annotate server/transfs.xml @ 1:8d9c8ba2ec86 draft

"planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/transfs commit ec28658e0e9cd92edff6e1f86427c6e80c69d572"

<tool id="xchem_transfs_scoring" name="XChem TransFS pose scoring" version="0.2.0">
    <description>using deep learning</description>

    <requirements>
        <!--requirement type="package" version="3.0.0">openbabel</requirement-->
        <!--requirement type="package" version="3.7">python</requirement-->
        <!-- many other requirements are needed -->
        <container type="docker">informaticsmatters/deep-app-ubuntu-1604:latest</container>
    </requirements>
    <command detect_errors="exit_code"><![CDATA[

    cd /train/fragalysis_test_files/ &&
    mkdir workdir &&
    cd workdir &&

    cp '$ligands' ligands.sdf &&
    cp '$receptor' receptor.pdb &&
	
    ##mkdir -p /root/train/ &&
    ##ln -s /train/fragalysis_test_files/ /root/train/ &&

    ##adduser centos --uid 1000 --quiet --no-create-home --system &&
    ##apt install sudo -y &&

    ## mkdir -p ligands &&
    cd ../ &&
    python '$__tool_directory__/transfs.py' -i ./workdir/ligands.sdf -r ./workdir/receptor.pdb -d $distance -w /train/fragalysis_test_files/workdir &&
    ls -l &&
    ls -l workdir &&
    sudo -u ubuntu cp ./workdir/output.sdf '$output' &&
    head -n 10000 ./workdir/output.sdf &&

    mkdir -p ./pdb &&
    cp -r ./workdir/receptor*.pdb ./pdb &&
    tar -cvhf archiv.tar ./pdb &&
    sudo -u ubuntu cp archiv.tar '$output_receptors' &&

    sudo -u ubuntu cp ./workdir/predictions.txt '$predictions'


    ]]></command>

    <inputs>
        <param type="data" name="receptor" format="pdb" label="Receptor" help="Select a receptor (pdb format)."/>
        <param type="data" name="ligands" format="sdf,mol" label="Ligands" help="Ligands (docked poses) in SDF format)"/>
        <param name="distance" type="float" value="2.0" min="1.0" max="5.0" label="Distance to waters" help="Remove waters closer than this distance to any ligand heavy atom"/>
        <param type="hidden" name="mock" value="" label="Mock calculations" help="Use random numbers instead of running on GPU"/>
    </inputs>
    <outputs>
        <data name="output" format="sdf" label="XChem pose scoring on ${on_string}"/>
        <data name="predictions" format="txt" label="Predictions on ${on_string}"/>
        <data name="output_receptors" format="tar" label="Receptors ${on_string}"/>

        <!--collection name="pdb_files" type="list" label="PDB files with variable number of waters">
            <discover_datasets pattern="__name_and_ext__" directory="pdb" />
        </collection-->
    </outputs>

    <tests>
	<test>
            <param name="receptor" value="receptor.pdb"/>
            <param name="ligands" value="ligands.sdf"/>
            <!--param name="mock" value="- -mock"/-->
            <param name="distance" value="4.0"/>
            <output name="output" ftype="sdf">
                <assert_contents>
                    <has_text text="TransFSReceptor"/>
                    <has_text text="TransFSScore"/>
                </assert_contents>
            </output>
            <!--output_collection name="pdb_files" type="list" count="2" /-->
        </test>
    </tests>
    <help><![CDATA[

.. class:: infomark

This tool performs scoring of docked ligand poses using deep learning.
It uses the gnina and libmolgrid toolkits to perform the scoring to generate
a prediction for how good the pose is.


-----

.. class:: infomark

**Inputs**

1. The protein receptor to dock into as a file in PDB format. This should have the ligand removed but retain the waters.
2. A set of ligand poses to score in SDF format.

-----

.. class:: infomark

**Outputs**

An SDF file is produced as output. The binding affinity scores are contained within the SDF file
as the TransFSScore property and the PDB file (with the waters that clash with the ligand removed)
that was used for the scoring as the TransFSReceptor property.
Values for the score range from 0 (poor binding) to 1 (good binding).

A set of PDB files is also output, each one with different crystallographic waters removed. Each ligand is
examined against input PDB structure and the with waters that clash (any heavy atom of the ligand closer than
the 'distance' parameter being removed. The filenames are encoded with the water numbers that are removed.

    ]]></help>
</tool>