Update changelog and docs, add new param to enable run cat on unbinned data

Author: dialvarezs

.vscode/settings.json

@@ -1,3 +1,24 @@
 {
-    "markdown.styles": ["public/vscode_markdown.css"]
+    "markdown.styles": [
+        "public/vscode_markdown.css"
+    ],
+    "workbench.colorCustomizations": {
+        "activityBar.activeBackground": "#2f7b49",
+        "activityBar.background": "#2f7b49",
+        "activityBar.foreground": "#e7e7e7",
+        "activityBar.inactiveForeground": "#e7e7e799",
+        "activityBarBadge.background": "#442c73",
+        "activityBarBadge.foreground": "#e7e7e7",
+        "commandCenter.border": "#e7e7e799",
+        "sash.hoverBorder": "#2f7b49",
+        "statusBar.background": "#215633",
+        "statusBar.foreground": "#e7e7e7",
+        "statusBarItem.hoverBackground": "#2f7b49",
+        "statusBarItem.remoteBackground": "#215633",
+        "statusBarItem.remoteForeground": "#e7e7e7",
+        "titleBar.activeBackground": "#215633",
+        "titleBar.activeForeground": "#e7e7e7",
+        "titleBar.inactiveBackground": "#21563399",
+        "titleBar.inactiveForeground": "#e7e7e799"
+    }
 }

CHANGELOG.md

@@ -3,6 +3,21 @@
 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
+
+### `Added`
+
+- [#799](https://github.com/nf-core/mag/pull/799) - Add `--cat_classify_unbinned`, to enable taxonomic classification of unbinned contigs using CAT (by @dialvarezs)
+
+### `Changed`
+- [#799](https://github.comf/nf-core/mag/pull/799) - Migrate from local CAT modules to nf-core ones, updating version (by @dialvarezs)
+
+### `Dependencies`
+
+| Tool    | Previous version | New version |
+| ------- | ---------------- | ----------- |
+| CAT     | 5.2.3            | 6.0.1       |
+
 ## v4.0.0 - [2025-05-22]
 
 ### `Added`

conf/base.config

@@ -114,7 +114,7 @@ process {
     }
     withName: CATPACK_BINS {
         cpus   = { 10 * task.attempt }
-        memory = { 128.GB * task.attempt }
+        memory = { 120.GB * task.attempt }
         time   = { 12.h * task.attempt }
     }
     withName: CATPACK_CONTIGS {
@@ -124,7 +124,7 @@ process {
     }
     withName: GTDBTK_CLASSIFYWF {
         cpus   = { 10 * task.attempt }
-        memory = { 120.GB * task.attempt }
+        memory = { 128.GB * task.attempt }
         time   = { 12.h * task.attempt }
     }
     //MEGAHIT returns exit code 250 when running out of memory

conf/modules.config

@@ -513,6 +513,7 @@ process {
             path: { "${params.outdir}/Taxonomy/CAT/db" },
             mode: params.publish_dir_mode,
             saveAs: { filename -> filename.equals('versions.yml') ? null : filename },
+            enabled: params.save_cat_db,
         ]
     }
 

docs/usage.md

@@ -127,21 +127,26 @@ The lineage directory (e.g., `bacteria_odb12`) should contain files such as `dat
 Then, you must provide `--busco_db <your_db>/` and `--busco_db_lineage <downloaded_lineage>` to the pipeline.
 You can also pass to `--busco_db` a URL pointing to a lineage tarball, or the tarball itself if stored locally.
 
-> [! WARNING]
+> [!WARNING]
 > When any kind of parameter is provided to `--busco_db`, BUSCO will run in offline mode.
 > If the lineage specified via `--busco_db_lineage` is not found locally, or if you attempt automatic lineage selection without having a complete lineage dataset pre-downloaded, BUSCO will fail.
 
 ### CAT
 
-> [! WARNING]
-> This database is very large at ~180 GB!
+> [!WARNING]
+> This database (CAT_nr) is very large at ~200 GB!
 > This can take a long time, so we strongly recommend downloading and unzipping prior the pipeline run.
 
-This database can be downloaded from the [CAT developers' website](https://tbb.bio.uu.nl/bastiaan/CAT_prepare/), which is based in the Netherlands (and could be slow for other regions of the world).
+This database can be downloaded from the [CAT developers' website](https://tbb.bio.uu.nl/tina/CAT_pack_prepare/), which is based in the Netherlands (and could be slow for other regions of the world).
+
+> [!NOTE]
+Only the `CAT_nr` database is supported by the pipeline.
+
+Enabling the `--cat_db_generate` option will create a new database using the latest version of the NCBI nr database. This requires a large download (over 200 GB) and several hours of subsequent processing. If you enable the `--save_cat_db` option, the database will be saved in the `Taxonomy/CAT/db` directory and can be reused in future runs by specifying its path with `--cat_db`.
 
 ### GTDB
 
-> [! WARNING]
+> [!WARNING]
 > This database is very large at ~110 GB!
 > This can take a long time, so we strongly recommend downloading and unzipping prior the pipeline run.
 

nextflow.config

@@ -93,6 +93,7 @@ params {
     cat_db                               = null
     cat_db_generate                      = false
     cat_official_taxonomy                = false
+    cat_classify_unbinned                = false
     save_cat_db                          = false
     skip_gtdbtk                          = false
     gtdb_db                              = "https://data.gtdb.ecogenomic.org/releases/release220/220.0/auxillary_files/gtdbtk_package/full_package/gtdbtk_r220_data.tar.gz"

nextflow_schema.json

@@ -520,6 +520,11 @@
                     "type": "boolean",
                     "description": "Only return official taxonomic ranks (Kingdom, Phylum, etc.) when running CAT."
                 },
+                "cat_classify_unbinned": {
+                    "type": "boolean",
+                    "description": "Classify unbinned contigs with CAT (contig mode).",
+                    "help_text": "This will run CAT classification on all unbinned contigs, which can be useful to get an idea of the taxonomic composition of the unbinned contigs."
+                },
                 "skip_gtdbtk": {
                     "type": "boolean",
                     "description": "Skip the running of GTDB, as well as the automatic download of the database"

subworkflows/local/catpack.nf

@@ -82,24 +82,26 @@ workflow CATPACK {
     =========================================
      */
 
-    CATPACK_CONTIGS(ch_unbins, ch_cat_db.db, ch_cat_db.taxonomy, [[:], []], [[:], []])
+    if (params.cat_classify_unbinned) {
+        CATPACK_CONTIGS(ch_unbins, ch_cat_db.db, ch_cat_db.taxonomy, [[:], []], [[:], []])
 
-    CATPACK_ADDNAMES_UNBINS(CATPACK_CONTIGS.out.contig2classification, ch_cat_db.taxonomy)
+        CATPACK_ADDNAMES_UNBINS(CATPACK_CONTIGS.out.contig2classification, ch_cat_db.taxonomy)
 
-    ch_unbin_classification = CATPACK_ADDNAMES_UNBINS.out.txt
-        .join(ch_unbins)
-        .multiMap { meta, names, contigs ->
-            names: [meta, names]
-            contigs: [meta, contigs]
-        }
+        ch_unbin_classification = CATPACK_ADDNAMES_UNBINS.out.txt
+            .join(ch_unbins)
+            .multiMap { meta, names, contigs ->
+                names: [meta, names]
+                contigs: [meta, contigs]
+            }
 
-    CATPACK_SUMMARISE(ch_unbin_classification.names, ch_unbin_classification.contigs)
+        CATPACK_SUMMARISE(ch_unbin_classification.names, ch_unbin_classification.contigs)
 
-    ch_versions = ch_versions.mix(
-        CATPACK_CONTIGS.out.versions.first(),
-        CATPACK_ADDNAMES_UNBINS.out.versions.first(),
-        CATPACK_SUMMARISE.out.versions.first(),
-    )
+        ch_versions = ch_versions.mix(
+            CATPACK_CONTIGS.out.versions.first(),
+            CATPACK_ADDNAMES_UNBINS.out.versions.first(),
+            CATPACK_SUMMARISE.out.versions.first(),
+        )
+    }
 
     emit:
     summary  = CATPACK_ADDNAMES_BINS.out.txt.map { _meta, summary -> summary }