Mercurial > repos > malex > tandem_repeats_finder
changeset 0:7676570eb676
Uploaded the config file
author | malex |
---|---|
date | Wed, 30 Nov 2011 12:18:10 -0500 |
parents | |
children | 2a3c8b2d5979 |
files | trf.xml |
diffstat | 1 files changed, 119 insertions(+), 0 deletions(-) [+] |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/trf.xml Wed Nov 30 12:18:10 2011 -0500 @@ -0,0 +1,119 @@ +<tool id="trf" name="Tandem Repeats Finder" version="4.04"> + <description>Detect tandem repeats that have undergone extensive mutational change</description> + <command interpreter="python">trf_wrapper.py + $input1 $match $mismatch $delta $mprobability $iprobability $minscore + $maxperiod $masked $flanking $noredundancy -o $outputdat -k $outputmask -t + $report -i $indices + </command> + <inputs> + <param format="fasta" name="input1" type="data"> + <label>Sequence</label> + </param> + <param name="match" size="4" type="text" value="2"> + <label>Match</label> + </param> + <param name="mismatch" size="4" type="text" value="7"> + <label>Mismatch</label> + </param> + <param name="delta" size="4" type="text" value="7"> + <label>Indels</label> + </param> + <param name="mprobability" size="4" type="integer" value="80" label="Matching probability, %"> + <validator type="in_range" message="(10-100)" min="10" max="100"/> + </param> + <param name="iprobability" size="4" type="integer" value="10" label="Indel probability, %"> + <validator type="in_range" message="(10-100)" min="10" max="100"/> + </param> + <param name="minscore" size="3" type="integer" value="50"> + <label>Minimum alignment score for repeat reporting</label> + <validator type="in_range" message="(30-150)" min="30" max="150"/> + </param> + <param name="maxperiod" size="4" type="integer" value="500"> + <label>Maximum period size for repeat reporting</label> + <validator type="in_range" message="(1-2000)" min="1" max="2000"/> + </param> + <param name="flanking" type="boolean" checked="no" truevalue="-f" falsevalue="" display="checkboxes"> + <label>Flanking sequence</label> + </param> + <param name="masked" type="boolean" checked="no" truevalue="-m" falsevalue="" display="checkboxes"> + <label>Masked Sequence File</label> + </param> + <param name="noredundancy" type="boolean" checked="no" truevalue="-r" falsevalue="" display="checkboxes"> + <label>No redundancy elimination</label> + </param> + </inputs> + <outputs> + <data format="html" name="report" label="${tool.name} on ${on_string}: Report"/> + <data format="html" name="indices" label="${tool.name} on ${on_string}: Indices"/> + <data format="tabular" name="outputdat" label="${tool.name} on ${on_string}: Data"/> + <data format="txt" name="outputmask" label="${tool.name} on ${on_string}: Masked Sequence"> + <filter>masked is True</filter> + </data> + </outputs> + <tests> + <test> + <param name="input1" value="trf_input.fasta"/> + <param name="match" value="2"/> + <param name="mismatch" value="7"/> + <param name="delta" value="7"/> + <param name="mprobability" value="80"/> + <param name="iprobability" value="10"/> + <param name="minscore" value="50"/> + <param name="maxperiod" value="500"/> + <param name="masked" value="-m"/> + <param name="flanking" value=""/> + <param name="noredundancy" value=""/> + <output name="outputdat" file="trf_out.dat"/> + <output name="outputmask" file="trf_out.mask"/> + </test> + </tests> + <help> +.. class:: warningmark + +The input dataset needs to be in FASTA format. + +----- + + Tandem Repeats Finder, Version 4.04 + + Copyright (C) Dr. Gary Benson 1999-2004. All rights reserved. + + + Please cite: + +G. Benson, "Tandem repeats finder: a program to analyze DNA sequences" Nucleic Acids Research (1999) Vol. 27, No. 2, pp. 573-580. + + +A tandem repeat in DNA is two or more adjacent, approximate copies of a pattern +of nucleotides. Tandem Repeats Finder is a program to locate and display tandem +repeats in DNA sequences. In order to use the program, the user submits a +sequence in FASTA format. There is no need to specify the pattern, the size of +the pattern or any other parameter. The output consists of two files: a repeat +table file and an alignment file. The repeat table contains information about +each repeat, including its location, size, number of copies and nucleotide +content. Clicking on the location indices for one of the table entries opens a +second web browser that shows an alignment of the copies against a consensus +pattern. The program is very fast, analyzing sequences on the order of .5Mb in +just a few seconds. Submitted sequences may be of arbitrary length. Repeats +with pattern size in the range from 1 to 2000 bases are detected. + </help> +</tool> +<!-- +Please use: trf File Match Mismatch Delta PM PI Minscore MaxPeriod [options] +Where: (all weights, penalties, and scores are positive) + File = sequences input file + Match = matching weight + Mismatch = mismatching penalty + Delta = indel penalty + PM = match probability (whole number) + PI = indel probability (whole number) + Minscore = minimum alignment score to report + MaxPeriod = maximum period size to report + [options] = one or more of the following : + -m masked sequence file + -f flanking sequence + -d data file + -h suppress html output + -r no redundancy elimination +Note the sequence file should be in FASTA format: +-->