|
3
|
1 <tool id="chip_seq_ratio_1" name="Chip-Seq Mapper" version="0.1.1">
|
|
|
2 <stdio>
|
|
|
3 <exit_code range="1:" level="fatal" description="Error"/>
|
|
|
4 </stdio>
|
|
|
5 <description></description>
|
|
|
6 <requirements>
|
|
|
7 <requirement type="package">r-base64enc</requirement>
|
|
|
8 <requirement type="package">r-r2html</requirement>
|
|
|
9 <requirement type="package">blast</requirement>
|
|
|
10 </requirements>
|
|
|
11 <command interpreter="python3">
|
|
|
12 ChipSeqRatioAnalysis.py
|
|
|
13 --ChipSeq=${ChipFile}
|
|
|
14 --InputSeq=${InputFile}
|
|
|
15 --Contigs=${ContigFile}
|
|
|
16 --output=${OutputFile}
|
|
|
17 --html=${ReportFile}
|
|
|
18 --max_cl=${MaxCl}
|
|
|
19 --bitscore=$bitscore
|
|
|
20 --nproc=16
|
|
|
21 </command>
|
|
|
22
|
|
|
23 <inputs>
|
|
|
24 <param name="ChipFile" label="Chip Sequences" type="data" format="fasta" help="NGS data in fasta format"/>
|
|
|
25 <param name="InputFile" label="Input Sequences" type="data" format="fasta" help="NGS data in fasta format"/>
|
|
|
26 <param name="ContigFile" label="Reference - Contig Sequences" type="data" format="fasta"
|
|
|
27 help="Contigs obtained from RepeatExplorer clustering pipeline in fasta file"/>
|
|
|
28 <param name="MaxCl" label="Number of clusters to be shown in graph" type="integer" value="200"/>
|
|
|
29 <param name="bitscore" label="Minimum bit score threshold" type="integer" value="30" help="All similarity hits with lower bit score will not be considered for ChIP/Input ratio calculation"/>
|
|
|
30 </inputs>
|
|
|
31 <outputs>
|
|
|
32 <data name="OutputFile" format="tabular"/>
|
|
|
33 <data name="ReportFile" format="html"/>
|
|
|
34 </outputs>
|
|
|
35
|
|
|
36 <help>
|
|
|
37 **What it does**
|
|
|
38
|
|
|
39 Analysis of NGS sequences from Chromatin Imunoprecipitation. ChiP
|
|
|
40 and Input reads are mapped to contigs obtained from graph based
|
|
|
41 repetitive sequence clustering(`Novak et al. 2013`__) to enriched repeats. Reads from input
|
|
|
42 and ChIP should be ideally short illumina reads with uniform length
|
|
|
43 above 80 nt. It is sufficiant to use about 1 milion of reads for both Input and Chip.
|
|
|
44 This method was first used in (`Neumann et al. 2012`__) for
|
|
|
45 identification of repetitive sequences associated with cetromeric
|
|
|
46 region. If you use this method, reference:
|
|
|
47
|
|
|
48
|
|
|
49 `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.`__.
|
|
|
50
|
|
|
51 .. __: http://bioinformatics.oxfordjournals.org/content/29/6/792.full
|
|
|
52
|
|
|
53 .. __: http://journals.plos.org/plosgenetics/article?id=10.1371/journal.pgen.1002777
|
|
|
54 .. __: http://journals.plos.org/plosgenetics/article?id=10.1371/journal.pgen.1002777
|
|
|
55
|
|
|
56 </help>
|
|
|
57
|
|
|
58 </tool>
|
|
|
59
|
|
|
60
|
