<?xml version="1.0" encoding="UTF-8"?>
<tool id="hd" name="Duplex Sequencing Analysis: hd" version="1.0.0">
    <description>Hamming distance (HD) analysis of tags</description>
    <requirements>
        <requirement type="package" version="2.7">python</requirement>
        <requirement type="package" version="1.4.0">matplotlib</requirement>
    </requirements>
    <command>
        python2 '$__tool_directory__/hd.py' --inputFile '$inputFile' --inputName1 '$inputFile.name' --inputFile2 '$inputFile2' --inputName2 '$inputFile2.name' --sample_size $sampleSize --subset_tag $subsetTag --nproc $nproc $onlyDCS --minFS $minFS --maxFS $maxFS
		$nr_above_bars --output_pdf $output_pdf --output_tabular $output_tabular 
        #if $inputFile2:
        --output_pdf2 $output_pdf2 --output_tabular2 $output_tabular2
        #end if
    </command>
    <inputs>
        <param name="inputFile" type="data" format="tabular" label="Dataset 1: input tags" optional="false"/>
        <param name="inputFile2" type="data" format="tabular" label="Dataset 2: input tags" optional="true" help="Input in tabular format with the family size, tag and the direction of the strand ('ab' or 'ba') for each family."/>
        <param name="sampleSize" type="integer" label="number of tags in the sample" value="1000" min="0" help="specifies the number of tags in one analysis. If sample size is 0, all tags of the dataset are compared against all tags."/>
        <param name="minFS" type="integer" label="minimum family size of the tags" min="1" value="1" help="filters the tags after their family size: Families with a smaller size are skipped. Default: min. family size = 1."/>
        <param name="maxFS" type="integer" label="max family size of the tags" min="0" value="0" help="filters the tags after their family size: Families with a larger size are skipped. If max. family size is 0, no upper bound is defined and the maximum family size in the analysis will be the maximum family size of the whole dataset. Default: max. family size = 0."/>
        <param name="onlyDCS" type="boolean" label="only DCS in the analysis?" truevalue="" falsevalue="--only_DCS" checked="False" help="Only tags, which have a partner tag (ab and ba) in the dataset, are included in the analysis."/>
        <param name="subsetTag" type="integer" label="shorten tag in the analysis?" value="0" help="By this parameter an analysis with shorter tag length is simulated. If this parameter is 0 (by default), the tags with its original length are used in the analysis."/>
        <param name="nproc" type="integer" label="number of processors" value="8" help="Number of processor used for computing."/>
        <param name="nr_above_bars" type="boolean" label="include numbers above bars?" truevalue="--nr_above_bars" falsevalue="" checked="True" help="The absolute and relative values of the data can be included or removed from the plots. "/>
 
    </inputs>
    <outputs>
        <data name="output_tabular" format="tabular"/>
        <data name="output_tabular2" format="tabular">
            <filter>inputFile2</filter>
        </data>
        <data name="output_pdf" format="pdf" />
        <data name="output_pdf2" format="pdf" >
            <filter>inputFile2</filter>
        </data>
    </outputs>
    <tests>
        <test>
            <param name="inputFile" value="Test_data.tabular"/>
            <param name="inputFile2" value="Test_data2.tabular"/>
            <param name="sampleSize" value="0"/>
            <output name="output_pdf" file="output_file.pdf" lines_diff="6"/>
            <output name="output_tabular" file="output_file.tabular"/>
            <output name="output_pdf2" file="output_file2.pdf" lines_diff="6"/>
            <output name="output_tabular2" file="output_file2.tabular"/>
        </test>
    </tests>
    <help> <![CDATA[
**What it does**
    
    This tool calculates the Hamming distance for the tags by comparing them to all tags in the dataset and finally searches for the minimum Hamming distance. 
    The Hamming distance is shown in a histogram separated by the family sizes or in a family size distribution separated by the Hamming distances. 
    This similarity measure was calculated for each tag to distinguish whether similar tags truly stem from different molecules or occured due to sequencing or PCR errros. 
    In addition, the tags of chimeric reads can be identified by calculating the Hamming distance for each half of the tag. 
    This analysis can be performed on only a sample (by default: sample size=1000) or on the whole dataset (sample size=0). 
    It is also possible to select on only those tags, which have a partner tag (ab and ba) in the dataset (DCSs) or to filter the dataset after the tag's family size. 
    
**Input**
    
    This tools expects a tabular file with the tags of all families, their sizes and information about forward (ab) and reverse (ba) strands. It is possible to upload two files which allows the performance of two analyses at the same time.
    
    +-----+----------------------------+----+
    | 1   | AAAAAAAAAAAATGTTGGAATCTT   | ba |
    +-----+----------------------------+----+
    | 10  | AAAAAAAAAAAGGCGGTCCACCCC   | ab |
    +-----+----------------------------+----+
    | 28  | AAAAAAAAAAATGGTATGGACCGA   | ab |
    +-----+----------------------------+----+
    
    
**Output**
    
    The output is one PDF file with the plots of the Hamming distance and a tabular file with the data of the plot for each dataset.
    
    
**About Author**
    
    Author: Monika Heinzl
    
    Department: Institute of Bioinformatics, Johannes Kepler University Linz, Austria
    
    Contact: monika.heinzl@edumail.at
    
   ]]> 
    
    </help>
    <citations>
        <citation type="bibtex">
            @misc{duplex,
            author = {Heinzl, Monika},
            year = {2018},
            title = {Development of algorithms for the analysis of duplex sequencing data}
         }
        </citation>
    </citations>
</tool>