Add module: dorado/basecaller

.gitignore

@@ -15,3 +15,18 @@ test_output/
 tests/data/
 work/
 .github/CODEOWNERS-tmp
+<<<<<<< HEAD
+=======
+
+# Local sandbox directories (dev/test artifacts, not for PR)
+**/sandbox/
+
+# Dorado pre-downloaded models — too large for git (use tests/data/models/ locally)
+modules/nf-core/dorado/basecaller/tests/data/models/
+>>>>>>> 5ea7c105e (Add module: dorado/basecaller)
+
+# Local sandbox directories (dev/test artifacts, not for PR)
+**/sandbox/
+
+# Dorado pre-downloaded models — too large for git (use tests/data/models/ locally)
+modules/nf-core/dorado/basecaller/tests/data/models/

modules/nf-core/dorado/basecaller/Dockerfile

@@ -0,0 +1,8 @@
+FROM nanoporetech/dorado:shac8f356489fa8b44b31beba841b84d2879de2088e
+
+LABEL version="1.4.0" \
+      maintainer="@sahuno" \
+      description="Oxford Nanopore dorado basecaller v1.4.0 — for nf-core/modules" \
+      org.opencontainers.image.version="1.4.0" \
+      org.opencontainers.image.source="https://github.com/nanoporetech/dorado" \
+      org.opencontainers.image.licenses="Oxford Nanopore Technologies PLC. Public License Version 1.0"

modules/nf-core/dorado/basecaller/environment.yml

@@ -0,0 +1,11 @@
+---
+# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/environment-schema.json
+# NOTE: dorado is not available on bioconda or conda-forge (ONTPL licence).
+# This environment.yml is a placeholder. The module uses the Docker/Singularity
+# container specified in main.nf (nanoporetech/dorado:shac8f..., v1.4.0).
+# Track 2 TODO: submit dorado to bioconda to enable conda-based deployment.
+channels:
+  - conda-forge
+  - bioconda
+dependencies:
+  - samtools=1.21

modules/nf-core/dorado/basecaller/main.nf

@@ -0,0 +1,54 @@
+process DORADO_BASECALLER {
+    tag "$meta.id"
+    label 'process_gpu'
+
+    // dorado is not on bioconda (ONTPL licence). Using
+    // Docker Hub image directly. SHA tag pins to v1.4.0; a semver tag is tracked in
+    // nanoporetech/dorado#1584. Same pattern as nf-core/parabricks modules.
+    conda null
+    container "docker.io/nanoporetech/dorado:shac8f356489fa8b44b31beba841b84d2879de2088e"
+
+    input:
+    tuple val(meta), path(pod5)                         // pod5 file or directory of pod5 files
+    val(model)                                          // combined model string e.g. "sup,5mCG_5hmCG@latest", "hac@v5.0.0"
+    tuple val(meta2), path(models_dir)                  // optional pre-downloaded models directory; pass [[],[]] to auto-download
+    tuple val(meta3), path(reference), path(fai)        // optional reference FASTA for alignment; pass [[],[],[]] to skip
+
+    output:
+    tuple val(meta), path("*.bam")      , emit: bam
+    tuple val(meta), path("*_summary.tsv"), emit: summary , optional: true
+    tuple val("${task.process}"), val('dorado'), eval("dorado --version 2>&1 | head -1 | sed 's/^//'"), emit: versions_dorado, topic: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args         = task.ext.args ?: ''
+    def prefix       = task.ext.prefix ?: "${meta.id}"
+    def models_arg   = models_dir ? "--models-directory ${models_dir}" : "--models-directory ."
+    def ref_arg      = reference  ? "--reference ${reference}"          : ""
+
+    """
+    dorado \\
+        basecaller \\
+        ${args} \\
+        --device cuda:all \\
+        ${models_arg} \\
+        ${ref_arg} \\
+        ${model} \\
+        ${pod5} \\
+        > ${prefix}.bam
+    """
+
+    stub:
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    """
+    touch ${prefix}.bam
+    touch ${prefix}_summary.tsv
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        dorado: 1.4.0
+    END_VERSIONS
+    """
+}

modules/nf-core/dorado/basecaller/meta.yml

@@ -0,0 +1,133 @@
+name: dorado_basecaller
+description: |
+  Basecall Oxford Nanopore pod5 files with automatic model selection, optional
+  modified base calling (e.g. 5mCG_5hmCG, 5mC, m6A), and optional alignment
+  to a reference genome using the dorado basecaller.
+keywords:
+  - basecalling
+  - ont
+  - long-read
+  - methylation
+  - modified-bases
+  - pod5
+  - nanopore
+tools:
+  - "dorado":
+      description: Oxford Nanopore's basecaller supporting automatic model selection,
+        modified base calling, and integrated alignment.
+      homepage: https://github.com/nanoporetech/dorado
+      documentation: https://software-docs.nanoporetech.com/dorado/latest/
+      tool_dev_url: https://github.com/nanoporetech/dorado
+      licence:
+        - "Oxford Nanopore Technologies PLC. Public License Version 1.0"
+      identifier: ""
+input:
+  - - meta:
+        type: map
+        description: |
+          Groovy Map containing sample information
+          e.g. `[ id:'test', single_end:false ]`
+    - pod5:
+        type: file
+        description: |
+          A single pod5 file or a directory of pod5 files to basecall.
+          Use --recursive in task.ext.args to scan directories recursively.
+        pattern: "*.pod5"
+        ontologies: []
+  - model:
+      type: string
+      description: |
+        Combined model string for automatic model resolution. Use the format
+        "{speed},{mod}@{version}" to basecall with modification calling in a
+        single argument, e.g. "sup,5mCG_5hmCG@latest", "hac,5mCG_5hmCG@v5.0.0".
+        For basecalling only (no mod calls) use "{speed}@{version}" e.g.
+        "sup@latest", "hac@v5.0.0". Can also be a path to an existing model
+        directory. Models are auto-downloaded if not found in models_dir.
+  - - meta2:
+        type: map
+        description: |
+          Groovy Map containing models directory information
+          e.g. `[ id:'dorado_models' ]`
+    - models_dir:
+        type: directory
+        description: |
+          Optional directory containing pre-downloaded dorado models.
+          If not provided (pass [[],[]]), models are downloaded automatically
+          into the task work directory. Pre-downloading is strongly recommended
+          for HPC environments without internet access on compute nodes.
+        pattern: "*/"
+        ontologies: []
+  - - meta3:
+        type: map
+        description: |
+          Groovy Map containing reference genome information
+          e.g. `[ id:'hg38' ]`
+    - reference:
+        type: file
+        description: |
+          Optional reference FASTA for integrated alignment. If provided, dorado
+          aligns basecalled reads and outputs a mapped BAM. Pass [[],[],[]] to
+          produce an unmapped BAM.
+        pattern: "*.{fa,fasta,fa.gz,fasta.gz}"
+        ontologies: []
+    - fai:
+        type: file
+        description: |
+          FASTA index (.fai) for the reference. Required when reference is provided.
+        pattern: "*.fai"
+        ontologies: []
+output:
+  bam:
+    - - meta:
+          type: map
+          description: |
+            Groovy Map containing sample information
+            e.g. `[ id:'test', single_end:false ]`
+      - "*.bam":
+          type: file
+          description: |
+            BAM file containing basecalled reads with base quality scores and
+            modification tags (MM/ML) when modified base calling is enabled.
+            Output sort order is SO:unknown (dorado does not sort).
+            Pipe to SAMTOOLS_SORT + SAMTOOLS_INDEX for coordinate-sorted, indexed BAMs.
+            Unmapped if no reference provided; mapped (unsorted) if reference provided.
+          pattern: "*.bam"
+          ontologies: []
+  summary:
+    - - meta:
+          type: map
+          description: |
+            Groovy Map containing sample information
+            e.g. `[ id:'test', single_end:false ]`
+      - "*_summary.tsv":
+          type: file
+          description: Per-read summary TSV with alignment statistics. Present when
+            --emit-summary is set in task.ext.args.
+          pattern: "*_summary.tsv"
+          ontologies:
+            - edam: http://edamontology.org/format_3475
+  versions_dorado:
+    - - ${task.process}:
+          type: string
+          description: The name of the process
+      - dorado:
+          type: string
+          description: The name of the tool
+      - dorado --version 2>&1 | head -1 | sed 's/^//':
+          type: eval
+          description: The expression to obtain the version of the tool
+topics:
+  versions:
+    - - ${task.process}:
+          type: string
+          description: The name of the process
+      - dorado:
+          type: string
+          description: The name of the tool
+      - dorado --version 2>&1 | head -1 | sed 's/^//':
+          type: eval
+          description: The expression to obtain the version of the tool
+authors:
+  - "@sahuno"
+maintainers:
+  - "@sahuno"

modules/nf-core/dorado/basecaller/tests/main.nf.test

@@ -0,0 +1,152 @@
+nextflow_process {
+
+    name "Test Process DORADO_BASECALLER"
+    script "../main.nf"
+    process "DORADO_BASECALLER"
+
+    tag "modules"
+    tag "modules_nfcore"
+    tag "dorado"
+    tag "dorado/basecaller"
+
+    // -------------------------------------------------------------------------
+    // Stub tests — run in CI without GPU or real basecalling
+    // -------------------------------------------------------------------------
+
+    test("homo sapiens - GIAB HG002 pod5, sup,5mCG_5hmCG@latest, no models_dir, no reference - stub") {
+
+        options "-stub"
+
+        when {
+            params {
+                module_args = ''
+            }
+            process {
+                """
+                input[0] = [
+                    [ id: 'HG002' ],
+                    file(params.modules_testdata_base_path + 'genomics/homo_sapiens/nanopore/pod5/HG002_PAW70337_giab_10reads.pod5',
+                         checkIfExists: true)
+                ]
+                input[1] = "sup,5mCG_5hmCG@latest"
+                input[2] = [[], []]
+                input[3] = [[], [], []]
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(process.out).match() }
+            )
+        }
+    }
+
+    test("homo sapiens - GIAB HG002 pod5, sup,5mCG_5hmCG@latest, no models_dir, with reference - stub") {
+
+        options "-stub"
+
+        when {
+            params {
+                module_args = '--mm2-opts "-Y"'
+            }
+            process {
+                """
+                input[0] = [
+                    [ id: 'HG002_aligned' ],
+                    file(params.modules_testdata_base_path + 'genomics/homo_sapiens/nanopore/pod5/HG002_PAW70337_giab_10reads.pod5',
+                         checkIfExists: true)
+                ]
+                input[1] = "sup,5mCG_5hmCG@latest"
+                input[2] = [[], []]
+                input[3] = [
+                    [ id: 'genome' ],
+                    file(params.modules_testdata_base_path + 'genomics/homo_sapiens/genome/genome.fasta',
+                         checkIfExists: true),
+                    file(params.modules_testdata_base_path + 'genomics/homo_sapiens/genome/genome.fasta.fai',
+                         checkIfExists: true)
+                ]
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(process.out).match() }
+            )
+        }
+    }
+
+    // -------------------------------------------------------------------------
+    // Real GPU tests — require --tag "gpu" and a GPU node
+    // Run via SLURM: nf-test test ... --profile singularity,gpu --tag gpu
+    // -------------------------------------------------------------------------
+
+    test("homo sapiens - GIAB HG002 pod5, sup,5mCG_5hmCG@latest, no models_dir, no reference") {
+
+        tag "gpu"
+
+        when {
+            params {
+                module_args = ''
+            }
+            process {
+                """
+                input[0] = [
+                    [ id: 'HG002' ],
+                    file(params.modules_testdata_base_path + 'genomics/homo_sapiens/nanopore/pod5/HG002_PAW70337_giab_10reads.pod5',
+                         checkIfExists: true)
+                ]
+                input[1] = "sup,5mCG_5hmCG@latest"
+                input[2] = [[], []]
+                input[3] = [[], [], []]
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(process.out).match() }
+            )
+        }
+    }
+
+    test("homo sapiens - GIAB HG002 pod5, sup,5mCG_5hmCG@latest, no models_dir, with reference") {
+
+        tag "gpu"
+
+        when {
+            params {
+                module_args = '--mm2-opts "-Y"'
+            }
+            process {
+                """
+                input[0] = [
+                    [ id: 'HG002_aligned' ],
+                    file(params.modules_testdata_base_path + 'genomics/homo_sapiens/nanopore/pod5/HG002_PAW70337_giab_10reads.pod5',
+                         checkIfExists: true)
+                ]
+                input[1] = "sup,5mCG_5hmCG@latest"
+                input[2] = [[], []]
+                input[3] = [
+                    [ id: 'genome' ],
+                    file(params.modules_testdata_base_path + 'genomics/homo_sapiens/genome/genome.fasta',
+                         checkIfExists: true),
+                    file(params.modules_testdata_base_path + 'genomics/homo_sapiens/genome/genome.fasta.fai',
+                         checkIfExists: true)
+                ]
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(process.out).match() }
+            )
+        }
+    }
+}