view featurestein.xml @ 0:0eb24d808e75 draft default tip

"planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/im-pipelines commit d1d0ec4ebc97b2274b18a0aab99f41addd5357ae"
author bgruening
date Mon, 27 Jul 2020 11:31:14 -0400
parents
children
line wrap: on
line source

<tool id="featurestein" name="'FeatureStein' fragment overlay scoring" version="@TOOL_VERSION@+galaxy@GALAXY_VERSION@">
    <description>feature overlay scoring</description>
    <macros>
        <import>macros.xml</import>
        <token name="@GALAXY_VERSION@">0</token>
    </macros>
    <expand macro="requirements" />
    <command detect_errors="exit_code">
<![CDATA[
        featurestein_generate -i '$fragments' -if sdf &&
        featurestein_score -i '$ligands' -if sdf -f featurestein.p -o output -of sdf --no-gzip
]]>
    </command>
    <inputs>
        <param name="fragments" format="sdf" type="data" label="Fragments to generate feature maps" help="In SDF format"/>
        <param name="ligands" format="sdf" type="data" label="Ligands to score" help="In SDF format"/>
    </inputs>
    <outputs>
        <data name="output" format="sdf" from_work_dir="output.sdf" label="The scored ligands"/>
    </outputs>
    <tests>
        <test>
            <param name="fragments" ftype='sdf' value="hits-17.sdf" />
            <param name="ligands" ftype='sdf' value="poses.sdf" />
            <output name="output" ftype="sdf">
                <assert_contents>
                    <has_n_lines n="692" />
                    <has_text text="FeatureStein_Qual" />
                    <has_text text="FeatureStein_Quant" />
                </assert_contents>
            </output>
        </test>
    </tests>
    <help>
<![CDATA[

.. class:: infomark

**What this tool does**

FeatureStein involves use of merged RDKit feature maps to score ligand poses in terms of how well the features overlap
with features from a set of ligands, typically fragment screening hits. The features are molecular features like
hydrogen bond donors and acceptors or hydrophobic groups.
See this Jupyter notebook for more information: https://github.com/tdudgeon/jupyter_mpro/blob/master/featurestein/FeatureStein.ipynb
and this blog for more general info on RDKit feature maps:
http://rdkit.blogspot.com/2017/11/using-feature-maps.html

This module generates the merged feature maps from a set of molecules (typically fragment screening hits) and then.
scores a set of ligands using those merged feature maps.

The fields that are created are:

- FeatureStein_Quant: the sum of the scores for each feature in the ligand
- FeatureStein_Qual: the FeatureStein_Quant score divided by the number of features (number between 0 and 1)

-----

.. class:: infomark

**Input**

- fragments: SD-file of fragments to generate feature maps and merge
- ligands: SD-file of ligands to score

-----

.. class:: infomark

 **Output**

SD-file of the ligands with the FeatureStein scores added.

]]>
    </help>
    <expand macro="citations" />
</tool>