Add Metaphlan4 profiler

CHANGELOG.md

@@ -16,6 +16,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
   - [#315](https://github.com/nf-core/taxprofiler/pull/315) Updated to nf-core pipeline template v2.9 (added by @sofstam & @jfy133)
   - [#319](https://github.com/nf-core/taxprofiler/pull/319) Added support for virus hit expansion in Kaiju (❤️ to @dnlrxn for requesting, added by @jfy133)
   - [#323](https://github.com/nf-core/taxprofiler/pull/323) Add ability to skip sequencing quality control tools (❤️ to @vinisalazar for requesting, added by @jfy133)
+  - [#318](https://github.com/nf-core/taxprofiler/pull/318) Added the profiler MetaPhlAn4 and removed MetaPhlAn3 (added by @LilyAnderssonLee)
 
 ### `Fixed`
 

CITATIONS.md

@@ -64,9 +64,9 @@
 
   > Breitwieser, Florian P., Daniel N. Baker, and Steven L. Salzberg. 2018. KrakenUniq: confident and fast metagenomics classification using unique k-mer counts. Genome Biology 19 (1): 198. doi: 10.1186/s13059-018-1568-0
 
-- [MetaPhlAn3](https://doi.org/10.7554/eLife.65088)
+- [MetaPhlAn](https://doi.org/10.1038/s41587-023-01688-w)
 
-  > Beghini, Francesco, Lauren J McIver, Aitor Blanco-Míguez, Leonard Dubois, Francesco Asnicar, Sagun Maharjan, Ana Mailyan, et al. 2021. “Integrating Taxonomic, Functional, and Strain-Level Profiling of Diverse Microbial Communities with BioBakery 3.” Edited by Peter Turnbaugh, Eduardo Franco, and C Titus Brown. ELife 10 (May): e65088. doi: 10.7554/eLife.65088
+  > Blanco-Míguez, A., Beghini, F., Cumbo, F. et al. Extending and improving metagenomic taxonomic profiling with uncharacterized species using MetaPhlAn 4. Nat Biotechnol (2023). doi: 10.1038/s41587-023-01688-w
 
 - [MALT](https://doi.org/10.1038/s41559-017-0446-6)
 

README.md

@@ -27,7 +27,7 @@
 3. Supports statistics for host-read removal ([Samtools](http://www.htslib.org/))
 4. Performs taxonomic classification and/or profiling using one or more of:
    - [Kraken2](https://ccb.jhu.edu/software/kraken2/)
-   - [MetaPhlAn3](https://huttenhower.sph.harvard.edu/metaphlan/)
+   - [MetaPhlAn](https://huttenhower.sph.harvard.edu/metaphlan/)
    - [MALT](https://uni-tuebingen.de/fakultaeten/mathematisch-naturwissenschaftliche-fakultaet/fachbereiche/informatik/lehrstuehle/algorithms-in-bioinformatics/software/malt/)
    - [DIAMOND](https://github.com/bbuchfink/diamond)
    - [Centrifuge](https://ccb.jhu.edu/software/centrifuge/)
@@ -68,7 +68,7 @@ Additionally, you will need a database sheet that looks as follows:
 ```
 tool,db_name,db_params,db_path
 kraken2,db2,--quick,/<path>/<to>/kraken2/testdb-kraken2.tar.gz
-metaphlan3,db1,,/<path>/<to>/metaphlan3/metaphlan_database/
+metaphlan,db1,,/<path>/<to>/metaphlan/metaphlan_database/
 ```
 
 That includes directories or `.tar.gz` archives containing databases for the tools you wish to run the pipeline against.
@@ -81,7 +81,7 @@ nextflow run nf-core/taxprofiler \
    --input samplesheet.csv \
    --databases databases.csv \
    --outdir <OUTDIR>  \
-   --run_kraken2 --run_metaphlan3
+   --run_kraken2 --run_metaphlan
 ```
 
 > **Warning:**

conf/modules.config

@@ -523,20 +523,20 @@ process {
         ]
     }
 
-    withName: METAPHLAN3_METAPHLAN3 {
+    withName: METAPHLAN_METAPHLAN {
         ext.args = { "${meta.db_params}" }
-        ext.prefix = params.perform_runmerging ? { "${meta.id}_${meta.db_name}.metaphlan3" } : { "${meta.id}_${meta.run_accession}_${meta.db_name}.metaphlan3" }
+        ext.prefix = params.perform_runmerging ? { "${meta.id}_${meta.db_name}.metaphlan" } : { "${meta.id}_${meta.run_accession}_${meta.db_name}.metaphlan" }
         publishDir = [
-            path: { "${params.outdir}/metaphlan3/${meta.db_name}/" },
+            path: { "${params.outdir}/metaphlan/${meta.db_name}/" },
             mode: params.publish_dir_mode,
             pattern: '*.{biom,txt}'
         ]
     }
 
-    withName: METAPHLAN3_MERGEMETAPHLANTABLES {
-        ext.prefix = { "metaphlan3_${meta.id}_combined_reports" }
+    withName: METAPHLAN_MERGEMETAPHLANTABLES {
+        ext.prefix = { "metaphlan_${meta.id}_combined_reports" }
         publishDir = [
-            path: { "${params.outdir}/metaphlan3/" },
+            path: { "${params.outdir}/metaphlan/" },
             mode: params.publish_dir_mode,
             pattern: '*.{txt}'
         ]

conf/test.config

@@ -34,7 +34,7 @@ params {
     run_kraken2                           = true
     run_bracken                           = true
     run_malt                              = false
-    run_metaphlan3                        = true
+    run_metaphlan                         = true
     run_centrifuge                        = true
     run_diamond                           = true
     run_krakenuniq                        = true

conf/test_full.config

@@ -57,7 +57,7 @@ params {
     malt_save_reads                     = false
     malt_generate_megansummary          = true
 
-    run_metaphlan3                      = true
+    run_metaphlan                       = true
 
     run_motus                           = true
     motus_save_mgc_read_counts          = true

conf/test_krakenuniq.config

@@ -38,7 +38,7 @@ params {
     run_kraken2                           = false
     run_bracken                           = false
     run_malt                              = false
-    run_metaphlan3                        = false
+    run_metaphlan                         = false
     run_centrifuge                        = false
     run_diamond                           = false
     run_krakenuniq                        = true

conf/test_motus.config

@@ -37,7 +37,7 @@ params {
     run_kraken2                           = false
     run_bracken                           = false
     run_malt                              = false
-    run_metaphlan3                        = false
+    run_metaphlan                         = false
     run_centrifuge                        = false
     run_diamond                           = false
     run_krakenuniq                        = false

conf/test_nopreprocessing.config

@@ -33,7 +33,7 @@ params {
     run_kraken2                           = true
     run_bracken                           = true
     run_malt                              = true
-    run_metaphlan3                        = true
+    run_metaphlan                         = true
     run_centrifuge                        = true
     run_diamond                           = true
     run_krakenuniq                        = true

conf/test_noprofiling.config

@@ -34,7 +34,7 @@ params {
     run_kraken2                           = false
     run_bracken                           = false
     run_malt                              = false
-    run_metaphlan3                        = false
+    run_metaphlan                         = false
     run_centrifuge                        = false
     run_diamond                           = false
     run_krakenuniq                        = false

conf/test_nothing.config

@@ -33,7 +33,7 @@ params {
     run_kraken2                           = false
     run_bracken                           = false
     run_malt                              = false
-    run_metaphlan3                        = false
+    run_metaphlan                         = false
     run_centrifuge                        = false
     run_diamond                           = false
     run_krakenuniq                        = false

docs/output.md

@@ -30,7 +30,7 @@ The pipeline is built using [Nextflow](https://www.nextflow.io/) and processes d
 - [Kaiju](#kaiju) - Taxonomic classifier that finds maximum (in-)exact matches on the protein-level.
 - [Diamond](#diamond) - Sequence aligner for protein and translated DNA searches.
 - [MALT](#malt) - Sequence alignment and analysis tool designed for processing high-throughput sequencing data, especially in the context of metagenomics
-- [MetaPhlAn3](#metaphlan3) - Genome-level marker gene based taxonomic classifier
+- [MetaPhlAn](#metaphlan) - Genome-level marker gene based taxonomic classifier
 - [mOTUs](#motus) - Tool for marker gene-based OTU (mOTU) profiling.
 - [ganon](#ganon) - Taxonomic classifier and profile that uses Interleaved Bloom Filters as indices based on k-mers/minimizers.
 - [TAXPASTA](#taxpasta) - Tool to standardise taxonomic profiles as well as merge profiles across samples from the same database and classifier/profiler.
@@ -429,23 +429,23 @@ The main output of MALT is the `.rma6` file format, which can be only loaded int
 
 You will only receive the `.sam` and `.megan` files if you supply `--malt_save_reads` and/or `--malt_generate_megansummary` parameters to the pipeline.
 
-### MetaPhlAn3
+### MetaPhlAn
 
-[MetaPhlAn3](https://github.com/biobakery/metaphlan) is a computational tool for profiling the composition of microbial communities (Bacteria, Archaea and Eukaryotes) from metagenomic shotgun sequencing data (i.e. not 16S) with species-level resolution via marker genes.
+[MetaPhlAn](https://github.com/biobakery/metaphlan) is a computational tool for profiling the composition of microbial communities (Bacteria, Archaea and Eukaryotes) from metagenomic shotgun sequencing data (i.e. not 16S) with species-level resolution via marker genes.
 
 <details markdown="1">
 <summary>Output files</summary>
 
-- `metaphlan3/`
-  - `metaphlan3_<db_name>_combined_reports.txt`: A combined profile of all samples aligned to a given database (as generated by `metaphlan_merge_tables`)
+- `metaphlan/`
+  - `metaphlan_<db_name>_combined_reports.txt`: A combined profile of all samples aligned to a given database (as generated by `metaphlan_merge_tables`)
   - `<db_name>/`
     - `<sample_id>.biom`: taxonomic profile in BIOM format
-    - `<sample_id>.bowtie2out.txt`: BowTie2 alignment information (can be re-used for skipping alignment when re-running MetaPhlAn3 with different parameters)
-    - `<sample_id>_profile.txt`: MetaPhlAn3 taxonomic profile including abundance estimates
+    - `<sample_id>.bowtie2out.txt`: BowTie2 alignment information (can be re-used for skipping alignment when re-running MetaPhlAn with different parameters)
+    - `<sample_id>_profile.txt`: MetaPhlAn taxonomic profile including abundance estimates
 
 </details>
 
-The main taxonomic profiling file from MetaPhlAn3 is the `*_profile.txt` file. This provides the abundance estimates from MetaPhlAn3 however does not include raw counts by default.
+The main taxonomic profiling file from MetaPhlAn is the `*_profile.txt` file. This provides the abundance estimates from MetaPhlAn however does not include raw counts by default.
 
 ### mOTUs
 
@@ -535,7 +535,7 @@ The following report files are used for the taxpasta step:
 - KrakenUniq: `<sample_id>_<db_name>.report.txt` Taxpasta uses the `reads` column for the standardised profile.
 - Kraken2: `<sample_id>_<db_name>.report.txt` Taxpasta uses the `direct_assigned_reads` column for the standardised profile.
 - MALT: `<sample_id>.txt.gz` Taxpasta uses the `count` (second) column from the output of MEGAN6's rma2info for the standardised profile.
-- MetaPhlAn3: `<sample_id>_profile.txt` Taxpasta uses the `relative_abundance` column multiplied with a fixed number to yield an integer for the standardised profile.
+- MetaPhlAn: `<sample_id>_profile.txt` Taxpasta uses the `relative_abundance` column multiplied with a fixed number to yield an integer for the standardised profile.
 - mOTUs: `<sample_id>.out` Taxpasta uses the `read_count` column for the standardised profile.
 
 > ⚠️ Please aware the outputs of each tool's standardised profile _may not_ be directly comparable between each tool. Some may report raw read counts, whereas others may report abundance information. Please always refer to the list above, for which information is used for each tool.

docs/usage.md

@@ -101,7 +101,7 @@ bracken,db1,;-r 150,/<path>/<to>/bracken/testdb-bracken.tar.gz
 kraken2,db2,--quick,/<path>/<to>/kraken2/testdb-kraken2.tar.gz
 krakenuniq,db3,,/<path>/<to>/krakenuniq/testdb-krakenuniq.tar.gz
 centrifuge,db1,,/<path>/<to>/centrifuge/minigut_cf.tar.gz
-metaphlan3,db1,,/<path>/<to>/metaphlan3/metaphlan_database/
+metaphlan,db1,,/<path>/<to>/metaphlan/metaphlan_database/
 motus,db_mOTU,,/<path>/<to>/motus/motus_database/
 ganon,db1,,/<path>/<to>/ganon/test-db-ganon.tar.gz
 ```
@@ -130,7 +130,7 @@ The (uncompressed) database paths (`db_path`) for each tool are expected to cont
 - [**Kraken2**:](#kraken2-custom-database) output of `kraken2-build` command(s).
 - [**KrakenUniq**:](#krakenuniq-custom-database) output of `krakenuniq-build` command(s).
 - [**MALT**](#malt-custom-database) output of `malt-build`.
-- [**MetaPhlAn3**:](#metaphlan3-custom-database) output of with `metaphlan --install` or downloaded from links on the [MetaPhlAn3 wiki](https://github.com/biobakery/MetaPhlAn/wiki/MetaPhlAn-3.0#customizing-the-database).
+- [**MetaPhlAn**:](#metaphlan-custom-database) output of with `metaphlan --install` or downloaded from links on the [MetaPhlAn wiki](https://github.com/biobakery/MetaPhlAn/wiki/MetaPhlAn-4#customizing-the-database).
 - [**mOTUs**:](#motus-custom-database) the directory `db_mOTU/` that is downloaded via `motus downloadDB`.
 - [**ganon**:](#ganon-custom-database) output of `ganon build` or `ganon build-custom`.
 
@@ -298,9 +298,9 @@ MALT does not support paired-end reads alignment (unlike other tools), therefore
 
 Krona can only be run on MALT output if path to Krona taxonomy database supplied to `--krona_taxonomy_directory`. Therefore if you do not supply the a Krona directory, Krona plots will not be produced for MALT.
 
-##### MetaPhlAn3
+##### MetaPhlAn
 
-MetaPhlAn3 currently does not accept FASTA files as input, therefore no output will be produced for these input files.
+MetaPhlAn4 is compatible with the MetaPhlAn3 database by adding the `--mpa3` paramter to the MetaPhlAn process in the config file `module.config`.
 
 ##### mOTUs
 
@@ -339,7 +339,7 @@ The following tools will produce multi-sample taxon tables:
 - **Centrifuge** (via KrakenTools' `combine_kreports.py` script)
 - **Kaiju** (via Kaiju's `kaiju2table` tool)
 - **Kraken2** (via KrakenTools' `combine_kreports.py` script)
-- **MetaPhlAn3** (via MetaPhlAn's `merge_metaphlan_tables.py` script)
+- **MetaPhlAn** (via MetaPhlAn's `merge_metaphlan_tables.py` script)
 - **mOTUs** (via the `motus merge` command)
 - **ganon** (via the `ganon table` command)
 
@@ -712,11 +712,11 @@ You can then add the `<YOUR_DB_NAME>/` path to your nf-core/taxprofiler database
 
 See the [MALT manual](https://software-ab.informatik.uni-tuebingen.de/download/malt/manual.pdf) for more information.
 
-#### MetaPhlAn3 custom database
+#### MetaPhlAn custom database
 
-MetaPhlAn3 does not allow (easy) construction of custom databases. Therefore we recommend to use the prebuilt database of marker genes that is provided by the developers.
+MetaPhlAn does not allow (easy) construction of custom databases. Therefore we recommend to use the prebuilt database of marker genes that is provided by the developers.
 
-To do this you need to have `MetaPhlAn3` installed on your machine.
+To do this you need to have `MetaPhlAn` installed on your machine.
 
 ```bash
 metaphlan --install --bowtie2db <YOUR_DB_NAME>/
@@ -731,21 +731,20 @@ You can then add the `<YOUR_DB_NAME>/` path to your nf-core/taxprofiler database
 <details markdown="1">
 <summary>Expected files in database directory</summary>
 
-- `metaphlan3`
-  - `mpa_v30_CHOCOPhlAn_201901.pkl`
-  - `mpa_v30_CHOCOPhlAn_201901.pkl`
-  - `mpa_v30_CHOCOPhlAn_201901.fasta`
-  - `mpa_v30_CHOCOPhlAn_201901.3.bt2`
-  - `mpa_v30_CHOCOPhlAn_201901.4.bt2`
-  - `mpa_v30_CHOCOPhlAn_201901.1.bt2`
-  - `mpa_v30_CHOCOPhlAn_201901.2.bt2`
-  - `mpa_v30_CHOCOPhlAn_201901.rev.1.bt2`
-  - `mpa_v30_CHOCOPhlAn_201901.rev.2.bt2`
+- `metaphlan`
+  - `mpa_vJan21_TOY_CHOCOPhlAnSGB_202103.pkl`
+  - `mpa_vJan21_TOY_CHOCOPhlAnSGB_202103.fna.bz2`
+  - `mpa_vJan21_TOY_CHOCOPhlAnSGB_202103.1.bt2l`
+  - `mpa_vJan21_TOY_CHOCOPhlAnSGB_202103.2.bt2l`
+  - `mpa_vJan21_TOY_CHOCOPhlAnSGB_202103.3.bt2l`
+  - `mpa_vJan21_TOY_CHOCOPhlAnSGB_202103.4.bt2l`
+  - `mpa_vJan21_TOY_CHOCOPhlAnSGB_202103.rev.1.bt2l`
+  - `mpa_vJan21_TOY_CHOCOPhlAnSGB_202103.rev.2.bt2l`
   - `mpa_latest`
 
 </details>
 
-More information on the MetaPhlAn3 database can be found [here](https://github.com/biobakery/MetaPhlAn/wiki/MetaPhlAn-3.1#installation).
+More information on the MetaPhlAn database can be found [here](https://github.com/biobakery/MetaPhlAn/wiki/MetaPhlAn-4#Pre-requisites).
 
 #### mOTUs custom database
 

modules.json

@@ -156,14 +156,14 @@
                         "git_sha": "c8e35eb2055c099720a75538d1b8adb3fb5a464c",
                         "installed_by": ["modules"]
                     },
-                    "metaphlan3/mergemetaphlantables": {
+                    "metaphlan/mergemetaphlantables": {
                         "branch": "master",
-                        "git_sha": "c8e35eb2055c099720a75538d1b8adb3fb5a464c",
+                        "git_sha": "9aa59197c0fb35c29e315bcd10c0fc9e1afc70a8",
                         "installed_by": ["modules"]
                     },
-                    "metaphlan3/metaphlan3": {
+                    "metaphlan/metaphlan": {
                         "branch": "master",
-                        "git_sha": "c8e35eb2055c099720a75538d1b8adb3fb5a464c",
+                        "git_sha": "31ec4470b455fe88c072151a5ea7821bfb2add38",
                         "installed_by": ["modules"]
                     },
                     "minimap2/align": {