<?xml version="1.0"?>
<tool id="genetrack" name="Genetrack" version="@WRAPPER_VERSION@.0">
    <description>peak predictor</description>
    <macros>
        <import>genetrack_macros.xml</import>
    </macros>
    <expand macro="requirements" />
    <command>
        python $__tool_directory__/genetrack.py
        --input_format $input_format_cond.input_format
        #if str($input_format_cond.input_format) == "scidx":
            #for $i in $input_format_cond.input_scidx:
                 --input "${i}" "${i.hid}"
            #end for
        #elif str($input_format_cond.input_format) == "gff":
            #for $i in $input_format_cond.input_gff:
                 --input "${i}" "${i.hid}"
            #end for
        #end if
        --sigma $sigma
        --exclusion $exclusion
        --up_width $up_width
        --down_width $down_width
        --filter $filter
        --chunk_size $chunk_size
    </command>
    <inputs>
        <conditional name="input_format_cond">
            <param name="input_format" type="select" label="Format of files for conversion">
                <option value="scidx" selected="True">ScIdx</option>
                <option value="gff">Gff</option>
            </param>
            <when value="scidx">
                <param name="input_scidx" type="data" format="scidx" multiple="True" label="Predict peaks on" />
            </when>
            <when value="gff">
                <param  name="input_gff" type="data" format="gff" multiple="True" label="Predict peaks on" />
            </when>
        </conditional>
        <param name="sigma" type="integer" value="5" min="1" label="Sigma to use when smoothing reads" help="Higher values increase computation but produce more smoothing." />
        <param name="exclusion" type="integer" value="20" min="1" label="Peak exclusion zone" help="Exclusion zone around each peak that prevents others from being called." />
        <param name="up_width" type="integer" value="10" min="0" label="Upstream width of called peaks" />
        <param name="down_width" type="integer" value="10" min="0" label="Downstream width of called peaks" />
        <param name="filter" type="integer" value="3" min="0" label="Absolute read filter" help="Removes peaks with lower peak height." />
        <param name="chunk_size" type="integer" value="10" min="1" label="Chunk each chromosome into" help="Value is millions of base pairs where each size increment uses about 20MB of memory." />
    </inputs>
    <outputs>
        <collection name="genetrack_output" type="list" label="Genetrack results on ${on_string}">
            <discover_datasets pattern="(?P&lt;designation&gt;.*)" directory="output" ext="gff" visible="false" />
        </collection>
    </outputs>
    <tests>
        <test>
            <param name="input_gff" value="genetrack_input2.gff" ftype="gff" />
            <param name="input_format" value="gff" />
            <param name="sigma" value="5" />
            <param name="exclusion" value="20" />
            <param name="up_width" value="10" />
            <param name="down_width" value="10" />
            <param name="filter" value="3" />
            <param name="chunk_size" value="10" />
            <output_collection name="genetrack_output" type="list">
                <element name="s5e20u10d10F3_on_data_1" file="genetrack_output2.gff" ftype="gff" />
            </output_collection>
        </test>
        <test>
            <param name="input_scidx" value="genetrack_input3.scidx" ftype="scidx" />
            <param name="input_format" value="scidx" />
            <param name="sigma" value="5" />
            <param name="exclusion" value="20" />
            <param name="up_width" value="10" />
            <param name="down_width" value="10" />
            <param name="filter" value="3" />
            <param name="chunk_size" value="10" />
            <output_collection name="genetrack_output" type="list">
                <element name="s5e20u10d10F3_on_data_1" file="genetrack_output3.gff" ftype="gff" />
            </output_collection>
        </test>
        <test>
            <param name="input_gff" value="genetrack_input_unsorted4.gff" ftype="gff" />
            <param name="input_format" value="gff" />
            <param name="sigma" value="5" />
            <param name="exclusion" value="20" />
            <param name="up_width" value="10" />
            <param name="down_width" value="10" />
            <param name="filter" value="3" />
            <param name="chunk_size" value="10" />
            <output_collection name="genetrack_output" type="list">
                <element name="s5e20u10d10F3_on_data_1" file="genetrack_output4.gff" ftype="gff" />
            </output_collection>
        </test>
    </tests>
    <help>
**What it does**

Genetrack takes a standard set of data on both the sense and antisense strands and smooths their relative reads.
It then calls the peaks present in the smoothed dataset and uses those peak locations to calculate the final
reads from surrounding reads.  Finally, it ensures each peak is above a threshold and that two peaks are not
too close to each other.

-----

**Options**

* **Sigma to use when smoothing reads** - Sigma to use when smoothing reads to call peaks.
* **Peak exclusion zone** - Exclusion zone around each peak that prevents others from being called.
* **Upstream width of called peaks** - Upstream width of called peaks.
* **Downstream width of called peaks** - Downstream width of called peaks.
* **Filter** - Absolute read filter.  Restricts output to only peaks with larger peak height.
* **Chunk each chromosome into** - Size, in millions of base pairs, to chunk each chromosome when processing.  Each 1 million size uses approximately 20MB of memory.
    </help>
    <expand macro="citations" />
</tool>