Mercurial > repos > bgruening > chembl

annotate chembl_structure_pipeline.xml @ 6:a57de37f12c2 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
"planemo upload for repository https://github.com/chembl/chembl_webresource_client commit 78f2261af4e00c830ea311337d0aed9b297aad8e"
author bgruening
date Wed, 07 Oct 2020 09:31:40 +0000
parents
children
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
6
a57de37f12c2 "planemo upload for repository https://github.com/chembl/chembl_webresource_client commit 78f2261af4e00c830ea311337d0aed9b297aad8e"
bgruening
parents:
diff changeset
1 <tool id="chembl_structure_pipeline" name="ChEMBL structure pipeline" version="@TOOL_VERSION@+galaxy@GALAXY_VERSION@">
a57de37f12c2 "planemo upload for repository https://github.com/chembl/chembl_webresource_client commit 78f2261af4e00c830ea311337d0aed9b297aad8e"
bgruening
parents:
diff changeset
2 <description>for curation and standardizing of molecular structures</description>
a57de37f12c2 "planemo upload for repository https://github.com/chembl/chembl_webresource_client commit 78f2261af4e00c830ea311337d0aed9b297aad8e"
bgruening
parents:
diff changeset
3 <macros>
a57de37f12c2 "planemo upload for repository https://github.com/chembl/chembl_webresource_client commit 78f2261af4e00c830ea311337d0aed9b297aad8e"
bgruening
parents:
diff changeset
4 <token name="@TOOL_VERSION@">1.0.0</token>
a57de37f12c2 "planemo upload for repository https://github.com/chembl/chembl_webresource_client commit 78f2261af4e00c830ea311337d0aed9b297aad8e"
bgruening
parents:
diff changeset
5 <token name="@GALAXY_VERSION@">0</token>
a57de37f12c2 "planemo upload for repository https://github.com/chembl/chembl_webresource_client commit 78f2261af4e00c830ea311337d0aed9b297aad8e"
bgruening
parents:
diff changeset
6 </macros>
a57de37f12c2 "planemo upload for repository https://github.com/chembl/chembl_webresource_client commit 78f2261af4e00c830ea311337d0aed9b297aad8e"
bgruening
parents:
diff changeset
7 <requirements>
a57de37f12c2 "planemo upload for repository https://github.com/chembl/chembl_webresource_client commit 78f2261af4e00c830ea311337d0aed9b297aad8e"
bgruening
parents:
diff changeset
8 <requirement type="package" version="@TOOL_VERSION@">chembl_structure_pipeline</requirement>
a57de37f12c2 "planemo upload for repository https://github.com/chembl/chembl_webresource_client commit 78f2261af4e00c830ea311337d0aed9b297aad8e"
bgruening
parents:
diff changeset
9 </requirements>
a57de37f12c2 "planemo upload for repository https://github.com/chembl/chembl_webresource_client commit 78f2261af4e00c830ea311337d0aed9b297aad8e"
bgruening
parents:
diff changeset
10 <command><![CDATA[
a57de37f12c2 "planemo upload for repository https://github.com/chembl/chembl_webresource_client commit 78f2261af4e00c830ea311337d0aed9b297aad8e"
bgruening
parents:
diff changeset
11 python '$__tool_directory__/structure_pipeline.py'
a57de37f12c2 "planemo upload for repository https://github.com/chembl/chembl_webresource_client commit 78f2261af4e00c830ea311337d0aed9b297aad8e"
bgruening
parents:
diff changeset
12 --input '$input'
a57de37f12c2 "planemo upload for repository https://github.com/chembl/chembl_webresource_client commit 78f2261af4e00c830ea311337d0aed9b297aad8e"
bgruening
parents:
diff changeset
13 --output '$output'
a57de37f12c2 "planemo upload for repository https://github.com/chembl/chembl_webresource_client commit 78f2261af4e00c830ea311337d0aed9b297aad8e"
bgruening
parents:
diff changeset
14 $standardize
a57de37f12c2 "planemo upload for repository https://github.com/chembl/chembl_webresource_client commit 78f2261af4e00c830ea311337d0aed9b297aad8e"
bgruening
parents:
diff changeset
15 $get_parent
a57de37f12c2 "planemo upload for repository https://github.com/chembl/chembl_webresource_client commit 78f2261af4e00c830ea311337d0aed9b297aad8e"
bgruening
parents:
diff changeset
16 $check
a57de37f12c2 "planemo upload for repository https://github.com/chembl/chembl_webresource_client commit 78f2261af4e00c830ea311337d0aed9b297aad8e"
bgruening
parents:
diff changeset
17 ]]>
a57de37f12c2 "planemo upload for repository https://github.com/chembl/chembl_webresource_client commit 78f2261af4e00c830ea311337d0aed9b297aad8e"
bgruening
parents:
diff changeset
18 </command>
a57de37f12c2 "planemo upload for repository https://github.com/chembl/chembl_webresource_client commit 78f2261af4e00c830ea311337d0aed9b297aad8e"
bgruening
parents:
diff changeset
19 <inputs>
a57de37f12c2 "planemo upload for repository https://github.com/chembl/chembl_webresource_client commit 78f2261af4e00c830ea311337d0aed9b297aad8e"
bgruening
parents:
diff changeset
20 <param label="SDF/MOL input" type="data" name="input" format="sdf,mol" argument="--input"/>
a57de37f12c2 "planemo upload for repository https://github.com/chembl/chembl_webresource_client commit 78f2261af4e00c830ea311337d0aed9b297aad8e"
bgruening
parents:
diff changeset
21 <param label="Standardize" checked="false" type="boolean" name="standardize" argument="--standardize" truevalue="--standardize" falsevalue="" help="Apply the 'Standardize' pipeline component"/>
a57de37f12c2 "planemo upload for repository https://github.com/chembl/chembl_webresource_client commit 78f2261af4e00c830ea311337d0aed9b297aad8e"
bgruening
parents:
diff changeset
22 <param label="Get parent" checked="false" type="boolean" name="get_parent" argument="--get_parent" truevalue="--get_parent" falsevalue="" help="Apply the 'GetParent' pipeline component"/>
a57de37f12c2 "planemo upload for repository https://github.com/chembl/chembl_webresource_client commit 78f2261af4e00c830ea311337d0aed9b297aad8e"
bgruening
parents:
diff changeset
23 <param label="Check" checked="false" type="boolean" name="check" argument="--check" truevalue="--check" falsevalue="" help="Apply the 'Check' pipeline component"/>
a57de37f12c2 "planemo upload for repository https://github.com/chembl/chembl_webresource_client commit 78f2261af4e00c830ea311337d0aed9b297aad8e"
bgruening
parents:
diff changeset
24 </inputs>
a57de37f12c2 "planemo upload for repository https://github.com/chembl/chembl_webresource_client commit 78f2261af4e00c830ea311337d0aed9b297aad8e"
bgruening
parents:
diff changeset
25 <outputs>
a57de37f12c2 "planemo upload for repository https://github.com/chembl/chembl_webresource_client commit 78f2261af4e00c830ea311337d0aed9b297aad8e"
bgruening
parents:
diff changeset
26 <data name="output" format="sdf" label="Processed molecules"/>
a57de37f12c2 "planemo upload for repository https://github.com/chembl/chembl_webresource_client commit 78f2261af4e00c830ea311337d0aed9b297aad8e"
bgruening
parents:
diff changeset
27 </outputs>
a57de37f12c2 "planemo upload for repository https://github.com/chembl/chembl_webresource_client commit 78f2261af4e00c830ea311337d0aed9b297aad8e"
bgruening
parents:
diff changeset
28 <tests>
a57de37f12c2 "planemo upload for repository https://github.com/chembl/chembl_webresource_client commit 78f2261af4e00c830ea311337d0aed9b297aad8e"
bgruening
parents:
diff changeset
29 <test>
a57de37f12c2 "planemo upload for repository https://github.com/chembl/chembl_webresource_client commit 78f2261af4e00c830ea311337d0aed9b297aad8e"
bgruening
parents:
diff changeset
30 <param name="input" value="o_molblock.mol" />
a57de37f12c2 "planemo upload for repository https://github.com/chembl/chembl_webresource_client commit 78f2261af4e00c830ea311337d0aed9b297aad8e"
bgruening
parents:
diff changeset
31 <param name="standardize" value="true" />
a57de37f12c2 "planemo upload for repository https://github.com/chembl/chembl_webresource_client commit 78f2261af4e00c830ea311337d0aed9b297aad8e"
bgruening
parents:
diff changeset
32 <output name="output" value="std_molblock.mol"/>
a57de37f12c2 "planemo upload for repository https://github.com/chembl/chembl_webresource_client commit 78f2261af4e00c830ea311337d0aed9b297aad8e"
bgruening
parents:
diff changeset
33 </test>
a57de37f12c2 "planemo upload for repository https://github.com/chembl/chembl_webresource_client commit 78f2261af4e00c830ea311337d0aed9b297aad8e"
bgruening
parents:
diff changeset
34 <test>
a57de37f12c2 "planemo upload for repository https://github.com/chembl/chembl_webresource_client commit 78f2261af4e00c830ea311337d0aed9b297aad8e"
bgruening
parents:
diff changeset
35 <param name="input" value="o_molblock.mol" ftype="mol" />
a57de37f12c2 "planemo upload for repository https://github.com/chembl/chembl_webresource_client commit 78f2261af4e00c830ea311337d0aed9b297aad8e"
bgruening
parents:
diff changeset
36 <param name="get_parent" value="true" />
a57de37f12c2 "planemo upload for repository https://github.com/chembl/chembl_webresource_client commit 78f2261af4e00c830ea311337d0aed9b297aad8e"
bgruening
parents:
diff changeset
37 <output name="output" value="parent_molblock.mol"/>
a57de37f12c2 "planemo upload for repository https://github.com/chembl/chembl_webresource_client commit 78f2261af4e00c830ea311337d0aed9b297aad8e"
bgruening
parents:
diff changeset
38 </test>
a57de37f12c2 "planemo upload for repository https://github.com/chembl/chembl_webresource_client commit 78f2261af4e00c830ea311337d0aed9b297aad8e"
bgruening
parents:
diff changeset
39 <test>
a57de37f12c2 "planemo upload for repository https://github.com/chembl/chembl_webresource_client commit 78f2261af4e00c830ea311337d0aed9b297aad8e"
bgruening
parents:
diff changeset
40 <param name="input" value="o_molblock.mol" ftype="mol" />
a57de37f12c2 "planemo upload for repository https://github.com/chembl/chembl_webresource_client commit 78f2261af4e00c830ea311337d0aed9b297aad8e"
bgruening
parents:
diff changeset
41 <param name="check" value="true" />
a57de37f12c2 "planemo upload for repository https://github.com/chembl/chembl_webresource_client commit 78f2261af4e00c830ea311337d0aed9b297aad8e"
bgruening
parents:
diff changeset
42 <output name="output" value="check.mol"/>
a57de37f12c2 "planemo upload for repository https://github.com/chembl/chembl_webresource_client commit 78f2261af4e00c830ea311337d0aed9b297aad8e"
bgruening
parents:
diff changeset
43 </test>
a57de37f12c2 "planemo upload for repository https://github.com/chembl/chembl_webresource_client commit 78f2261af4e00c830ea311337d0aed9b297aad8e"
bgruening
parents:
diff changeset
44 <test>
a57de37f12c2 "planemo upload for repository https://github.com/chembl/chembl_webresource_client commit 78f2261af4e00c830ea311337d0aed9b297aad8e"
bgruening
parents:
diff changeset
45 <param name="input" value="10mol.sdf" ftype="sdf" />
a57de37f12c2 "planemo upload for repository https://github.com/chembl/chembl_webresource_client commit 78f2261af4e00c830ea311337d0aed9b297aad8e"
bgruening
parents:
diff changeset
46 <param name="standardize" value="true" />
a57de37f12c2 "planemo upload for repository https://github.com/chembl/chembl_webresource_client commit 78f2261af4e00c830ea311337d0aed9b297aad8e"
bgruening
parents:
diff changeset
47 <param name="get_parent" value="true" />
a57de37f12c2 "planemo upload for repository https://github.com/chembl/chembl_webresource_client commit 78f2261af4e00c830ea311337d0aed9b297aad8e"
bgruening
parents:
diff changeset
48 <param name="check" value="true" />
a57de37f12c2 "planemo upload for repository https://github.com/chembl/chembl_webresource_client commit 78f2261af4e00c830ea311337d0aed9b297aad8e"
bgruening
parents:
diff changeset
49 <output name="output" value="pipeline_multi.sdf"/>
a57de37f12c2 "planemo upload for repository https://github.com/chembl/chembl_webresource_client commit 78f2261af4e00c830ea311337d0aed9b297aad8e"
bgruening
parents:
diff changeset
50 </test>
a57de37f12c2 "planemo upload for repository https://github.com/chembl/chembl_webresource_client commit 78f2261af4e00c830ea311337d0aed9b297aad8e"
bgruening
parents:
diff changeset
51 </tests>
a57de37f12c2 "planemo upload for repository https://github.com/chembl/chembl_webresource_client commit 78f2261af4e00c830ea311337d0aed9b297aad8e"
bgruening
parents:
diff changeset
52 <help><![CDATA[
a57de37f12c2 "planemo upload for repository https://github.com/chembl/chembl_webresource_client commit 78f2261af4e00c830ea311337d0aed9b297aad8e"
bgruening
parents:
diff changeset
53
a57de37f12c2 "planemo upload for repository https://github.com/chembl/chembl_webresource_client commit 78f2261af4e00c830ea311337d0aed9b297aad8e"
bgruening
parents:
diff changeset
54 Apply the ChEMBL chemical curation pipeline to a set of chemical structures in SDF
a57de37f12c2 "planemo upload for repository https://github.com/chembl/chembl_webresource_client commit 78f2261af4e00c830ea311337d0aed9b297aad8e"
bgruening
parents:
diff changeset
55 format. The pipeline is described in detail in the citation provided (Bento et al.,
a57de37f12c2 "planemo upload for repository https://github.com/chembl/chembl_webresource_client commit 78f2261af4e00c830ea311337d0aed9b297aad8e"
bgruening
parents:
diff changeset
56 2020).
a57de37f12c2 "planemo upload for repository https://github.com/chembl/chembl_webresource_client commit 78f2261af4e00c830ea311337d0aed9b297aad8e"
bgruening
parents:
diff changeset
57
a57de37f12c2 "planemo upload for repository https://github.com/chembl/chembl_webresource_client commit 78f2261af4e00c830ea311337d0aed9b297aad8e"
bgruening
parents:
diff changeset
58 The pipeline consists of three components:
a57de37f12c2 "planemo upload for repository https://github.com/chembl/chembl_webresource_client commit 78f2261af4e00c830ea311337d0aed9b297aad8e"
bgruening
parents:
diff changeset
59 - a Standardizer which formats compounds according to defined rules and conventions, based mostly on FDA/IUPAC guidelines.
a57de37f12c2 "planemo upload for repository https://github.com/chembl/chembl_webresource_client commit 78f2261af4e00c830ea311337d0aed9b297aad8e"
bgruening
parents:
diff changeset
60 - a GetParent component that removes any salts and solvents from the compound to create its parent.
a57de37f12c2 "planemo upload for repository https://github.com/chembl/chembl_webresource_client commit 78f2261af4e00c830ea311337d0aed9b297aad8e"
bgruening
parents:
diff changeset
61 - a Checker to test the validity of chemical structures and flag any serious errors. Errors are given a code from 0 (least serious) to 10 (most serious), the highest of which is stored in the SDF field `<MaxPenaltyScore>`. A list of all errors encountered is recorded under `<IssueMessages>`.
a57de37f12c2 "planemo upload for repository https://github.com/chembl/chembl_webresource_client commit 78f2261af4e00c830ea311337d0aed9b297aad8e"
bgruening
parents:
diff changeset
62
a57de37f12c2 "planemo upload for repository https://github.com/chembl/chembl_webresource_client commit 78f2261af4e00c830ea311337d0aed9b297aad8e"
bgruening
parents:
diff changeset
63 Either one or more of these protocols can be applied in a single Galaxy job.
a57de37f12c2 "planemo upload for repository https://github.com/chembl/chembl_webresource_client commit 78f2261af4e00c830ea311337d0aed9b297aad8e"
bgruening
parents:
diff changeset
64
a57de37f12c2 "planemo upload for repository https://github.com/chembl/chembl_webresource_client commit 78f2261af4e00c830ea311337d0aed9b297aad8e"
bgruening
parents:
diff changeset
65 -----
a57de37f12c2 "planemo upload for repository https://github.com/chembl/chembl_webresource_client commit 78f2261af4e00c830ea311337d0aed9b297aad8e"
bgruening
parents:
diff changeset
66
a57de37f12c2 "planemo upload for repository https://github.com/chembl/chembl_webresource_client commit 78f2261af4e00c830ea311337d0aed9b297aad8e"
bgruening
parents:
diff changeset
67 .. class:: infomark
a57de37f12c2 "planemo upload for repository https://github.com/chembl/chembl_webresource_client commit 78f2261af4e00c830ea311337d0aed9b297aad8e"
bgruening
parents:
diff changeset
68
a57de37f12c2 "planemo upload for repository https://github.com/chembl/chembl_webresource_client commit 78f2261af4e00c830ea311337d0aed9b297aad8e"
bgruening
parents:
diff changeset
69 **Input**
a57de37f12c2 "planemo upload for repository https://github.com/chembl/chembl_webresource_client commit 78f2261af4e00c830ea311337d0aed9b297aad8e"
bgruening
parents:
diff changeset
70
a57de37f12c2 "planemo upload for repository https://github.com/chembl/chembl_webresource_client commit 78f2261af4e00c830ea311337d0aed9b297aad8e"
bgruening
parents:
diff changeset
71 One or more molecules in MOL/SDF format.
a57de37f12c2 "planemo upload for repository https://github.com/chembl/chembl_webresource_client commit 78f2261af4e00c830ea311337d0aed9b297aad8e"
bgruening
parents:
diff changeset
72
a57de37f12c2 "planemo upload for repository https://github.com/chembl/chembl_webresource_client commit 78f2261af4e00c830ea311337d0aed9b297aad8e"
bgruening
parents:
diff changeset
73 -----
a57de37f12c2 "planemo upload for repository https://github.com/chembl/chembl_webresource_client commit 78f2261af4e00c830ea311337d0aed9b297aad8e"
bgruening
parents:
diff changeset
74
a57de37f12c2 "planemo upload for repository https://github.com/chembl/chembl_webresource_client commit 78f2261af4e00c830ea311337d0aed9b297aad8e"
bgruening
parents:
diff changeset
75 .. class:: infomark
a57de37f12c2 "planemo upload for repository https://github.com/chembl/chembl_webresource_client commit 78f2261af4e00c830ea311337d0aed9b297aad8e"
bgruening
parents:
diff changeset
76
a57de37f12c2 "planemo upload for repository https://github.com/chembl/chembl_webresource_client commit 78f2261af4e00c830ea311337d0aed9b297aad8e"
bgruening
parents:
diff changeset
77 **Output**
a57de37f12c2 "planemo upload for repository https://github.com/chembl/chembl_webresource_client commit 78f2261af4e00c830ea311337d0aed9b297aad8e"
bgruening
parents:
diff changeset
78
a57de37f12c2 "planemo upload for repository https://github.com/chembl/chembl_webresource_client commit 78f2261af4e00c830ea311337d0aed9b297aad8e"
bgruening
parents:
diff changeset
79 A MOL/SD-file containing the processed molecules.
a57de37f12c2 "planemo upload for repository https://github.com/chembl/chembl_webresource_client commit 78f2261af4e00c830ea311337d0aed9b297aad8e"
bgruening
parents:
diff changeset
80
a57de37f12c2 "planemo upload for repository https://github.com/chembl/chembl_webresource_client commit 78f2261af4e00c830ea311337d0aed9b297aad8e"
bgruening
parents:
diff changeset
81 ]]></help>
a57de37f12c2 "planemo upload for repository https://github.com/chembl/chembl_webresource_client commit 78f2261af4e00c830ea311337d0aed9b297aad8e"
bgruening
parents:
diff changeset
82 <citations>
a57de37f12c2 "planemo upload for repository https://github.com/chembl/chembl_webresource_client commit 78f2261af4e00c830ea311337d0aed9b297aad8e"
bgruening
parents:
diff changeset
83 <citation type="doi">10.1186/s13321-020-00456-1</citation>
a57de37f12c2 "planemo upload for repository https://github.com/chembl/chembl_webresource_client commit 78f2261af4e00c830ea311337d0aed9b297aad8e"
bgruening
parents:
diff changeset
84 </citations>
a57de37f12c2 "planemo upload for repository https://github.com/chembl/chembl_webresource_client commit 78f2261af4e00c830ea311337d0aed9b297aad8e"
bgruening
parents:
diff changeset
85 </tool>