annotate butina_clustering.xml @ 10:73de2fe4bf92 draft

"planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/chemfp commit deb7ad38cefd13df312431b1138054a68381efdf"

<tool id="ctb_chemfp_butina_clustering" name="Taylor-Butina clustering" version="1.5">
    <description>of molecular fingerprints</description>
    <requirements>
        <requirement type="package" version="1.5">chemfp</requirement>
        <requirement type="package" version="2.4.1">openbabel</requirement>
    </requirements>
    <command detect_errors="exit_code">
<![CDATA[
        python '$__tool_directory__/butina_clustering.py'
            -i '$infile'
            -t $threshold
            -o '$outfile'
            -p \${GALAXY_SLOTS:-1}
]]>
    </command>
    <inputs>
        <param name="infile" type="data" format="fps" label="Fingerprint dataset" help="Dataset missing? See TIP below"/>
        <param name='threshold' type='float' label='Threshold' value='0.8'/>
    </inputs>
    <outputs>
        <data format="tabular" name="outfile"/>
    </outputs>
    <tests>
        <test>
            <param name="infile" ftype="fps" value="targets.fps"/>
            <param name='threshold' value='0.8' ></param>
            <output name="outfile" ftype="tabular"  file='Taylor-Butina_Clustering_on_data_q.txt'/>
        </test>
    </tests>
<help>
<![CDATA[


.. class:: infomark

**What this tool does**

Unsupervised non-hierarchical clustering of molecular fingerprints, based on the Taylor-Butina algorithm, which guarantees that every cluster contains molecules which are within a distance cutoff of the central molecule. This tool is based on the chemfp_ project.

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

-----

.. 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:: infomark

**Output**

* Example::

	0 true singletons
	=>

	0 false singletons
	=>

	1 clusters
	55091849 has 12 other members
	=> 6499094 6485578 55079807 3153534 55102353 55091466 55091416 6485577 55169009 55091752 55091467 55168823


]]>
 </help>
    <citations>
        <citation type="doi">10.1186/1758-2946-5-S1-P36</citation>
        <citation type="doi">10.1021/ci9803381</citation>
    </citations>
</tool>