Window size

CHANGELOG.md

@@ -5,6 +5,20 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [[1.3.0](https://github.com/sanger-tol/sequencecomposition/releases/tag/1.3.0)] – –
 
+### Enhancements & fixes
+
+- New `--window_size` parameter to select the size of the windows to compute statistics on.
+  It replaces the `--window_size_info` parameter, which only affected output naming.
+- Better validation of the `--selected_fw_output` parameter.
+
+### Parameters
+
+| Old parameter        | New parameter   |
+| -------------------- | --------------- |
+| `--window_size_info` | `--window_size` |
+
+> **NB:** Parameter has been **updated** if both old and new parameter information is present. </br> **NB:** Parameter has been **added** if just the new parameter information is present. </br> **NB:** Parameter has been **removed** if new parameter information isn't present.
+
 ## [[1.2.1](https://github.com/sanger-tol/sequencecomposition/releases/tag/1.2.1)] – Easter Bells (patch 1) – [2026-05-15]
 
 ### Enhancements & fixes

conf/modules.config

@@ -12,7 +12,17 @@
 
 process {
 
+    withName: "FASTAWINDOWS" {
+        ext.args = { "-w ${ params.window_size }" }
+    }
+
     withName: BGZIPTABIX {
+        ext.prefix = {
+            def ws = params.window_size as int
+            def ws_label = (ws % 1000 == 0) ? "${ws.intdiv(1000)}k" : "${ws}bp"
+            return "${meta.id}.${ws_label}"
+        }
+
         ext.args2  = { "--preset bed" + (column_numbers ? "" : " --skip-lines 1") }
         publishDir = [
             path: { "${meta.outdir}/${meta.analysis_subdir}" },

nextflow.config

@@ -12,9 +12,10 @@ params {
     // Input options
     input                        = null
     fasta                        = null
-    window_size_info             = ".1k"
-    // keep in sync with the `--window_size` parameter of fasta_windows
+
+    // Output options
     selected_fw_output           = "${projectDir}/assets/fasta_windows.csv"
+    window_size                  = 1000
 
     // Boilerplate options
     outdir                       = 'results'

nextflow_schema.json

@@ -10,7 +10,7 @@
             "type": "object",
             "fa_icon": "fas fa-terminal",
             "description": "Define where the pipeline should find input data and save output data.",
-            "required": ["outdir", "window_size_info", "selected_fw_output"],
+            "required": ["outdir", "window_size", "selected_fw_output"],
             "properties": {
                 "fasta": {
                     "type": "string",
@@ -41,16 +41,18 @@
                 "selected_fw_output": {
                     "type": "string",
                     "default": "${projectDir}/assets/fasta_windows.csv",
+                    "format": "file-path",
+                    "exists": true,
                     "description": "Path to comma-separated file containing information about the statistics to select from fasta_windows' output.",
                     "hidden": true,
                     "fa_icon": "fas fa-barcode"
                 },
-                "window_size_info": {
-                    "type": "string",
-                    "default": ".1k",
-                    "hidden": true,
-                    "description": "String to add to all file names generated by the pipeline. This is meant to reflect the size of the windows fasta_windows is computing statistics on.",
-                    "fa_icon": "fas fa-arrows-alt-h"
+                "window_size": {
+                    "type": "integer",
+                    "default": 1000,
+                    "description": "Window size (in base pairs) used to partition sequences for calculating per-window statistics",
+                    "fa_icon": "fas fa-chart-bar",
+                    "minimum": 1
                 },
                 "email": {
                     "type": "string",

subworkflows/local/fasta_windows.nf

@@ -10,7 +10,6 @@ workflow FASTA_WINDOWS {
     take:
     fasta_fai // [file: /path/to/genome.fa, file: /path/to/genome.fai]
     output_selection // file: /path/to/fasta_windows.csv
-    window_size_info // value, used to build meta.id and name files
 
     main:
 
@@ -40,7 +39,7 @@ workflow FASTA_WINDOWS {
     ch_freq_bed_input = FASTAWINDOWS.out.freq
         .combine(ch_config.freq)
         .multiMap { meta, freq_file_tsv, column_number, outdir, filename ->
-            path: [meta + [id: meta.id + "." + filename + window_size_info, analysis_subdir: outdir], freq_file_tsv, meta.max_length]
+            path: [meta + [id: meta.id + "." + filename, analysis_subdir: outdir], freq_file_tsv, meta.max_length]
             column_number: ["1-3,${column_number}", 1, "bedGraph"]
         }
 
@@ -58,7 +57,7 @@ workflow FASTA_WINDOWS {
         .mix(FASTAWINDOWS.out.dinuc.combine(ch_config.dinuc))
         .mix(FASTAWINDOWS.out.trinuc.combine(ch_config.trinuc))
         .mix(FASTAWINDOWS.out.tetranuc.combine(ch_config.tetranuc))
-        .map { meta, path, outdir, filename -> [meta + [id: meta.id + "." + filename + window_size_info, analysis_subdir: outdir], path] }
+        .map { meta, path, outdir, filename -> [meta + [id: meta.id + "." + filename, analysis_subdir: outdir], path] }
 
     // Compress the BED file
     ch_tsv_with_seq_length = ch_tsv.map { meta, tsv -> [meta, tsv, meta.max_length] }

workflows/sequencecomposition.nf

@@ -48,7 +48,6 @@ workflow SEQUENCECOMPOSITION {
     FASTA_WINDOWS(
         PARAMS_CHECK.out.fasta_fai,
         file(params.selected_fw_output, checkExists: true),
-        params.window_size_info,
     )
 
     //