annotate build/tools/NameMatcher/NameMatcher.xml @ 11:40c15b7467f1 draft default tip

planemo upload for repository https://forgemia.inra.fr/metexplore/met4j-galaxy commit 61dbdbae896d18b519a470e056cb8b4f98394518
author metexplore
date Thu, 13 Feb 2025 15:08:22 +0000
parents 6a112eaf8f38
children
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
9
0976a6257300 planemo upload for repository https://forgemia.inra.fr/metexplore/met4j-galaxy commit 05db35f63cadb9d56dafff594a3507c59cd85273
metexplore
parents: 8
diff changeset
1 <?xml version="1.0" encoding="UTF-8" standalone="no"?>
11
40c15b7467f1 planemo upload for repository https://forgemia.inra.fr/metexplore/met4j-galaxy commit 61dbdbae896d18b519a470e056cb8b4f98394518
metexplore
parents: 10
diff changeset
2 <tool id="met4j_NameMatcher" name="NameMatcher" version="2.0.1">
6
7a6f2380fc1d planemo upload for repository https://forgemia.inra.fr/metexplore/met4j-galaxy
metexplore
parents:
diff changeset
3 <description>This tool runs edit-distance based fuzzy matching to perform near-similar name matching between a metabolic model and a list of chemical names in a dataset. A harmonization processing is performed on chemical names with substitutions of common patterns among synonyms, in order to create aliases on which classical fuzzy matching can be run efficiently.</description>
7a6f2380fc1d planemo upload for repository https://forgemia.inra.fr/metexplore/met4j-galaxy
metexplore
parents:
diff changeset
4 <xrefs>
7a6f2380fc1d planemo upload for repository https://forgemia.inra.fr/metexplore/met4j-galaxy
metexplore
parents:
diff changeset
5 <xref type="bio.tools">met4j</xref>
7a6f2380fc1d planemo upload for repository https://forgemia.inra.fr/metexplore/met4j-galaxy
metexplore
parents:
diff changeset
6 </xrefs>
7a6f2380fc1d planemo upload for repository https://forgemia.inra.fr/metexplore/met4j-galaxy
metexplore
parents:
diff changeset
7 <requirements>
11
40c15b7467f1 planemo upload for repository https://forgemia.inra.fr/metexplore/met4j-galaxy commit 61dbdbae896d18b519a470e056cb8b4f98394518
metexplore
parents: 10
diff changeset
8 <container type="singularity">oras://registry.forgemia.inra.fr/metexplore/met4j/met4j-singularity:2.0.1</container>
6
7a6f2380fc1d planemo upload for repository https://forgemia.inra.fr/metexplore/met4j-galaxy
metexplore
parents:
diff changeset
9 </requirements>
7a6f2380fc1d planemo upload for repository https://forgemia.inra.fr/metexplore/met4j-galaxy
metexplore
parents:
diff changeset
10 <command detect_errors="exit_code"><![CDATA[sh /usr/bin/met4j.sh mapping.NameMatcher#if str($n):
7a6f2380fc1d planemo upload for repository https://forgemia.inra.fr/metexplore/met4j-galaxy
metexplore
parents:
diff changeset
11 -nMatch "$n"
7a6f2380fc1d planemo upload for repository https://forgemia.inra.fr/metexplore/met4j-galaxy
metexplore
parents:
diff changeset
12 #end if
7a6f2380fc1d planemo upload for repository https://forgemia.inra.fr/metexplore/met4j-galaxy
metexplore
parents:
diff changeset
13 #if str($nSkip):
7a6f2380fc1d planemo upload for repository https://forgemia.inra.fr/metexplore/met4j-galaxy
metexplore
parents:
diff changeset
14 -skip "$nSkip"
7a6f2380fc1d planemo upload for repository https://forgemia.inra.fr/metexplore/met4j-galaxy
metexplore
parents:
diff changeset
15 #end if
7a6f2380fc1d planemo upload for repository https://forgemia.inra.fr/metexplore/met4j-galaxy
metexplore
parents:
diff changeset
16 #if str($col):
7a6f2380fc1d planemo upload for repository https://forgemia.inra.fr/metexplore/met4j-galaxy
metexplore
parents:
diff changeset
17 -col "$col"
7a6f2380fc1d planemo upload for repository https://forgemia.inra.fr/metexplore/met4j-galaxy
metexplore
parents:
diff changeset
18 #end if
9
0976a6257300 planemo upload for repository https://forgemia.inra.fr/metexplore/met4j-galaxy commit 05db35f63cadb9d56dafff594a3507c59cd85273
metexplore
parents: 8
diff changeset
19 -i "$sbml"
6
7a6f2380fc1d planemo upload for repository https://forgemia.inra.fr/metexplore/met4j-galaxy
metexplore
parents:
diff changeset
20 -compound "$input"
7a6f2380fc1d planemo upload for repository https://forgemia.inra.fr/metexplore/met4j-galaxy
metexplore
parents:
diff changeset
21 #if str($comment):
7a6f2380fc1d planemo upload for repository https://forgemia.inra.fr/metexplore/met4j-galaxy
metexplore
parents:
diff changeset
22 -c "$comment"
7a6f2380fc1d planemo upload for repository https://forgemia.inra.fr/metexplore/met4j-galaxy
metexplore
parents:
diff changeset
23 #end if
7a6f2380fc1d planemo upload for repository https://forgemia.inra.fr/metexplore/met4j-galaxy
metexplore
parents:
diff changeset
24 #if str($sep):
7a6f2380fc1d planemo upload for repository https://forgemia.inra.fr/metexplore/met4j-galaxy
metexplore
parents:
diff changeset
25 -sep "$sep"
7a6f2380fc1d planemo upload for repository https://forgemia.inra.fr/metexplore/met4j-galaxy
metexplore
parents:
diff changeset
26 #end if
7a6f2380fc1d planemo upload for repository https://forgemia.inra.fr/metexplore/met4j-galaxy
metexplore
parents:
diff changeset
27 -o "$outputFile"
7a6f2380fc1d planemo upload for repository https://forgemia.inra.fr/metexplore/met4j-galaxy
metexplore
parents:
diff changeset
28 ]]></command>
7a6f2380fc1d planemo upload for repository https://forgemia.inra.fr/metexplore/met4j-galaxy
metexplore
parents:
diff changeset
29 <inputs>
9
0976a6257300 planemo upload for repository https://forgemia.inra.fr/metexplore/met4j-galaxy commit 05db35f63cadb9d56dafff594a3507c59cd85273
metexplore
parents: 8
diff changeset
30 <param argument="-nMatch" label="[1] Number of matchs to return per name" name="n" optional="true" type="text" value="1">
6
7a6f2380fc1d planemo upload for repository https://forgemia.inra.fr/metexplore/met4j-galaxy
metexplore
parents:
diff changeset
31 <sanitizer invalid_char="_">
7a6f2380fc1d planemo upload for repository https://forgemia.inra.fr/metexplore/met4j-galaxy
metexplore
parents:
diff changeset
32 <valid initial="string.printable"/>
7a6f2380fc1d planemo upload for repository https://forgemia.inra.fr/metexplore/met4j-galaxy
metexplore
parents:
diff changeset
33 </sanitizer>
7a6f2380fc1d planemo upload for repository https://forgemia.inra.fr/metexplore/met4j-galaxy
metexplore
parents:
diff changeset
34 </param>
7a6f2380fc1d planemo upload for repository https://forgemia.inra.fr/metexplore/met4j-galaxy
metexplore
parents:
diff changeset
35 <param argument="-skip" label="[0] Number of lines to skip at the beginning of the compound file" name="nSkip" optional="true" type="text" value="0">
7a6f2380fc1d planemo upload for repository https://forgemia.inra.fr/metexplore/met4j-galaxy
metexplore
parents:
diff changeset
36 <sanitizer invalid_char="_">
7a6f2380fc1d planemo upload for repository https://forgemia.inra.fr/metexplore/met4j-galaxy
metexplore
parents:
diff changeset
37 <valid initial="string.printable"/>
7a6f2380fc1d planemo upload for repository https://forgemia.inra.fr/metexplore/met4j-galaxy
metexplore
parents:
diff changeset
38 </sanitizer>
7a6f2380fc1d planemo upload for repository https://forgemia.inra.fr/metexplore/met4j-galaxy
metexplore
parents:
diff changeset
39 </param>
7a6f2380fc1d planemo upload for repository https://forgemia.inra.fr/metexplore/met4j-galaxy
metexplore
parents:
diff changeset
40 <param argument="-col" label="[1] column containing compounds' names" name="col" optional="true" type="text" value="1">
7a6f2380fc1d planemo upload for repository https://forgemia.inra.fr/metexplore/met4j-galaxy
metexplore
parents:
diff changeset
41 <sanitizer invalid_char="_">
7a6f2380fc1d planemo upload for repository https://forgemia.inra.fr/metexplore/met4j-galaxy
metexplore
parents:
diff changeset
42 <valid initial="string.printable"/>
7a6f2380fc1d planemo upload for repository https://forgemia.inra.fr/metexplore/met4j-galaxy
metexplore
parents:
diff changeset
43 </sanitizer>
7a6f2380fc1d planemo upload for repository https://forgemia.inra.fr/metexplore/met4j-galaxy
metexplore
parents:
diff changeset
44 </param>
9
0976a6257300 planemo upload for repository https://forgemia.inra.fr/metexplore/met4j-galaxy commit 05db35f63cadb9d56dafff594a3507c59cd85273
metexplore
parents: 8
diff changeset
45 <param argument="-i" format="sbml" label="Original sbml file" name="sbml" optional="false" type="data" value=""/>
6
7a6f2380fc1d planemo upload for repository https://forgemia.inra.fr/metexplore/met4j-galaxy
metexplore
parents:
diff changeset
46 <param argument="-compound" format="tsv" label="Compound file containing one column with compound names to search among the SBML entries" name="input" optional="false" type="data" value=""/>
7a6f2380fc1d planemo upload for repository https://forgemia.inra.fr/metexplore/met4j-galaxy
metexplore
parents:
diff changeset
47 <param argument="-c" label="[#] Comment String in the compound file. The lines beginning by this string won't be read" name="comment" optional="true" type="text" value="#">
7a6f2380fc1d planemo upload for repository https://forgemia.inra.fr/metexplore/met4j-galaxy
metexplore
parents:
diff changeset
48 <sanitizer invalid_char="_">
7a6f2380fc1d planemo upload for repository https://forgemia.inra.fr/metexplore/met4j-galaxy
metexplore
parents:
diff changeset
49 <valid initial="string.printable"/>
7a6f2380fc1d planemo upload for repository https://forgemia.inra.fr/metexplore/met4j-galaxy
metexplore
parents:
diff changeset
50 </sanitizer>
7a6f2380fc1d planemo upload for repository https://forgemia.inra.fr/metexplore/met4j-galaxy
metexplore
parents:
diff changeset
51 </param>
7a6f2380fc1d planemo upload for repository https://forgemia.inra.fr/metexplore/met4j-galaxy
metexplore
parents:
diff changeset
52 <param argument="-sep" label="[\t] separator in the compound file to split the colmumns." name="sep" optional="true" type="text" value="&#9;">
7a6f2380fc1d planemo upload for repository https://forgemia.inra.fr/metexplore/met4j-galaxy
metexplore
parents:
diff changeset
53 <sanitizer invalid_char="_">
7a6f2380fc1d planemo upload for repository https://forgemia.inra.fr/metexplore/met4j-galaxy
metexplore
parents:
diff changeset
54 <valid initial="string.printable"/>
7a6f2380fc1d planemo upload for repository https://forgemia.inra.fr/metexplore/met4j-galaxy
metexplore
parents:
diff changeset
55 </sanitizer>
7a6f2380fc1d planemo upload for repository https://forgemia.inra.fr/metexplore/met4j-galaxy
metexplore
parents:
diff changeset
56 </param>
7a6f2380fc1d planemo upload for repository https://forgemia.inra.fr/metexplore/met4j-galaxy
metexplore
parents:
diff changeset
57 </inputs>
7a6f2380fc1d planemo upload for repository https://forgemia.inra.fr/metexplore/met4j-galaxy
metexplore
parents:
diff changeset
58 <outputs>
7a6f2380fc1d planemo upload for repository https://forgemia.inra.fr/metexplore/met4j-galaxy
metexplore
parents:
diff changeset
59 <data format="tsv" name="outputFile"/>
7a6f2380fc1d planemo upload for repository https://forgemia.inra.fr/metexplore/met4j-galaxy
metexplore
parents:
diff changeset
60 </outputs>
7a6f2380fc1d planemo upload for repository https://forgemia.inra.fr/metexplore/met4j-galaxy
metexplore
parents:
diff changeset
61 <tests/>
7a6f2380fc1d planemo upload for repository https://forgemia.inra.fr/metexplore/met4j-galaxy
metexplore
parents:
diff changeset
62 <help><![CDATA[Metabolic models and Metabolomics Data often refer compounds only by using their common names, which vary greatly according to the source, thus impeding interoperability between models, databases and experimental data. This requires a tedious step of manual mapping. Fuzzy matching is a range of methods which can potentially helps fasten this process, by allowing the search for near-similar names. Fuzzy matching is primarily designed for common language search engines and is frequently based on edit distance, i.e. the number of edits to transform a character string into another, effectively managing typo, case and special character variations, and allowing auto-completion. However, edit-distance based search fall short when mapping chemical names: As an example, alpha-D-Glucose et Glucose would require more edits than between Fructose and Glucose.
11
40c15b7467f1 planemo upload for repository https://forgemia.inra.fr/metexplore/met4j-galaxy commit 61dbdbae896d18b519a470e056cb8b4f98394518
metexplore
parents: 10
diff changeset
63
6
7a6f2380fc1d planemo upload for repository https://forgemia.inra.fr/metexplore/met4j-galaxy
metexplore
parents:
diff changeset
64 This tool runs edit-distance based fuzzy matching to perform near-similar name matching between a metabolic model and a list of chemical names in a dataset. A harmonization processing is performed on chemical names with substitutions of common patterns among synonyms, in order to create aliases on which classical fuzzy matching can be run efficiently.]]></help>
7a6f2380fc1d planemo upload for repository https://forgemia.inra.fr/metexplore/met4j-galaxy
metexplore
parents:
diff changeset
65 <citations/>
7a6f2380fc1d planemo upload for repository https://forgemia.inra.fr/metexplore/met4j-galaxy
metexplore
parents:
diff changeset
66 </tool>