view chemfp_clustering/nxn_clustering.xml @ 31:a2ba3431eca4 draft

planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/chemfp commit a44c0a13283e873a740eabcad04f021208290dfe-dirty

<tool id="ctb_chemfp_nxn_clustering" name="NxN Clustering" version="0.2">
    <description>of molecular fingerprints</description>
    <requirements>
        <requirement type="package" version="1.7.0">numpy</requirement>
        <requirement type="package" version="1.1p1">chemfp</requirement>
        <requirement type="package" version="1.2.1">matplotlib</requirement>
        <requirement type="package" version="0.12.0">scipy</requirement>
        <requirement type="package" version="2.3.2">openbabel</requirement>
    </requirements>
    <command interpreter='python'>
<![CDATA[
        nxn_clustering.py
            -i $infile
            -t $threshold
            #if str($output_files) in ['both', 'image']:
                --cluster $image
            #end if
            #if str($output_files) in ['both', 'matrix']:
                --smatrix $smilarity_matrix
            #end if
            --oformat $oformat
]]>
    </command>
    <inputs>
        <param name="infile" type="data" format="fps" label="Finperprint dataset" help="Dataset missing? See TIP below"/>
        <param name='threshold' type='float' value='0.0' />
        <param name='oformat' type='select' format='text' label="Format of the resulting picture">
            <option value='png'>PNG</option>
            <option value='svg'>SVG</option>
        </param>
        <param name='output_files' type='select' format='text' label="Output options">
            <option value='both'>NxN matrix and Image</option>
            <option value='image'>Image</option>
            <option value='matrix'>NxN Matrix</option>
        </param>

    </inputs>
    <outputs>
        <data name="image" type="data" format="svg" label="${tool.name} on ${on_string} - Cluster Image">
            <filter>output_files == "both" or output_files == "image"</filter>
            <change_format>
                <when input="oformat" value="png" format="png"/>
            </change_format>
        </data>
        <data name="smilarity_matrix" format="binary" label="${tool.name} on ${on_string} - Similarity Matrix">
            <filter>output_files == "both" or output_files == "matrix"</filter>
        </data>
    </outputs>
    <tests>
        <test>
            <param name="infile" ftype="fps" value="q.fps" />
            <param name='treshold' value='0.75' />
            <param name='output_files' value='image' />
            <output ftype="svg" name="outfile" file='NxN_Clustering_on_q.svg' />
        </test>
    </tests>
    <help>
<![CDATA[

.. class:: infomark

**What this tool does**

Generating hierarchical clusters and visualizing clusters with dendrograms.
For the clustering and the fingerprint handling the chemfp_ project is used.

.. _chemfp: http://chemfp.com/

-----

.. class:: warningmark

**Hint**

The plotting of the cluster image is sensible only with a small dataset.

-----

.. class:: infomark

**Input**

Molecular fingerprints in FPS format. Open Babel Fastsearch index is not supported.

* Example::

	-  fingerprints in FPS format

		#FPS1
		#num_bits=881
		#type=CACTVS-E_SCREEN/1.0 extended=2
		#software=CACTVS/unknown
		#source=/home/mohammed/galaxy-central/database/files/000/dataset_423.dat
		#date=2012-02-09T13:20:37
		07ce04000000000000000000000000000080060000000c000000000000001a800f0000780008100000701487e960cc0bed3248000580644626004101b4844805901b041c2e
		19511e45039b8b2926101609401b13e40800000000000100200000040080000010000002000000000000	55169009
		07ce04000000000000000000000000000080060000000c000000000000001a800f0000780008100000701087e960cc0bed3248000580644626004101b4844805901b041c2e
		19111e45039b8b2926105609401313e40800000000000100200000040080000010000002000000000000	55079807
		........

	- Tanimoto threshold : 0.8 (between 0 and 1)

-----

.. class:: informark

**Output**

* Example::

	.. image:: $PATH_TO_IMAGES/NxN_clustering.png

-----

.. class:: infomark

**Cite**

The chemfp_ project from Andrew Dalke!

.. _chemfp: http://chemfp.com/

]]>
    </help>

</tool>