Mercurial > repos > althonos > gecco
annotate gecco.xml @ 4:88dc16b4f583 draft
"Fix number of allowed different lines in `galaxy/gecco.xml` tests"
author | althonos |
---|---|
date | Sat, 11 Dec 2021 23:31:48 +0000 |
parents | 359232b58f6a |
children | d64fe390f3c9 |
rev | line source |
---|---|
0 | 1 <?xml version='1.0' encoding='utf-8'?> |
3
359232b58f6a
"Update Galaxy tool wrapper to follow the IUC best practices"
althonos
parents:
0
diff
changeset
|
2 <tool id="gecco" name="GECCO" version="0.8.5" python_template_version="3.5"> |
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 | 4 <requirements> |
3
359232b58f6a
"Update Galaxy tool wrapper to follow the IUC best practices"
althonos
parents:
0
diff
changeset
|
5 <requirement type="package" version="0.8.5">gecco</requirement> |
0 | 6 </requirements> |
7 <version_command>gecco --version</version_command> | |
8 <command detect_errors="aggressive"><![CDATA[ | |
9 | |
10 #if str($input.ext) == 'genbank': | |
11 #set $file_extension = 'gbk' | |
12 #else: | |
13 #set $file_extension = $input.ext | |
14 #end if | |
15 ln -s '$input' input_tempfile.$file_extension && | |
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 |
359232b58f6a
"Update Galaxy tool wrapper to follow the IUC best practices"
althonos
parents:
0
diff
changeset
|
21 --force-clusters-tsv |
359232b58f6a
"Update Galaxy tool wrapper to follow the IUC best practices"
althonos
parents:
0
diff
changeset
|
22 #if $cds: |
359232b58f6a
"Update Galaxy tool wrapper to follow the IUC best practices"
althonos
parents:
0
diff
changeset
|
23 --cds $cds |
359232b58f6a
"Update Galaxy tool wrapper to follow the IUC best practices"
althonos
parents:
0
diff
changeset
|
24 #end if |
359232b58f6a
"Update Galaxy tool wrapper to follow the IUC best practices"
althonos
parents:
0
diff
changeset
|
25 #if $threshold: |
359232b58f6a
"Update Galaxy tool wrapper to follow the IUC best practices"
althonos
parents:
0
diff
changeset
|
26 --threshold $threshold |
359232b58f6a
"Update Galaxy tool wrapper to follow the IUC best practices"
althonos
parents:
0
diff
changeset
|
27 #end if |
359232b58f6a
"Update Galaxy tool wrapper to follow the IUC best practices"
althonos
parents:
0
diff
changeset
|
28 #if $antismash_sideload: |
359232b58f6a
"Update Galaxy tool wrapper to follow the IUC best practices"
althonos
parents:
0
diff
changeset
|
29 --antismash-sideload |
359232b58f6a
"Update Galaxy tool wrapper to follow the IUC best practices"
althonos
parents:
0
diff
changeset
|
30 #end if |
359232b58f6a
"Update Galaxy tool wrapper to follow the IUC best practices"
althonos
parents:
0
diff
changeset
|
31 |
359232b58f6a
"Update Galaxy tool wrapper to follow the IUC best practices"
althonos
parents:
0
diff
changeset
|
32 && mv input_tempfile.features.tsv '$features' |
359232b58f6a
"Update Galaxy tool wrapper to follow the IUC best practices"
althonos
parents:
0
diff
changeset
|
33 && mv input_tempfile.clusters.tsv '$clusters' |
359232b58f6a
"Update Galaxy tool wrapper to follow the IUC best practices"
althonos
parents:
0
diff
changeset
|
34 #if $antismash_sideload |
359232b58f6a
"Update Galaxy tool wrapper to follow the IUC best practices"
althonos
parents:
0
diff
changeset
|
35 && mv input_tempfile.sideload.json '$sideload' |
359232b58f6a
"Update Galaxy tool wrapper to follow the IUC best practices"
althonos
parents:
0
diff
changeset
|
36 #end if |
0 | 37 |
38 ]]></command> | |
39 <inputs> | |
3
359232b58f6a
"Update Galaxy tool wrapper to follow the IUC best practices"
althonos
parents:
0
diff
changeset
|
40 <param name="input" type="data" format="genbank,fasta,embl" label="Sequence file in GenBank, EMBL or FASTA format"/> |
359232b58f6a
"Update Galaxy tool wrapper to follow the IUC best practices"
althonos
parents:
0
diff
changeset
|
41 <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
|
42 <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
|
43 <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
|
44 <option value="antismash">antiSMASH</option> |
359232b58f6a
"Update Galaxy tool wrapper to follow the IUC best practices"
althonos
parents:
0
diff
changeset
|
45 <option value="gecco" selected="true">GECCO</option> |
359232b58f6a
"Update Galaxy tool wrapper to follow the IUC best practices"
althonos
parents:
0
diff
changeset
|
46 </param> |
359232b58f6a
"Update Galaxy tool wrapper to follow the IUC best practices"
althonos
parents:
0
diff
changeset
|
47 <param argument="--antismash-sideload" type="boolean" checked="false" label="Generate an antiSMASH v6 sideload JSON file"/> |
0 | 48 </inputs> |
49 <outputs> | |
50 <collection name="records" type="list" label="${tool.name} detected Biosynthetic Gene Clusters on ${on_string} (GenBank)"> | |
51 <discover_datasets pattern="(?P<designation>.*)\.gbk" ext="genbank" visible="false" /> | |
52 </collection> | |
53 <data name="features" format="tabular" label="${tool.name} summary of detected features on ${on_string} (TSV)"/> | |
54 <data name="clusters" format="tabular" label="${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
|
55 <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
|
56 <filter>antismash_sideload</filter> |
359232b58f6a
"Update Galaxy tool wrapper to follow the IUC best practices"
althonos
parents:
0
diff
changeset
|
57 </data> |
0 | 58 </outputs> |
59 <tests> | |
60 <test> | |
61 <param name="input" value="BGC0001866.fna"/> | |
62 <output name="features" file="features.tsv"/> | |
63 <output name="clusters" file="clusters.tsv"/> | |
64 <output_collection name="records" type="list"> | |
4
88dc16b4f583
"Fix number of allowed different lines in `galaxy/gecco.xml` tests"
althonos
parents:
3
diff
changeset
|
65 <element name="BGC0001866.1_cluster_1" file="BGC0001866.1_cluster_1.gbk" ftype="genbank" compare="diff" lines_diff="4"/> |
0 | 66 </output_collection> |
67 </test> | |
3
359232b58f6a
"Update Galaxy tool wrapper to follow the IUC best practices"
althonos
parents:
0
diff
changeset
|
68 <test> |
359232b58f6a
"Update Galaxy tool wrapper to follow the IUC best practices"
althonos
parents:
0
diff
changeset
|
69 <param name="input" value="BGC0001866.fna"/> |
359232b58f6a
"Update Galaxy tool wrapper to follow the IUC best practices"
althonos
parents:
0
diff
changeset
|
70 <param name="antismash_sideload" value="True"/> |
359232b58f6a
"Update Galaxy tool wrapper to follow the IUC best practices"
althonos
parents:
0
diff
changeset
|
71 <output name="features" file="features.tsv"/> |
359232b58f6a
"Update Galaxy tool wrapper to follow the IUC best practices"
althonos
parents:
0
diff
changeset
|
72 <output name="clusters" file="clusters.tsv"/> |
359232b58f6a
"Update Galaxy tool wrapper to follow the IUC best practices"
althonos
parents:
0
diff
changeset
|
73 <output name="sideload" file="sideload.json"/> |
359232b58f6a
"Update Galaxy tool wrapper to follow the IUC best practices"
althonos
parents:
0
diff
changeset
|
74 <output_collection name="records" type="list"> |
4
88dc16b4f583
"Fix number of allowed different lines in `galaxy/gecco.xml` tests"
althonos
parents:
3
diff
changeset
|
75 <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
|
76 </output_collection> |
359232b58f6a
"Update Galaxy tool wrapper to follow the IUC best practices"
althonos
parents:
0
diff
changeset
|
77 </test> |
0 | 78 </tests> |
3
359232b58f6a
"Update Galaxy tool wrapper to follow the IUC best practices"
althonos
parents:
0
diff
changeset
|
79 <help><![CDATA[ |
0 | 80 |
3
359232b58f6a
"Update Galaxy tool wrapper to follow the IUC best practices"
althonos
parents:
0
diff
changeset
|
81 Overview |
359232b58f6a
"Update Galaxy tool wrapper to follow the IUC best practices"
althonos
parents:
0
diff
changeset
|
82 -------- |
0 | 83 |
3
359232b58f6a
"Update Galaxy tool wrapper to follow the IUC best practices"
althonos
parents:
0
diff
changeset
|
84 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 | 85 It is developed in the Zeller group and is part of the suite of computational microbiome analysis tools hosted at EMBL. |
86 | |
3
359232b58f6a
"Update Galaxy tool wrapper to follow the IUC best practices"
althonos
parents:
0
diff
changeset
|
87 Input |
359232b58f6a
"Update Galaxy tool wrapper to follow the IUC best practices"
althonos
parents:
0
diff
changeset
|
88 ----- |
0 | 89 |
90 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. | |
91 | |
3
359232b58f6a
"Update Galaxy tool wrapper to follow the IUC best practices"
althonos
parents:
0
diff
changeset
|
92 Output |
359232b58f6a
"Update Galaxy tool wrapper to follow the IUC best practices"
althonos
parents:
0
diff
changeset
|
93 ------ |
0 | 94 |
95 GECCO will create the following files once done (using the same prefix as the input file): | |
96 | |
3
359232b58f6a
"Update Galaxy tool wrapper to follow the IUC best practices"
althonos
parents:
0
diff
changeset
|
97 - ``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
|
98 - ``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
|
99 - ``{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 | 100 |
3
359232b58f6a
"Update Galaxy tool wrapper to follow the IUC best practices"
althonos
parents:
0
diff
changeset
|
101 Contact |
359232b58f6a
"Update Galaxy tool wrapper to follow the IUC best practices"
althonos
parents:
0
diff
changeset
|
102 ------- |
0 | 103 |
3
359232b58f6a
"Update Galaxy tool wrapper to follow the IUC best practices"
althonos
parents:
0
diff
changeset
|
104 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
|
105 `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
|
106 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
|
107 |
359232b58f6a
"Update Galaxy tool wrapper to follow the IUC best practices"
althonos
parents:
0
diff
changeset
|
108 ]]></help> |
0 | 109 <citations> |
3
359232b58f6a
"Update Galaxy tool wrapper to follow the IUC best practices"
althonos
parents:
0
diff
changeset
|
110 <citation type="doi">10.1101/2021.05.03.442509</citation> |
0 | 111 </citations> |
112 </tool> |