udpate gtdbtk and make it run again

Author: bgruening

tools/gtdbtk/gtdbtk_classify_wf.xml

@@ -12,24 +12,35 @@
 
 mkdir input_dir &&
 mkdir output_dir &&
+mkdir scratch_dir &&
+mkdir tmp_dir &&
 #for $i in $input:
     ## gtdbtk uses the file extension to determine the input format.
-    #set ext = "." + $i.ext
-    #set input_identifier = re.sub('[^\w\-.]', '_', str($i.element_identifier)) + $ext
+    #set ext = $i.ext
+    #if $ext.endswith(".gz")
+        #set ext = "gz"
+    #end if
+    #set input_identifier = re.sub('[^\w\-.]', '_', str($i.element_identifier)) + "." + $ext
     ln -s '${i}' input_dir/'${input_identifier}' &&
 #end for
 export GTDBTK_DATA_PATH=$gtdbtk_db.fields.path &&
 gtdbtk classify_wf
 --genome_dir input_dir
 --extension '$ext'
 --out_dir output_dir
+--prefix gtdbtk
 --cpus "\${GALAXY_SLOTS:-4}"
+--tmpdir tmp_dir
+$advanced.place_species
 --min_perc_aa $advanced.min_perc_aa
+$advanced.genes
+--pplacer_cpus "\${GALAXY_SLOTS:-4}"
 $advanced.force
+--scratch_dir scratch_dir
+$advanced.write_single_copy_genes
+--keep_intermediates
 --min_af $advanced.min_af
-$full_tree
-## Required unless mash_db is available:
---skip_ani_screen
+$advanced.full_tree
 
 #if str($advanced.output_process_log) == 'yes':
     && cat output_dir/gtdbtk.warnings.log output_dir/gtdbtk.log > '$process_log'
@@ -44,16 +55,19 @@ $full_tree
             </options>
         </param>
         <section name="advanced" title="Advanced options">
+            <param argument="--place_species" type="boolean" truevalue="--place_species" falsevalue="" checked="false" label="Place species in pplacer trees even if they are classified with skani?"/>
             <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="--genes" type="boolean" truevalue="--genes" falsevalue="" checked="false" label="Input files contain predicted proteins as amino acids?" help="This skips gene calling, ANI screening, and ANI classification."/>
             <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="--write_single_copy_genes" type="boolean" truevalue="--write_single_copy_genes" falsevalue="" checked="false" label="Output unaligned single-copy marker genes?"/>
+            <param argument="--min_af" type="float" min="0" max="1" value="0.5" label="Minimum alignment fraction to assign genome to a species cluster"/>
             <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>
     <outputs>
         <data name="process_log" format="txt" label="${tool.name} on ${on_string} (process log)">
-            <filter>advanced['output_process_log']</filter>
+            <filter>advanced['output_process_log'] == 'yes'</filter>
         </data>
         <collection name="output_align" type="list" format="fasta.gz" label="${tool.name} on ${on_string} (align)">
             <discover_datasets pattern="(?P&lt;designation&gt;.+)\.fasta.gz" ext="fasta.gz" directory="output_dir/align"/>
@@ -130,6 +144,22 @@ $full_tree
         <test expect_failure="true">
             <param name="input" value="genome_1.fna.gz" ftype="fasta.gz"/>
             <param name="gtdbtk_db" value="gtdbtk214"/>
+            <section name="advanced">
+                <param name="place_species" value="true"/>
+                <param name="genes" value="true"/>
+                <param name="force" value="true"/>
+                <param name="write_single_copy_genes" value="true"/>
+            </section>
+            <assert_command>
+                <has_text text="--prefix gtdbtk"/>
+                <has_text text="--place_species"/>
+                <has_text text="--genes"/>
+                <has_text text="--pplacer_cpus"/>
+                <has_text text="--force"/>
+                <has_text text="--write_single_copy_genes"/>
+                <has_text text="--keep_intermediates"/>
+                <has_text text="--skip_ani_screen" negate="true"/>
+            </assert_command>
             <assert_stderr>
                 <has_text text="Fatal error: Exit code 1"/>
             </assert_stderr>
@@ -162,4 +192,3 @@ Results can be impacted by a lack of marker genes or contamination.
     ]]></help>
     <expand macro="citations"/>
 </tool>
-

tools/gtdbtk/macros.xml

@@ -1,7 +1,7 @@
 <macros>
-    <token name="@TOOL_VERSION@">2.7.1</token>
+    <token name="@TOOL_VERSION@">2.7.2</token>
     <token name="@VERSION_SUFFIX@">0</token>
-    <token name="@PROFILE@">22.05</token>
+    <token name="@PROFILE@">24.0</token>
     <xml name="requirements">
         <requirements>
             <requirement type="package" version="@TOOL_VERSION@">gtdbtk</requirement>