Mercurial > repos > bgruening > ctb_im_cluster_butina

comparison cluster_butina.xml @ 0:ad2b25cca758 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
"planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/im-pipelines commit 598dd288a384481b7602a0f6322c5081dc8da5d9"
author bgruening
date Tue, 21 Jul 2020 05:23:57 -0400
parents
children
comparison
equal deleted inserted replaced
-1:000000000000 0:ad2b25cca758
1 <tool id="ctb_im_cluster_butina" name="Butina Cluster" version="@TOOL_VERSION@+galaxy@GALAXY_VERSION@">
2 <description>using RDKit</description>
3 <macros>
4 <import>macros.xml</import>
5 <token name="@GALAXY_VERSION@">0</token>
6 </macros>
7 <expand macro="requirements" />
8 <command detect_errors="exit_code"><![CDATA[
9 cluster_butina
10 -i '$infile'
11 -if sdf
12 -t '$threshold'
13 -d '$descriptor_opts'
14 -m '$metric_opts'
15 #if $number != ''
16 -n '$number'
17 #end if
18 -e '$exclude'
19 #if $fragment_opts:
20 --fragment-method '$fragment_opts'
21 #end if
22 #if $field_conditional.use_field == 't':
23 #if $field_conditional.field:
24 -f '$field_conditional.field'
25 $field_conditional.field_opts
26 #end if
27 #end if
28 $output_fragment
29 --meta
30 -o outp
31 -of sdf &>> $logfile &&
32 cat outp_metrics.txt &>> $logfile &&
33 gzip -d outp.sdf.gz
34 ]]></command>
35 <inputs>
36 <param name="infile" type="data" format="sdf" label="Input file" help="Input file in SDF format"/>
37 <param name="threshold" min="0" max="1" type="float" value="0.7" label="Threshold" help="Similarity clustering threshold (1.0 means identical)"/>
38 <param name="descriptor_opts" type="select" label="Descriptor Options" help="Descriptor or fingerprint type (default rdkit)">
39 <option value="rdkit" selected="true">rdkit</option>
40 <option value="maccs">maccs</option>
41 <option value="morgan2">morgan2</option>
42 <option value="morgan3">morgan3</option>
43 </param>
44 <param name="metric_opts" type="select" label="Similarity metric" help="Default is the Tanimoto coefficient">
45 <option value="tanimoto" selected="true">tanimoto</option>
46 <option value="asymmetric">asymmetric</option>
47 <option value="braunblanquet">braunblanquet</option>
48 <option value="cosine">cosine</option>
49 <option value="dice">dice</option>
50 <option value="kulczynski">kulczynski</option>
51 <option value="mcconnaughey">mcconnaughey</option>
52 <option value="rogotgoldberg">rogotgoldberg</option>
53 <option value="russel">russel</option>
54 <option value="sokal">sokal</option>
55 </param>
56 <param name="number" type="integer" optional="true" label="Maximum number for diverse subset selection" help="Maximum number to pick for diverse subset selection. Leave blank for no maximum."/>
57 <param name="exclude" min="0" max="1" type="float" value="0.9" label="Exclude threshold" help="Threshold for excluding structures in diverse subset selection (1.0 means identical)"/>
58 <param name="fragment_opts" type="select" optional="true" label="Find single fragment" help="Find single fragment if more than one">
59 <option value="hac" selected="true">Biggest by heavy atom count</option>
60 <option value="mw">Biggest by molecular weight</option>
61 </param>
62 <param name="output_fragment" type="boolean" label="Output Fragment" truevalue="--output-fragment" falsevalue="" help="Output the biggest fragment rather than the original molecule"/>
63 <conditional name="field_conditional">
64 <param name="use_field" type="boolean" label="Use field" truevalue="t" falsevalue="f" help="Use a field to optimize diverse subset selection"/>
65 <when value="t">
66 <param name="field" type="text" label="Field" help="Field to use to optimise diverse subset selection"/>
67 <param name="field_opts" type="select" label="Field options" help="pick lowest or highest value specified by the 'field' component">
68 <option value="--min" selected="true">min</option>
69 <option value="--max">max</option>
70 </param>
71 </when>
72 <when value="f" />
73 </conditional>
74 </inputs>
75
76 <expand macro="outputs" />
77 <tests>
78 <test>
79 <param name="infile" value="Kinase_inhibs.sdf" ftype="sdf"/>
80 <param name="descriptor_opts" value="rdkit"/>
81 <param name="metric_opts" value="tanimoto"/>
82 <param name="threshold" value="0.6"/>
83 <param name="fragment_opts" value="hac"/>
84 <output name="outfile" ftype='sdf' file="cluster_butina_output1.sdf"/>
85 <output name="logfile">
86 <assert_contents>
87 <has_text text="Found 30 clusters"/>
88 </assert_contents>
89 </output>
90 </test>
91 </tests>
92 <help><![CDATA[
93
94 .. class:: infomark
95
96 **What this tool does**
97
98 This tool performs Butina clustering for a set of input molecules, using the chemistry toolkit RDKit, and returns results in SDF format.
99
100
101 -----
102
103 .. class:: infomark
104
105 **Input**
106
107 | - Molecules in `SDF format`_
108 | - A number of other parameters can be set, including the fingerprint type and the similarity metric to use.
109
110 .. _SDF format: http://en.wikipedia.org/wiki/Chemical_table_file
111
112
113 -----
114
115 .. class:: infomark
116
117 **Output**
118
119 SD file containing clusters.
120
121 ]]></help>
122 <expand macro="citations"/>
123 </tool>