Merge pull request #30 from nf-core/add-kraken

Add Kraken2 database build
nf-core · Apr 11, 2024 · db16f00 · db16f00
2 parents ae17e0d + e52525a
commit db16f00
Show file tree

Hide file tree

Showing 38 changed files with 1,111 additions and 49 deletions.
diff --git a/CITATIONS.md b/CITATIONS.md
@@ -52,6 +52,10 @@
 
 > Menzel, P., Ng, K. L., & Krogh, A. (2016). Fast and sensitive taxonomic classification for metagenomics with Kaiju. Nature Communications, 7, 11257. https://doi.org/10.1038/ncomms11257
 
+- [Kraken2](https://doi.org/10.1186/s13059-019-1891-0)
+
+  > 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
+
 - [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
diff --git a/README.md b/README.md
@@ -19,7 +19,7 @@
 
 ## Introduction
 
-**nf-core/createtaxdb** is a bioinformatics pipeline that constructs metagenomic classifier databases from the same input reference genome set for multiple classifiers and profilers in a highly automated and parallelised manner.
+**nf-core/createtaxdb** is a bioinformatics pipeline that constructs custom metagenomic classifier databases from the same input reference genome set for multiple classifiers and profilers in a highly automated and parallelised manner.
 
 <!-- TODO nf-core:
    Complete this sentence with a 2-3 sentence summary of what types of data the pipeline ingests, a brief overview of the
@@ -35,6 +35,7 @@
    - [Centrifuge](https://doi.org/10.1101/gr.210641.116)
    - [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)
    - [MALT](https://doi.org/10.1038/s41559-017-0446-6)
 
 ## Usage

diff --git a/conf/modules.config b/conf/modules.config
@@ -57,7 +57,6 @@ process {
 
     withName: 'MALT_BUILD' {
         ext.args   = { "--sequenceType ${params.malt_sequencetype}" }
-
     }
 
 }
diff --git a/conf/test.config b/conf/test.config
@@ -27,7 +27,9 @@ params {
     build_kaiju      = true
     build_malt       = true
     build_centrifuge = true
+    build_kraken2    = true
 
+    accession2taxid  = 'https://raw.githubusercontent.com/nf-core/test-datasets/createtaxdb/data/taxonomy/nucl_gb.accession2taxid'
     nucl2taxid       = 'https://raw.githubusercontent.com/nf-core/test-datasets/createtaxdb/data/taxonomy/nucl2tax.map'
     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/nodes.dmp'

diff --git a/conf/test_nothing.config b/conf/test_nothing.config
@@ -29,5 +29,6 @@ params {
     build_kaiju      = false
     build_malt       = false
     build_centrifuge = false
+    build_kraken2    = false
 
 }
diff --git a/docs/output.md b/docs/output.md
@@ -17,6 +17,7 @@ The pipeline is built using [Nextflow](https://www.nextflow.io/) and processes d
 - [Centrifuge](#centrifuge) - Database files for Centrifuge
 - [DIAMOND](#diamond) - Database files for DIAMOND
 - [Kaiju](#kaiju) - Database files for Kaiju
+- [Kraken2](#kraken2) - Database files for Kraken2
 - [MALT](#malt) - Database files for MALT
 
 ### MultiQC
@@ -92,6 +93,23 @@ The `dmnd` file can be given to one of the DIAMOND alignment commands with `diam
 
 The `fmi` file can be given to Kaiju itself with `kaiju -f <your_database>.fmi` etc.
 
+### Kraken2
+
+[Kraken2](https://ccb.jhu.edu/software/kraken2/) is a taxonomic classification system using exact k-mer matches to achieve high accuracy and fast classification speeds.
+
+<details markdown="1">
+<summary>Output files</summary>
+
+- `kraken2/`
+  - `<db_name>/`
+    - `hash.k2d`: Kraken2 hash database file
+    - `opts.k2d`: Kraken2 opts database file
+    - `taxo.k2d`: Kraken2 taxo database file
+
+</details>
+
+The resulting `<db_name>/` directory can be given to Kraken2 itself with `kraken2 --db <your_database_name>` etc.
+
 ### 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.

diff --git a/main.nf b/main.nf
@@ -40,8 +40,24 @@ workflow NFCORE_CREATETAXDB {
     //
     // WORKFLOW: Run pipeline
     //
+    ch_samplesheet       = samplesheet
+    ch_taxonomy_namesdmp = file(params.namesdmp)
+    ch_taxonomy_nodesdmp = file(params.nodesdmp)
+    ch_accession2taxid   = file(params.accession2taxid)
+    ch_nucl2taxid        = file(params.nucl2taxid)
+    ch_prot2taxid        = file(params.prot2taxid)
+    ch_malt_mapdb        = file(params.malt_mapdb)
+
+
     CREATETAXDB (
-        samplesheet
+        ch_samplesheet,
+        ch_taxonomy_namesdmp,
+        ch_taxonomy_nodesdmp,
+        ch_accession2taxid,
+        ch_nucl2taxid,
+        ch_prot2taxid,
+        ch_malt_mapdb,
+
     )
 
     emit:

diff --git a/modules.json b/modules.json
@@ -25,11 +25,26 @@
                         "git_sha": "b29f6beb86d1d24d680277fb1a3f4de7b8b8a92c",
                         "installed_by": ["modules"]
                     },
+                    "gunzip": {
+                        "branch": "master",
+                        "git_sha": "3a5fef109d113b4997c9822198664ca5f2716208",
+                        "installed_by": ["modules"]
+                    },
                     "kaiju/mkfmi": {
                         "branch": "master",
                         "git_sha": "7365564c402cbd01e9407810730efd10039997a3",
                         "installed_by": ["modules"]
                     },
+                    "kraken2/add": {
+                        "branch": "master",
+                        "git_sha": "ca87ad032a62f025f0c373facacef2df0c5411b2",
+                        "installed_by": ["fasta_build_add_kraken2"]
+                    },
+                    "kraken2/build": {
+                        "branch": "master",
+                        "git_sha": "ca87ad032a62f025f0c373facacef2df0c5411b2",
+                        "installed_by": ["fasta_build_add_kraken2"]
+                    },
                     "malt/build": {
                         "branch": "master",
                         "git_sha": "7d3bac628092d1aead36960c4b6ae41302a9f797",
@@ -54,6 +69,11 @@
             },
             "subworkflows": {
                 "nf-core": {
+                    "fasta_build_add_kraken2": {
+                        "branch": "master",
+                        "git_sha": "a4d1e13a2da05307deb65a87d501aa6520162dcd",
+                        "installed_by": ["subworkflows"]
+                    },
                     "utils_nextflow_pipeline": {
                         "branch": "master",
                         "git_sha": "5caf7640a9ef1d18d765d55339be751bb0969dfa",

diff --git a/modules/nf-core/gunzip/environment.yml b/modules/nf-core/gunzip/environment.yml
diff --git a/modules/nf-core/gunzip/main.nf b/modules/nf-core/gunzip/main.nf
diff --git a/modules/nf-core/gunzip/meta.yml b/modules/nf-core/gunzip/meta.yml
diff --git a/modules/nf-core/gunzip/tests/main.nf.test b/modules/nf-core/gunzip/tests/main.nf.test
diff --git a/modules/nf-core/gunzip/tests/main.nf.test.snap b/modules/nf-core/gunzip/tests/main.nf.test.snap
diff --git a/modules/nf-core/gunzip/tests/tags.yml b/modules/nf-core/gunzip/tests/tags.yml
diff --git a/modules/nf-core/kraken2/add/environment.yml b/modules/nf-core/kraken2/add/environment.yml
diff --git a/modules/nf-core/kraken2/add/main.nf b/modules/nf-core/kraken2/add/main.nf
-Original file line number
+Diff line change
@@ Expand Up / @@ -57,7 +57,6 @@ process { @@
         withName: 'MALT_BUILD' {
             ext.args   = { "--sequenceType ${params.malt_sequencetype}" }
         }
     }