://journals.plos.org/plosgenetics/article?id=10.1371/journal.pgen.1002777
      
    </help>

</tool>