Add centrifuge build

CITATIONS.md

@@ -40,6 +40,10 @@
 
   > Kurtzer GM, Sochat V, Bauer MW. Singularity: Scientific containers for mobility of compute. PLoS One. 2017 May 11;12(5):e0177459. doi: 10.1371/journal.pone.0177459. eCollection 2017. PubMed PMID: 28494014; PubMed Central PMCID: PMC5426675.
 
+- [Centrifuge](https://doi.org/10.1101/gr.210641.116)
+
+  > Kim, D., Song, L., Breitwieser, F. P., & Salzberg, S. L. (2016). Centrifuge: rapid and sensitive classification of metagenomic sequences. Genome Research, 26(12), 1721–1729. https://doi.org/10.1101/gr.210641.116
+
 - [DIAMOND](https://doi.org/10.1038/nmeth.3176)
 
   > Buchfink, B., Xie, C., & Huson, D. H. (2015). Fast and sensitive protein alignment using DIAMOND. Nature Methods, 12(1), 59–60. https://doi.org/10.1038/nmeth.3176

README.md

@@ -35,7 +35,8 @@
 -->
 
 1. Prepares input FASTA files for building
-2. Build's databases for:
+2. Builds databases for:
+   - [Centrifuge](https://doi.org/10.1101/gr.210641.116)
    - [DIAMOND](https://doi.org/10.1038/nmeth.3176)
    - [Kaiju](https://doi.org/10.1038/ncomms11257)
    - [MALT](https://doi.org/10.1038/s41559-017-0446-6)

conf/modules.config

@@ -37,10 +37,22 @@ process {
 
     withName: 'CAT_CAT_DNA' {
         ext.prefix = { "${meta.id}.fna" }
+        publishDir = [
+            path: { "${params.outdir}/cat" },
+            mode: params.publish_dir_mode,
+            saveAs: { filename -> filename.equals('versions.yml') ? null : filename },
+            enabled: params.save_concatenated_fastas
+        ]
     }
 
     withName: 'CAT_CAT_AA' {
         ext.prefix = { "${meta.id}.faa" }
+        publishDir = [
+            path: { "${params.outdir}/cat" },
+            mode: params.publish_dir_mode,
+            saveAs: { filename -> filename.equals('versions.yml') ? null : filename },
+            enabled: params.save_concatenated_fastas
+        ]
     }
 
     withName: 'MALT_BUILD' {

conf/test.config

@@ -23,12 +23,13 @@ params {
 
     input         = 'https://raw.githubusercontent.com/nf-core/test-datasets/createtaxdb/samplesheets/test.csv'
 
-    build_diamond = true
-    build_kaiju   = true
-    build_malt    = true
-
-    prot2taxid    = 'https://raw.githubusercontent.com/nf-core/test-datasets/createtaxdb/data/taxonomy/prot.accession2taxid.gz'
-    nodesdmp      = 'https://raw.githubusercontent.com/nf-core/test-datasets/createtaxdb/data/taxonomy/prot_nodes.dmp'
-    namesdmp      = 'https://raw.githubusercontent.com/nf-core/test-datasets/createtaxdb/data/taxonomy/prot_names.dmp'
-    malt_mapdb    = 's3://ngi-igenomes/test-data/createtaxdb/taxonomy/megan-nucl-Feb2022.db.zip'
+    build_diamond    = true
+    build_kaiju      = true
+    build_malt       = true
+    build_centrifuge = true
+
+    prot2taxid       = 'https://raw.githubusercontent.com/nf-core/test-datasets/createtaxdb/data/taxonomy/prot.accession2taxid.gz'
+    nodesdmp         = 'https://raw.githubusercontent.com/nf-core/test-datasets/createtaxdb/data/taxonomy/prot_nodes.dmp'
+    namesdmp         = 'https://raw.githubusercontent.com/nf-core/test-datasets/createtaxdb/data/taxonomy/prot_names.dmp'
+    malt_mapdb       = 's3://ngi-igenomes/test-data/createtaxdb/taxonomy/megan-nucl-Feb2022.db.zip'
 }

conf/test_nothing.config

@@ -23,12 +23,13 @@ params {
 
     input         = 'https://raw.githubusercontent.com/nf-core/test-datasets/createtaxdb/samplesheets/test.csv'
 
-    build_diamond = false
-    build_kaiju   = false
-    build_malt    = false
-
-    prot2taxid    = 'https://raw.githubusercontent.com/nf-core/test-datasets/createtaxdb/data/taxonomy/prot.accession2taxid.gz'
-    nodesdmp      = 'https://raw.githubusercontent.com/nf-core/test-datasets/createtaxdb/data/taxonomy/prot_nodes.dmp'
-    namesdmp      = 'https://raw.githubusercontent.com/nf-core/test-datasets/createtaxdb/data/taxonomy/prot_names.dmp'
-    malt_mapdb    = 's3://ngi-igenomes/test-data/createtaxdb/taxonomy/megan-nucl-Feb2022.db.zip'
+    build_diamond    = true
+    build_kaiju      = true
+    build_malt       = true
+    build_centrifuge = true
+
+    prot2taxid       = 'https://raw.githubusercontent.com/nf-core/test-datasets/createtaxdb/data/taxonomy/prot.accession2taxid.gz'
+    nodesdmp         = 'https://raw.githubusercontent.com/nf-core/test-datasets/createtaxdb/data/taxonomy/prot_nodes.dmp'
+    namesdmp         = 'https://raw.githubusercontent.com/nf-core/test-datasets/createtaxdb/data/taxonomy/prot_names.dmp'
+    malt_mapdb       = 's3://ngi-igenomes/test-data/createtaxdb/taxonomy/megan-nucl-Feb2022.db.zip'
 }

lib/WorkflowCreatetaxdb.groovy

@@ -58,9 +58,10 @@ class WorkflowCreatetaxdb {
         // Uncomment function in methodsDescriptionText to render in MultiQC report
         def citation_text = [
                 "Tools used in the workflow included:",
-                params.build_diamond ? "DIAMOND (Buchfink et al. 2015)," : "",
-                params.build_kaiju   ? "Kaiju (Menzel et al. 2016)," : "",
-                params.build_malt    ? "MALT (Vågene et al. 2018)," : "",
+                params.build_centrifuge ? "Centrifuge (Kim et al. 2016)," : "",
+                params.build_diamond    ? "DIAMOND (Buchfink et al. 2015)," : "",
+                params.build_kaiju      ? "Kaiju (Menzel et al. 2016)," : "",
+                params.build_malt       ? "MALT (Vågene et al. 2018)," : "",
                 "and MultiQC (Ewels et al. 2016)",
                 "."
             ].join(' ').trim()
@@ -73,9 +74,10 @@ class WorkflowCreatetaxdb {
         // Can use ternary operators to dynamically construct based conditions, e.g. params["run_xyz"] ? "<li>Author (2023) Pub name, Journal, DOI</li>" : "",
         // Uncomment function in methodsDescriptionText to render in MultiQC report
         def reference_text = [
-                params.build_diamond ? "<li>Buchfink, B., Xie, C., & Huson, D. H. (2015). Fast and sensitive protein alignment using DIAMOND. Nature Methods, 12(1), 59–60. <a href=\"https://doi.org/10.1038/nmeth.3176\">10.1038/nmeth.3176</a></li>" : "",
-                params.build_kaiju   ? "<li>Menzel, P., Ng, K. L., & Krogh, A. (2016). Fast and sensitive taxonomic classification for metagenomics with Kaiju. Nature Communications, 7, 11257. <a href=\"https://doi.org/10.1038/ncomms11257\">10.1038/ncomms11257</a></li>" : "",
-                params.build_malt    ? "<li>Vågene, Å. J., Herbig, A., Campana, M. G., Robles García, N. M., Warinner, C., Sabin, S., Spyrou, M. A., Andrades Valtueña, A., Huson, D., Tuross, N., Bos, K. I., & Krause, J. (2018). Salmonella enterica genomes from victims of a major sixteenth-century epidemic in Mexico. Nature Ecology & Evolution, 2(3), 520–528.  <a href=\"https://doi.org/10.1038/s41559-017-0446-6\">10.1038/s41559-017-0446-6</a></li>" : "",                "<li>Ewels, P., Magnusson, M., Lundin, S., & Käller, M. (2016). MultiQC: summarize analysis results for multiple tools and samples in a single report. Bioinformatics , 32(19), 3047–3048. doi: /10.1093/bioinformatics/btw354</li>"
+                params.build_centrifuge ? "<li>Kim, D., Song, L., Breitwieser, F. P., & Salzberg, S. L. (2016). Centrifuge: rapid and sensitive classification of metagenomic sequences. Genome Research, 26(12), 1721–1729.  <a href=\"https://doi.org/10.1101/gr.210641.116\">10.1101/gr.210641.116</a></li>" : "",
+                params.build_diamond    ? "<li>Buchfink, B., Xie, C., & Huson, D. H. (2015). Fast and sensitive protein alignment using DIAMOND. Nature Methods, 12(1), 59–60. <a href=\"https://doi.org/10.1038/nmeth.3176\">10.1038/nmeth.3176</a></li>" : "",
+                params.build_kaiju      ? "<li>Menzel, P., Ng, K. L., & Krogh, A. (2016). Fast and sensitive taxonomic classification for metagenomics with Kaiju. Nature Communications, 7, 11257. <a href=\"https://doi.org/10.1038/ncomms11257\">10.1038/ncomms11257</a></li>" : "",
+                params.build_malt       ? "<li>Vågene, Å. J., Herbig, A., Campana, M. G., Robles García, N. M., Warinner, C., Sabin, S., Spyrou, M. A., Andrades Valtueña, A., Huson, D., Tuross, N., Bos, K. I., & Krause, J. (2018). Salmonella enterica genomes from victims of a major sixteenth-century epidemic in Mexico. Nature Ecology & Evolution, 2(3), 520–528.  <a href=\"https://doi.org/10.1038/s41559-017-0446-6\">10.1038/s41559-017-0446-6</a></li>" : "",                "<li>Ewels, P., Magnusson, M., Lundin, S., & Käller, M. (2016). MultiQC: summarize analysis results for multiple tools and samples in a single report. Bioinformatics , 32(19), 3047–3048. doi: /10.1093/bioinformatics/btw354</li>"
             ].join(' ').trim()
 
         return reference_text

modules.json

@@ -10,6 +10,11 @@
                         "git_sha": "3f5420aa22e00bd030a2556dfdffc9e164ec0ec5",
                         "installed_by": ["modules"]
                     },
+                    "centrifuge/build": {
+                        "branch": "master",
+                        "git_sha": "64163cd7ae556fc00664181b1ed520e827223034",
+                        "installed_by": ["modules"]
+                    },
                     "custom/dumpsoftwareversions": {
                         "branch": "master",
                         "git_sha": "8ec825f465b9c17f9d83000022995b4f7de6fe93",