Mercurial > repos > bgruening > ctb_im_max_min_picker

comparison max_min_picker.xml @ 0:2d9ca306538d 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 05:23:34 -0400
parents
children
comparison
equal deleted inserted replaced
-1:000000000000 0:2d9ca306538d
1 <tool id="ctb_im_max_min_picker" name="Pick" version="@TOOL_VERSION@+galaxy@GALAXY_VERSION@">
2 <description>diverse compounds from a library with Butina clustering</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 max_min_picker
10 -i '$infile'
11 -if sdf
12 -t '$threshold'
13 -d '$descriptor_opts'
14 #if $number != ''
15 -n $number
16 #end if
17 --fragment-method '$fragment_opts'
18 #if $seedfile
19 -s '$seedfile'
20 #end if
21 $out_fragment
22 --meta
23 -o outp
24 -of sdf &>> $logfile &&
25 cat outp_metrics.txt &>> $logfile &&
26 gzip -d outp.sdf.gz
27 ]]></command>
28 <inputs>
29 <param name="infile" type="data" format="sdf" label="Input file" help="Input file in SDF or JSON format"/>
30 <param name="threshold" type="float" label="Similarity threshold" value="0.7" min="0" max="1" help="1.0 means identical"/>
31 <param name="descriptor_opts" type="select" label="Type of descriptor or fingerprint" help="Default is morgan2">
32 <option value="maccs">maccs</option>
33 <option value="morgan2" selected="true">morgan2</option>
34 <option value="morgan3">morgan3</option>
35 </param>
36 <param name="number" type="integer" optional="true" label="Maximum number to pick for diverse subset selection" help="ABC"/>
37 <param name="fragment_opts" type="select" label="Fragment" help="Approach to find biggest fragment, if more than one is found">
38 <option value="hac" selected="true">Biggest by heavy atom count</option>
39 <option value="mw">Biggest by molecular weight</option>
40 </param>
41 <param name="seedfile" type="data" format="sdf" optional="true" label="Seed file" help="Optional file containing any seed molecules that have already been picked"/>
42 <param name="out_fragment" type="boolean" label="Output fragment" truevalue="--output-fragment" falsevalue="" help="Output the biggest fragment rather than the original molecule"/>
43 </inputs>
44
45 <expand macro="outputs" />
46
47 <tests>
48 <test>
49 <param name="infile" value="Kinase_inhibs.sdf" ftype="sdf"/>
50 <param name="threshold" value="0.5"/>
51 <param name="descriptor_opts" value="morgan2" />
52 <param name="fragment_opts" value="hac" />
53 <output name="outfile" ftype='sdf'>
54 <assert_contents>
55 <has_text_matching expression="^([^\$]+?\$\$\$\$){33}?$"/>
56 </assert_contents>
57 </output>
58 <output name="logfile">
59 <assert_contents>
60 <has_text text="36 candidates 36 total"/>
61 <has_text text="Output 33 molecules"/>
62 </assert_contents>
63 </output>
64 </test>
65 </tests>
66 <help>
67 <![CDATA[
68
69 .. class:: infomark
70
71 **What this tool does**
72
73 This molecule selects a subset from a library, ensuring the subset reflects the diversity of the library overall by applying Butina clustering.
74
75
76 -----
77
78 .. class:: infomark
79
80 **Input**
81
82 | - Compounds in `SDF Format`_
83 | - Various options: similarity threshold, type of fingerprint, seem molecule.
84
85 .. _SDF Format: http://en.wikipedia.org/wiki/Chemical_table_file
86
87
88 -----
89
90 .. class:: infomark
91
92 **Output**
93
94 SD-file containing picked compounds.
95
96 ]]></help>
97 <expand macro="citations" />
98 </tool>