view fsd.xml @ 16:6bd9ef49d013 draft

planemo upload for repository commit dfaab79252a858e8df16bbea3607ebf1b6962e5a
author mheinzl
date Mon, 08 Oct 2018 05:50:18 -0400
parents 32921a67437b
children 2e517a54eedc
line wrap: on
line source

<?xml version="1.0" encoding="UTF-8"?>
<!-- galaxy version 16.04 -->
<tool id="fsd" name="FSD" version="1.0.0">
    <description>: Family Size Distribution of duplex sequencing tags</description>
        <requirement type="package" version="2.7">python</requirement>
        <requirement type="package" version="1.4.0">matplotlib</requirement>
        python2 '$__tool_directory__/' --inputFile1 '${file1}' --inputName1 '${}' 
--inputFile2 '${file2}' --inputName2 '${}' --inputFile3 '${file3}' --inputName3 '${}' 
--inputFile4 '${file4}' --inputName4 '${}' --output_pdf $output_pdf --output_tabular $output_tabular 
        <param name="file1" type="data" format="tabular" label="Dataset 1: input tags" optional="false"/>
        <param name="file2" type="data" format="tabular" label="Dataset 2: input tags" optional="true"  />
        <param name="file3" type="data" format="tabular" label="Dataset 3: input tags" optional="true" />
        <param name="file4" type="data" format="tabular" label="Dataset 4: input tags" optional="true"  help="Input in tabular format with the family size, tags and the direction of the strand ('ab' or 'ba') for each family. Name of the files can have max. 34 charcters!"/>
        <data name="output_pdf" format="pdf" />
        <data name="output_tabular" format="tabular"/>
            <param name="file1" value="Test_data.tabular"/>
            <param name="file2" value="Test_data2.tabular"/>
            <param name="file3" value="Test_data3.tabular"/>
            <param name="file4" value="Test_data4.tabular"/>
            <output name="output_pdf" file="output_file.pdf" lines_diff="285"/>
            <output name="output_tabular" file="output_file.tabular"/>
            <param name="file1" value="Test_data.tabular"/>
            <param name="file2" value="Test_data2.tabular"/>
            <param name="file3" value="Test_data3.tabular"/>
            <output name="output_pdf" file="output_file2.pdf" lines_diff="285"/>
            <output name="output_tabular" file="output_file2.tabular"/>

**What it does**
This tool will create a distribution of family sizes of each tag, which is separated after tags that have only the forward (ab) strand, the reverse (ba) strand or both strands (ab+ba) of the DCS and a family size distribution without separation is created. 
This tools expects a tabular file with the tags of all families, their sizes and information about forward (ab) and reverse (ba) strands:: 

The output is a PDF file with the plot and a tabular file with the data of the plot.
**About Author**
Author: Monika Heinzl
Department: Institute of Bioinformatics, Johannes Kepler University Linz, Austria
        <citation type="bibtex">
            author = {Heinzl, Monika},
            year = {2018},
            title = {Development of algorithms for the analysis of duplex sequencing data}