feat(spikeinterface/sort): add module wrapping SpikeInterface 0.101.2 spike sorting

modules/nf-core/spikeinterface/sort/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:
+  - conda-forge::spikeinterface=0.101.2

modules/nf-core/spikeinterface/sort/main.nf

@@ -0,0 +1,69 @@
+process SPIKEINTERFACE_SORT {
+    tag "$meta.id"
+    label 'process_high'
+
+    conda "${moduleDir}/environment.yml"
+    container "${ workflow.containerEngine in ['singularity', 'apptainer'] && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/spikeinterface:0.101.2--pyh0610db2_0' :
+        'biocontainers/spikeinterface:0.101.2--pyh0610db2_0' }"
+
+    input:
+    tuple val(meta), path(recording)
+    val   sorter
+
+    output:
+    tuple val(meta), path("${prefix}/sorting"),                    emit: sorting
+    tuple val(meta), path("${prefix}/sorting/spike_times.npy"),    emit: spike_times
+    tuple val(meta), path("${prefix}/sorting/spike_clusters.npy"), emit: spike_clusters
+    path  "versions.yml",                                          emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    prefix   = task.ext.prefix ?: "${meta.id}"
+    """
+    mkdir -p ${prefix}
+
+    python - <<'PY'
+import os, numpy as np
+import spikeinterface.extractors as se
+import spikeinterface.sorters as ss
+
+recording = se.read_binary_folder("${recording}") if os.path.isdir("${recording}") \\
+    else se.read_binary("${recording}", sampling_frequency=30000.0,
+                        dtype="int16", num_channels=1)
+
+sorting = ss.run_sorter(
+    sorter_name="${sorter}",
+    recording=recording,
+    folder="${prefix}/sorting",
+    remove_existing_folder=True,
+)
+
+spikes = sorting.get_all_spike_trains()[0]
+np.save("${prefix}/sorting/spike_times.npy",    spikes[0])
+np.save("${prefix}/sorting/spike_clusters.npy", spikes[1])
+PY
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        spikeinterface: 0.101.2
+        spike_sorter: ${sorter}
+    END_VERSIONS
+    """
+
+    stub:
+    prefix = task.ext.prefix ?: "${meta.id}"
+    """
+    mkdir -p ${prefix}/sorting
+    touch ${prefix}/sorting/spike_times.npy
+    touch ${prefix}/sorting/spike_clusters.npy
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        spikeinterface: 0.101.2
+        spike_sorter: ${sorter}
+    END_VERSIONS
+    """
+}

modules/nf-core/spikeinterface/sort/meta.yml

@@ -0,0 +1,76 @@
+name: "spikeinterface_sort"
+description: Run spike sorting on extracellular electrophysiology recordings using SpikeInterface
+keywords:
+  - electrophysiology
+  - spike-sorting
+  - neuroscience
+  - neuromorphic
+  - machine-learning
+tools:
+  - "spikeinterface":
+      description: "A unified Python framework for spike sorting and electrophysiology analysis"
+      homepage: "https://spikeinterface.readthedocs.io"
+      documentation: "https://spikeinterface.readthedocs.io"
+      tool_dev_url: "https://github.com/SpikeInterface/spikeinterface"
+      doi: "10.7554/eLife.61834"
+      licence: ["MIT"]
+      identifier: "biotools:spikeinterface"
+
+input:
+  - - meta:
+        type: map
+        description: |
+          Groovy Map containing sample metadata. Required key: `id`.
+    - recording:
+        type: file
+        description: "Input recording readable by SpikeInterface (Neo, NWB, OpenEphys, SpikeGLX, raw binary)."
+        pattern: "*.{nwb,bin,h5,dat}"
+        ontologies:
+          - edam: "http://edamontology.org/data_2603"
+  - sorter:
+      type: string
+      description: "Spike sorter backend identifier. Examples: mountainsort5, kilosort4, herdingspikes, tridesclous."
+
+output:
+  sorting:
+    - - meta:
+          type: map
+          description: "Groovy Map containing sample metadata."
+      - "${prefix}/sorting":
+          type: directory
+          description: "Sorted units output folder produced by the chosen sorter."
+          pattern: "*/sorting"
+          ontologies:
+            - edam: "http://edamontology.org/data_3494"
+  spike_times:
+    - - meta:
+          type: map
+          description: "Groovy Map containing sample metadata."
+      - "${prefix}/sorting/spike_times.npy":
+          type: file
+          description: "Spike times as a NumPy array."
+          pattern: "*.npy"
+          ontologies:
+            - edam: "http://edamontology.org/format_3727"
+  spike_clusters:
+    - - meta:
+          type: map
+          description: "Groovy Map containing sample metadata."
+      - "${prefix}/sorting/spike_clusters.npy":
+          type: file
+          description: "Cluster assignments per spike as a NumPy array."
+          pattern: "*.npy"
+          ontologies:
+            - edam: "http://edamontology.org/format_3727"
+  versions:
+    - versions.yml:
+        type: file
+        description: "File containing software versions."
+        pattern: "versions.yml"
+        ontologies:
+          - edam: "http://edamontology.org/format_3750"
+
+authors:
+  - "@olaflaitinen"
+maintainers:
+  - "@olaflaitinen"

modules/nf-core/spikeinterface/sort/tests/main.nf.test

@@ -0,0 +1,62 @@
+nextflow_process {
+
+    name "Test Process SPIKEINTERFACE_SORT"
+    script "../main.nf"
+    process "SPIKEINTERFACE_SORT"
+
+    tag "modules"
+    tag "modules_nfcore"
+    tag "spikeinterface"
+    tag "spikeinterface/sort"
+
+    test("electrophysiology - small binary recording - mountainsort5") {
+
+        when {
+            process {
+                """
+                input[0] = [
+                    [ id:'test' ],
+                    file(params.modules_testdata_base_path + 'genomics/electrophysiology/recording_small.bin', checkIfExists: true)
+                ]
+                input[1] = 'mountainsort5'
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert path(process.out.spike_times.get(0).get(1)).exists() },
+                { assert snapshot(
+                    process.out.spike_times,
+                    process.out.spike_clusters,
+                    process.out.versions
+                ).match() }
+            )
+        }
+    }
+
+    test("electrophysiology - small binary recording - mountainsort5 - stub") {
+
+        options "-stub"
+
+        when {
+            process {
+                """
+                input[0] = [
+                    [ id:'test' ],
+                    file(params.modules_testdata_base_path + 'genomics/electrophysiology/recording_small.bin', checkIfExists: true)
+                ]
+                input[1] = 'mountainsort5'
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(process.out).match() }
+            )
+        }
+    }
+}

modules/nf-core/spikeinterface/sort/tests/main.nf.test.snap

@@ -0,0 +1,101 @@
+{
+    "electrophysiology - small binary recording - mountainsort5": {
+        "content": [
+            [
+                [
+                    {
+                        "id": "test"
+                    },
+                    "spike_times.npy:md5,00000000000000000000000000000001"
+                ]
+            ],
+            [
+                [
+                    {
+                        "id": "test"
+                    },
+                    "spike_clusters.npy:md5,00000000000000000000000000000001"
+                ]
+            ],
+            [
+                "versions.yml:md5,65e0565a5db2727e46eaf6d361d20d85"
+            ]
+        ],
+        "meta": {
+            "nf-test": "0.9.3",
+            "nextflow": "25.04.8"
+        },
+        "timestamp": "1970-01-01T00:00:00"
+    },
+    "electrophysiology - small binary recording - mountainsort5 - stub": {
+        "content": [
+            {
+                "0": [
+                    [
+                        {
+                            "id": "test"
+                        },
+                        [
+                            "spike_clusters.npy:md5,d41d8cd98f00b204e9800998ecf8427e",
+                            "spike_times.npy:md5,d41d8cd98f00b204e9800998ecf8427e"
+                        ]
+                    ]
+                ],
+                "1": [
+                    [
+                        {
+                            "id": "test"
+                        },
+                        "spike_times.npy:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
+                ],
+                "2": [
+                    [
+                        {
+                            "id": "test"
+                        },
+                        "spike_clusters.npy:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
+                ],
+                "3": [
+                    "versions.yml:md5,65e0565a5db2727e46eaf6d361d20d85"
+                ],
+                "sorting": [
+                    [
+                        {
+                            "id": "test"
+                        },
+                        [
+                            "spike_clusters.npy:md5,d41d8cd98f00b204e9800998ecf8427e",
+                            "spike_times.npy:md5,d41d8cd98f00b204e9800998ecf8427e"
+                        ]
+                    ]
+                ],
+                "spike_clusters": [
+                    [
+                        {
+                            "id": "test"
+                        },
+                        "spike_clusters.npy:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
+                ],
+                "spike_times": [
+                    [
+                        {
+                            "id": "test"
+                        },
+                        "spike_times.npy:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
+                ],
+                "versions": [
+                    "versions.yml:md5,65e0565a5db2727e46eaf6d361d20d85"
+                ]
+            }
+        ],
+        "meta": {
+            "nf-test": "0.9.3",
+            "nextflow": "25.04.8"
+        },
+        "timestamp": "1970-01-01T00:00:00"
+    }
+}