Greengenes2 2022.10 Support

CHANGELOG.md

@@ -7,6 +7,8 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ### `Added`
 
+- [#666](https://github.com/nf-core/ampliseq/pull/666) - Added Greengenes2 database, version 2022.10, support for QIIME2 taxonomic classification.
+
 ### `Changed`
 
 ### `Fixed`

bin/taxref_reformat_qiime_greengenes2022.sh

@@ -0,0 +1,9 @@
+#!/bin/sh
+
+# Decompress files.
+gzip -c -d 2022.10.seqs.fna.gz > 2022.10.seqs.fna
+gzip -c -d 2022.10.taxonomy.md5.tsv.gz > 2022.10.taxonomy.md5.tsv
+
+# Select and rename files
+mv *.fna greengenes2022.fna
+mv *.tsv greengenes2022.tax

conf/ref_databases.config

@@ -306,6 +306,12 @@ params {
             citation = "McDonald, D., Price, M., Goodrich, J. et al. An improved Greengenes taxonomy with explicit ranks for ecological and evolutionary analyses of bacteria and archaea. ISME J 6, 610–618 (2012). https://doi.org/10.1038/ismej.2011.139"
             fmtscript = "taxref_reformat_qiime_greengenes85.sh"
         }
+        'greengenes2022' {
+            title = "Greengenes2 16S - Version 2022.10"
+            file = [ "http://ftp.microbio.me/greengenes_release/2022.10/2022.10.seqs.fna.gz", "http://ftp.microbio.me/greengenes_release/2022.10/2022.10.taxonomy.md5.tsv.gz" ]
+            citation = "McDonald, D., Jiang, Y., Balaban, M. et al. Greengenes2 unifies microbial data in a single reference tree. Nat Biotechnol (2023). https://doi.org/10.1038/s41587-023-01845-1"
+            fmtscript = "taxref_reformat_qiime_greengenes2022.sh"
+        }
     }
     //Sintax taxonomic reference databases
     sintax_ref_databases {

docs/usage.md

@@ -225,6 +225,7 @@ Pre-configured reference taxonomy databases are:
 | sbdi-gtdb    | +     | -      | -       | -      | 16S rRNA                                      |
 | rdp          | +     | -      | +       | -      | 16S rRNA                                      |
 | greengenes   | -     | -      | +       | (+)¹   | 16S rRNA                                      |
+| greengenes2  | -     | -      | -       | +      | 16S rRNA                                      |
 | pr2          | +     | -      | -       | -      | 18S rRNA                                      |
 | unite-fungi  | +     | +      | -       | +      | eukaryotic nuclear ribosomal ITS region       |
 | unite-alleuk | +     | +      | -       | +      | eukaryotic nuclear ribosomal ITS region       |

nextflow_schema.json

@@ -429,7 +429,8 @@
                         "unite-alleuk=8.3",
                         "unite-alleuk=8.2",
                         "unite-alleuk",
-                        "greengenes85"
+                        "greengenes85",
+                        "greengenes2022"
                     ]
                 },
                 "classifier": {