annotate gtdbtk_classify_wf.xml @ 0:a20cd9311046 draft

planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
author estrain
date Thu, 12 Mar 2026 20:07:08 +0000
parents
children 353347ef2386
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
0
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
1 <tool id="gtdbtk_classify_wf" name="GTDB-Tk Classify genomes" version="0.1.3" profile="24">
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
2 <description>by placement in GTDB reference tree</description>
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
3 <requirements>
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
4 <requirement type="package" version="2.5.2">gtdbtk</requirement>
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
5 </requirements>
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
6 <command detect_errors="exit_code"><![CDATA[
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
7 #import re
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
8
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
9 mkdir input_dir &&
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
10 mkdir output_dir &&
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
11 ## GTDBTK can process *.fna. and $.fna.gz but unzipping everying to simplify the workflow
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
12 #for $i in $input:
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
13 #set cleaned = re.sub(r'\.fna|\.fasta|\.fa|\.gz', '', $i.element_identifier)
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
14 #set final_name = cleaned + '.fna'
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
15 #if $i.ext in ['fasta.gz']:
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
16 gunzip -c '${i}' > input_dir/'${final_name}' &&
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
17 #else:
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
18 ln -s '${i}' input_dir/'${final_name}' &&
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
19 #end if
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
20 #end for
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
21 export GTDBTK_DATA_PATH=$gtdbtk_db.fields.path &&
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
22 gtdbtk classify_wf
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
23 --genome_dir input_dir
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
24 --out_dir output_dir
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
25 --mash_db $gtdbtk_db.fields.path
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
26 --cpus \${GALAXY_SLOTS:-4}
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
27
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
28 #if str($advanced.output_process_log) == 'yes':
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
29 && cat output_dir/gtdbtk.warnings.log output_dir/gtdbtk.log > '$process_log'
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
30 #end if
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
31 ]]></command>
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
32 <inputs>
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
33 <param name="input" type="data" format="fasta,fasta.gz" multiple="true" label="Fasta (Genome) files"/>
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
34 <param name="gtdbtk_db" type="select" label="GTDB-Tk database">
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
35 <options from_data_table="gtdbtk_database_versioned">
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
36 <validator type="no_options" message="No locally cached GTDB-Tk database is available"/>
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
37 </options>
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
38 </param>
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
39 <section name="advanced" title="Advanced options">
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
40 <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"/>
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
41 <param argument="--force" type="boolean" truevalue="--force" falsevalue="" checked="false" label="Continue processing if an error occurs on a single genome?"/>
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
42 <param argument="--min_af" type="float" min="0" max="1" value="0.65" label="Minimum alignment fraction to consider closest genome"/>
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
43 <param name="output_process_log" type="boolean" truevalue="yes" falsevalue="no" checked="false" label="Output process log file?"/>
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
44 </section>
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
45 </inputs>
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
46 <outputs>
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
47 <data name="process_log" format="txt" label="${tool.name} on ${on_string} (process log)">
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
48 <filter>advanced['output_process_log']</filter>
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
49 </data>
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
50 <collection name="output_align" type="list" format="fasta.gz" label="${tool.name} on ${on_string} (align)">
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
51 <discover_datasets pattern="(?P&lt;designation&gt;.+)\.fasta.gz" ext="fasta.gz" directory="output_dir/align"/>
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
52 </collection>
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
53 <collection name="output_identfy" type="list" format="tsv" label="${tool.name} on ${on_string} (identify)">
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
54 <discover_datasets pattern="(?P&lt;designation&gt;.+)\.tsv" ext="tsv" directory="output_dir/identify"/>
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
55 </collection>
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
56 <collection name="output_classify" type="list" format="newick" label="${tool.name} on ${on_string} (classify)">
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
57 <discover_datasets pattern="(?P&lt;designation&gt;.+)\.tree" ext="newick" directory="output_dir/classify"/>
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
58 </collection>
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
59 <collection name="output_summary" type="list" format="tsv" label="${tool.name} on ${on_string} (summary)">
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
60 <discover_datasets pattern="(?P&lt;designation&gt;.+)\.tsv" ext="tsv" directory="output_dir"/>
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
61 </collection>
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
62 </outputs>
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
63 <tests>
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
64 <!-- The commented test here is valid if we could store the GTDB-Tk database -->
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
65 <!--
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
66 <test expect_num_outputs="4">
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
67 <param name="input" value="genome_1.fna.gz" ftype="fasta.gz"/>
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
68 <param name="gtdbtk_db" value="gtdbtk214"/>
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
69 <output_collection name="output_summary" type="list" count="1">
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
70 <element name="gtdbtk.ar53.summary" ftype="tsv">
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
71 <assert_contents>
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
72 <has_text text="user_genome"/>
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
73 </assert_contents>
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
74 </element>
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
75 </output_collection>
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
76 <output_collection name="output_identfy" type="list" count="4">
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
77 <element name="gtdbtk.ar53.markers_summary" ftype="tsv">
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
78 <assert_contents>
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
79 <has_text text="number_unique_genes"/>
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
80 </assert_contents>
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
81 </element>
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
82 <element name="gtdbtk.bac120.markers_summary" ftype="tsv">
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
83 <assert_contents>
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
84 <has_text text="genome_1_fna_gz"/>
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
85 </assert_contents>
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
86 </element>
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
87 <element name="gtdbtk.failed_genomes" ftype="tsv">
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
88 <assert_contents>
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
89 <has_size value="0"/>
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
90 </assert_contents>
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
91 </element>
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
92 <element name="gtdbtk.translation_table_summary" ftype="tsv">
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
93 <assert_contents>
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
94 <has_text text="genome_1_fna_gz"/>
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
95 </assert_contents>
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
96 </element>
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
97 </output_collection>
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
98 <output_collection name="output_classify" type="list" count="1">
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
99 <element name="gtdbtk.ar53.classify" ftype="newick">
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
100 <assert_contents>
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
101 <has_text text="GB_GCA_"/>
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
102 </assert_contents>
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
103 </element>
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
104 </output_collection>
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
105 <output_collection name="output_align" type="list" count="2">
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
106 <element name="gtdbtk.ar53.msa" ftype="fasta.gz" decompress="true">
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
107 <assert_contents>
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
108 <has_text text="GB_GCA_000008085"/>
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
109 </assert_contents>
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
110 </element>
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
111 <element name="gtdbtk.ar53.user_msa" ftype="fasta.gz" decompress="true">
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
112 <assert_contents>
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
113 <has_text text="genome_1_fna_gz"/>
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
114 </assert_contents>
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
115 </element>
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
116 </output_collection>
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
117 </test>
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
118 -->
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
119 <!-- GTDB-Tk databases are far too large to test currently -->
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
120 <test expect_failure="true">
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
121 <param name="input" value="genome_1.fna.gz" ftype="fasta.gz"/>
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
122 <param name="gtdbtk_db" value="gtdbtk214"/>
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
123 <assert_stderr>
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
124 <has_text text="Fatal error: Exit code 1"/>
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
125 </assert_stderr>
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
126 </test>
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
127 </tests>
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
128 <help><![CDATA[
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
129 **What it does**
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
130
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
131 GTDB-Tk is a software toolkit for assigning objective taxonomic classifications to bacterial and archaeal genomes
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
132 based on the Genome Database Taxonomy GTDB. It is designed to work with recent advances that allow hundreds or
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
133 thousands of metagenome-assembled genomes (MAGs) to be obtained directly from environmental samples. It can also
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
134 be applied to isolate and single-cell genomes.
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
135
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
136 This tool accepts one or more fasta (genome) files and determines taxonomic classification of genomes by
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
137 maximum-likelihood (ML) placement. The classification workflow consists of three steps: identify, align, and
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
138 classify.
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
139
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
140 The identify step calls genes using Prodigal, and uses HMM models and the HMMER package to identify the 120 bacterial
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
141 and 122 archaeal marker genes used for phylogenetic inference. Multiple sequence alignments (MSA) are obtained by
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
142 aligning marker genes to their respective HMM model.
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
143
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
144 The align step concatenates the aligned marker genes and filters the concatenated MSA to approximately 5,000
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
145 amino acids.
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
146
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
147 Finally, the classify step uses pplacer to find the maximum-likelihood placement of each genome in the GTDB-Tk
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
148 reference tree. GTDB-Tk classifies each genome based on its placement in the reference tree, its relative evolutionary
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
149 divergence, and/or average nucleotide identity (ANI) to reference genomes.
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
150
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
151 Results can be impacted by a lack of marker genes or contamination.
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
152 ]]></help>
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
153 <expand macro="citations"/>
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
154 </tool>
a20cd9311046 planemo upload commit bdb45cf3a98e21f5002866b6789a1457f521bf5d
estrain
parents:
diff changeset
155