Add metacache

CHANGELOG.md

@@ -3,10 +3,11 @@
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/)
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
-## dev - [unreleased]
+## v1.3.0dev [unreleased]
 
 ### `Added`
 
+- [#682](https://github.com/nf-core/taxprofiler/pull/682) Added metacache classifier and improved nf-tests (added by @sofstam)
 - [#559](https://github.com/nf-core/taxprofiler/pull/559) Profiling of long reads with motus (added by @LilyAnderssonLee and @sofstam )
 - [#595](https://github.com/nf-core/taxprofiler/pull/595) **New classifier** [sylph](https://github.com/bluenote-1577/sylph) (added by @sofstam)
 - [#608](https://github.com/nf-core/taxprofiler/pull/608) **New classifier** [melon](https://github.com/xinehc/melon) (added by @parisis and @sofstam)

CITATIONS.md

@@ -133,6 +133,10 @@
 
   > Shaw, J., & Yu, Y. W. (2024). Rapid species-level metagenome profiling and containment estimation with Sylph. Nature Biotechnology. https://doi.org/10.1038/s41587-024-02412-y
 
+- [MetaCachae](https://doi.org/10.1093/bioinformatics/btx520)
+
+  > Müller, A., Hundt, C., Hildebrandt, A., Hankeln, T., & Schmidt, B.(2017). MetaCache: context-aware classification of metagenomic reads using minhashing. Bioinformatics, 33(23), 3740–3748. https://doi.org/10.1093/bioinformatics/btx520
+
 ## Software packaging/containerisation tools
 
 - [Anaconda](https://anaconda.com)

README.md

@@ -49,6 +49,7 @@
    - [ganon](https://pirovc.github.io/ganon/)
    - [sylph](https://github.com/bluenote-1577/sylph)
    - [Melon](https://github.com/xinehc/melon)
+   - [MetaCache](https://github.com/muellan/metacache)
 5. Perform optional post-processing with:
    - [bracken](https://ccb.jhu.edu/software/bracken/)
 6. Standardises output tables ([`Taxpasta`](https://taxpasta.readthedocs.io))

conf/modules.config

@@ -920,6 +920,19 @@ process {
         ]
     }
 
+
+    withName: METACACHE_QUERY {
+        tag        = { "${meta.db_name}|${meta.id}" }
+        ext.args   = { "${meta.db_params}" }
+        ext.prefix = { params.perform_runmerging ? "${meta.id}_${meta.db_name}" : "${meta.id}_${meta.run_accession}_${meta.db_name}" }
+        publishDir = [
+            path: { "${params.outdir}/metacache/${meta.db_name}/" },
+            mode: params.publish_dir_mode,
+            pattern: '*.txt'
+        ]
+    }
+
+
     withName: TAXPASTA_MERGE {
         tag        = { "${meta.tool}|${meta.id}" }
         ext.prefix = { "${meta.tool}_${meta.id}" }

conf/test.config

@@ -48,6 +48,7 @@ params {
     run_kmcp                               = true
     run_sylph                              = true
     run_melon                              = true
+    run_metacache                          = true
     sylph_taxonomy                         = params.pipelines_testdata_base_path + 'taxprofiler/data/database/sylph/test_taxonomy.tsv.gz'
     krona_taxonomy_directory               = params.pipelines_testdata_base_path + 'modules/data/genomics/sarscov2/metagenome/krona_taxonomy.tab'
     malt_save_reads                        = true

conf/test_alternativepreprocessing.config

@@ -49,6 +49,7 @@ params {
     run_kmcp                           = false
     run_sylph                          = false
     run_melon                          = false
+    run_metacache                      = false
 }
 
 process {

conf/test_bbduk.config

@@ -47,6 +47,7 @@ params {
     run_kmcp                           = false
     run_sylph                          = false
     run_melon                          = false
+    run_metacache                      = false
 }
 
 process {

conf/test_falco.config

@@ -47,6 +47,7 @@ params {
     run_kmcp                           = false
     run_sylph                          = false
     run_melon                          = false
+    run_metacache                      = false
 }
 
 process {

conf/test_fastp.config

@@ -49,6 +49,7 @@ params {
     run_kmcp                               = false
     run_sylph                              = false
     run_melon                              = false
+    run_metacache                          = false
 }
 
 process {

conf/test_full.config

@@ -76,6 +76,9 @@ params {
 
     run_sylph				                       = true
     sylph_taxonomy                         = params.pipelines_testdata_base_path + 'taxprofiler/data/database/sylph/sylph_taxonomy.tsv.gz'
+    run_metacache                          = true
+    metacache_abundances                   = true
+
     run_profile_standardisation            = true
     run_krona                              = true
     run_melon                              = true

conf/test_krakenuniq.config

@@ -52,6 +52,7 @@ params {
     run_ganon                              = false
     run_sylph                              = false
     run_melon                              = false
+    run_metacache                          = false
     run_krona                              = true
     krona_taxonomy_directory               = params.pipelines_testdata_base_path + 'modules/data/genomics/sarscov2/metagenome/krona_taxonomy.tab'
     malt_save_reads                        = false

conf/test_malt.config

@@ -51,6 +51,7 @@ params {
     run_kmcp                               = false
     run_sylph                              = false
     run_melon                              = false
+    run_metacache                          = false
 }
 
 process {

conf/test_minimal.config

@@ -47,6 +47,7 @@ params {
     run_ganon                              = false
     run_sylph                              = false
     run_melon                              = false
+    run_metacache                          = false
 }
 
 process {

conf/test_motus.config

@@ -28,32 +28,35 @@ params {
     config_profile_description             = 'Minimal test to check mOTUs function'
 
     // Input data
-    input                                  = params.pipelines_testdata_base_path + 'taxprofiler/samplesheet.csv'
-    databases                              = 'database_motus.csv'
-    perform_shortread_qc                   = false
-    perform_longread_qc                    = false
-    perform_shortread_redundancyestimation = false
-    perform_shortread_complexityfilter     = false
-    perform_shortread_hostremoval          = false
-    perform_longread_hostremoval           = false
-    perform_runmerging                     = false
-    hostremoval_reference                  = params.pipelines_testdata_base_path + 'modules/data/genomics/homo_sapiens/genome/genome.fasta'
-    run_kaiju                              = false
-    run_kraken2                            = false
-    run_bracken                            = false
-    run_malt                               = false
-    run_metaphlan                          = false
-    run_centrifuge                         = false
-    run_diamond                            = false
-    run_krakenuniq                         = false
-    run_motus                              = true
-    run_kmcp                               = false
-    run_ganon                              = false
-    motus_save_mgc_read_counts             = false
-    motus_remove_ncbi_ids                  = false
-    motus_use_relative_abundance           = false
-    motus_save_splitlong_reads             = false
-    run_profile_standardisation            = true
+    input                                   = params.pipelines_testdata_base_path + 'taxprofiler/samplesheet.csv'
+    databases                               = 'database_motus.csv'
+    perform_shortread_qc                    = false
+    perform_longread_qc                     = false
+    perform_shortread_redundancyestimation  = false
+    perform_shortread_complexityfilter      = false
+    perform_shortread_hostremoval           = false
+    perform_longread_hostremoval            = false
+    perform_runmerging                      = false
+    hostremoval_reference                   = params.pipelines_testdata_base_path + 'modules/data/genomics/homo_sapiens/genome/genome.fasta'
+    run_kaiju                               = false
+    run_kraken2                             = false
+    run_bracken                             = false
+    run_malt                                = false
+    run_metaphlan                           = false
+    run_centrifuge                          = false
+    run_diamond                             = false
+    run_krakenuniq                          = false
+    run_motus                               = true
+    run_kmcp                                = false
+    run_ganon                               = false
+    run_sylph                               = false
+    run_melon                               = false
+    run_metacache                           = false
+    motus_save_mgc_read_counts              = false
+    motus_remove_ncbi_ids                   = false
+    motus_use_relative_abundance            = false
+    motus_save_splitlong_reads              = false
+    run_profile_standardisation             = true
 }
 
 process {

conf/test_nopreprocessing.config

@@ -49,6 +49,7 @@ params {
     run_krona                              = true
     run_sylph                              = true
     run_melon                              = true
+    run_metacache                          = true
     sylph_taxonomy                         = params.pipelines_testdata_base_path + 'taxprofiler/data/database/sylph/test_taxonomy.tsv.gz'
 }
 

conf/test_noprofiling.config

@@ -48,6 +48,7 @@ params {
     run_ganon                              = false
     run_sylph                              = false
     run_melon                              = false
+    run_metacache                          = false
 }
 
 process {

conf/test_prinseqplusplus.config

@@ -48,6 +48,7 @@ params {
     run_kmcp                               = false
     run_sylph                              = false
     run_melon                              = false
+    run_metacache                          = false
 }
 
 process {

docs/output.md

@@ -40,6 +40,7 @@ The pipeline is built using [Nextflow](https://www.nextflow.io/) and processes d
 - [ganon](#ganon) - Taxonomic classifier and profile that uses Interleaved Bloom Filters as indices based on k-mers/minimizers.
 - [sylph](#sylph) - Taxonomic classifier that performs ultrafast average nucleotide identity (ANI) querying or metagenomic profiling for metagenomic shotgun samples.
 - [Melon](#Melon) - Taxonomic classifier that uses ribosomal marker genes to classify and quantify long-read metagenomic data.
+- [MetaCache](#metacache) - Taxonomic classifier using minhashing
 - [TAXPASTA](#taxpasta) - Tool to standardise taxonomic profiles as well as merge profiles across samples from the same database and classifier/profiler.
 - [MultiQC](#multiqc) - Aggregate report describing results and QC from the whole pipeline
 - [Pipeline information](#pipeline-information) - Report metrics generated during the workflow execution
@@ -655,6 +656,25 @@ For further descriptions of the contents of each file, see the [sylph documentat
 The main taxonomic classification files from melon are the `*.tsv` and `*.json` files.
 For further descriptions of the contents of each file, see the [melon documentation](https://github.com/xinehc/melon#run-melon).
 
+### MetaCache
+
+[MetaCache](https://github.com/muellan/metacache) is a taxonomic classifier that minhashing for the classification of reads
+
+<details markdown="1">
+<summary>Output files</summary>
+
+- `metacache/`
+  - `<db_name>/`
+    - `<sample_id>.abundances.txt`: Absolute and relative abundance of each taxon on each rank in .txt format
+    - `<sample_id>.mspping.txt`: Mapping outout in .txt format
+
+</details>
+
+MetaCache's default read mapping output format is:
+`read_header | rank:taxon_name`
+
+For further description see [MetaCache documentation](https://github.com/muellan/metacache/blob/d7646eca4c4dc131262b16d2910923fce3f5d4fc/docs/output.md#classification-output).
+
 ### Krona
 
 [Krona](https://github.com/marbl/Krona) allows the exploration of (metagenomic) hierarchical data with interactive zooming, multi-layered pie charts.

docs/usage.md

@@ -147,6 +147,7 @@ ganon,db1,,/<path>/<to>/ganon/test-db-ganon.tar.gz
 kmcp,db1,;-I 20,/<path>/<to>/kmcp/test-db-kmcp.tar.gz
 sylph,db1,-m 80,/<path>/<to>/sylph/test-db-sylph.tar.gz
 melon,db1,,/<path>/<to>/melon/test-db-melon.tar.gz
+metacache,db1,,/<path>/<to>/metacache/test-db-metacache.tar.gz
 ```
 
 ```csv
@@ -163,6 +164,7 @@ ganon,db1,,short,/<path>/<to>/ganon/test-db-ganon.tar.gz
 kmcp,db1,;-I 20,short,/<path>/<to>/kmcp/test-db-kmcp.tar.gz
 sylph,db1,-m 80,long,/<path>/<to>/sylph/test-db-sylph.tar.gz
 melon,db1,,long,/<path>/<to>/melon/test-db-melon.tar.gz
+metacache,db1,,long,/<path>/<to>/metacache/test-db-metacache.tar.gz
 ```
 
 :::warning
@@ -215,6 +217,7 @@ The (uncompressed) database paths (`db_path`) for each tool are expected to cont
 - [**KMCP**:](usage/tutorials.md#kmcp-custom-database) output of `kmcp index`. Note: `kmcp index` uses the output of an upstream `kmcp compute` step.
 - [**sylph**:](usage/tutotials.md#sylph-custom-database) output of `sylph sketch` command.
 - [**Melon**:](usage/tutorials.md#melon-custom-database) output of `diamond makedb` and `minimap2`.
+- [**MetaCache**:](usage/tutorials.md#metacache-custom-database) output of `metacache build` command
 
 ## Running the pipeline
 
@@ -506,6 +509,10 @@ Currently, no specific tips or suggestions.
 Melon is only suitable for long-read metagenomic profiling.
 Therefore, nf-core/taxprofiler does not currently run Melon on data specified as being sequenced with `Illumina` or any other short-read platform in the input samplesheet.
 
+##### MetaCache
+
+Currently, no specific tips or suggestions.
+
 #### Post Processing
 
 ##### Visualisation

docs/usage/tutorials.md

@@ -740,3 +740,22 @@ You can then add the path to `<YOUR_DB_NAME>/` to your nf-core/taxprofiler datab
 </details>
 
 More information on the Melon database can be found [here](https://github.com/xinehc/melon#database-setup).
+
+#### MetaCache custom database
+
+To build a custom MetaCache database, you need download the NCBI taxonomy. The fasta files can either be combined into a singile file or you can put them all together within a directory
+
+```bash
+download-ncbi-taxonomy ncbi_taxonomy
+metacache build metacache all_genomes.fasta -taxonomy ncbi_taxonomy
+```
+
+<details markdown="1">
+<summary>Expected files in database directory</summary>
+
+- `metacache`
+  - `database/<custom_name>.meta`
+  - `database/<custom_name>.cache0`
+  </details>
+
+More information on custom MetaCache database construction can be found [here](https://github.com/muellan/metacache/blob/d7646eca4c4dc131262b16d2910923fce3f5d4fc/docs/building.md).

modules.json

@@ -165,6 +165,11 @@
                         "git_sha": "83fe5c85a83aae68a6eb0561e04cbba1e153ac5a",
                         "installed_by": ["modules"]
                     },
+                    "metacache/query": {
+                        "branch": "master",
+                        "git_sha": "41dfa3f7c0ffabb96a6a813fe321c6d1cc5b6e46",
+                        "installed_by": ["modules"]
+                    },
                     "metaphlan/mergemetaphlantables": {
                         "branch": "master",
                         "git_sha": "41dfa3f7c0ffabb96a6a813fe321c6d1cc5b6e46",