Mercurial > repos > althonos > gecco

changeset 9:d64fe390f3c9 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
"Fix test files used in Galaxy test workflow"
author althonos
date Thu, 24 Feb 2022 16:35:48 +0000
parents cebc53d02da6
children 9156eb4ee20c
files CHANGELOG.md gecco.xml test-data/BGC0001866.1_cluster_1.gbk test-data/clusters.tsv test-data/sideload.json
diffstat 5 files changed, 27 insertions(+), 11 deletions(-) [+]
line wrap: on
line diff
--- a/CHANGELOG.md	Tue Feb 22 16:04:07 2022 +0000
+++ b/CHANGELOG.md	Thu Feb 24 16:35:48 2022 +0000
@@ -5,7 +5,12 @@
 and this project adheres to [Semantic Versioning](http://semver.org/spec/v2.0.0.html).
 
 ## [Unreleased]
-[Unreleased]: https://git.embl.de/grp-zeller/GECCO/compare/v0.8.9...master
+[Unreleased]: https://git.embl.de/grp-zeller/GECCO/compare/v0.8.10...master
+
+## [v0.8.10] - 2022-02-23
+[v0.8.10]: https://git.embl.de/grp-zeller/GECCO/compare/v0.8.9...v0.8.10
+### Fixed
+- `--antismash-sideload` flag of `gecco run` causing command to crash.
 
 ## [v0.8.9] - 2022-02-22
 [v0.8.9]: https://git.embl.de/grp-zeller/GECCO/compare/v0.8.8...v0.8.9
--- a/gecco.xml	Tue Feb 22 16:04:07 2022 +0000
+++ b/gecco.xml	Thu Feb 24 16:35:48 2022 +0000
@@ -1,8 +1,8 @@
 <?xml version='1.0' encoding='utf-8'?>
-<tool id="gecco" name="GECCO" version="0.8.5" python_template_version="3.5">
+<tool id="gecco" name="GECCO" version="0.8.10" python_template_version="3.5">
     <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>
     <requirements>
-        <requirement type="package" version="0.8.5">gecco</requirement>
+        <requirement type="package" version="0.8.10">gecco</requirement>
     </requirements>
     <version_command>gecco --version</version_command>
     <command detect_errors="aggressive"><![CDATA[
@@ -18,7 +18,11 @@
         --format $input.ext
         --genome input_tempfile.$file_extension
         --postproc $postproc
+        --edge-distance $edge_distance
         --force-clusters-tsv
+        #if $mask
+            --mask
+        #end if
         #if $cds:
             --cds $cds
         #end if
@@ -38,12 +42,14 @@
     ]]></command>
     <inputs>
         <param name="input" type="data" format="genbank,fasta,embl" label="Sequence file in GenBank, EMBL or FASTA format"/>
+        <param argument="--mask" type="boolean" checked="false" label="Enable masking of regions with unknown nucleotides when finding ORFs"/>
         <param argument="--cds" type="integer" min="0" value="" optional="true" label="Minimum number of genes required for a cluster"/>
         <param argument="--threshold" type="float" min="0" max="1" value="" optional="true" label="Probability threshold for cluster detection"/>
         <param argument="--postproc" type="select" label="Post-processing method for gene cluster validation">
             <option value="antismash">antiSMASH</option>
             <option value="gecco" selected="true">GECCO</option>
         </param>
+        <param argument="--edge-distance" type="integer" min="0" value="10" label="Number of genes from the contig edges to filter out"/>
         <param argument="--antismash-sideload" type="boolean" checked="false" label="Generate an antiSMASH v6 sideload JSON file"/>
     </inputs>
     <outputs>
@@ -61,6 +67,12 @@
             <param name="input" value="BGC0001866.fna"/>
             <output name="features" file="features.tsv"/>
             <output name="clusters" file="clusters.tsv"/>
+        </test>
+        <test>
+            <param name="input" value="BGC0001866.fna"/>
+            <param name="edge_distance" value="0"/>
+            <output name="features" file="features.tsv"/>
+            <output name="clusters" file="clusters.tsv"/>
             <output_collection name="records" type="list">
                 <element name="BGC0001866.1_cluster_1" file="BGC0001866.1_cluster_1.gbk" ftype="genbank" compare="diff" lines_diff="4"/>
             </output_collection>
@@ -68,6 +80,7 @@
         <test>
             <param name="input" value="BGC0001866.fna"/>
             <param name="antismash_sideload" value="True"/>
+            <param name="edge_distance" value="0"/>
             <output name="features" file="features.tsv"/>
             <output name="clusters" file="clusters.tsv"/>
             <output name="sideload" file="sideload.json"/>
--- a/test-data/BGC0001866.1_cluster_1.gbk	Tue Feb 22 16:04:07 2022 +0000
+++ b/test-data/BGC0001866.1_cluster_1.gbk	Thu Feb 24 16:35:48 2022 +0000
@@ -15,7 +15,7 @@
   JOURNAL   bioRxiv (2021.05.03.442509)
   REMARK    doi:10.1101/2021.05.03.442509
 COMMENT     ##GECCO-Data-START##
-            version                :: GECCO v0.8.5
+            version                :: GECCO v0.8.10
             creation_date          :: 2021-11-21T16:33:58.470847
             biosyn_class           :: Polyketide
             alkaloid_probability   :: 0.0
@@ -23,8 +23,7 @@
             ripp_probability       :: 0.0
             saccharide_probability :: 0.0
             terpene_probability    :: 0.0
-            nrp_probability        :: 0.14
-            other_probability      :: 0.0
+            nrp_probability        :: 0.09999999999999998
             ##GECCO-Data-END##
 FEATURES             Location/Qualifiers
      CDS             complement(1..1143)
--- a/test-data/clusters.tsv	Tue Feb 22 16:04:07 2022 +0000
+++ b/test-data/clusters.tsv	Thu Feb 24 16:35:48 2022 +0000
@@ -1,2 +1,2 @@
-sequence_id	bgc_id	start	end	average_p	max_p	type	alkaloid_probability	polyketide_probability	ripp_probability	saccharide_probability	terpene_probability	nrp_probability	other_probability	proteins	domains
-BGC0001866.1	BGC0001866.1_cluster_1	347	32979	0.9969495815733557	0.9999999447224028	Polyketide	0.0	0.98	0.0	0.0	0.0	0.14	0.0	BGC0001866.1_1;BGC0001866.1_2;BGC0001866.1_3;BGC0001866.1_4;BGC0001866.1_5;BGC0001866.1_6;BGC0001866.1_7;BGC0001866.1_8;BGC0001866.1_9;BGC0001866.1_10;BGC0001866.1_11;BGC0001866.1_12;BGC0001866.1_13;BGC0001866.1_14;BGC0001866.1_15;BGC0001866.1_16;BGC0001866.1_17;BGC0001866.1_18;BGC0001866.1_19;BGC0001866.1_20;BGC0001866.1_21;BGC0001866.1_22;BGC0001866.1_23	PF00106;PF00107;PF00109;PF00135;PF00394;PF00550;PF00698;PF00743;PF00891;PF00975;PF02801;PF06609;PF07690;PF07731;PF08241;PF08242;PF08493;PF08659;PF13434;PF13489;PF13649;PF13847;PF14765;PF16073;PF16197
+sequence_id	bgc_id	start	end	average_p	max_p	type	alkaloid_probability	polyketide_probability	ripp_probability	saccharide_probability	terpene_probability	nrp_probability	proteins	domains
+BGC0001866.1	BGC0001866.1_cluster_1	347	32979	0.9969495815733557	0.9999999447224028	Polyketide	0.0	0.98	0.0	0.0	0.0	0.09999999999999998	BGC0001866.1_1;BGC0001866.1_2;BGC0001866.1_3;BGC0001866.1_4;BGC0001866.1_5;BGC0001866.1_6;BGC0001866.1_7;BGC0001866.1_8;BGC0001866.1_9;BGC0001866.1_10;BGC0001866.1_11;BGC0001866.1_12;BGC0001866.1_13;BGC0001866.1_14;BGC0001866.1_15;BGC0001866.1_16;BGC0001866.1_17;BGC0001866.1_18;BGC0001866.1_19;BGC0001866.1_20;BGC0001866.1_21;BGC0001866.1_22;BGC0001866.1_23	PF00106;PF00107;PF00109;PF00135;PF00394;PF00550;PF00698;PF00743;PF00891;PF00975;PF02801;PF06609;PF07690;PF07731;PF08241;PF08242;PF08493;PF08659;PF13434;PF13489;PF13649;PF13847;PF14765;PF16073;PF16197
--- a/test-data/sideload.json	Tue Feb 22 16:04:07 2022 +0000
+++ b/test-data/sideload.json	Thu Feb 24 16:35:48 2022 +0000
@@ -8,8 +8,7 @@
                         "alkaloid_probability": "0.000",
                         "average_p": "0.997",
                         "max_p": "1.000",
-                        "nrp_probability": "0.140",
-                        "other_probability": "0.000",
+                        "nrp_probability": "0.100",
                         "polyketide_probability": "0.980",
                         "ripp_probability": "0.000",
                         "saccharide_probability": "0.000",
@@ -31,6 +30,6 @@
         },
         "description": "Biosynthetic Gene Cluster prediction with Conditional Random Fields.",
         "name": "GECCO",
-        "version": "0.8.5"
+        "version": "0.8.10"
     }
 }
\ No newline at end of file