Merge pull request #675 from erikrikarddaniel/add-zehr-nifh

Add Zehr nifH database
nf-core · Dec 12, 2023 · a1ad717 · a1ad717
2 parents 4e10651 + 09ae4b7
commit a1ad717
Show file tree

Hide file tree

Showing 6 changed files with 80 additions and 36 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -7,6 +7,9 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ### `Added`
 
+- [#674](https://github.com/nf-core/ampliseq/pull/674) - Add PhytoRef database for DADA2 taxonomy assignment using `--dada_ref_taxonomy phytoref`
+- [#675](https://github.com/nf-core/ampliseq/pull/675) - Add the Zehr lab nifH database for DADA2 taxonomy assignment using `--dada_ref_taxonomy zehr-nifh`
+
 ### `Changed`
 
 ### `Fixed`

diff --git a/bin/taxref_reformat_phytoref.sh b/bin/taxref_reformat_phytoref.sh
@@ -0,0 +1,7 @@
+#!/bin/sh
+
+# Write the assignTaxonomy() fasta file: assignTaxonomy.fna
+cat PhytoRef_with_taxonomy.fasta | sed '/>/s/>[^|]*|/>/' | sed '/>/s/|/;/g' > assignTaxonomy.fna
+
+# Write the addSpecies() fasta file: addSpecies.fna
+cat PhytoRef_with_taxonomy.fasta | sed '/^>/s/>\([^|]\+\)|.*|\([^|]\+\)/>\1 \2/' > addSpecies.fna
diff --git a/bin/taxref_reformat_zehr-nifh.sh b/bin/taxref_reformat_zehr-nifh.sh
@@ -0,0 +1,7 @@
+#!/bin/sh
+
+# Write the assignTaxonomy() fasta file: assignTaxonomy.fna
+cp *.fasta assignTaxonomy.fna
+
+# Write the addSpecies() fasta file: addSpecies.fna
+cut -d, -f 2,6,7 *.csv  | grep -v '^sequence,' | sed 's/\(.*\),[0-9]* \(.*\),\(.*\)/>\3 \2\n\1/' > addSpecies.fna
diff --git a/conf/ref_databases.config b/conf/ref_databases.config
@@ -25,22 +25,6 @@ params {
             fmtscript = "taxref_reformat_coidb.sh"
             dbversion = "COIDB 221216 (https://doi.org/10.17044/scilifelab.20514192.v2)"
         }
-        'midori2-co1' {
-            title = "MIDORI2 - CO1 Taxonomy Database - Release GB250"
-            file = [ "http://reference-midori.info/download/Databases/GenBank250/DADA2_sp/uniq/MIDORI2_UNIQ_NUC_SP_GB250_CO1_DADA2.fasta.gz" ]
-            citation = "Machida RJ, Leray M, Ho SL, Knowlton N. Metazoan mitochondrial gene sequence reference datasets for taxonomic assignment of environmental samples. Sci Data. 2017 Mar 14;4:170027. doi: 10.1038/sdata.2017.27. PMID: 28291235; PMCID: PMC5349245."
-            fmtscript = "taxref_reformat_midori2.sh"
-            dbversion = "MIDORI2-CO1 GB250 (http://reference-midori.info/download/Databases/GenBank250/DADA2_sp/uniq/MIDORI2_UNIQ_NUC_SP_GB250_CO1_DADA2.fasta.gz)"
-            taxlevels = "Phylum,Class,Order,Family,Genus,Species"
-        }
-        'midori2-co1=gb250' {
-            title = "MIDORI2 - CO1 Taxonomy Database - Release GB250"
-            file = [ "http://reference-midori.info/download/Databases/GenBank250/DADA2_sp/uniq/MIDORI2_UNIQ_NUC_SP_GB250_CO1_DADA2.fasta.gz" ]
-            citation = "Machida RJ, Leray M, Ho SL, Knowlton N. Metazoan mitochondrial gene sequence reference datasets for taxonomic assignment of environmental samples. Sci Data. 2017 Mar 14;4:170027. doi: 10.1038/sdata.2017.27. PMID: 28291235; PMCID: PMC5349245."
-            fmtscript = "taxref_reformat_midori2.sh"
-            dbversion = "MIDORI2-CO1 GB250 (http://reference-midori.info/download/Databases/GenBank250/DADA2_sp/uniq/MIDORI2_UNIQ_NUC_SP_GB250_CO1_DADA2.fasta.gz)"
-            taxlevels = "Phylum,Class,Order,Family,Genus,Species"
-        }
         'gtdb' {
             title = "GTDB - Genome Taxonomy Database - Release R08-RS214.1"
             file = [ "https://data.ace.uq.edu.au/public/gtdb/data/releases/release214/214.1/genomic_files_reps/bac120_ssu_reps_r214.tar.gz", "https://data.ace.uq.edu.au/public/gtdb/data/releases/release214/214.1/genomic_files_reps/ar53_ssu_reps_r214.tar.gz" ]
@@ -76,6 +60,30 @@ params {
             fmtscript = "taxref_reformat_gtdb.sh"
             dbversion = "GTDB R05-RS95 (https://data.ace.uq.edu.au/public/gtdb/data/releases/release95/95.0/)"
         }
+        'midori2-co1' {
+            title = "MIDORI2 - CO1 Taxonomy Database - Release GB250"
+            file = [ "http://reference-midori.info/download/Databases/GenBank250/DADA2_sp/uniq/MIDORI2_UNIQ_NUC_SP_GB250_CO1_DADA2.fasta.gz" ]
+            citation = "Machida RJ, Leray M, Ho SL, Knowlton N. Metazoan mitochondrial gene sequence reference datasets for taxonomic assignment of environmental samples. Sci Data. 2017 Mar 14;4:170027. doi: 10.1038/sdata.2017.27. PMID: 28291235; PMCID: PMC5349245."
+            fmtscript = "taxref_reformat_midori2.sh"
+            dbversion = "MIDORI2-CO1 GB250 (http://reference-midori.info/download/Databases/GenBank250/DADA2_sp/uniq/MIDORI2_UNIQ_NUC_SP_GB250_CO1_DADA2.fasta.gz)"
+            taxlevels = "Phylum,Class,Order,Family,Genus,Species"
+        }
+        'midori2-co1=gb250' {
+            title = "MIDORI2 - CO1 Taxonomy Database - Release GB250"
+            file = [ "http://reference-midori.info/download/Databases/GenBank250/DADA2_sp/uniq/MIDORI2_UNIQ_NUC_SP_GB250_CO1_DADA2.fasta.gz" ]
+            citation = "Machida RJ, Leray M, Ho SL, Knowlton N. Metazoan mitochondrial gene sequence reference datasets for taxonomic assignment of environmental samples. Sci Data. 2017 Mar 14;4:170027. doi: 10.1038/sdata.2017.27. PMID: 28291235; PMCID: PMC5349245."
+            fmtscript = "taxref_reformat_midori2.sh"
+            dbversion = "MIDORI2-CO1 GB250 (http://reference-midori.info/download/Databases/GenBank250/DADA2_sp/uniq/MIDORI2_UNIQ_NUC_SP_GB250_CO1_DADA2.fasta.gz)"
+            taxlevels = "Phylum,Class,Order,Family,Genus,Species"
+        }
+        'phytoref' {
+            title = "PhytoRef plastid 16S rRNA database for photosynthetic eukaryotes"
+            file = [ "http://phytoref.sb-roscoff.fr/static/downloads/PhytoRef_with_taxonomy.fasta" ]
+            citation = "Decelle, Johan, Sarah Romac, Rowena F. Stern, El Mahdi Bendif, Adriana Zingone, Stéphane Audic, Michael D. Guiry, et al. 2015. PhytoREF: A Reference Database of the Plastidial 16S rRNA Gene of Photosynthetic Eukaryotes with Curated Taxonomy. Molecular Ecology Resources 15 (6): 1435–45. https://doi.org/10.1111/1755-0998.12401."
+            fmtscript = "taxref_reformat_phytoref.sh"
+            dbversion = "unversioned"
+            taxlevels = "Domain,Supergroup,Subphylum,Class,Subclass,Order,Suborder,Family,Genus,Species"
+        }
         'pr2' {
             title = "PR2 - Protist Reference Ribosomal Database - Version 5.0.0"
             file = [ "https://github.com/pr2database/pr2database/releases/download/v5.0.0/pr2_version_5.0.0_SSU_dada2.fasta.gz", "https://github.com/pr2database/pr2database/releases/download/v5.0.0/pr2_version_5.0.0_SSU_UTAX.fasta.gz" ]
@@ -239,6 +247,22 @@ params {
             dbversion = "UNITE-alleuk v8.2 (https://doi.org/10.15156/BIO/786370)"
             shfile = [ "https://scilifelab.figshare.com/ndownloader/files/34994569", "https://scilifelab.figshare.com/ndownloader/files/34994572"]
         }
+        'zehr-nifh' {
+            title = "Zehr lab nifH database - version 2.5.0"
+            file = [ "https://raw.githubusercontent.com/moyn413/nifHdada2/master/nifH_dada2_v2.0.5.fasta", "https://raw.githubusercontent.com/moyn413/nifHdada2/master/nifH_dada2_phylum_v2.0.5.csv" ]
+            citation = "M. A. Moynihan & C. Furbo Reeder 2023. nifHdada2 GitHub repository, v2.0.5. Zenodo. http://doi.org/10.5281/zenodo.7996213"
+            fmtscript = "taxref_reformat_zehr-nifh.sh"
+            dbversion = "Zehr-nifH v. 2.5.0"
+            taxlevels = "Domain,Phylum,Class,Order,Family,Genus"
+        }
+        'zehr-nifh=2.5.0' {
+            title = "Zehr lab nifH database - version 2.5.0"
+            file = [ "https://raw.githubusercontent.com/moyn413/nifHdada2/master/nifH_dada2_v2.0.5.fasta", "https://raw.githubusercontent.com/moyn413/nifHdada2/master/nifH_dada2_phylum_v2.0.5.csv" ]
+            citation = "M. A. Moynihan & C. Furbo Reeder 2023. nifHdada2 GitHub repository, v2.0.5. Zenodo. http://doi.org/10.5281/zenodo.7996213"
+            fmtscript = "taxref_reformat_zehr-nifh.sh"
+            dbversion = "Zehr-nifH v. 2.5.0"
+            taxlevels = "Domain,Phylum,Class,Order,Family,Genus"
+        }
     }
     //QIIME2 taxonomic reference databases
     qiime_ref_databases {

diff --git a/docs/output.md b/docs/output.md
@@ -140,7 +140,7 @@ DADA2 reduces sequence errors and dereplicates sequences by quality filtering, d
   - `ASV_table.tsv`: Counts for each ASV sequence.
   - `DADA2_stats.tsv`: Tracking read numbers through DADA2 processing steps, for each sample.
   - `DADA2_table.rds`: DADA2 ASV table as R object.
-  - `DADA2_tables.tsv`: DADA2 ASV table.
+  - `DADA2_table.tsv`: DADA2 ASV table.
 - `dada2/args/`: Directory containing files with all parameters for DADA2 steps.
 - `dada2/log/`: Directory containing log files for DADA2 steps.
 - `dada2/QC/`

diff --git a/nextflow_schema.json b/nextflow_schema.json
@@ -335,36 +335,39 @@
                     "description": "Name of supported database, and optionally also version number",
                     "default": "silva=138",
                     "enum": [
-                        "midori2-co1=gb250",
-                        "midori2-co1",
+                        "coidb",
+                        "coidb=221216",
+                        "gtdb",
                         "gtdb=R05-RS95",
                         "gtdb=R06-RS202",
                         "gtdb=R07-RS207",
                         "gtdb=R08-RS214",
-                        "gtdb",
-                        "coidb",
-                        "coidb=221216",
-                        "pr2=5.0.0",
-                        "pr2=4.14.0",
-                        "pr2=4.13.0",
+                        "midori2-co1",
+                        "midori2-co1=gb250",
+                        "phytoref",
                         "pr2",
-                        "rdp=18",
+                        "pr2=4.13.0",
+                        "pr2=4.14.0",
+                        "pr2=5.0.0",
                         "rdp",
+                        "rdp=18",
                         "sbdi-gtdb",
-                        "sbdi-gtdb=R07-RS207-1",
-                        "sbdi-gtdb=R06-RS202-3",
                         "sbdi-gtdb=R06-RS202-1",
+                        "sbdi-gtdb=R06-RS202-3",
+                        "sbdi-gtdb=R07-RS207-1",
+                        "silva",
                         "silva=132",
                         "silva=138",
-                        "silva",
-                        "unite-fungi=9.0",
-                        "unite-fungi=8.3",
-                        "unite-fungi=8.2",
-                        "unite-fungi",
-                        "unite-alleuk=9.0",
-                        "unite-alleuk=8.3",
+                        "unite-alleuk",
                         "unite-alleuk=8.2",
-                        "unite-alleuk"
+                        "unite-alleuk=8.3",
+                        "unite-alleuk=9.0",
+                        "unite-fungi",
+                        "unite-fungi=8.2",
+                        "unite-fungi=8.3",
+                        "unite-fungi=9.0",
+                        "zehr-nifh",
+                        "zehr-nifh=2.5.0"
                     ]
                 },
                 "dada_ref_tax_custom": {