Metacache

README.md

@@ -45,6 +45,7 @@ The pipeline is designed to be a companion pipeline to [nf-core/taxprofiler](htt
    - [MALT](https://doi.org/10.1038/s41559-017-0446-6)
    - [sourmash](https://doi.org/10.21105/joss.06830)
    - [sylph](https://doi.org/10.1038/s41587-024-02412-y)
+   - [MetaCache](https://doi.org/10.1093/bioinformatics/btx520)
 
 ## Usage
 
@@ -81,6 +82,7 @@ nextflow run nf-core/createtaxdb \
    --ganon_build_options='--kmer-size 45' \
    --build_diamond \
    --diamond_build_options='--no-parse-seqids' \
+   --build_metacache \
    --outdir <OUTDIR>
 ```
 

conf/modules.config

@@ -161,4 +161,9 @@ process {
         ext.prefix = { "${meta.id}-sylph" }
         ext.args   = { "${params.sylph_build_options}" }
     }
+
+    withName: METACACHE_BUILD {
+        ext.prefix = { "${meta.id}-metacache" }
+        ext.args   = { "${params.metacache_build_options}" }
+    }
 }

conf/test.config

@@ -40,6 +40,7 @@ params {
     build_sourmash_dna               = true
     build_sourmash_protein           = true
     build_sylph                      = true
+    build_metacache                  = true
 
     unzip_batch_size                 = 1
 

conf/test_alternatives.config

@@ -57,6 +57,7 @@ params {
     malt_mapdb_format                = 'mdb'
 
     build_sylph                      = false
+    build_metacache                  = false
 
     // General output options
     generate_downstream_samplesheets = true

conf/test_full.config

@@ -41,6 +41,7 @@ params {
     build_sourmash_protein           = true
     unzip_batch_size                 = 50
     build_sylph                      = true
+    build_metacache                  = true
 
     // General output options
     generate_downstream_samplesheets = true

conf/test_minimal.config

@@ -32,5 +32,6 @@ params {
     build_sourmash_dna               = false
     build_sourmash_protein           = false
     build_sylph                      = false
+    build_metacache                  = false
     generate_downstream_samplesheets = false
 }

docs/output.md

@@ -23,6 +23,7 @@ The pipeline is built using [Nextflow](https://www.nextflow.io/) and processes d
 - [MALT](#malt) - Database files for MALT
 - [sourmash](#sourmash) - Database files for sourmash
 - [sylph](#sylph) - Database files for sylph
+- [MetaCache](#metacache) - Database files for MetaCache
 
 The pipeline can also generate downstream pipeline input samplesheets.
 These are stored in `<outdir>/downstream_samplesheets`.
@@ -237,6 +238,21 @@ and the k-mer size for which the index was created.
 
 The `<your_database>-sylph.syldb` file can be given to sylph profile itself with `sylph profile <your_database>-sylph.syldb <...>` etc.
 
+### metacache
+
+[MetaCache](https://github.com/muellan/metacache) is a classification system for mapping genomic sequences (short reads, long reads, contigs, ...) from metagenomic samples to their most likely taxon of origin.
+
+<details markdown="1">
+<summary>Output files</summary>
+
+- `metacache/`
+  - `<your_database>.meta`: sequence signature database binary file
+  - `<your_database>.cache0`: sequence signature database binary file
+
+</details>
+
+The `<your_database>-metacache/<your_database>-.meta` file can be given to metacache query itself with `metacache query metacache/<your_database>.meta <...>` etc.
+
 ### Downstream samplesheets
 
 The pipeline can also generate input files for the following downstream

docs/usage/faq.md

@@ -36,6 +36,10 @@ We provide a list of required or recommended files, and which pipeline parameter
   - a MEGAN 'mapDB' mapping file (`--malt_mapdb`)
 - sourmash (no additional files required)
 - sylph (no additional files required)
+- metacache
+  - taxonomy name dump file (`--namesdmp`)
+  - taxonomy nodes dump file (`--nodesdmp`)
+  - custom seqid2taxid file (`--nucl2taxid`)
 
 \* _will be automatically downloaded if not supplied. You must supply this to the pipeline if on an offline cluster._
 
@@ -401,6 +405,7 @@ tar czvf kmcp-krakenuniq.tar.gz krakenuniq/database-kmcp-index/
 tar czvf <dbname>-krakenuniq.tar.gz krakenuniq/<dbname>-krakenuniq/
 tar czvf <dbname>-ganon.tar.gz ganon/
 tar czvf <dbname>-malt.tar.gz malt/malt_index/
+tar czvf <dbname>-metacache.tar.gz metacache/
 ```
 
 ## I get an error about `ConcurrentModificationExeception`

modules.json

@@ -71,6 +71,11 @@
                         "git_sha": "41dfa3f7c0ffabb96a6a813fe321c6d1cc5b6e46",
                         "installed_by": ["modules"]
                     },
+                    "metacache/build": {
+                        "branch": "master",
+                        "git_sha": "e753770db613ce014b3c4bc94f6cba443427b726",
+                        "installed_by": ["modules"]
+                    },
                     "multiqc": {
                         "branch": "master",
                         "git_sha": "af27af1be706e6a2bb8fe454175b0cdf77f47b49",