Added kmer_len as a parameter to set the kmer distribution files used…

… by BRACKEN to estimate the abundance at a single taxonomic level
phac-nml · Apr 12, 2024 · 6e75e48 · 6e75e48
1 parent d009b7f
commit 6e75e48
Show file tree

Hide file tree

Showing 4 changed files with 16 additions and 3 deletions.
diff --git a/modules/local/bracken/main.nf b/modules/local/bracken/main.nf
@@ -9,6 +9,7 @@ process BRACKEN {
     tuple val(meta), path(report_txt)
     path(bracken_db)
     val(taxonomic_level)
+    val(kmer_len)
 
     output:
     tuple val(meta), path("*_bracken.txt"),                     emit: bracken_reports
@@ -33,9 +34,11 @@ process BRACKEN {
         -i ${report_txt} \\
         -w ${meta.id}_${taxonomic_level}_bracken.txt \\
         -o ${meta.id}_${taxonomic_level}_bracken_abundances_unsorted.tsv \\
-        -l ${taxonomic_level}
+        -l ${taxonomic_level} \\
+        -r ${kmer_len}
 
-    # generate header to be used when adjusting the bracken report and abundances for unclassified reads
+
+    # generate header to be used when adjusting the bracken report and abundances for unclassified reads in ADJUST_BRACKEN
     paste <(echo "meta.id") <(head -n 1 ${meta.id}_${taxonomic_level}_bracken_abundances_unsorted.tsv) | tr \$'\\t' ',' > bracken_abundances_header.csv
 
     cat <<-END_VERSIONS > versions.yml

diff --git a/nextflow.config b/nextflow.config
@@ -16,6 +16,7 @@ params {
     kraken2_db                 = null
     bracken_db                 = null
     taxonomic_level            = 'S'
+    kmer_len                   = 100
     top_n                      = 5
 
     // Boilerplate options

diff --git a/nextflow_schema.json b/nextflow_schema.json
@@ -73,6 +73,13 @@
                     "description": "Requested taxonomic level for BRACKEN",
                     "default": "S"
                 },
+                "kmer_len": {
+                    "type": "integer",
+                    "errorMessage": "kmer_len must be provided as one of: 50, 75, 100, 150, 200, 250, or 300",
+                    "enum": [50, 75, 100, 150, 200, 250, 300],
+                    "description": "Requested kmer length for the BRACKEN distribution file used during abundance estimation",
+                    "default": 100
+                },
                 "top_n": {
                     "type": "integer",
                     "default": 5,

diff --git a/workflows/speciesabundance.nf b/workflows/speciesabundance.nf
@@ -80,6 +80,7 @@ workflow SpAnce {
     bracken_database = select_bracken_database(params.bracken_db)
     ch_taxonomic_level = Channel.value(params.taxonomic_level)
     ch_top_n = Channel.value(params.top_n)
+    ch_kmer_len = Channel.value(params.kmer_len)
 
     FASTP_TRIM (
         input
@@ -95,7 +96,8 @@ workflow SpAnce {
     BRACKEN (
         KRAKEN2.out.report_txt,
         bracken_database,
-        ch_taxonomic_level
+        ch_taxonomic_level,
+        ch_kmer_len
     )
     ch_versions = ch_versions.mix(BRACKEN.out.versions)