Skip to content

Gtdb-TK: add version 226 #7303

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 5 commits into from
Sep 29, 2025
Merged

Gtdb-TK: add version 226 #7303

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
e2889e1
gtdbtk: update DM for 226
bernt-matthias Sep 25, 2025
1850687
update gtdbtk tool to accept 226
bernt-matthias Sep 25, 2025
e334372
update test
bernt-matthias Sep 25, 2025
5f0fbe7
disable test that is timing out
bernt-matthias Sep 25, 2025
c64fee6
remove lint skip file
bernt-matthias Sep 25, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 0 additions & 1 deletion data_managers/data_manager_gtdbtk_database_installer/.lint_skip
View file
Open in desktop

This file was deleted.

5 changes: 5 additions & 0 deletions ...managers/data_manager_gtdbtk_database_installer/data_manager/gtdbtk_database_installer.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -33,6 +33,11 @@
"meta_ar": "https://data.gtdb.ecogenomic.org/releases/release220/220.0/ar53_metadata_r220.tsv.gz",
"meta_bac": "https://data.gtdb.ecogenomic.org/releases/release220/220.0/bac120_metadata_r220.tsv.gz",
},
"226": {
"full": "https://data.ace.uq.edu.au/public/gtdb/data/releases/release226/226.0/auxillary_files/gtdbtk_package/full_package/gtdbtk_r226_data.tar.gz",
"meta_ar": "https://data.ace.uq.edu.au/public/gtdb/data/releases/release226/226.0/ar53_metadata_r226.tsv.gz",
"meta_bac": "https://data.ace.uq.edu.au/public/gtdb/data/releases/release226/226.0/bac120_metadata_r226.tsv.gz",
},
}


Expand Down
10 changes: 6 additions & 4 deletions ...anagers/data_manager_gtdbtk_database_installer/data_manager/gtdbtk_database_installer.xml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,8 +1,8 @@
<tool id="gtdbtk_database_installer" name="GTDB-Tk Database Installer" tool_type="manage_data" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="@PROFILE@">
<description></description>
<macros>
<token name="@TOOL_VERSION@">202</token>
<token name="@VERSION_SUFFIX@">4</token>
<token name="@TOOL_VERSION@">226</token>
<token name="@VERSION_SUFFIX@">0</token>
<token name="@PROFILE@">20.09</token>
</macros>
<requirements>
Expand All @@ -25,6 +25,7 @@ python '$__tool_directory__/gtdbtk_database_installer.py'
<option value="207">207</option>
<option value="214">214</option>
<option value="220">220</option>
<option value="226">226</option>
</param>
</inputs>
<outputs>
Expand All @@ -43,8 +44,9 @@ python '$__tool_directory__/gtdbtk_database_installer.py'
</assert_contents>
</output>
</test>
<!-- Test meta data download with tsv.gz-->
<!-- to large .. takes to much time
<test>
<!-- Test meta data download with tsv.gz-->
<param name="release" value="220"/>
<param name="meta" value="true"/>
<output name="out_file">
Expand All @@ -53,7 +55,7 @@ python '$__tool_directory__/gtdbtk_database_installer.py'
<has_text text="metadata_tables_release_220_downloaded_"/>
</assert_contents>
</output>
</test>
</test> -->
<test>
<!-- Test meta data download with tar.gz -->
<param name="release" value="207"/>
Expand Down
39 changes: 21 additions & 18 deletions tools/gtdbtk/gtdbtk_classify_wf.xml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -23,11 +23,11 @@ gtdbtk classify_wf
--genome_dir input_dir
--extension '$ext'
--out_dir output_dir
--cpus \${GALAXY_SLOTS:-4}
--cpus "\${GALAXY_SLOTS:-4}"
--min_perc_aa $advanced.min_perc_aa
$advanced.force
--min_af $advanced.min_af

$full_tree
## Required unless mash_db is available:
--skip_ani_screen

Expand All @@ -39,14 +39,15 @@ $advanced.force
<param name="input" type="data" format="fasta,fasta.gz" multiple="true" label="Fasta (Genome) files"/>
<param name="gtdbtk_db" type="select" label="GTDB-Tk database" help="This version of GTDB-Tk requires GTDB version 220. Please contact your service administrator if this version is not available to select.">
<options from_data_table="gtdbtk_database_versioned">
<filter type="regexp" column="version" value="^220$"/>
<filter type="regexp" column="version" value="^22(0|6)$"/>
<validator type="no_options" message="No locally cached GTDB-Tk database is available"/>
</options>
</param>
<section name="advanced" title="Advanced options">
<param argument="--min_perc_aa" type="integer" min="0" max="100" value="10" label="Exclude genomes that do not have at least this percentage of AA in the MSA" help="Inclusive bound"/>
<param argument="--force" type="boolean" truevalue="--force" falsevalue="" checked="false" label="Continue processing if an error occurs on a single genome?"/>
<param argument="--min_af" type="float" min="0" max="1" value="0.65" label="Minimum alignment fraction to consider closest genome"/>
<param argument="--full_tree" type="boolean" truevalue="--full_tree" falsevalue="" checked="false" label="Use the full tree" help="Use the unsplit bacterial tree for the classify step; this is the original GTDB-Tk approach (version &lt; 2) and requires more than 320 GB of RAM to load the reference tree (default: False)"/>
<param name="output_process_log" type="boolean" truevalue="yes" falsevalue="no" checked="false" label="Output process log file?"/>
</section>
</inputs>
Expand All @@ -68,13 +69,15 @@ $advanced.force
</collection>
</outputs>
<tests>
<!-- The commented test here is valid if we could store the GTDB-Tk database -->
<!--
<test expect_num_outputs="4">
<param name="input" value="genome_1.fna.gz" ftype="fasta.gz"/>
<param name="gtdbtk_db" value="gtdbtk214"/>
<!-- Test works with mock DB https://data.ace.uq.edu.au/public/gtdb/data/releases/release226/226.0/auxillary_files/gtdbtk_package/mockup_db/ which is still a bit large -->
<!-- <test expect_num_outputs="4">
<param name="input" location="https://data.ace.uq.edu.au/public/gtdb/data/releases/release226/226.0/auxillary_files/gtdbtk_package/mockup_db/test_genome_G021783475.fna.gz" ftype="fasta.gz"/>
<param name="gtdbtk_db" value="gtdbtk226"/>
<section name="advanced">
<param name="full_tree" value="true"/>
</section>
<output_collection name="output_summary" type="list" count="1">
<element name="gtdbtk.ar53.summary" ftype="tsv">
<element name="gtdbtk.bac120.summary" ftype="tsv">
<assert_contents>
<has_text text="user_genome"/>
</assert_contents>
Expand All @@ -88,7 +91,7 @@ $advanced.force
</element>
<element name="gtdbtk.bac120.markers_summary" ftype="tsv">
<assert_contents>
<has_text text="genome_1_fna_gz"/>
<has_text text="test_genome_G021783475"/>
</assert_contents>
</element>
<element name="gtdbtk.failed_genomes" ftype="tsv">
Expand All @@ -98,31 +101,31 @@ $advanced.force
</element>
<element name="gtdbtk.translation_table_summary" ftype="tsv">
<assert_contents>
<has_text text="genome_1_fna_gz"/>
<has_text text="test_genome_G021783475"/>
</assert_contents>
</element>
</output_collection>
<output_collection name="output_classify" type="list" count="1">
<element name="gtdbtk.ar53.classify" ftype="newick">
<element name="gtdbtk.bac120.classify" ftype="newick">
<assert_contents>
<has_text text="GB_GCA_"/>
</assert_contents>
</element>
</output_collection>
<output_collection name="output_align" type="list" count="2">
<element name="gtdbtk.ar53.msa" ftype="fasta.gz" decompress="true">
<element name="gtdbtk.bac120.msa" ftype="fasta.gz" decompress="true">
<assert_contents>
<has_text text="GB_GCA_000008085"/>
<has_text text="GB_GCA_"/>
</assert_contents>
</element>
<element name="gtdbtk.ar53.user_msa" ftype="fasta.gz" decompress="true">
<element name="gtdbtk.bac120.user_msa" ftype="fasta.gz" decompress="true">
<assert_contents>
<has_text text="genome_1_fna_gz"/>
<has_text text="test_genome_G021783475"/>
</assert_contents>
</element>
</output_collection>
</test>
-->
</test> -->

<!-- GTDB-Tk databases are far too large to test currently -->
<test expect_failure="true">
<param name="input" value="genome_1.fna.gz" ftype="fasta.gz"/>
Expand Down
2 changes: 1 addition & 1 deletion tools/gtdbtk/macros.xml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
<macros>
<token name="@TOOL_VERSION@">2.5.2</token>
<token name="@VERSION_SUFFIX@">0</token>
<token name="@VERSION_SUFFIX@">1</token>
<token name="@PROFILE@">22.05</token>
<xml name="requirements">
<requirements>
Expand Down
3 changes: 2 additions & 1 deletion tools/gtdbtk/test-data/gtdbtk_database_versioned.loc.test
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -23,4 +23,5 @@
#drwxr-sr-x 4 gvk G-824019 4096 Apr 21 2021 pplacer/
#drwxr-sr-x 2 gvk G-824019 4096 Apr 20 2021 radii/
#drwxr-sr-x 2 gvk G-824019 4096 Apr 20 2021 taxonomy/
gtdbtk214 GTDB-Tk database 214 ${__HERE__}/gtdbtk214/
gtdbtk214 GTDB-Tk database 214 214 ${__HERE__}/gtdbtk214/
gtdbtk226 GTDB-Tk database 226 226 ${__HERE__}/226.0-data/