gecco: gecco.xml annotate

annotate gecco.xml @ 19:cc91d730cc4f draft

Fix syntax of Galaxy script for GECCO

author	althonos
date	Mon, 16 Jan 2023 18:35:56 +0000
parents	56b924f62165
children	64b724dd8d04

rev	line source
0 1625927fc16f "Release v0.8.4" althonos parents: diff changeset	1 <?xml version='1.0' encoding='utf-8'?>
19 cc91d730cc4f Fix syntax of Galaxy script for GECCO althonos parents: 14 diff changeset	2 <tool id="gecco" name="GECCO" version="0.9.6" 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>
19 cc91d730cc4f Fix syntax of Galaxy script for GECCO althonos parents: 14 diff changeset	4 <creator>
cc91d730cc4f Fix syntax of Galaxy script for GECCO althonos parents: 14 diff changeset	5 <organization name="Zeller Team" url="https://www.embl.org/groups/zeller/"/>
cc91d730cc4f Fix syntax of Galaxy script for GECCO althonos parents: 14 diff changeset	6 </creator>
cc91d730cc4f Fix syntax of Galaxy script for GECCO althonos parents: 14 diff changeset	7 <edam_topics>
cc91d730cc4f Fix syntax of Galaxy script for GECCO althonos parents: 14 diff changeset	8 <edam_topic>topic_0080</edam_topic>
cc91d730cc4f Fix syntax of Galaxy script for GECCO althonos parents: 14 diff changeset	9 </edam_topics>
cc91d730cc4f Fix syntax of Galaxy script for GECCO althonos parents: 14 diff changeset	10 <edam_operations>
cc91d730cc4f Fix syntax of Galaxy script for GECCO althonos parents: 14 diff changeset	11 <edam_operation>operation_0415</edam_operation>
cc91d730cc4f Fix syntax of Galaxy script for GECCO althonos parents: 14 diff changeset	12 </edam_operations>
0 1625927fc16f "Release v0.8.4" althonos parents: diff changeset	13 <requirements>
19 cc91d730cc4f Fix syntax of Galaxy script for GECCO althonos parents: 14 diff changeset	14 <requirement type="package" version="0.9.6">gecco</requirement>
0 1625927fc16f "Release v0.8.4" althonos parents: diff changeset	15 </requirements>
1625927fc16f "Release v0.8.4" althonos parents: diff changeset	16 <version_command>gecco --version</version_command>
1625927fc16f "Release v0.8.4" althonos parents: diff changeset	17 <command detect_errors="aggressive"><![CDATA[
1625927fc16f "Release v0.8.4" althonos parents: diff changeset	18
1625927fc16f "Release v0.8.4" althonos parents: diff changeset	19 #if str($input.ext) == 'genbank':
1625927fc16f "Release v0.8.4" althonos parents: diff changeset	20 #set $file_extension = 'gbk'
1625927fc16f "Release v0.8.4" althonos parents: diff changeset	21 #else:
1625927fc16f "Release v0.8.4" althonos parents: diff changeset	22 #set $file_extension = $input.ext
1625927fc16f "Release v0.8.4" althonos parents: diff changeset	23 #end if
1625927fc16f "Release v0.8.4" althonos parents: diff changeset	24 ln -s '$input' input_tempfile.$file_extension &&
1625927fc16f "Release v0.8.4" althonos parents: diff changeset	25
3 359232b58f6a "Update Galaxy tool wrapper to follow the IUC best practices" althonos parents: 0 diff changeset	26 gecco -vv run
359232b58f6a "Update Galaxy tool wrapper to follow the IUC best practices" althonos parents: 0 diff changeset	27 --format $input.ext
359232b58f6a "Update Galaxy tool wrapper to follow the IUC best practices" althonos parents: 0 diff changeset	28 --genome input_tempfile.$file_extension
359232b58f6a "Update Galaxy tool wrapper to follow the IUC best practices" althonos parents: 0 diff changeset	29 --postproc $postproc
14 56b924f62165 "Update tests files for Galaxy tool wrapper" althonos parents: 9 diff changeset	30 --force-tsv
56b924f62165 "Update tests files for Galaxy tool wrapper" althonos parents: 9 diff changeset	31 #if $edge_distance
56b924f62165 "Update tests files for Galaxy tool wrapper" althonos parents: 9 diff changeset	32 --edge-distance $edge_distance
56b924f62165 "Update tests files for Galaxy tool wrapper" althonos parents: 9 diff changeset	33 #end if
9 d64fe390f3c9 "Fix test files used in Galaxy test workflow" althonos parents: 4 diff changeset	34 #if $mask
d64fe390f3c9 "Fix test files used in Galaxy test workflow" althonos parents: 4 diff changeset	35 --mask
d64fe390f3c9 "Fix test files used in Galaxy test workflow" althonos parents: 4 diff changeset	36 #end if
3 359232b58f6a "Update Galaxy tool wrapper to follow the IUC best practices" althonos parents: 0 diff changeset	37 #if $cds:
359232b58f6a "Update Galaxy tool wrapper to follow the IUC best practices" althonos parents: 0 diff changeset	38 --cds $cds
359232b58f6a "Update Galaxy tool wrapper to follow the IUC best practices" althonos parents: 0 diff changeset	39 #end if
359232b58f6a "Update Galaxy tool wrapper to follow the IUC best practices" althonos parents: 0 diff changeset	40 #if $threshold:
359232b58f6a "Update Galaxy tool wrapper to follow the IUC best practices" althonos parents: 0 diff changeset	41 --threshold $threshold
359232b58f6a "Update Galaxy tool wrapper to follow the IUC best practices" althonos parents: 0 diff changeset	42 #end if
359232b58f6a "Update Galaxy tool wrapper to follow the IUC best practices" althonos parents: 0 diff changeset	43 #if $antismash_sideload:
359232b58f6a "Update Galaxy tool wrapper to follow the IUC best practices" althonos parents: 0 diff changeset	44 --antismash-sideload
359232b58f6a "Update Galaxy tool wrapper to follow the IUC best practices" althonos parents: 0 diff changeset	45 #end if
19 cc91d730cc4f Fix syntax of Galaxy script for GECCO althonos parents: 14 diff changeset	46 #unless $pad:
cc91d730cc4f Fix syntax of Galaxy script for GECCO althonos parents: 14 diff changeset	47 --no-pad
cc91d730cc4f Fix syntax of Galaxy script for GECCO althonos parents: 14 diff changeset	48 #end unless
3 359232b58f6a "Update Galaxy tool wrapper to follow the IUC best practices" althonos parents: 0 diff changeset	49
14 56b924f62165 "Update tests files for Galaxy tool wrapper" althonos parents: 9 diff changeset	50 && mv input_tempfile.genes.tsv '$genes'
3 359232b58f6a "Update Galaxy tool wrapper to follow the IUC best practices" althonos parents: 0 diff changeset	51 && mv input_tempfile.features.tsv '$features'
359232b58f6a "Update Galaxy tool wrapper to follow the IUC best practices" althonos parents: 0 diff changeset	52 && mv input_tempfile.clusters.tsv '$clusters'
359232b58f6a "Update Galaxy tool wrapper to follow the IUC best practices" althonos parents: 0 diff changeset	53 #if $antismash_sideload
359232b58f6a "Update Galaxy tool wrapper to follow the IUC best practices" althonos parents: 0 diff changeset	54 && mv input_tempfile.sideload.json '$sideload'
359232b58f6a "Update Galaxy tool wrapper to follow the IUC best practices" althonos parents: 0 diff changeset	55 #end if
0 1625927fc16f "Release v0.8.4" althonos parents: diff changeset	56
1625927fc16f "Release v0.8.4" althonos parents: diff changeset	57 ]]></command>
1625927fc16f "Release v0.8.4" althonos parents: diff changeset	58 <inputs>
3 359232b58f6a "Update Galaxy tool wrapper to follow the IUC best practices" althonos parents: 0 diff changeset	59 <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	60 <param argument="--mask" type="boolean" checked="false" label="Enable masking of regions with unknown nucleotides when finding ORFs"/>
19 cc91d730cc4f Fix syntax of Galaxy script for GECCO althonos parents: 14 diff changeset	61 <param argument="--pad" type="boolean" checked="true" label="Enable padding of gene sequences smaller than the CRF window length"/>
3 359232b58f6a "Update Galaxy tool wrapper to follow the IUC best practices" althonos parents: 0 diff changeset	62 <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	63 <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	64 <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	65 <option value="antismash">antiSMASH</option>
359232b58f6a "Update Galaxy tool wrapper to follow the IUC best practices" althonos parents: 0 diff changeset	66 <option value="gecco" selected="true">GECCO</option>
359232b58f6a "Update Galaxy tool wrapper to follow the IUC best practices" althonos parents: 0 diff changeset	67 </param>
14 56b924f62165 "Update tests files for Galaxy tool wrapper" althonos parents: 9 diff changeset	68 <param argument="--edge-distance" type="integer" min="0" optional="true" value="" 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	69 <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	70 </inputs>
1625927fc16f "Release v0.8.4" althonos parents: diff changeset	71 <outputs>
1625927fc16f "Release v0.8.4" althonos parents: diff changeset	72 <collection name="records" type="list" label="${tool.name} detected Biosynthetic Gene Clusters on ${on_string} (GenBank)">
1625927fc16f "Release v0.8.4" althonos parents: diff changeset	73 <discover_datasets pattern="(?P<designation>.*)\.gbk" ext="genbank" visible="false" />
1625927fc16f "Release v0.8.4" althonos parents: diff changeset	74 </collection>
14 56b924f62165 "Update tests files for Galaxy tool wrapper" althonos parents: 9 diff changeset	75 <data name="genes" format="tabular" label="${tool.name} summary of detected genes on ${on_string} (TSV)"/>
0 1625927fc16f "Release v0.8.4" althonos parents: diff changeset	76 <data name="features" format="tabular" label="${tool.name} summary of detected features on ${on_string} (TSV)"/>
1625927fc16f "Release v0.8.4" althonos parents: diff changeset	77 <data name="clusters" format="tabular" label="${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	78 <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	79 <filter>antismash_sideload</filter>
359232b58f6a "Update Galaxy tool wrapper to follow the IUC best practices" althonos parents: 0 diff changeset	80 </data>
0 1625927fc16f "Release v0.8.4" althonos parents: diff changeset	81 </outputs>
1625927fc16f "Release v0.8.4" althonos parents: diff changeset	82 <tests>
1625927fc16f "Release v0.8.4" althonos parents: diff changeset	83 <test>
1625927fc16f "Release v0.8.4" althonos parents: diff changeset	84 <param name="input" value="BGC0001866.fna"/>
1625927fc16f "Release v0.8.4" althonos parents: diff changeset	85 <output name="features" file="features.tsv"/>
14 56b924f62165 "Update tests files for Galaxy tool wrapper" althonos parents: 9 diff changeset	86 <output name="genes" file="genes.tsv"/>
0 1625927fc16f "Release v0.8.4" althonos parents: diff changeset	87 <output name="clusters" file="clusters.tsv"/>
19 cc91d730cc4f Fix syntax of Galaxy script for GECCO althonos parents: 14 diff changeset	88 <param name="edge_distance" value="10"/>
9 d64fe390f3c9 "Fix test files used in Galaxy test workflow" althonos parents: 4 diff changeset	89 </test>
d64fe390f3c9 "Fix test files used in Galaxy test workflow" althonos parents: 4 diff changeset	90 <test>
d64fe390f3c9 "Fix test files used in Galaxy test workflow" althonos parents: 4 diff changeset	91 <param name="input" value="BGC0001866.fna"/>
d64fe390f3c9 "Fix test files used in Galaxy test workflow" althonos parents: 4 diff changeset	92 <output name="features" file="features.tsv"/>
14 56b924f62165 "Update tests files for Galaxy tool wrapper" althonos parents: 9 diff changeset	93 <output name="genes" file="genes.tsv"/>
9 d64fe390f3c9 "Fix test files used in Galaxy test workflow" althonos parents: 4 diff changeset	94 <output name="clusters" file="clusters.tsv"/>
0 1625927fc16f "Release v0.8.4" althonos parents: diff changeset	95 <output_collection name="records" type="list">
4 88dc16b4f583 "Fix number of allowed different lines in `galaxy/gecco.xml` tests" althonos parents: 3 diff changeset	96 <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	97 </output_collection>
1625927fc16f "Release v0.8.4" althonos parents: diff changeset	98 </test>
3 359232b58f6a "Update Galaxy tool wrapper to follow the IUC best practices" althonos parents: 0 diff changeset	99 <test>
359232b58f6a "Update Galaxy tool wrapper to follow the IUC best practices" althonos parents: 0 diff changeset	100 <param name="input" value="BGC0001866.fna"/>
359232b58f6a "Update Galaxy tool wrapper to follow the IUC best practices" althonos parents: 0 diff changeset	101 <param name="antismash_sideload" value="True"/>
359232b58f6a "Update Galaxy tool wrapper to follow the IUC best practices" althonos parents: 0 diff changeset	102 <output name="features" file="features.tsv"/>
14 56b924f62165 "Update tests files for Galaxy tool wrapper" althonos parents: 9 diff changeset	103 <output name="genes" file="genes.tsv"/>
3 359232b58f6a "Update Galaxy tool wrapper to follow the IUC best practices" althonos parents: 0 diff changeset	104 <output name="clusters" file="clusters.tsv"/>
359232b58f6a "Update Galaxy tool wrapper to follow the IUC best practices" althonos parents: 0 diff changeset	105 <output name="sideload" file="sideload.json"/>
359232b58f6a "Update Galaxy tool wrapper to follow the IUC best practices" althonos parents: 0 diff changeset	106 <output_collection name="records" type="list">
4 88dc16b4f583 "Fix number of allowed different lines in `galaxy/gecco.xml` tests" althonos parents: 3 diff changeset	107 <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	108 </output_collection>
359232b58f6a "Update Galaxy tool wrapper to follow the IUC best practices" althonos parents: 0 diff changeset	109 </test>
0 1625927fc16f "Release v0.8.4" althonos parents: diff changeset	110 </tests>
3 359232b58f6a "Update Galaxy tool wrapper to follow the IUC best practices" althonos parents: 0 diff changeset	111 <help><![CDATA[
0 1625927fc16f "Release v0.8.4" althonos parents: diff changeset	112
3 359232b58f6a "Update Galaxy tool wrapper to follow the IUC best practices" althonos parents: 0 diff changeset	113 Overview
359232b58f6a "Update Galaxy tool wrapper to follow the IUC best practices" althonos parents: 0 diff changeset	114 --------
0 1625927fc16f "Release v0.8.4" althonos parents: diff changeset	115
3 359232b58f6a "Update Galaxy tool wrapper to follow the IUC best practices" althonos parents: 0 diff changeset	116 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	117 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	118
3 359232b58f6a "Update Galaxy tool wrapper to follow the IUC best practices" althonos parents: 0 diff changeset	119 Input
359232b58f6a "Update Galaxy tool wrapper to follow the IUC best practices" althonos parents: 0 diff changeset	120 -----
0 1625927fc16f "Release v0.8.4" althonos parents: diff changeset	121
1625927fc16f "Release v0.8.4" althonos parents: diff changeset	122 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	123
3 359232b58f6a "Update Galaxy tool wrapper to follow the IUC best practices" althonos parents: 0 diff changeset	124 Output
359232b58f6a "Update Galaxy tool wrapper to follow the IUC best practices" althonos parents: 0 diff changeset	125 ------
0 1625927fc16f "Release v0.8.4" althonos parents: diff changeset	126
1625927fc16f "Release v0.8.4" althonos parents: diff changeset	127 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	128
14 56b924f62165 "Update tests files for Galaxy tool wrapper" althonos parents: 9 diff changeset	129 - ``features.tsv``: The genes file, containing the genes identified in the input sequences.
56b924f62165 "Update tests files for Galaxy tool wrapper" althonos parents: 9 diff changeset	130 - ``features.tsv``: The features file, containing the protein domains identified in the input sequences.
56b924f62165 "Update tests files for Galaxy tool wrapper" althonos parents: 9 diff changeset	131 - ``clusters.tsv``: A clusters file, containing the coordinates of the predicted clusters, along their putative biosynthetic type.
3 359232b58f6a "Update Galaxy tool wrapper to follow the IUC best practices" althonos parents: 0 diff changeset	132 - ``{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	133
3 359232b58f6a "Update Galaxy tool wrapper to follow the IUC best practices" althonos parents: 0 diff changeset	134 Contact
359232b58f6a "Update Galaxy tool wrapper to follow the IUC best practices" althonos parents: 0 diff changeset	135 -------
0 1625927fc16f "Release v0.8.4" althonos parents: diff changeset	136
3 359232b58f6a "Update Galaxy tool wrapper to follow the IUC best practices" althonos parents: 0 diff changeset	137 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	138 `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	139 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	140
359232b58f6a "Update Galaxy tool wrapper to follow the IUC best practices" althonos parents: 0 diff changeset	141 ]]></help>
0 1625927fc16f "Release v0.8.4" althonos parents: diff changeset	142 <citations>
3 359232b58f6a "Update Galaxy tool wrapper to follow the IUC best practices" althonos parents: 0 diff changeset	143 <citation type="doi">10.1101/2021.05.03.442509</citation>
0 1625927fc16f "Release v0.8.4" althonos parents: diff changeset	144 </citations>
1625927fc16f "Release v0.8.4" althonos parents: diff changeset	145 </tool>

Mercurial > repos > althonos > gecco

annotate gecco.xml @ 19:cc91d730cc4f draft