annotate gecco.xml @ 12:e6597056a493 draft

"Release v0.9.1-alpha3"
author althonos
date Mon, 28 Mar 2022 15:41:47 +0000
parents d64fe390f3c9
children 56b924f62165
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
0
1625927fc16f "Release v0.8.4"
althonos
parents:
diff changeset
1 <?xml version='1.0' encoding='utf-8'?>
9
d64fe390f3c9 "Fix test files used in Galaxy test workflow"
althonos
parents: 4
diff changeset
2 <tool id="gecco" name="GECCO" version="0.8.10" python_template_version="3.5">
3
359232b58f6a "Update Galaxy tool wrapper to follow the IUC best practices"
althonos
parents: 0
diff changeset
3 <description>is a fast and scalable method for identifying putative novel Biosynthetic Gene Clusters (BGCs) in genomic and metagenomic data using Conditional Random Fields (CRFs).</description>
0
1625927fc16f "Release v0.8.4"
althonos
parents:
diff changeset
4 <requirements>
9
d64fe390f3c9 "Fix test files used in Galaxy test workflow"
althonos
parents: 4
diff changeset
5 <requirement type="package" version="0.8.10">gecco</requirement>
0
1625927fc16f "Release v0.8.4"
althonos
parents:
diff changeset
6 </requirements>
1625927fc16f "Release v0.8.4"
althonos
parents:
diff changeset
7 <version_command>gecco --version</version_command>
1625927fc16f "Release v0.8.4"
althonos
parents:
diff changeset
8 <command detect_errors="aggressive"><![CDATA[
1625927fc16f "Release v0.8.4"
althonos
parents:
diff changeset
9
1625927fc16f "Release v0.8.4"
althonos
parents:
diff changeset
10 #if str($input.ext) == 'genbank':
1625927fc16f "Release v0.8.4"
althonos
parents:
diff changeset
11 #set $file_extension = 'gbk'
1625927fc16f "Release v0.8.4"
althonos
parents:
diff changeset
12 #else:
1625927fc16f "Release v0.8.4"
althonos
parents:
diff changeset
13 #set $file_extension = $input.ext
1625927fc16f "Release v0.8.4"
althonos
parents:
diff changeset
14 #end if
1625927fc16f "Release v0.8.4"
althonos
parents:
diff changeset
15 ln -s '$input' input_tempfile.$file_extension &&
1625927fc16f "Release v0.8.4"
althonos
parents:
diff changeset
16
3
359232b58f6a "Update Galaxy tool wrapper to follow the IUC best practices"
althonos
parents: 0
diff changeset
17 gecco -vv run
359232b58f6a "Update Galaxy tool wrapper to follow the IUC best practices"
althonos
parents: 0
diff changeset
18 --format $input.ext
359232b58f6a "Update Galaxy tool wrapper to follow the IUC best practices"
althonos
parents: 0
diff changeset
19 --genome input_tempfile.$file_extension
359232b58f6a "Update Galaxy tool wrapper to follow the IUC best practices"
althonos
parents: 0
diff changeset
20 --postproc $postproc
9
d64fe390f3c9 "Fix test files used in Galaxy test workflow"
althonos
parents: 4
diff changeset
21 --edge-distance $edge_distance
3
359232b58f6a "Update Galaxy tool wrapper to follow the IUC best practices"
althonos
parents: 0
diff changeset
22 --force-clusters-tsv
9
d64fe390f3c9 "Fix test files used in Galaxy test workflow"
althonos
parents: 4
diff changeset
23 #if $mask
d64fe390f3c9 "Fix test files used in Galaxy test workflow"
althonos
parents: 4
diff changeset
24 --mask
d64fe390f3c9 "Fix test files used in Galaxy test workflow"
althonos
parents: 4
diff changeset
25 #end if
3
359232b58f6a "Update Galaxy tool wrapper to follow the IUC best practices"
althonos
parents: 0
diff changeset
26 #if $cds:
359232b58f6a "Update Galaxy tool wrapper to follow the IUC best practices"
althonos
parents: 0
diff changeset
27 --cds $cds
359232b58f6a "Update Galaxy tool wrapper to follow the IUC best practices"
althonos
parents: 0
diff changeset
28 #end if
359232b58f6a "Update Galaxy tool wrapper to follow the IUC best practices"
althonos
parents: 0
diff changeset
29 #if $threshold:
359232b58f6a "Update Galaxy tool wrapper to follow the IUC best practices"
althonos
parents: 0
diff changeset
30 --threshold $threshold
359232b58f6a "Update Galaxy tool wrapper to follow the IUC best practices"
althonos
parents: 0
diff changeset
31 #end if
359232b58f6a "Update Galaxy tool wrapper to follow the IUC best practices"
althonos
parents: 0
diff changeset
32 #if $antismash_sideload:
359232b58f6a "Update Galaxy tool wrapper to follow the IUC best practices"
althonos
parents: 0
diff changeset
33 --antismash-sideload
359232b58f6a "Update Galaxy tool wrapper to follow the IUC best practices"
althonos
parents: 0
diff changeset
34 #end if
359232b58f6a "Update Galaxy tool wrapper to follow the IUC best practices"
althonos
parents: 0
diff changeset
35
359232b58f6a "Update Galaxy tool wrapper to follow the IUC best practices"
althonos
parents: 0
diff changeset
36 && mv input_tempfile.features.tsv '$features'
359232b58f6a "Update Galaxy tool wrapper to follow the IUC best practices"
althonos
parents: 0
diff changeset
37 && mv input_tempfile.clusters.tsv '$clusters'
359232b58f6a "Update Galaxy tool wrapper to follow the IUC best practices"
althonos
parents: 0
diff changeset
38 #if $antismash_sideload
359232b58f6a "Update Galaxy tool wrapper to follow the IUC best practices"
althonos
parents: 0
diff changeset
39 && mv input_tempfile.sideload.json '$sideload'
359232b58f6a "Update Galaxy tool wrapper to follow the IUC best practices"
althonos
parents: 0
diff changeset
40 #end if
0
1625927fc16f "Release v0.8.4"
althonos
parents:
diff changeset
41
1625927fc16f "Release v0.8.4"
althonos
parents:
diff changeset
42 ]]></command>
1625927fc16f "Release v0.8.4"
althonos
parents:
diff changeset
43 <inputs>
3
359232b58f6a "Update Galaxy tool wrapper to follow the IUC best practices"
althonos
parents: 0
diff changeset
44 <param name="input" type="data" format="genbank,fasta,embl" label="Sequence file in GenBank, EMBL or FASTA format"/>
9
d64fe390f3c9 "Fix test files used in Galaxy test workflow"
althonos
parents: 4
diff changeset
45 <param argument="--mask" type="boolean" checked="false" label="Enable masking of regions with unknown nucleotides when finding ORFs"/>
3
359232b58f6a "Update Galaxy tool wrapper to follow the IUC best practices"
althonos
parents: 0
diff changeset
46 <param argument="--cds" type="integer" min="0" value="" optional="true" label="Minimum number of genes required for a cluster"/>
359232b58f6a "Update Galaxy tool wrapper to follow the IUC best practices"
althonos
parents: 0
diff changeset
47 <param argument="--threshold" type="float" min="0" max="1" value="" optional="true" label="Probability threshold for cluster detection"/>
359232b58f6a "Update Galaxy tool wrapper to follow the IUC best practices"
althonos
parents: 0
diff changeset
48 <param argument="--postproc" type="select" label="Post-processing method for gene cluster validation">
359232b58f6a "Update Galaxy tool wrapper to follow the IUC best practices"
althonos
parents: 0
diff changeset
49 <option value="antismash">antiSMASH</option>
359232b58f6a "Update Galaxy tool wrapper to follow the IUC best practices"
althonos
parents: 0
diff changeset
50 <option value="gecco" selected="true">GECCO</option>
359232b58f6a "Update Galaxy tool wrapper to follow the IUC best practices"
althonos
parents: 0
diff changeset
51 </param>
9
d64fe390f3c9 "Fix test files used in Galaxy test workflow"
althonos
parents: 4
diff changeset
52 <param argument="--edge-distance" type="integer" min="0" value="10" label="Number of genes from the contig edges to filter out"/>
3
359232b58f6a "Update Galaxy tool wrapper to follow the IUC best practices"
althonos
parents: 0
diff changeset
53 <param argument="--antismash-sideload" type="boolean" checked="false" label="Generate an antiSMASH v6 sideload JSON file"/>
0
1625927fc16f "Release v0.8.4"
althonos
parents:
diff changeset
54 </inputs>
1625927fc16f "Release v0.8.4"
althonos
parents:
diff changeset
55 <outputs>
1625927fc16f "Release v0.8.4"
althonos
parents:
diff changeset
56 <collection name="records" type="list" label="${tool.name} detected Biosynthetic Gene Clusters on ${on_string} (GenBank)">
1625927fc16f "Release v0.8.4"
althonos
parents:
diff changeset
57 <discover_datasets pattern="(?P&lt;designation&gt;.*)\.gbk" ext="genbank" visible="false" />
1625927fc16f "Release v0.8.4"
althonos
parents:
diff changeset
58 </collection>
1625927fc16f "Release v0.8.4"
althonos
parents:
diff changeset
59 <data name="features" format="tabular" label="${tool.name} summary of detected features on ${on_string} (TSV)"/>
1625927fc16f "Release v0.8.4"
althonos
parents:
diff changeset
60 <data name="clusters" format="tabular" label="${tool.name} summary of detected BGCs on ${on_string} (TSV)"/>
3
359232b58f6a "Update Galaxy tool wrapper to follow the IUC best practices"
althonos
parents: 0
diff changeset
61 <data name="sideload" format="json" label="antiSMASH v6 sideload file with ${tool.name} detected BGCs on ${on_string} (JSON)">
359232b58f6a "Update Galaxy tool wrapper to follow the IUC best practices"
althonos
parents: 0
diff changeset
62 <filter>antismash_sideload</filter>
359232b58f6a "Update Galaxy tool wrapper to follow the IUC best practices"
althonos
parents: 0
diff changeset
63 </data>
0
1625927fc16f "Release v0.8.4"
althonos
parents:
diff changeset
64 </outputs>
1625927fc16f "Release v0.8.4"
althonos
parents:
diff changeset
65 <tests>
1625927fc16f "Release v0.8.4"
althonos
parents:
diff changeset
66 <test>
1625927fc16f "Release v0.8.4"
althonos
parents:
diff changeset
67 <param name="input" value="BGC0001866.fna"/>
1625927fc16f "Release v0.8.4"
althonos
parents:
diff changeset
68 <output name="features" file="features.tsv"/>
1625927fc16f "Release v0.8.4"
althonos
parents:
diff changeset
69 <output name="clusters" file="clusters.tsv"/>
9
d64fe390f3c9 "Fix test files used in Galaxy test workflow"
althonos
parents: 4
diff changeset
70 </test>
d64fe390f3c9 "Fix test files used in Galaxy test workflow"
althonos
parents: 4
diff changeset
71 <test>
d64fe390f3c9 "Fix test files used in Galaxy test workflow"
althonos
parents: 4
diff changeset
72 <param name="input" value="BGC0001866.fna"/>
d64fe390f3c9 "Fix test files used in Galaxy test workflow"
althonos
parents: 4
diff changeset
73 <param name="edge_distance" value="0"/>
d64fe390f3c9 "Fix test files used in Galaxy test workflow"
althonos
parents: 4
diff changeset
74 <output name="features" file="features.tsv"/>
d64fe390f3c9 "Fix test files used in Galaxy test workflow"
althonos
parents: 4
diff changeset
75 <output name="clusters" file="clusters.tsv"/>
0
1625927fc16f "Release v0.8.4"
althonos
parents:
diff changeset
76 <output_collection name="records" type="list">
4
88dc16b4f583 "Fix number of allowed different lines in `galaxy/gecco.xml` tests"
althonos
parents: 3
diff changeset
77 <element name="BGC0001866.1_cluster_1" file="BGC0001866.1_cluster_1.gbk" ftype="genbank" compare="diff" lines_diff="4"/>
0
1625927fc16f "Release v0.8.4"
althonos
parents:
diff changeset
78 </output_collection>
1625927fc16f "Release v0.8.4"
althonos
parents:
diff changeset
79 </test>
3
359232b58f6a "Update Galaxy tool wrapper to follow the IUC best practices"
althonos
parents: 0
diff changeset
80 <test>
359232b58f6a "Update Galaxy tool wrapper to follow the IUC best practices"
althonos
parents: 0
diff changeset
81 <param name="input" value="BGC0001866.fna"/>
359232b58f6a "Update Galaxy tool wrapper to follow the IUC best practices"
althonos
parents: 0
diff changeset
82 <param name="antismash_sideload" value="True"/>
9
d64fe390f3c9 "Fix test files used in Galaxy test workflow"
althonos
parents: 4
diff changeset
83 <param name="edge_distance" value="0"/>
3
359232b58f6a "Update Galaxy tool wrapper to follow the IUC best practices"
althonos
parents: 0
diff changeset
84 <output name="features" file="features.tsv"/>
359232b58f6a "Update Galaxy tool wrapper to follow the IUC best practices"
althonos
parents: 0
diff changeset
85 <output name="clusters" file="clusters.tsv"/>
359232b58f6a "Update Galaxy tool wrapper to follow the IUC best practices"
althonos
parents: 0
diff changeset
86 <output name="sideload" file="sideload.json"/>
359232b58f6a "Update Galaxy tool wrapper to follow the IUC best practices"
althonos
parents: 0
diff changeset
87 <output_collection name="records" type="list">
4
88dc16b4f583 "Fix number of allowed different lines in `galaxy/gecco.xml` tests"
althonos
parents: 3
diff changeset
88 <element name="BGC0001866.1_cluster_1" file="BGC0001866.1_cluster_1.gbk" ftype="genbank" compare="diff" lines_diff="4"/>
3
359232b58f6a "Update Galaxy tool wrapper to follow the IUC best practices"
althonos
parents: 0
diff changeset
89 </output_collection>
359232b58f6a "Update Galaxy tool wrapper to follow the IUC best practices"
althonos
parents: 0
diff changeset
90 </test>
0
1625927fc16f "Release v0.8.4"
althonos
parents:
diff changeset
91 </tests>
3
359232b58f6a "Update Galaxy tool wrapper to follow the IUC best practices"
althonos
parents: 0
diff changeset
92 <help><![CDATA[
0
1625927fc16f "Release v0.8.4"
althonos
parents:
diff changeset
93
3
359232b58f6a "Update Galaxy tool wrapper to follow the IUC best practices"
althonos
parents: 0
diff changeset
94 Overview
359232b58f6a "Update Galaxy tool wrapper to follow the IUC best practices"
althonos
parents: 0
diff changeset
95 --------
0
1625927fc16f "Release v0.8.4"
althonos
parents:
diff changeset
96
3
359232b58f6a "Update Galaxy tool wrapper to follow the IUC best practices"
althonos
parents: 0
diff changeset
97 GECCO (Gene Cluster prediction with Conditional Random Fields) is a fast and scalable method for identifying putative novel Biosynthetic Gene Clusters (BGCs) in genomic and metagenomic data using Conditional Random Fields (CRFs).
0
1625927fc16f "Release v0.8.4"
althonos
parents:
diff changeset
98 It is developed in the Zeller group and is part of the suite of computational microbiome analysis tools hosted at EMBL.
1625927fc16f "Release v0.8.4"
althonos
parents:
diff changeset
99
3
359232b58f6a "Update Galaxy tool wrapper to follow the IUC best practices"
althonos
parents: 0
diff changeset
100 Input
359232b58f6a "Update Galaxy tool wrapper to follow the IUC best practices"
althonos
parents: 0
diff changeset
101 -----
0
1625927fc16f "Release v0.8.4"
althonos
parents:
diff changeset
102
1625927fc16f "Release v0.8.4"
althonos
parents:
diff changeset
103 GECCO works with DNA sequences, and loads them using Biopython, allowing it to support a large variety of formats, including the common FASTA and GenBank files.
1625927fc16f "Release v0.8.4"
althonos
parents:
diff changeset
104
3
359232b58f6a "Update Galaxy tool wrapper to follow the IUC best practices"
althonos
parents: 0
diff changeset
105 Output
359232b58f6a "Update Galaxy tool wrapper to follow the IUC best practices"
althonos
parents: 0
diff changeset
106 ------
0
1625927fc16f "Release v0.8.4"
althonos
parents:
diff changeset
107
1625927fc16f "Release v0.8.4"
althonos
parents:
diff changeset
108 GECCO will create the following files once done (using the same prefix as the input file):
1625927fc16f "Release v0.8.4"
althonos
parents:
diff changeset
109
3
359232b58f6a "Update Galaxy tool wrapper to follow the IUC best practices"
althonos
parents: 0
diff changeset
110 - ``features.tsv``: The features file, containing the identified proteins and domains in the input sequences.
359232b58f6a "Update Galaxy tool wrapper to follow the IUC best practices"
althonos
parents: 0
diff changeset
111 - ``clusters.tsv``: If any were found, a clusters file, containing the coordinates of the predicted clusters, along their putative biosynthetic type.
359232b58f6a "Update Galaxy tool wrapper to follow the IUC best practices"
althonos
parents: 0
diff changeset
112 - ``{sequence}_cluster_{N}.gbk``: If any BGCs were found, a GenBank file per cluster, containing the cluster sequence annotated with its member proteins and domains.
0
1625927fc16f "Release v0.8.4"
althonos
parents:
diff changeset
113
3
359232b58f6a "Update Galaxy tool wrapper to follow the IUC best practices"
althonos
parents: 0
diff changeset
114 Contact
359232b58f6a "Update Galaxy tool wrapper to follow the IUC best practices"
althonos
parents: 0
diff changeset
115 -------
0
1625927fc16f "Release v0.8.4"
althonos
parents:
diff changeset
116
3
359232b58f6a "Update Galaxy tool wrapper to follow the IUC best practices"
althonos
parents: 0
diff changeset
117 If you have any question about GECCO, if you run into any issue, or if you would like to make a feature request, please create an issue in the
359232b58f6a "Update Galaxy tool wrapper to follow the IUC best practices"
althonos
parents: 0
diff changeset
118 `GitHub repository <https://github.com/zellerlab/gecco>`_. You can also directly contact `Martin Larralde via email <mailto:martin.larralde@embl.de>`_.
359232b58f6a "Update Galaxy tool wrapper to follow the IUC best practices"
althonos
parents: 0
diff changeset
119 If you want to contribute to GECCO, please have a look at the contribution guide first, and feel free to open a pull request on the GitHub repository.
359232b58f6a "Update Galaxy tool wrapper to follow the IUC best practices"
althonos
parents: 0
diff changeset
120
359232b58f6a "Update Galaxy tool wrapper to follow the IUC best practices"
althonos
parents: 0
diff changeset
121 ]]></help>
0
1625927fc16f "Release v0.8.4"
althonos
parents:
diff changeset
122 <citations>
3
359232b58f6a "Update Galaxy tool wrapper to follow the IUC best practices"
althonos
parents: 0
diff changeset
123 <citation type="doi">10.1101/2021.05.03.442509</citation>
0
1625927fc16f "Release v0.8.4"
althonos
parents:
diff changeset
124 </citations>
1625927fc16f "Release v0.8.4"
althonos
parents:
diff changeset
125 </tool>