<tool id="ip_superdsm" name="SuperDSM" version="0.1.2-1" profile="20.05">
   <description>globally optimal segmentation method based on superadditivity and deformable shape models for cell nuclei in fluorescence microscopy images</description>
   <requirements> 
        <requirement type="package" version="0.1.2">superdsm</requirement>
        <requirement type="package" version="1.6.0">ray-core</requirement>
        <requirement type="package" version="0.18.1">scikit-image</requirement>
   </requirements>
   <command detect_errors="aggressive">
   <![CDATA[
   python '$__tool_directory__/run-superdsm.py'
   '${dataset}'
   'cfg.json'
   'masks.png'
   'overlay.png'
   $seg_border
   \${GALAXY_SLOTS:-4}
   > stdout.txt
   ]]>
   </command>
   <inputs>
        <param name="dataset" type="data" format="tiff,png" label="Dataset" />
        <param name="seg_border" type="integer" min="1" value="8" label="Width of the outlines (in pixels) of the segmentation results (overlays)" />
        <!--
        <section name="config" title="Hyperparameters" expanded="false">
        </section>
        -->
    </inputs>
    <outputs>
        <data format="txt" name="stdout" from_work_dir="stdout.txt" label="${tool.name} on ${on_string}: stdout" />
        <data format="json" name="cfg" from_work_dir="cfg.json" label="${tool.name} on ${on_string}: cfg" />
        <data format="png" name="masks" from_work_dir="masks.png" label="${tool.name} on ${on_string}: masks" />
        <data format="png" name="overlay" from_work_dir="overlay.png" label="${tool.name} on ${on_string}: overlay" />
    </outputs>
    <tests>
        <test>
            <param name="dataset" value="BBBC033_C2_z28.png" />
            <output name="overlay" value="overlay.png" ftype="png" compare="sim_size" />
        </test>
    </tests>
    <help>
        This tool permits the segmentation of cell nuclei in 2-D fluorescence microscopy images.

        You can either use an individual input image (PNG, TIF) or a collection of such images.
    </help>
    <citations>
        <citation type="doi">10.1109/TPAMI.2022.3185583</citation>
    </citations>
</tool>