nf-core · heylf · Jun 2, 2025 · May 17, 2025 · May 17, 2025 · May 17, 2025
diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml
@@ -82,7 +82,22 @@ jobs:
       - name: Clean up Disk space
         uses: jlumbroso/free-disk-space@54081f138730dfa15788a46383842cd2f914a1be # v1.3.1
 
-      - name: "Run pipeline with test data ${{ matrix.NXF_VER }} | ${{ matrix.test_name }} | ${{ matrix.profile }}"
+      - name: "Run pipeline in image mode with test data ${{ matrix.NXF_VER }} | ${{ matrix.test_name }} | ${{ matrix.profile }}"
         continue-on-error: ${{ matrix.NXF_VER == 'latest-everything' }}
         run: |
-          nextflow run ${GITHUB_WORKSPACE} -profile ${{ matrix.test_name }},${{ matrix.profile }} --outdir ./results
+          nextflow run ${GITHUB_WORKSPACE} -profile ${{ matrix.test_name }},${{ matrix.profile }} -stub --outdir ./results --mode image
+
+      - name: "Run pipeline in coordinate mode with test data ${{ matrix.NXF_VER }} | ${{ matrix.test_name }} | ${{ matrix.profile }}"
+        continue-on-error: ${{ matrix.NXF_VER == 'latest-everything' }}
+        run: |
+          nextflow run ${GITHUB_WORKSPACE} -profile ${{ matrix.test_name }},${{ matrix.profile }} -stub --outdir ./results --mode coordinate
+
+      - name: "Run pipeline in preview mode with test data ${{ matrix.NXF_VER }} | ${{ matrix.test_name }} | ${{ matrix.profile }}"
+        continue-on-error: ${{ matrix.NXF_VER == 'latest-everything' }}
+        run: |
+          nextflow run ${GITHUB_WORKSPACE} -profile ${{ matrix.test_name }},${{ matrix.profile }} -stub --outdir ./results --mode preview
+
+      - name: "Run pipeline in segfree mode with test data ${{ matrix.NXF_VER }} | ${{ matrix.test_name }} | ${{ matrix.profile }}"
+        continue-on-error: ${{ matrix.NXF_VER == 'latest-everything' }}
+        run: |
+          nextflow run ${GITHUB_WORKSPACE} -profile ${{ matrix.test_name }},${{ matrix.profile }} -stub --outdir ./results --mode segfree
diff --git a/README.md b/README.md
@@ -26,8 +26,6 @@
 <!-- TODO nf-core: Include a figure that guides the user through the major workflow steps. Many nf-core
      workflows use the "tube map" design for that. See https://nf-co.re/docs/contributing/design_guidelines#examples for examples.   -->
 
-1. Present QC for raw reads ([`MultiQC`](http://multiqc.info/))
-
 ## Usage
 
 On release, automated continuous integration tests run the pipeline on a full-sized dataset on the AWS cloud infrastructure. This ensures that the pipeline runs on AWS, has sensible resource allocation defaults set to run on real-world datasets, and permits the persistent storage of results to benchmark between pipeline releases and other analysis sources. The results obtained from the full-sized test can be viewed on the [nf-core website](https://nf-co.re/spatialxe/results).
@@ -61,7 +59,7 @@ nextflow run nf-core/spatialxe \
 
 ## Run coordinate-based segmentation mode <br>
 
-`PROSEG -> BAYSOR -> XR-IMPORT_SEGMENTATION -> SPATIALDATA -> QC`
+`PROSEG -> PROSEG2BAYSOR -> XR-IMPORT_SEGMENTATION -> SPATIALDATA -> QC`
 
 ```bash
 nextflow run nf-core/spatialxe \
@@ -71,6 +69,30 @@ nextflow run nf-core/spatialxe \
    --mode coordinate
 ```
 
+## Run segfree mode <br>
+
+`BAYSOR_SEGFREE`
+
+```bash
+nextflow run nf-core/spatialxe \
+   -profile <docker/singularity/.../institute> \
+   --input samplesheet.csv \
+   --outdir <OUTDIR> \
+   --mode segfree
+```
+
+## Run preview mode <br>
+
+`BAYSOR_PREVIEW`
+
+```bash
+nextflow run nf-core/spatialxe \
+   -profile <docker/singularity/.../institute> \
+   --input samplesheet.csv \
+   --outdir <OUTDIR> \
+   --mode preview
+```
+
 > [!WARNING]
 > Please provide pipeline parameters via the CLI or Nextflow `-params-file` option. Custom config files including those provided by the `-c` Nextflow option can be used to provide any configuration _**except for parameters**_; see [docs](https://nf-co.re/docs/usage/getting_started/configuration#custom-configuration-files).
 

diff --git a/conf/modules.config b/conf/modules.config
@@ -27,6 +27,13 @@ process {
         ]
     }
 
+    withName: XENIUMRANGER_RESEGMENT {
+        publishDir = [
+            path: "${params.outdir}/xeniumranger/resegment",
+            mode: params.publish_dir_mode
+        ]
+    }
+
     withName: XENIUMRANGER_IMPORT_SEGMENTATION {
         publishDir = [
             path: "${params.outdir}/xeniumranger/import_segementation",

diff --git a/conf/test.config b/conf/test.config
@@ -12,19 +12,14 @@
 
 process {
 
-    withLabel: process_high {
-        resourceLimits = [
-        cpus: 8,
-        memory: '8.GB',
-        time: '1.h'
-        ]
-    }
+    resourceLimits = [
+        cpus: 4,
+        memory: '15.GB',
+        time: '2.h'
+    ]
 
-    withName: CELLPOSE {
-        resourceLimits = [
-            cpus: 4,
-            memory: '8.GB'
-        ]
+    withName: UNTAR {
+        ext.prefix = "test_bundle"
     }
 }
 

diff --git a/docs/images/spatialxe-metromap.png b/docs/images/spatialxe-metromap.png
diff --git a/docs/images/spatialxe-metromap.svg b/docs/images/spatialxe-metromap.svg
diff --git a/docs/usage.md b/docs/usage.md
@@ -40,10 +40,10 @@ This runs the default image mode:<br>
 
 ```bash
 nextflow run nf-core/spatialxe \
+        -profile <docker/singularity/...>
         --input ./samplesheet.csv \
         --outdir ./results \
-        --mode image \
-        -profile <docker/singularity/...>
+        --mode image
 ```
 
 #### Coordinate-based (transcripts-based) segmentation mode
@@ -53,10 +53,10 @@ This runs the default coordinate mode:<br>
 
 ```bash
 nextflow run nf-core/spatialxe \
+        -profile <docker/singularity/...>
         --input ./samplesheet.csv \
         --outdir ./results \
-        --mode coordinate \
-        -profile <docker/singularity/...>
+        --mode coordinate
 ```
 
 ### Image-based Segmentation mode (--mode image): <br>
@@ -73,26 +73,26 @@ nextflow run nf-core/spatialxe \
 
 #### Run Segmentation with the methods methods mentioned above : <br>
 
-eg: To run proseg segmentation use the `coordinate` mode and the `proseg` segmentation method
+eg: To run proseg segmentation use the `coordinate` mode and the `proseg` segmentation method (--method)
 
 ```bash
 nextflow run nf-core/spatialxe \
+        -profile <docker/singularity/...>
         --input ./samplesheet.csv \
         --outdir ./results \
         --mode coordinate \
-        --segmentation proseg \
-        -profile <docker/singularity/...>
+        --method proseg
 ```
 
-eg: To run cellpose segmentation use the `image` mode and the `cellpose` segmentation method
+eg: To run cellpose segmentation use the `image` mode and the `cellpose` segmentation method (--method)
 
 ```bash
 nextflow run nf-core/spatialxe \
+        -profile <docker/singularity/...>
         --input ./samplesheet.csv \
         --outdir ./results \
         --mode image \
-        --segmentation cellpose \
-        -profile <docker/singularity/...>
+        --method cellpose
 ```
 
 This will launch the pipeline with the `docker` configuration profile. See below for more information about profiles.

diff --git a/modules.json b/modules.json
@@ -11,11 +11,6 @@
                         "installed_by": ["modules"],
                         "patch": "modules/nf-core/cellpose/cellpose.diff"
                     },
-                    "gunzip": {
-                        "branch": "master",
-                        "git_sha": "81880787133db07d9b4c1febd152c090eb8325dc",
-                        "installed_by": ["modules"]
-                    },
                     "multiqc": {
                         "branch": "master",
                         "git_sha": "7b50cb7be890e4b28cffb82e438cc6a8d7805d3f",
@@ -24,7 +19,8 @@
                     "untar": {
                         "branch": "master",
                         "git_sha": "05954dab2ff481bcb999f24455da29a5828af08d",
-                        "installed_by": ["modules"]
+                        "installed_by": ["modules"],
+                        "patch": "modules/nf-core/untar/untar.diff"
                     },
                     "unzip": {
                         "branch": "master",

diff --git a/modules/local/baysor/create_dataset/templates/create_dataset.py b/modules/local/baysor/create_dataset/templates/create_dataset.py
@@ -1,4 +1,4 @@
-#!/usr/bin/env python
+#!/usr/bin/env python3
 
 import csv
 import random
@@ -41,18 +41,16 @@ def generate_dataset(
 
             # randomize csv rows to write
             for row in reader:
-                if random.random() < sample_fraction:
+                if random.random() < float(sample_fraction):
                     writer.writerow(row)
 
-        # print(f"Sampled data written to {sampled_transcripts}")
-
         return None
 
     @staticmethod
-    def generate_version_yml(version: str) -> None:
+    def generate_version_yml() -> None:
         with open("versions.yml", "w") as yml:
             yml.write('"${task.process}":\\n')
-            yml.write(f'Baysor-Preview Create Dataset: {version}"\\n')
+            yml.write("Baysor-Preview Create Dataset: 0.7.1'\\n")
 
         return None
 
@@ -64,17 +62,16 @@ def main() -> None:
     transcripts: str = "${transcripts}"
     sample_fraction: float = "${sample_fraction}"
     sampled_transcripts: str = "sampled_transcripts.csv"
-    version: str = "${VERSION}"
 
     # generate dataset
-    BaysorPreview.generate_dataset(
+    BaysorPreview.generate_dataset (
         transcripts=transcripts,
         sampled_transcripts=sampled_transcripts,
         sample_fraction=sample_fraction
     )
 
     # generate versions.yml
-    BaysorPreview.generate_version_yml(version=version)
+    BaysorPreview.generate_version_yml()
 
     return None
 

diff --git a/modules/local/baysor/run/main.nf b/modules/local/baysor/run/main.nf
@@ -58,10 +58,12 @@ process BAYSOR_RUN {
     """
     touch segmentation.csv
     touch segmentation_polygons_2d.json
+    touch segmentation_polygons_3d.json
     touch segmentation_log.log
     touch segmentation_counts.loom
     touch segmentation_cell_stats.csv
     touch segmentation_params.dump.toml
+    touch segmentation_run.html
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":

diff --git a/modules/local/spatialconverter/parquet_to_csv/main.nf b/modules/local/spatialconverter/parquet_to_csv/main.nf
@@ -4,26 +4,27 @@ process PARQUET_TO_CSV {
 
     container "ghcr.io/scverse/spatialdata:spatialdata0.3.0_spatialdata-io0.1.7_spatialdata-plot0.2.9"
 
-    if (workflow.profile.tokenize(',').intersect(['conda', 'mamba']).size() >= 1) {
-        error "PARQUET_TO_CSV module does not support Conda. Please use Docker / Singularity / Podman instead."
-    }
-
     input:
     tuple val(meta), path(transcripts)
+    val(extension)
 
     output:
-    tuple val(meta), path("*.csv")   , emit: transcripts_csv
-    path("versions.yml")             , emit: versions
+    tuple val(meta), path("*.csv*"), emit: transcripts_csv
+    path("versions.yml")           , emit: versions
 
     when:
     task.ext.when == null || task.ext.when
 
     script:
+    if (workflow.profile.tokenize(',').intersect(['conda', 'mamba']).size() >= 1) {
+        error "PARQUET_TO_CSV module does not support Conda. Please use Docker / Singularity / Podman instead."
+    }
+
     template 'parquet_to_csv.py'
 
     stub:
     """
-    touch ${transcripts}
+    touch ${transcripts}.csv
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":
         spatialconverter: "${task.version}"

diff --git a/modules/local/spatialconverter/parquet_to_csv/templates/parquet_to_csv.py b/modules/local/spatialconverter/parquet_to_csv/templates/parquet_to_csv.py
@@ -1,17 +1,38 @@
 #!/usr/bin/env python
 
 import pandas as pd
+from pathlib import Path
+
+
+def convert_parquet (
+        transcripts: Path,
+        extension: str = '.csv'
+    ) -> None:
+
+    df = pd.read_parquet(transcripts, engine = 'pyarrow')
+
+    if extension == ".gz":
+        output = transcripts.replace(".parquet", ".csv.gz")
+        df.to_csv(f"{output}", compression='gzip', index=False)
+    else:
+        output = transcripts.replace(".parquet", ".csv")
+        df.to_csv(f"{output}", index=False)
+
+    return None
+
 
 if __name__ == '__main__':
-    print("[START]")
-    df = pd.read_parquet("${transcripts}")
-    output="${transcripts}".replace(".parquet",".csv")
-    df.to_csv(f"{output}", index=False)
+
+    transcripts: str = "${transcripts}"
+    extension: str = "${extension}"
+
+    # generate transcripts.csv(.gz)
+    convert_parquet (
+        transcripts=transcripts,
+        extension=extension
+    )
 
     #Output version information
     with open("versions.yml", "w") as f:
         f.write('"${task.process}":\\n')
         f.write(f'spatialconverter: "v0.0.1"\\n')
-
-    print("[FINISH]")
-
diff --git a/modules/local/spatialdata/merge/main.nf b/modules/local/spatialdata/merge/main.nf
@@ -6,11 +6,11 @@ process SPATIALDATA_MERGE {
 
     input:
     tuple val(meta), path(ref_bundle, stageAs: "*")
-    tuple val(meta), path(add_bundle, stageAs: "*")
+    path(add_bundle, stageAs: "*")
 
     output:
-    tuple val(meta), path("spatialdata_spatialxe")    , emit: spatialxe_bundle
-    path "versions.yml"                               , emit: versions
+    tuple val(meta), path("spatialdata_spatialxe"), emit: spatialxe_bundle
+    path("versions.yml")                          , emit: versions
 
     when:
     task.ext.when == null || task.ext.when
@@ -22,6 +22,7 @@ process SPATIALDATA_MERGE {
     }
 
     def args = task.ext.args ?: ''
+
     template 'merge.py'
 
     stub: