outdated dev

README.md

@@ -12,7 +12,9 @@
 
 ## Introduction
 
-**nf-core/spatialxe** is a bioinformatics best-practice processing and quality control pipeline for Xenium data. **The pipeline is currently under developement and no completed yet!**
+**nf-core/spatialxe** is a bioinformatics best-practice processing and quality control pipeline for Xenium data. **The pipeline is currently under developement and not completed yet!**. The current plan for the pipeline implementation is shown in the metromap below. Please note that the pipeline steps and methods might change as we move forward in the development cycle.
+
+![nf-core/spatialxe-metromap](docs/images/spatialxe-metromap.png)
 
 The pipeline is built using [Nextflow](https://www.nextflow.io), a workflow tool to run tasks across multiple compute infrastructures in a very portable manner. It uses Docker/Singularity containers making installation trivial and results highly reproducible. The [Nextflow DSL2](https://www.nextflow.io/docs/latest/dsl2.html) implementation of this pipeline uses one container per process which makes it much easier to maintain and update software dependencies. Where possible, these processes have been submitted to and installed from [nf-core/modules](https://github.com/nf-core/modules) in order to make them available to all nf-core pipelines, and to everyone within the Nextflow community!
 
@@ -22,8 +24,6 @@ On release, automated continuous integration tests run the pipeline on a full-si
 
 ## Pipeline summary
 
-
-
 ## Quick Start
 
 1. Install [`Nextflow`](https://www.nextflow.io/docs/latest/getstarted.html#installation) (`>=22.10.1`)

modules.json

@@ -5,6 +5,11 @@
         "https://github.com/nf-core/modules.git": {
             "modules": {
                 "nf-core": {
+                    "cellpose": {
+                        "branch": "master",
+                        "git_sha": "666652151335353eef2fcd58880bcef5bc2928e1",
+                        "installed_by": ["modules"]
+                    },
                     "custom/dumpsoftwareversions": {
                         "branch": "master",
                         "git_sha": "c8e35eb2055c099720a75538d1b8adb3fb5a464c",
@@ -24,6 +29,11 @@
                         "branch": "master",
                         "git_sha": "b5e1891a88491d8731b5e68e22bd907726caec4a",
                         "installed_by": ["modules"]
+                    },
+                    "xeniumranger/resegment": {
+                        "branch": "master",
+                        "git_sha": "b5e1891a88491d8731b5e68e22bd907726caec4a",
+                        "installed_by": ["modules"]
                     }
                 }
             }

modules/local/proseg/main.nf

@@ -0,0 +1,82 @@
+process PROSEG {
+    tag "$meta.id"
+    label 'process_high'
+
+    container "nf-core/proseg:1.1.8"
+
+    input:
+    tuple val(meta), path(transcripts)
+
+    output:
+    tuple val(meta), path("cell-polygons.geojson.gz"), emit: cell_polygons_2d
+    path("expected-counts.csv.gz"), emit: expected_counts
+    path("cell-metadata.csv.gz"), emit: cell_metadata
+    path("transcript-metadata.csv.gz"), emit: transcript_metadata
+    path("gene-metadata.csv.gz"), emit: gene_metadata
+    path("rates.csv.gz"), emit: rates
+    path("cell-polygons-layers.geojson.gz"), emit:  cell_polygons_layers
+    path("cell-hulls.geojson.gz"), emit: cell_hulls
+    path("versions.yml"), emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    // Exit if running this module with -profile conda / -profile mamba
+    if (workflow.profile.tokenize(',').intersect(['conda', 'mamba']).size() >= 1) {
+        error "PROSEG module does not support Conda. Please use Docker / Singularity / Podman instead."
+    }
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    def platform = preset ? "${params.preset}" : ""
+
+    // check for preset values
+    if (!(platform in ['xenium', 'cosmx', 'merscope'])) {
+        error "${platform} is an invalid platform (preset) type. Please specify xenium, cosmx, or merscope"
+    }
+
+    """
+    proseg \\
+        --${preset} \\
+        ${transcripts} \\
+        --nthreads ${task.cpus} \\
+        --output-expected-counts expected-counts.csv.gz \\
+        --output-cell-metadata cell-metadata.csv.gz \\
+        --output-transcript-metadata transcript-metadata.csv.gz \\
+        --output-gene-metadata gene-metadata.csv.gz \\
+        --output-rates rates.csv.gz \\
+        --output-cell-polygons cell-polygons.geojson.gz \\
+        --output-cell-polygon-layers cell-polygons-layers.geojson.gz \\
+        --output-cell-hulls cell-hulls.geojson.gz \\
+        ${args}
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        proseg: \$(proseg --version | sed 's/proseg //')
+    END_VERSIONS
+    """
+
+    stub:
+    // Exit if running this module with -profile conda / -profile mamba
+    if (workflow.profile.tokenize(',').intersect(['conda', 'mamba']).size() >= 1) {
+        error "PROSEG module does not support Conda. Please use Docker / Singularity / Podman instead."
+    }
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+
+    """
+    touch expected-counts.csv.gz
+    touch cell-metadata.csv.gz
+    touch transcript-metadata.csv.gz
+    touch gene-metadata.csv.gz
+    touch rates.csv.gz
+    touch cell-polygons.geojson.gz
+    touch cell-polygons-layers.geojson.gz
+    touch cell-hulls.geojson.gz
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        proseg: \$(proseg --version | sed 's/proseg //')
+    END_VERSIONS
+    """
+}

modules/local/proseg/meta.yml

@@ -0,0 +1,76 @@
+name: "proseg"
+description: Probabilistic cell segmentation for in situ spatial transcriptomics
+keywords:
+  - segmentation
+  - cell segmentation
+  - spatialomics
+  - probabilistic segmentation
+  - in situ spatial transcriptomics
+tools:
+  - "proseg":
+      description: "Proseg (probabilistic segmentation) is a cell segmentation method for in situ spatial transcriptomics. Xenium, CosMx, and MERSCOPE platforms are currently supported."
+      homepage: "https://github.com/dcjones/proseg/tree/main"
+      documentation: "https://github.com/dcjones/proseg/blob/main/README.md"
+      tool_dev_url: "https://github.com/dcjones/proseg"
+      doi: ""
+      licence: ["GNU Public License"]
+
+input:
+  - - meta:
+        type: map
+        description: |
+          Groovy Map containing run information
+          e.g. `[ id:'run_id']`
+    - transcripts:
+        type: file
+        description: |
+          File containing the transcript position
+        pattern: "transcripts.csv.gz"
+
+output:
+  - - meta:
+        type: map
+        description: |
+          Groovy Map containing run information
+          e.g. `[ id:'run_id']`
+    - cell_polygons:
+        type: file
+        description: 2D polygons for each cell in GeoJSON format. These are flattened from 3D
+        pattern: "cell-polygons.geojson.gz"
+  - - expected_counts:
+        type: file
+        description: cell-by-gene count matrix
+        pattern: "expected-counts.csv.gz"
+  - - cell_metadata:
+        type: file
+        description: Cell centroids, volume, and other information
+        pattern: "cell-metadata.csv.gz"
+  - - transcript_metadata:
+        type: file
+        description: Transcript ids, genes, revised positions, assignment probability
+        pattern: "transcript-metadata.csv.gz"
+  - - gene_metadata:
+        type: file
+        description: Per-gene summary statistics
+        pattern: "gene-metadata.csv.gz"
+  - - rates:
+        type: file
+        description: Cell-by-gene Poisson rate parameters
+        pattern: "rates.csv.gz"
+  - - cell_polygon_layers:
+        type: file
+        description: A separate, non-overlapping cell polygon for each z-layer, preserving 3D segmentation
+        pattern: "cell-polygons-layers.geojson.gz"
+  - - cell_hulls:
+        type: file
+        description: Convex hulls around assigned transcripts
+        pattern: "cell-hulls.geojson.gz"
+  - - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+
+authors:
+  - "@khersameesh24"
+maintainers:
+  - "@khersameesh24"

modules/local/proseg/preprocess/main.nf

@@ -0,0 +1,53 @@
+process PROSEG2BAYSOR {
+    tag "$meta.id"
+    label 'process_high'
+
+    container "nf-core/proseg:1.1.8"
+
+    input:
+    path(transcript_metadata)
+    path(cell_polygons)
+
+    output:
+    path("xr-transcript-metadata.csv"), emit: xr_metadata
+    path("xr-cell-polygons.geojson"), emit: xr_polygons
+
+    script:
+    // Exit if running this module with -profile conda / -profile mamba
+    if (workflow.profile.tokenize(',').intersect(['conda', 'mamba']).size() >= 1) {
+        error "PROSEG2BAYSOR (preprocess) module does not support Conda. Please use Docker / Singularity / Podman instead."
+    }
+
+    """
+    proseg-to-baysor  \
+        ${transcript_metadata} \
+        ${cell_polygons} \
+        --output-transcript-metadata xr-transcript-metadata.csv \
+        --output-cell-polygons xr-cell-polygons.geojson
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        proseg: \$(proseg --version | sed 's/proseg //')
+    END_VERSIONS
+
+    """
+
+    stub:
+    // Exit if running this module with -profile conda / -profile mamba
+    if (workflow.profile.tokenize(',').intersect(['conda', 'mamba']).size() >= 1) {
+        error "PROSEG module does not support Conda. Please use Docker / Singularity / Podman instead."
+    }
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+
+    """
+    touch xr-transcript-metadata.csv
+    touch xr-cell-polygons.geojson
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        proseg: \$(proseg --version | sed 's/proseg //')
+    END_VERSIONS
+    """
+}
+

modules/local/proseg/tests/main.nf.test

@@ -0,0 +1,77 @@
+nextflow_process {
+
+    name "Test Process PROSEG"
+    script "../main.nf"
+    process "PROSEG"
+
+    tag "modules"
+    tag "modules_nfcore"
+    tag "proseg"
+    tag "segmentation"
+    tag "cell_segmentation"
+
+
+    setup {
+            run("UNZIP") {
+                script "modules/nf-core/unzip/main.nf"
+                process {
+                    """
+                    input[0] = [[], file('https://raw.githubusercontent.com/nf-core/test-datasets/spatialxe/Xenium_Prime_Mouse_Ileum_tiny_outs.zip', checkIfExists: true)]
+                    """
+                }
+            }
+    }
+
+    test("proseg - transcripts.csv") {
+
+        when {
+            process {
+                """
+                input[0] = Channel.of([
+                            [id: "test_run_proseg"],
+                        ]).combine(UNZIP.out.unzipped_archive.map { it[1] } + "/transcripts.csv")
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(process.out).match() },
+                { assert file(process.out.expected_counts.get(0).get(1).find { file(it).name == 'expected-counts.csv.gz' }).exists() },
+                { assert file(process.out.cell_metadata.get(0).get(1).find { file(it).name == 'cell-metadata.csv.gz' }).exists() },
+                { assert file(process.out.transcript_metadata.get(0).get(1).find { file(it).name == 'transcript-metadata.csv.gz' }).exists() },
+                { assert file(process.out.gene_metadata.get(0).get(1).find { file(it).name == 'gene-metadata.csv.gz' }).exists() },
+                { assert file(process.out.rates.get(0).get(1).find { file(it).name == 'rates.csv.gz' }).exists() },
+                { assert file(process.out.cell_polygons.get(0).get(1).find { file(it).name == 'cell-polygons.geojson.gz' }).exists() },
+                { assert file(process.out.cell_polygons_layers.get(0).get(1).find { file(it).name == 'cell-polygons-layers.geojson.gz' }).exists() },
+                { assert file(process.out.cell-hulls.get(0).get(1).find { file(it).name == 'cell-hulls.geojson.gz' }).exists() },
+            )
+        }
+
+    }
+
+    test("proseg stub") {
+
+        options "-stub"
+
+        when {
+            process {
+                """
+                input[0] = Channel.of([
+                            [id: "test_run_proseg"],
+                        ]).combine(UNZIP.out.unzipped_archive.map { it[1] } + "/transcripts.csv")
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(process.out).match() }
+            )
+        }
+
+    }
+
+}

modules/local/proseg/tests/tags.yml

@@ -0,0 +1,2 @@
+proseg:
+  - "modules/nf-core/proseg/**"