Deacon index set operations

modules/nf-core/deacon/index/main.nf

@@ -1,5 +1,6 @@
 process DEACON_INDEX {
-    tag "$fasta"
+    tag "fasta - ${meta.id} - ${subcommand ?: 'build'}"
+
     label 'process_low'
 
     conda "${moduleDir}/environment.yml"
@@ -8,10 +9,12 @@ process DEACON_INDEX {
         'biocontainers/deacon:0.13.2--h7ef3eeb_0' }"
 
     input:
-    tuple val(meta), path(fasta)
+    tuple val(meta), path(reference)        // reference fasta file (for build) or idx index (for set operations)
+    val(subcommand)                         // build, union, intersect or diff
+    tuple val(meta_set), path(set_genomes)  // one (or more for union) idx indexes (or fasta files for diff)
 
     output:
-    tuple val(meta), path("*.idx"), emit: index
+    tuple val(meta_out), path("*.idx"), emit: index
     tuple val("${task.process}"), val('deacon'), eval('deacon --version | head -n1 | sed "s/deacon //g"'), emit: versions_deacon, topic: versions
 
     when:
@@ -20,17 +23,72 @@ process DEACON_INDEX {
     script:
     def args = task.ext.args ?: ''
     def prefix = task.ext.prefix ?: "${meta.id}"
+
+    // default to build if no subcommand is provided
+    subcommand = subcommand ?: "build"
+
+    // validate provided subcommand
+    def valid_subcommands = ['build', 'union', 'intersect', 'diff']
+    if (!(subcommand in valid_subcommands)) {
+        error "Invalid deacon index subcommand: '${subcommand}'. Must be one of: ${valid_subcommands.join(', ')}, or empty to default to `build`"
+    }
+
+    // create new meta map that stores utilised deacon index subcommand
+    meta_out = meta + [operation: subcommand]
+
+    // validate inputs based on subcommand
+    if (subcommand == 'build') {
+        if (set_genomes) {
+            error "Subcommand 'build' does not accept set_genomes input. Received: ${set_genomes}"
+        }
+    }
+    else {
+        // union, intersect, or diff require set_genomes input
+        if (!set_genomes) {
+            error "Subcommand '${subcommand}' requires set_genomes input (idx or fasta files)"
+        }
+
+        // create list of files (in case of a single file input)
+        def files_to_check = [set_genomes].flatten()
+
+        // union and intersect accept 1 or more idx files
+        if (subcommand == 'union' || subcommand == 'intersect') {
+            def non_idx = files_to_check.findAll { file -> !file.name.endsWith('.idx') }
+            if (non_idx) {
+                error "Subcommand '${subcommand}' requires .idx files. Found non-index files: ${non_idx.collect { it.name }.join(', ')}"
+            }
+        }
+
+        // diff accepts exactly 1 idx or fasta file
+        else if (subcommand == 'diff') {
+            def valid_exts = ['.idx', '.fa', '.fasta', '.fna']
+            def invalid_files = files_to_check.findAll { file ->
+                    !valid_exts.any { ext -> file.name.endsWith(ext) }
+            }
+            if (invalid_files) {
+                error "Subcommand 'diff' requires .idx or fasta files (.fa, .fasta, .fna). Found invalid files: ${invalid_files.collect { it.name }.join(', ')}"
+            }
+
+            if (files_to_check.size() > 1) {
+                error "Subcommand 'diff' expects a single file for set operation. Received ${files_to_check.size()} files."
+            }
+        }
+    }
+
     """
     deacon \\
         index \\
-        build \\
-        --threads ${task.cpus} \\
-        $args \\
-        $fasta > ${prefix}.idx
+        ${subcommand} \\
+        ${subcommand == 'build' ? "--threads ${task.cpus}" : ""} \\
+        ${args} \\
+        ${subcommand == 'build' ? "${reference}" : "${reference} ${set_genomes}"} \\
+        > ${prefix}.idx
     """
 
     stub:
-    def prefix = task.ext.prefix ?: "${fasta.baseName}"
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    subcommand = subcommand ?: 'build'
+    meta_out = meta + [operation: subcommand]
     """
     touch ${prefix}.idx
     """

modules/nf-core/deacon/index/meta.yml

@@ -17,24 +17,52 @@ tools:
       doi: "10.1093/bioinformatics/btae004"
       licence: ["MIT"]
       identifier: "biotools:deacon"
-
 input:
   - - meta:
         type: map
         description: |
           Groovy Map containing reference information.
           e.g. [ id:'test', single_end:false ]
-    - fasta:
+    - reference:
         type: file
-        description: Input genome fasta file
-        pattern: "*.{fasta,fasta.gz,fas,fas.gz,fa,fa.gz,fna,fna.gz}"
+        description: |
+          Main input file for deacon index
+          - For 'build': fasta genome file
+          - For 'union'/'intersect'/'diff': .idx index file
+        pattern: "*.{fasta,fasta.gz,fas,fas.gz,fa,fa.gz,fna,fna.gz,idx}"
+        ontologies:
+          - edam: "http://edamontology.org/data_2044" # Sequence
+          - edam: "http://edamontology.org/format_1929" # FASTA
+          - edam: "http://edamontology.org/data_3210" # Genome index
+  - subcommand:
+      type: string
+      description: |
+        Deacon index subcommand to execute: 'build' (default), 'union', 'intersect', or 'diff'.
+        - build: Index minimizers contained within a fastx file
+        - union: Combine multiple minimizer indexes (A ∪ B…)
+        - intersect: Intersect multiple minimizer indexes (A ∩ B…)
+        - diff: SSubtract minimizers in one index from another (A - B)
+      pattern: "build|union|intersect|diff"
+  - - meta_set:
+        type: map
+        description: |
+          Groovy Map containing metadata for set operation genome index/fasta files.
+          e.g. [ id:'genome' ]
+    - set_genomes:
+        type: file
+        description: |
+          Optional input for set operations (union/intersect/diff).
+          - For union/intersect: One or more .idx files to combine/intersect with the main reference index
+          - For diff: A single .idx or fasta file to subtract from the main reference index
+          - Not required for build
+        pattern: "*.{idx,fasta,fasta.gz,fas,fas.gz,fa,fa.gz,fna,fna.gz}"
         ontologies:
+          - edam: "http://edamontology.org/data_3210" # Genome index
           - edam: "http://edamontology.org/data_2044" # Sequence
           - edam: "http://edamontology.org/format_1929" # FASTA
-
 output:
   index:
-    - - meta:
+    - - meta_out:
           type: map
           description: |
             Groovy Map containing reference information.
@@ -55,7 +83,6 @@ output:
       - deacon --version | head -n1 | sed "s/deacon //g":
           type: eval
           description: The expression to obtain the version of the tool
-
 topics:
   versions:
     - - ${task.process}:
@@ -71,3 +98,4 @@ authors:
   - "@mberacochea"
 maintainers:
   - "@mberacochea"
+  - "@pmoris"

modules/nf-core/deacon/index/tests/main.nf.test

@@ -18,6 +18,8 @@ nextflow_process {
                     [ id:'test'],
                     file(params.modules_testdata_base_path + 'genomics/sarscov2/genome/genome.fasta', checkIfExists: true)
                 ]
+                input[1] = ''       // should default to 'build'
+                input[2] = [[:], []]  // empty tuple for optional set operation genome input
                 """
             }
         }
@@ -44,6 +46,8 @@ nextflow_process {
                     [ id:'test'],
                     file(params.modules_testdata_base_path + 'genomics/sarscov2/genome/genome.fasta.gz', checkIfExists: true)
                 ]
+                input[1] = ''       // should default to 'build'
+                input[2] = [[:], []]  // empty tuple for optional set operation genome input
                 """
             }
         }
@@ -71,6 +75,8 @@ nextflow_process {
                     [ id:'test'],
                     file(params.modules_testdata_base_path + 'genomics/sarscov2/genome/genome.fasta', checkIfExists: true)
                 ]
+                input[1] = ''       // should default to 'build'
+                input[2] = [[:], []]  // empty tuple for optional set operation genome input
                 """
             }
         }

modules/nf-core/deacon/index/tests/main.nf.test.snap

@@ -4,7 +4,8 @@
             [
                 [
                     {
-                        "id": "test"
+                        "id": "test",
+                        "operation": "build"
                     },
                     "test.idx:md5,84e4985c91800686db9c9dca28fabd1a"
                 ]
@@ -19,21 +20,22 @@
                 ]
             }
         ],
+        "timestamp": "2026-02-13T17:04:37.800900709",
         "meta": {
-            "nf-test": "0.9.3",
+            "nf-test": "0.9.4",
             "nextflow": "25.10.2"
-        },
-        "timestamp": "2026-02-12T12:49:12.213473021"
+        }
     },
     "index sarscov2 - fasta - stub": {
         "content": [
             {
                 "0": [
                     [
                         {
-                            "id": "test"
+                            "id": "test",
+                            "operation": "build"
                         },
-                        "genome.idx:md5,d41d8cd98f00b204e9800998ecf8427e"
+                        "test.idx:md5,d41d8cd98f00b204e9800998ecf8427e"
                     ]
                 ],
                 "1": [
@@ -46,9 +48,10 @@
                 "index": [
                     [
                         {
-                            "id": "test"
+                            "id": "test",
+                            "operation": "build"
                         },
-                        "genome.idx:md5,d41d8cd98f00b204e9800998ecf8427e"
+                        "test.idx:md5,d41d8cd98f00b204e9800998ecf8427e"
                     ]
                 ],
                 "versions_deacon": [
@@ -69,19 +72,20 @@
                 ]
             }
         ],
+        "timestamp": "2026-02-13T17:31:45.177093319",
         "meta": {
-            "nf-test": "0.9.3",
+            "nf-test": "0.9.4",
             "nextflow": "25.10.2"
-        },
-        "timestamp": "2026-02-12T12:49:26.132617722"
+        }
     },
     "index sarscov2 - fasta gzipped": {
         "content": [
             {
                 "0": [
                     [
                         {
-                            "id": "test"
+                            "id": "test",
+                            "operation": "build"
                         },
                         "test.idx:md5,84e4985c91800686db9c9dca28fabd1a"
                     ]
@@ -96,7 +100,8 @@
                 "index": [
                     [
                         {
-                            "id": "test"
+                            "id": "test",
+                            "operation": "build"
                         },
                         "test.idx:md5,84e4985c91800686db9c9dca28fabd1a"
                     ]
@@ -119,10 +124,10 @@
                 ]
             }
         ],
+        "timestamp": "2026-02-13T17:04:46.61203129",
         "meta": {
-            "nf-test": "0.9.3",
+            "nf-test": "0.9.4",
             "nextflow": "25.10.2"
-        },
-        "timestamp": "2026-02-12T12:49:19.142528704"
+        }
     }
 }

modules/nf-core/deacon/index_diff/environment.yml

@@ -0,0 +1,7 @@
+---
+# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/environment-schema.json
+channels:
+  - conda-forge
+  - bioconda
+dependencies:
+  - bioconda::deacon=0.13.2

modules/nf-core/deacon/index_diff/main.nf

@@ -0,0 +1,50 @@
+process DEACON_INDEX_DIFF {
+    tag "fasta"
+
+    label 'process_low'
+
+    conda "${moduleDir}/environment.yml"
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/deacon:0.13.2--h7ef3eeb_1':
+        'biocontainers/deacon:0.13.2--h7ef3eeb_0' }"
+
+    input:
+    tuple val(meta_index), path(index)      // deacon .idx index file
+    tuple val(meta_genome), path(genome)    // a single fasta or .idx file to subtract from the main index
+
+    output:
+    tuple val(meta_index), path("*.idx"), emit: index
+    tuple val("${task.process}"), val('deacon'), eval('deacon --version | head -n1 | sed "s/deacon //g"'), emit: versions_deacon, topic: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta_index.id}"
+    // TODO: we could optionally construct a new prefix + meta_out.id based on the two input meta.ids, but just using the original id of the main index file seems more straightforward since it can always be modified in a custom config
+    // def prefix = task.ext.prefix ?: "${meta_index.id}_diff_${meta_genome.id}"
+    // def meta_out = meta_index + [ id: "${prefix}" ]
+    // def meta_out = meta.clone()
+    // meta_out.id = "${prefix}"
+
+    """
+    deacon \\
+        index \\
+        diff \\
+        ${args} \\
+        ${index} \\
+        ${genome} \\
+        > ${prefix}.idx
+    """
+
+    stub:
+    def prefix = task.ext.prefix ?: "${meta_index.id}"
+    // TODO: we could optionally construct a new meta_out.id based on the two input meta.ids instead
+    // def prefix = task.ext.prefix ?: "${meta_index.id}_diff_${meta_genome.id}"
+    // def meta_out = meta.clone()
+    // meta_out.id = "${prefix}"
+    """
+    touch ${prefix}.idx
+    """
+}