# HG changeset patch
# User estrain
# Date 1773346028 0
# Node ID a20cd931104652269b9739f7e480597b7c5a293c

planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d

diff -r 000000000000 -r a20cd9311046 gtdbtk_classify_wf.xml
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/gtdbtk_classify_wf.xml	Thu Mar 12 20:07:08 2026 +0000
@@ -0,0 +1,155 @@
+<tool id="gtdbtk_classify_wf" name="GTDB-Tk Classify genomes" version="0.1.3" profile="24">
+    <description>by placement in GTDB reference tree</description>
+        <requirements>
+            <requirement type="package" version="2.5.2">gtdbtk</requirement>
+        </requirements>
+    <command detect_errors="exit_code"><![CDATA[
+#import re
+
+mkdir input_dir &&
+mkdir output_dir &&
+## GTDBTK can process *.fna. and $.fna.gz but unzipping everying to simplify the workflow
+#for $i in $input:
+    #set cleaned = re.sub(r'\.fna|\.fasta|\.fa|\.gz', '', $i.element_identifier)
+    #set final_name = cleaned + '.fna'
+    #if $i.ext in ['fasta.gz']:
+        gunzip -c '${i}' > input_dir/'${final_name}' &&
+    #else:
+        ln -s '${i}' input_dir/'${final_name}' &&
+    #end if
+#end for
+export GTDBTK_DATA_PATH=$gtdbtk_db.fields.path &&
+gtdbtk classify_wf
+--genome_dir input_dir
+--out_dir output_dir
+--mash_db $gtdbtk_db.fields.path
+--cpus \${GALAXY_SLOTS:-4}
+
+#if str($advanced.output_process_log) == 'yes':
+    && cat output_dir/gtdbtk.warnings.log output_dir/gtdbtk.log > '$process_log'
+#end if
+    ]]></command>
+    <inputs>
+        <param name="input" type="data" format="fasta,fasta.gz" multiple="true" label="Fasta (Genome) files"/>
+        <param name="gtdbtk_db" type="select" label="GTDB-Tk database">
+            <options from_data_table="gtdbtk_database_versioned">
+                <validator type="no_options" message="No locally cached GTDB-Tk database is available"/>
+            </options>
+        </param>
+        <section name="advanced" title="Advanced options">
+            <param argument="--min_perc_aa" type="integer" min="0" max="100" value="10" label="Exclude genomes that do not have at least this percentage of AA in the MSA" help="Inclusive bound"/>
+            <param argument="--force" type="boolean" truevalue="--force" falsevalue="" checked="false" label="Continue processing if an error occurs on a single genome?"/>
+            <param argument="--min_af" type="float" min="0" max="1" value="0.65" label="Minimum alignment fraction to consider closest genome"/>
+            <param name="output_process_log" type="boolean" truevalue="yes" falsevalue="no" checked="false" label="Output process log file?"/>
+        </section>
+    </inputs>
+    <outputs>
+        <data name="process_log" format="txt" label="${tool.name} on ${on_string} (process log)">
+            <filter>advanced['output_process_log']</filter>
+        </data>
+        <collection name="output_align" type="list" format="fasta.gz" label="${tool.name} on ${on_string} (align)">
+            <discover_datasets pattern="(?P&lt;designation&gt;.+)\.fasta.gz" ext="fasta.gz" directory="output_dir/align"/>
+        </collection>
+        <collection name="output_identfy" type="list" format="tsv" label="${tool.name} on ${on_string} (identify)">
+            <discover_datasets pattern="(?P&lt;designation&gt;.+)\.tsv" ext="tsv" directory="output_dir/identify"/>
+        </collection>
+        <collection name="output_classify" type="list" format="newick" label="${tool.name} on ${on_string} (classify)">
+            <discover_datasets pattern="(?P&lt;designation&gt;.+)\.tree" ext="newick" directory="output_dir/classify"/>
+        </collection>
+        <collection name="output_summary" type="list" format="tsv" label="${tool.name} on ${on_string} (summary)">
+            <discover_datasets pattern="(?P&lt;designation&gt;.+)\.tsv" ext="tsv" directory="output_dir"/>
+        </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"/>
+            <output_collection name="output_summary" type="list" count="1">
+                <element name="gtdbtk.ar53.summary" ftype="tsv">
+                    <assert_contents>
+                        <has_text text="user_genome"/>
+                    </assert_contents>
+                </element>
+            </output_collection>
+            <output_collection name="output_identfy" type="list" count="4">
+                <element name="gtdbtk.ar53.markers_summary" ftype="tsv">
+                    <assert_contents>
+                        <has_text text="number_unique_genes"/>
+                    </assert_contents>
+                </element>
+                <element name="gtdbtk.bac120.markers_summary" ftype="tsv">
+                    <assert_contents>
+                        <has_text text="genome_1_fna_gz"/>
+                    </assert_contents>
+                </element>
+                <element name="gtdbtk.failed_genomes" ftype="tsv">
+                    <assert_contents>
+                        <has_size value="0"/>
+                    </assert_contents>
+                </element>
+                <element name="gtdbtk.translation_table_summary" ftype="tsv">
+                    <assert_contents>
+                        <has_text text="genome_1_fna_gz"/>
+                    </assert_contents>
+                </element>
+            </output_collection>
+            <output_collection name="output_classify" type="list" count="1">
+                <element name="gtdbtk.ar53.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">
+                    <assert_contents>
+                        <has_text text="GB_GCA_000008085"/>
+                    </assert_contents>
+                </element>
+                <element name="gtdbtk.ar53.user_msa" ftype="fasta.gz" decompress="true">
+                    <assert_contents>
+                        <has_text text="genome_1_fna_gz"/>
+                    </assert_contents>
+                </element>
+            </output_collection>
+        </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"/>
+            <param name="gtdbtk_db" value="gtdbtk214"/>
+            <assert_stderr>
+                <has_text text="Fatal error: Exit code 1"/>
+            </assert_stderr>
+        </test>
+    </tests>
+    <help><![CDATA[
+**What it does**
+
+GTDB-Tk is a software toolkit for assigning objective taxonomic classifications to bacterial and archaeal genomes
+based on the Genome Database Taxonomy GTDB. It is designed to work with recent advances that allow hundreds or
+thousands of metagenome-assembled genomes (MAGs) to be obtained directly from environmental samples. It can also
+be applied to isolate and single-cell genomes. 
+
+This tool accepts one or more fasta (genome) files and determines taxonomic classification of genomes by
+maximum-likelihood (ML) placement.  The classification workflow consists of three steps: identify, align, and
+classify.
+
+The identify step calls genes using Prodigal, and uses HMM models and the HMMER package to identify the 120 bacterial
+and 122 archaeal marker genes used for phylogenetic inference.  Multiple sequence alignments (MSA) are obtained by
+aligning marker genes to their respective HMM model.
+
+The align step concatenates the aligned marker genes and filters the concatenated MSA to approximately 5,000
+amino acids.
+
+Finally, the classify step uses pplacer to find the maximum-likelihood placement of each genome in the GTDB-Tk
+reference tree. GTDB-Tk classifies each genome based on its placement in the reference tree, its relative evolutionary
+divergence, and/or average nucleotide identity (ANI) to reference genomes.
+
+Results can be impacted by a lack of marker genes or contamination. 
+    ]]></help>
+    <expand macro="citations"/>
+</tool>
+