Merge pull request #36 from nf-core/add-krakenuniqbuild

Add KrakenUniq Build

CITATIONS.md

@@ -60,6 +60,10 @@
 
   > Wood, D. E., Lu, J., & Langmead, B. (2019). Improved metagenomic analysis with Kraken 2. Genome Biology, 20(1), 257. https://doi.org/10.1186/s13059-019-1891-0
 
+- [KrakenUniq](https://doi.org/10.1186/s13059-018-1568-0)
+
+  > Breitwieser, F. P., Baker, D. N., & Salzberg, S. L. (2018). KrakenUniq: confident and fast metagenomics classification using unique k-mer counts. Genome Biology, 19(1), 198. https://doi.org/10.1186/s13059-018-1568-0
+
 - [MALT](https://doi.org/10.1038/s41559-017-0446-6)
 
   > 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. https://doi.org/10.1038/s41559-017-0446-6

README.md

@@ -37,6 +37,7 @@
    - [DIAMOND](https://doi.org/10.1038/nmeth.3176)
    - [Kaiju](https://doi.org/10.1038/ncomms11257)
    - [Kraken2](https://doi.org/10.1186/s13059-019-1891-0)
+   - [KrakenUniq](https://doi.org/10.1186/s13059-018-1568-0)
    - [MALT](https://doi.org/10.1038/s41559-017-0446-6)
 
 ## Usage

conf/test.config

@@ -16,7 +16,7 @@ params {
 
     // Limit resources so that this can run on GitHub Actions
     max_cpus   = 2
-    max_memory = '6.GB'
+    max_memory = '14.GB'
     max_time   = '6.h'
 
     // Input data
@@ -26,12 +26,13 @@ params {
 
     dbname           = "database"
 
+    build_bracken    = true
     build_diamond    = true
     build_kaiju      = true
     build_malt       = true
     build_centrifuge = true
     build_kraken2    = true
-    build_bracken    = true
+    build_krakenuniq = true
 
     accession2taxid  = params.pipelines_testdata_base_path + 'createtaxdb/data/taxonomy/nucl_gb.accession2taxid'
     nucl2taxid       = params.pipelines_testdata_base_path + 'createtaxdb/data/taxonomy/nucl2tax.map'
@@ -40,3 +41,10 @@ params {
     namesdmp         = params.pipelines_testdata_base_path + 'createtaxdb/data/taxonomy/names.dmp'
     malt_mapdb       = 's3://ngi-igenomes/test-data/createtaxdb/taxonomy/megan-nucl-Feb2022.db.zip'
 }
+
+process {
+    withName:'KRAKENUNIQ_BUILD'{
+        memory = { check_max( 12.GB * task.attempt, 'memory'  ) }
+        ext.args = "--work-on-disk --max-db-size 14 --kmer-len 15 --minimizer-len 13 --jellyfish-bin \$(which jellyfish)"
+    }
+}

conf/test_full.config

@@ -19,11 +19,11 @@ params {
     // TODO nf-core: Give any required params for the test so that command line flags are not needed
     input = params.pipelines_testdata_base_path + 'viralrecon/samplesheet/samplesheet_full_illumina_amplicon.csv'
 
+    build_bracken    = true
     build_diamond    = true
     build_kaiju      = true
     build_malt       = true
     build_centrifuge = true
     build_kraken2    = true
-    build_bracken    = true
-
+    build_krakenuniq = true
 }

conf/test_nothing.config

@@ -25,11 +25,11 @@ params {
 
     input         = 'https://raw.githubusercontent.com/nf-core/test-datasets/createtaxdb/samplesheets/test.csv'
 
+    build_bracken    = false
     build_diamond    = false
     build_kaiju      = false
     build_malt       = false
     build_centrifuge = false
     build_kraken2    = false
-    build_bracken    = false
-
+    build_krakenuniq = false
 }

docs/output.md

@@ -19,6 +19,7 @@ The pipeline is built using [Nextflow](https://www.nextflow.io/) and processes d
 - [DIAMOND](#diamond) - Database files for DIAMOND
 - [Kaiju](#kaiju) - Database files for Kaiju
 - [Kraken2](#kraken2) - Database files for Kraken2
+- [KrakenUniq](#krakenuniq) - Database files for KrakenUniq
 - [MALT](#malt) - Database files for MALT
 
 ### MultiQC
@@ -139,6 +140,24 @@ The `fmi` file can be given to Kaiju itself with `kaiju -f <your_database>.fmi`
 
 The resulting `<db_name>/` directory can be given to Kraken2 itself with `kraken2 --db <your_database_name>` etc.
 
+### KrakenUniq
+
+[KrakenUniq](https://github.com/fbreitwieser/krakenuniq) Metagenomics classifier with unique k-mer counting for more specific results.
+
+<details markdown="1">
+<summary>Output files</summary>
+
+- `kraken2/`
+  - `<db_name>/`
+  - `database-build.log`: KrakenUniq build process log
+  - `database.idx`: KrakenUniq index file
+  - `database.kdb`: KrakenUniq database file
+  - `taxDB`: KrakenUniq taxonomy information file
+
+</details>
+
+Note there may be additional files in this directory, however the ones listed above are the reportedly the required ones.
+
 ### MALT
 
 [MALT](https://software-ab.cs.uni-tuebingen.de/download/malt) is a fast replacement for BLASTX, BLASTP and BLASTN, and provides both local and semi-global alignment capabilities.

modules.json

@@ -50,6 +50,12 @@
                         "git_sha": "ca87ad032a62f025f0c373facacef2df0c5411b2",
                         "installed_by": ["fasta_build_add_kraken2_bracken"]
                     },
+                    "krakenuniq/build": {
+                        "branch": "master",
+                        "git_sha": "e3857325a14ef6e50e33c104c0a3be0ccaabbeb1",
+                        "installed_by": ["modules"],
+                        "patch": "modules/nf-core/krakenuniq/build/krakenuniq-build.diff"
+                    },
                     "malt/build": {
                         "branch": "master",
                         "git_sha": "7d3bac628092d1aead36960c4b6ae41302a9f797",

nextflow.config

@@ -65,14 +65,15 @@ params {
     malt_mapdb      = null
 
     // tool specific options
+    build_bracken            = false
     build_diamond            = false
     build_kaiju              = false
     build_malt               = false
     malt_sequencetype        = "DNA"
     build_centrifuge         = false
     build_kraken2            = false
     kraken2_keepintermediate = false
-    build_bracken            = false
+    build_krakenuniq         = false
 }
 
 // Load base.config by default for all pipelines

nextflow_schema.json

@@ -107,6 +107,12 @@
             "description": "",
             "default": "",
             "properties": {
+                "build_bracken": {
+                    "type": "boolean",
+                    "fa_icon": "fas fa-save",
+                    "description": "Turn on extending of Kraken2 database to include Bracken files. Requires nucleotide FASTA File input.",
+                    "help_text": "Bracken2 databases are simply just a Kraken2 database with two additional files.\n\nNote however this requires a Kraken2 database _with_ intermediate files still in it, thus can result in large database directories."
+                },
                 "build_centrifuge": {
                     "type": "boolean",
                     "description": "Turn on building of Centrifuge database. Requires nucleotide FASTA file input.",
@@ -145,11 +151,10 @@
                     "fa_icon": "fas fa-save",
                     "description": "Retain intermediate Kraken2 build files for inspection."
                 },
-                "build_bracken": {
+                "build_krakenuniq": {
                     "type": "boolean",
-                    "fa_icon": "fas fa-save",
-                    "description": "Turn on extending of Kraken2 database to include Bracken files. Requires nucleotide FASTA File input.",
-                    "help_text": "Bracken2 databases are simply just a Kraken2 database with two additional files.\n\nNote however this requires a Kraken2 database _with_ intermediate files still in it, thus can result in large database directories."
+                    "fa_icon": "fas fa-toggle-on",
+                    "description": "Turn on building of KrakenUniq database. Requires nucleotide FASTA file input."
                 }
             },
             "fa_icon": "fas fa-database"

subworkflows/local/utils_nfcore_createtaxdb_pipeline/main.nf

@@ -199,6 +199,7 @@ def toolCitationText() {
             params.build_diamond    ? "DIAMOND (Buchfink et al. 2015)," : "",
             params.build_kaiju      ? "Kaiju (Menzel et al. 2016)," : "",
             params.build_kraken2    ? "Kraken2 (Wood et al. 2019)," : "",
+            params.build_krakenuniq ? "KrakenUniq (Breitwieser et al. 2018)," : "",
             params.build_malt       ? "MALT (Vågene et al. 2018)," : "",
             "and MultiQC (Ewels et al. 2016)",
             "."
@@ -217,7 +218,9 @@ def toolBibliographyText() {
             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_kraken2    ? "<li>Wood, D. E., Lu, J., & Langmead, B. (2019). Improved metagenomic analysis with Kraken 2. Genome Biology, 20(1), 257.  <a href=\"https://doi.org/10.1186/s13059-019-1891-0\">10.1186/s13059-019-1891-0</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_krakenuniq  ? "<li>Breitwieser, F. P., Baker, D. N., & Salzberg, S. L. (2018). KrakenUniq: confident and fast metagenomics classification using unique k-mer counts. Genome Biology, 19(1), 198.  <a href=\"https://doi.org/10.1186/s13059-018-1568-0\">10.1186/s13059-018-1568-0</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

tests/test.nf.test

@@ -18,15 +18,19 @@ nextflow_pipeline {
             assertAll(
                 { assert workflow.success },
                 { assert snapshot(
+                        file("$outputDir/bracken/database/database100mers.kmer_distrib").name,
+                        file("$outputDir/bracken/database/database100mers.kraken").name,
+                        file("$outputDir/bracken/database/database.kraken").name,
                         path("$outputDir/centrifuge/"),
                         path("$outputDir/diamond/database.dmnd"),
                         path("$outputDir/kaiju/database.fmi"),
                         path("$outputDir/kraken2/database/hash.k2d"),
                         file("$outputDir/kraken2/database/opts.k2d").name,
                         path("$outputDir/kraken2/database/taxo.k2d"),
-                        file("$outputDir/bracken/database/database100mers.kmer_distrib").name,
-                        file("$outputDir/bracken/database/database100mers.kraken").name,
-                        file("$outputDir/bracken/database/database.kraken").name,
+                        path("$outputDir/krakenuniq/database/database-build.log").readLines().last().contains('database.idx'),
+                        file("$outputDir/krakenuniq/database/database.idx").name,
+                        file("$outputDir/krakenuniq/database/database.kdb"),
+                        file("$outputDir/krakenuniq/database/taxDB"),
                         path("$outputDir/malt/malt-build.log").readLines().last().contains('Peak memory'),
                         path("$outputDir/malt/malt_index/index0.idx"),
                         path("$outputDir/malt/malt_index/ref.db"),

tests/test.nf.test.snap

@@ -1,6 +1,9 @@
 {
     "test_profile": {
         "content": [
+            "database100mers.kmer_distrib",
+            "database100mers.kraken",
+            "database.kraken",
             [
                 "database.1.cf:md5,1481615ab90b5573f6d9e57f97890178",
                 "database.2.cf:md5,d50fa66e215e80284314ff6521dcd4a4",
@@ -12,9 +15,10 @@
             "hash.k2d:md5,01122a04dcef29ceb3baa68a9f6e6ef5",
             "opts.k2d",
             "taxo.k2d:md5,cd8170a8c5a1b763a9ac1ffa2107cc88",
-            "database100mers.kmer_distrib",
-            "database100mers.kraken",
-            "database.kraken",
+            true,
+            "database.idx",
+            "database.kdb:md5,a24fce43bedbc6c420f6e36d10c112a3",
+            "taxDB:md5,1aed1afa948daffc236deba1c5d635db",
             true,
             "index0.idx:md5,876139dc930e68992cd2625e08bba48a",
             "ref.db:md5,377073f58a9f9b85acca59fcf21744a9",
@@ -26,8 +30,8 @@
         ],
         "meta": {
             "nf-test": "0.8.4",
-            "nextflow": "24.04.1"
+            "nextflow": "24.04.2"
         },
-        "timestamp": "2024-05-23T08:15:27.641419595"
+        "timestamp": "2024-05-30T10:54:40.551963562"
     }
 }