Mercurial > repos > althonos > gecco
annotate gecco.xml @ 9:d64fe390f3c9 draft
"Fix test files used in Galaxy test workflow"
| author | althonos |
|---|---|
| date | Thu, 24 Feb 2022 16:35:48 +0000 |
| parents | 88dc16b4f583 |
| children | 56b924f62165 |
| rev | line source |
|---|---|
| 0 | 1 <?xml version='1.0' encoding='utf-8'?> |
| 9 | 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 | 4 <requirements> |
| 9 | 5 <requirement type="package" version="0.8.10">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 |
| 9 | 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 | 23 #if $mask |
| 24 --mask | |
| 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 | 41 |
| 42 ]]></command> | |
| 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 | 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 | 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 | 54 </inputs> |
| 55 <outputs> | |
| 56 <collection name="records" type="list" label="${tool.name} detected Biosynthetic Gene Clusters on ${on_string} (GenBank)"> | |
| 57 <discover_datasets pattern="(?P<designation>.*)\.gbk" ext="genbank" visible="false" /> | |
| 58 </collection> | |
| 59 <data name="features" format="tabular" label="${tool.name} summary of detected features on ${on_string} (TSV)"/> | |
| 60 <data name="clusters" format="tabular" label="${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 | 64 </outputs> |
| 65 <tests> | |
| 66 <test> | |
| 67 <param name="input" value="BGC0001866.fna"/> | |
| 68 <output name="features" file="features.tsv"/> | |
| 69 <output name="clusters" file="clusters.tsv"/> | |
| 9 | 70 </test> |
| 71 <test> | |
| 72 <param name="input" value="BGC0001866.fna"/> | |
| 73 <param name="edge_distance" value="0"/> | |
| 74 <output name="features" file="features.tsv"/> | |
| 75 <output name="clusters" file="clusters.tsv"/> | |
| 0 | 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 | 78 </output_collection> |
| 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 | 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 | 91 </tests> |
|
3
359232b58f6a
"Update Galaxy tool wrapper to follow the IUC best practices"
althonos
parents:
0
diff
changeset
|
92 <help><![CDATA[ |
| 0 | 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 | 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 | 98 It is developed in the Zeller group and is part of the suite of computational microbiome analysis tools hosted at EMBL. |
| 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 | 102 |
| 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. | |
| 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 | 107 |
| 108 GECCO will create the following files once done (using the same prefix as the input file): | |
| 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 | 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 | 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 | 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 | 124 </citations> |
| 125 </tool> |