nf-core · muniheart · May 16, 2025 · May 16, 2025 · May 16, 2025 · May 16, 2025
@@ -28,7 +28,7 @@ jobs:
       fail-fast: false
       matrix:
         NXF_VER:
-          - "24.10.0"
+          - "25.04.2"
           - "latest-everything"
         profile:
           - "conda"

@@ -7,6 +7,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ### `Added`
 
+- [#614](https://github.com/nf-core/taxprofiler/pull/614) Updated module `krakenuniq/preloadedkrakenuniq` to fix preload mechanism. The RAM chunk size can now be customised on a per-database basis. (added by @muniheart with help from / ❤️ to @jfy133)
 - [#600](https://github.com/nf-core/taxprofiler/pull/600) Added metaphlan to multiqc report (❤️ to @harper357 for reporting and added by @sofstam)
 - [#605](https://github.com/nf-core/taxprofiler/pull/605) Added documentation on how to generate Bracken reports for different taxonomic levels (❤️ to @MajoroMask for reporting and added by @jfy133)
 
@@ -19,9 +20,14 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 ### `Changed`
 
 - [#602](https://github.com/nf-core/taxprofiler/pull/600) Rename (undocumented) `test_nothing` profile to `test_minimal` for consistency with other pipelines (by @jfy133)
+- [#614](https://github.com/nf-core/taxprofiler/pull/614) There is now no default `krakenuniq_ram_chunk_size` value for KrakenUniq. By default now the entire database will be loaded into memory unless you use the parameter, or specify `--preload-size` in a database sheet. (added by @muniheart with help from / ❤️ to @jfy133)
 
 ### `Dependencies`
 
+| Tool     | Previous version | New version |
+| -------- | ---------------- | ----------- |
+| Nextflow | 24.10.0          | 25.04.2     |
+
 ### `Deprecated`
 
 ## v1.2.3 - Bouncy Basenji Patch [2024-03-13]

@@ -10,7 +10,7 @@
 
 [![nf-test](https://img.shields.io/badge/unit_tests-nf--test-337ab7.svg)](https://www.nf-test.com)
 
-[![Nextflow](https://img.shields.io/badge/nextflow%20DSL2-%E2%89%A524.10.0-23aa62.svg)](https://www.nextflow.io/)
+[![Nextflow](https://img.shields.io/badge/nextflow%20DSL2-%E2%89%A525.04.2-23aa62.svg)](https://www.nextflow.io/)
 [![run with conda](http://img.shields.io/badge/run%20with-conda-3EB049?labelColor=000000&logo=anaconda)](https://docs.conda.io/en/latest/)
 [![run with docker](https://img.shields.io/badge/run%20with-docker-0db7ed?labelColor=000000&logo=docker)](https://www.docker.com/)
 [![run with singularity](https://img.shields.io/badge/run%20with-singularity-1d355c.svg?labelColor=000000)](https://sylabs.io/docs/)

@@ -604,7 +604,16 @@ process {
 
     withName: KRAKENUNIQ_PRELOADEDKRAKENUNIQ {
         tag = { "${meta.db_name}|${task.index}" }
-        ext.args = { "${meta.db_params}" }
+        // Save current state of process scope arguments.
+        def args = ext.args ?: ''
+        // Concatenate arguments from lowest to highest precedence.
+        ext.args = {
+            [
+                args,
+                params.krakenuniq_ram_chunk_size ? "--preload-size ${params.krakenuniq_ram_chunk_size}" : '',
+                "${meta.db_params}"
+            ].join(' ').trim()
+            }
         // one run with multiple samples, so fix ID to just db name to ensure clean log name
         ext.prefix = { "${meta.db_name}.krakenuniq" }
         publishDir = [

@@ -19,82 +19,83 @@ process {
     resourceLimits = [
         cpus: 4,
         memory: '15.GB',
-        time: '6.h'
+        time: '6.h',
     ]
 }
 
 params {
-    config_profile_name        = 'Test profile'
-    config_profile_description = 'Minimal test to check KrakenUniq function'
+    config_profile_name                    = 'Test profile'
+    config_profile_description             = 'Minimal test to check KrakenUniq function'
 
     // Input data
-    input                                   = params.pipelines_testdata_base_path + 'taxprofiler/samplesheet.csv'
-    databases                               = params.pipelines_testdata_base_path + 'taxprofiler/database_krakenuniq.csv'
-    perform_shortread_qc                    = true
-    perform_longread_qc                     = true
-    perform_shortread_redundancyestimation  = false
-    shortread_qc_mergepairs                 = true
-    perform_shortread_complexityfilter      = true
-    perform_shortread_hostremoval           = true
-    perform_longread_hostremoval            = true
-    perform_runmerging                      = true
-    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                          = true
-    run_motus                               = false
-    run_kmcp                                = false
-    run_ganon                               = false
-    run_krona                               = true
-    krona_taxonomy_directory                = params.pipelines_testdata_base_path + 'modules/data/genomics/sarscov2/metagenome/krona_taxonomy.tab'
-    malt_save_reads                         = false
-    kraken2_save_reads                      = false
-    centrifuge_save_reads                   = false
-    diamond_save_reads                      = false
-    run_profile_standardisation             = true
+    input                                  = params.pipelines_testdata_base_path + 'taxprofiler/samplesheet.csv'
+    databases                              = params.pipelines_testdata_base_path + 'taxprofiler/database_krakenuniq.csv'
+    perform_shortread_qc                   = true
+    perform_longread_qc                    = true
+    perform_shortread_redundancyestimation = false
+    shortread_qc_mergepairs                = true
+    perform_shortread_complexityfilter     = true
+    perform_shortread_hostremoval          = true
+    perform_longread_hostremoval           = true
+    perform_runmerging                     = true
+    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                         = true
+    run_motus                              = false
+    run_kmcp                               = false
+    run_ganon                              = false
+    run_krona                              = true
+    krona_taxonomy_directory               = params.pipelines_testdata_base_path + 'modules/data/genomics/sarscov2/metagenome/krona_taxonomy.tab'
+    malt_save_reads                        = false
+    kraken2_save_reads                     = false
+    centrifuge_save_reads                  = false
+    diamond_save_reads                     = false
+    run_profile_standardisation            = true
+    krakenuniq_ram_chunk_size              = '2G'
 }
 
 process {
     withName: MALT_RUN {
-        tag = {"${meta.db_name}|${meta.id}"}
-        maxForks = 1
-        ext.args = { "${meta.db_params} -m ${params.malt_mode} -J-Xmx12G" }
+        tag        = { "${meta.db_name}|${meta.id}" }
+        maxForks   = 1
+        ext.args   = { "${meta.db_params} -m ${params.malt_mode} -J-Xmx12G" }
         ext.prefix = { "${meta.db_name}" }
         publishDir = [
             path: { "${params.outdir}/malt/${meta.db_name}/" },
             mode: params.publish_dir_mode,
-            pattern: '*.{rma6,log,sam}'
+            pattern: '*.{rma6,log,sam}',
         ]
     }
     withName: MEGAN_RMA2INFO_TSV {
-        tag = {"${meta.db_name}|${meta.id}"}
-        maxForks = 1
-        ext.args = "-c2c Taxonomy"
+        tag        = { "${meta.db_name}|${meta.id}" }
+        maxForks   = 1
+        ext.args   = "-c2c Taxonomy"
         ext.prefix = { "${meta.id}" }
         publishDir = [
             path: { "${params.outdir}/malt/${meta.db_name}/" },
             mode: params.publish_dir_mode,
-            pattern: '*.{txt.gz,megan}'
+            pattern: '*.{txt.gz,megan}',
         ]
     }
     withName: MEGAN_RMA2INFO_KRONA {
-        tag = {"${meta.db_name}|${meta.id}"}
-        maxForks = 1
-        ext.args = { "--read2class Taxonomy" }
+        tag        = { "${meta.db_name}|${meta.id}" }
+        maxForks   = 1
+        ext.args   = { "--read2class Taxonomy" }
         ext.prefix = { "${meta.id}_${meta.db_name}" }
     }
     withName: NONPAREIL_NONPAREIL {
-        ext.args = { "-k 5" }
+        ext.args   = { "-k 5" }
         ext.prefix = { "${meta.id}_${meta.run_accession}" }
         publishDir = [
             path: { "${params.outdir}/nonpareil/" },
             mode: params.publish_dir_mode,
-            pattern: '*.np{a,c,l,o}'
+            pattern: '*.np{a,c,l,o}',
         ]
     }
 }
@@ -137,7 +137,7 @@
                     },
                     "krakenuniq/preloadedkrakenuniq": {
                         "branch": "master",
-                        "git_sha": "2512434a59d282cba0fbc53ddb81dd8f244dc428",
+                        "git_sha": "4f6fe8971ddce2a2856f67b944fa86bc59b1b9a9",
                         "installed_by": ["modules"]
                     },
                     "krona/ktimporttaxonomy": {