Build branch openpipeline_spatial/main with version main to openpipeline_spatial on branch main (4449aa6)

Build pipeline: openpipelines-bio.openpipeline-spatial.main-rbsrs

Source commit: 4449aa6094

Source message: Merge pull request #56 from openpipelines-bio/op_v4_1_0

Update OpenPipeline dependency to v4.1.0

CHANGELOG.md

@@ -8,10 +8,24 @@
 
 * `convert/from_h5mu_to_seurat_with_fov`: Added converter component for H5MU data to Seurat objects with spatial FOV (PR #51).
 
+## MAJOR CHANGES
+
+* Pin OpenPipeline dependency to v4.1.0 (PR #56).
+
 ## MINOR CHANGES
 
 * Pin ome-zarr to 0.13.0 to avoid a chunk shape incompatibility with zarr 3.x (PR #48).
 
+* Bump Viash to 0.9.7 (PR #57).
+
+* Bump anndata to 0.12.16 (PR #57).
+
+* Bump mudata to 0.3.8 (PR #57).
+
+* Bump scanpy to 1.11.4 (PR #57)
+
+* Testing: bump viashpy to 0.10.0 (PR #57).
+
 ## BUG FIXES
 
 * `convert/from_h5mu_to_spatialdata`: Make sure the AnnData table is properly parsed before inserting into the new SpatialData object (PR #53).

_viash.yaml

@@ -1,4 +1,4 @@
-viash_version: 0.9.4
+viash_version: 0.9.7
 source: src
 target: target
 name: openpipeline_spatial
@@ -10,7 +10,7 @@ repositories:
   - name: openpipeline
     repo: openpipeline
     type: vsh
-    tag: v4.0.3
+    tag: v4.1.0
 info:
   test_resources:
     - type: s3

src/base/requirements/anndata.yaml

@@ -1,3 +1,4 @@
 packages:
-  - anndata~=0.12.7
+  - anndata~=0.12.16
-  - awkward 
+  - awkward
+  - scipy~=1.17.1 # Exclude scipy 1.17.0 because https://github.com/scverse/anndata/issues/339

src/base/requirements/anndata_mudata.yaml

@@ -1,5 +1,5 @@
 __merge__: [/src/base/requirements/anndata.yaml, .]
 packages:
-  - mudata~=0.3.2
+  - mudata~=0.3.8
 script: |
     exec("try:\n  import zarr; from importlib.metadata import version\nexcept ModuleNotFoundError:\n  exit(0)\nelse:  assert int(version(\"zarr\").partition(\".\")[0]) > 2")

src/base/requirements/scanpy.yaml

@@ -1,2 +1,2 @@
 packages:
-  - scanpy~=1.10.4
+  - scanpy~=1.11.4

src/base/requirements/viashpy.yaml

@@ -1,2 +1,2 @@
 packages:
-  - viashpy==0.9.0
+  - viashpy==0.10.0

src/workflows/multiomics/spatial_process_samples/config.vsh.yaml

@@ -144,6 +144,15 @@ argument_groups:
         type: integer
         description: Minimum of non-zero values per protein.
 
+  - name: "Cross-modality filtering"
+    arguments:
+      - name: "--intersect_obs"
+        type: boolean_true
+        description: |
+          After per-modality filtering and multisample processing, remove observations
+          that are not present in all processed modalities so that each modality shares
+          the same set of cells.
+
   - name: "Highly variable features detection"
     arguments:
       - name: "--highly_variable_features_var_output"

src/workflows/multiomics/spatial_process_samples/main.nf

@@ -34,6 +34,7 @@ workflow run_wf {
           "prot_min_proteins_per_cell": state.prot_min_proteins_per_cell,
           "prot_max_proteins_per_cell": state.prot_max_proteins_per_cell,
           "prot_min_cells_per_protein": state.prot_min_cells_per_protein,
+          "intersect_obs": state.intersect_obs,
           "highly_variable_features_var_output": state.highly_variable_features_var_output,
           "highly_variable_features_obs_batch_key": state.highly_variable_features_obs_batch_key,
           "var_gene_names": state.var_gene_names,

target/_private/executable/filter/subset_cosmx/.config.vsh.yaml

@@ -112,7 +112,7 @@ repositories:
 - type: "vsh"
   name: "openpipeline"
   repo: "openpipeline"
-  tag: "v4.0.3"
+  tag: "v4.1.0"
 links:
   repository: "https://github.com/openpipelines-bio/openpipeline_spatial"
   docker_registry: "ghcr.io"
@@ -201,7 +201,7 @@ engines:
   - type: "python"
     user: false
     packages:
-    - "scanpy~=1.10.4"
+    - "scanpy~=1.11.4"
     - "squidpy~=1.8.1"
     upgrade: true
   test_setup:
@@ -212,7 +212,7 @@ engines:
   - type: "python"
     user: false
     packages:
-    - "viashpy==0.9.0"
+    - "viashpy==0.10.0"
     github:
     - "openpipelines-bio/core#subdirectory=packages/python/openpipeline_testutils"
     upgrade: true
@@ -226,8 +226,8 @@ build_info:
   engine: "docker|native"
   output: "target/_private/executable/filter/subset_cosmx"
   executable: "target/_private/executable/filter/subset_cosmx/subset_cosmx"
-  viash_version: "0.9.4"
+  viash_version: "0.9.7"
-  git_commit: "e087099616271bd0f11e825b7817ec14ebef62d7"
+  git_commit: "4449aa6094a686af0a5fbe99b9aaafd01ae75aff"
   git_remote: "https://github.com/openpipelines-bio/openpipeline_spatial"
 package_config:
   name: "openpipeline_spatial"
@@ -241,8 +241,8 @@ package_config:
   - type: "vsh"
     name: "openpipeline"
     repo: "openpipeline"
-    tag: "v4.0.3"
+    tag: "v4.1.0"
-  viash_version: "0.9.4"
+  viash_version: "0.9.7"
   source: "src"
   target: "target"
   config_mods:

target/_private/executable/filter/subset_cosmx/subset_cosmx

@@ -2,7 +2,7 @@
 
 # subset_cosmx main
 # 
-# This wrapper script is auto-generated by viash 0.9.4 and is thus a derivative
+# This wrapper script is auto-generated by viash 0.9.7 and is thus a derivative
 # work thereof. This software comes with ABSOLUTELY NO WARRANTY from Data
 # Intuitive.
 # 
@@ -454,13 +454,13 @@ RUN apt-get update && \
   rm -rf /var/lib/apt/lists/*
 
 RUN pip install --upgrade pip && \
-  pip install --upgrade --no-cache-dir "scanpy~=1.10.4" "squidpy~=1.8.1"
+  pip install --upgrade --no-cache-dir "scanpy~=1.11.4" "squidpy~=1.8.1"
 
 LABEL org.opencontainers.image.authors="Dorien Roosen, Weiwei Schultz"
 LABEL org.opencontainers.image.description="Companion container for running component filter subset_cosmx"
-LABEL org.opencontainers.image.created="2026-05-22T11:53:11Z"
+LABEL org.opencontainers.image.created="2026-06-01T12:50:40Z"
 LABEL org.opencontainers.image.source="https://github.com/openpipelines-bio/openpipeline_spatial"
-LABEL org.opencontainers.image.revision="e087099616271bd0f11e825b7817ec14ebef62d7"
+LABEL org.opencontainers.image.revision="4449aa6094a686af0a5fbe99b9aaafd01ae75aff"
 LABEL org.opencontainers.image.version="main"
 
 VIASHDOCKER

target/_private/nextflow/filter/subset_cosmx/.config.vsh.yaml

@@ -112,7 +112,7 @@ repositories:
 - type: "vsh"
   name: "openpipeline"
   repo: "openpipeline"
-  tag: "v4.0.3"
+  tag: "v4.1.0"
 links:
   repository: "https://github.com/openpipelines-bio/openpipeline_spatial"
   docker_registry: "ghcr.io"
@@ -201,7 +201,7 @@ engines:
   - type: "python"
     user: false
     packages:
-    - "scanpy~=1.10.4"
+    - "scanpy~=1.11.4"
     - "squidpy~=1.8.1"
     upgrade: true
   test_setup:
@@ -212,7 +212,7 @@ engines:
   - type: "python"
     user: false
     packages:
-    - "viashpy==0.9.0"
+    - "viashpy==0.10.0"
     github:
     - "openpipelines-bio/core#subdirectory=packages/python/openpipeline_testutils"
     upgrade: true
@@ -226,8 +226,8 @@ build_info:
   engine: "docker|native"
   output: "target/_private/nextflow/filter/subset_cosmx"
   executable: "target/_private/nextflow/filter/subset_cosmx/main.nf"
-  viash_version: "0.9.4"
+  viash_version: "0.9.7"
-  git_commit: "e087099616271bd0f11e825b7817ec14ebef62d7"
+  git_commit: "4449aa6094a686af0a5fbe99b9aaafd01ae75aff"
   git_remote: "https://github.com/openpipelines-bio/openpipeline_spatial"
 package_config:
   name: "openpipeline_spatial"
@@ -241,8 +241,8 @@ package_config:
   - type: "vsh"
     name: "openpipeline"
     repo: "openpipeline"
-    tag: "v4.0.3"
+    tag: "v4.1.0"
-  viash_version: "0.9.4"
+  viash_version: "0.9.7"
   source: "src"
   target: "target"
   config_mods:

target/_private/nextflow/filter/subset_cosmx/main.nf

@@ -1,6 +1,6 @@
 // subset_cosmx main
 // 
-// This wrapper script is auto-generated by viash 0.9.4 and is thus a derivative
+// This wrapper script is auto-generated by viash 0.9.7 and is thus a derivative
 // work thereof. This software comes with ABSOLUTELY NO WARRANTY from Data
 // Intuitive.
 // 
@@ -1354,47 +1354,42 @@ def readCsv(file_path) {
   def splitRegex = java.util.regex.Pattern.compile(''',(?=(?:[^"]*"[^"]*")*[^"]*$)''')
   def removeQuote = java.util.regex.Pattern.compile('''"(.*)"''')
 
-  def br = java.nio.file.Files.newBufferedReader(inputFile)
+  java.nio.file.Files.newBufferedReader(inputFile).withCloseable { br ->
+    def row = 0
+    def header = null
+    def line
 
-  def row = -1
+    while (header == null && (line = br.readLine()) != null) {
-  def header = null
+      if (!line.startsWith("#")) {
-  while (br.ready() && header == null) {
+        header = splitRegex.split(line, -1).collect { field ->
-    def line = br.readLine()
+          def m = removeQuote.matcher(field)
-    row++
+          m.find() ? m.replaceFirst('$1') : field
-    if (!line.startsWith("#")) {
-      header = splitRegex.split(line, -1).collect{field ->
-        m = removeQuote.matcher(field)
-        m.find() ? m.replaceFirst('$1') : field
-      }
-    }
-  }
-  assert header != null: "CSV file should contain a header"
-
-  while (br.ready()) {
-    def line = br.readLine()
-    row++
-    if (line == null) {
-      br.close()
-      break
-    }
-
-    if (!line.startsWith("#")) {
-      def predata = splitRegex.split(line, -1)
-      def data = predata.collect{field ->
-        if (field == "") {
-          return null
-        }
-        def m = removeQuote.matcher(field)
-        if (m.find()) {
-          return m.replaceFirst('$1')
-        } else {
-          return field
         }
       }
-      assert header.size() == data.size(): "Row $row should contain the same number as fields as the header"
+      row++
-      
+    }
-      def dataMap = [header, data].transpose().collectEntries().findAll{it.value != null}
+    assert header != null : "CSV file should contain a header"
-      output.add(dataMap)
+
+    while ((line = br.readLine()) != null) {
+      row++
+      if (!line.startsWith("#")) {
+        def predata = splitRegex.split(line, -1)
+        def data = predata.collect { field ->
+          if (field == "") {
+            return null
+          }
+          def m = removeQuote.matcher(field)
+          if (m.find()) {
+            return m.replaceFirst('$1')
+          } else {
+            return field
+          }
+        }
+        assert header.size() == data.size() : "Row $row should contain the same number as fields as the header"
+
+        def dataMap = [header, data].transpose().collectEntries().findAll { it.value != null }
+        output.add(dataMap)
+      }
     }
   }
 
@@ -1710,10 +1705,25 @@ process publishFilesProc {
   ]
     .transpose()
     .collectMany{infile, outfile ->
-      if (infile.toString() != outfile.toString()) {
+      def infileString = infile.toString()
+      def outfileString = outfile.toString()
+      if (infileString != outfileString) {
+        /* Trailing slashes are removed from both the source and destination arguments.
+           From source arguments, this is useful when a source argument may have a trailing slash
+           and specify a symbolic link to a directory. Without removing the slash, cp will dereference
+           the symbolic link. 
+           See https://www.gnu.org/software/coreutils/manual/html_node/Trailing-slashes.html#Trailing-slashes-1
+
+           For the destination path addding a trailing slash is a problem when publishing directories: 
+           it requires the destination directory to exist. This fails because we only create the parent
+           directories first.
+        */
+        def regexTrailingSlashes = ~/\/+$/
+        def infileNoTrailingSlash = infileString - regexTrailingSlashes
+        def outfileNoTrailingSlash = outfileString - regexTrailingSlashes
         [
-          "[ -d \"\$(dirname '${outfile.toString()}')\" ] || mkdir -p \"\$(dirname '${outfile.toString()}')\"",
+          "[ -d \"\$(dirname '${outfileNoTrailingSlash}')\" ] || mkdir -p \"\$(dirname '${outfileNoTrailingSlash}')\"",
-          "cp -r '${infile.toString()}' '${outfile.toString()}'"
+          "cp -a '${infileNoTrailingSlash}' '${outfileNoTrailingSlash}'"
         ]
       } else {
         // no need to copy if infile is the same as outfile
@@ -3187,7 +3197,7 @@ meta = [
       "type" : "vsh",
       "name" : "openpipeline",
       "repo" : "openpipeline",
-      "tag" : "v4.0.3"
+      "tag" : "v4.1.0"
     }
   ],
   "links" : {
@@ -3295,7 +3305,7 @@ meta = [
           "type" : "python",
           "user" : false,
           "packages" : [
-            "scanpy~=1.10.4",
+            "scanpy~=1.11.4",
             "squidpy~=1.8.1"
           ],
           "upgrade" : true
@@ -3313,7 +3323,7 @@ meta = [
           "type" : "python",
           "user" : false,
           "packages" : [
-            "viashpy==0.9.0"
+            "viashpy==0.10.0"
           ],
           "github" : [
             "openpipelines-bio/core#subdirectory=packages/python/openpipeline_testutils"
@@ -3332,8 +3342,8 @@ meta = [
     "runner" : "nextflow",
     "engine" : "docker|native",
     "output" : "/workdir/root/repo/target/_private/nextflow/filter/subset_cosmx",
-    "viash_version" : "0.9.4",
+    "viash_version" : "0.9.7",
-    "git_commit" : "e087099616271bd0f11e825b7817ec14ebef62d7",
+    "git_commit" : "4449aa6094a686af0a5fbe99b9aaafd01ae75aff",
     "git_remote" : "https://github.com/openpipelines-bio/openpipeline_spatial"
   },
   "package_config" : {
@@ -3353,10 +3363,10 @@ meta = [
         "type" : "vsh",
         "name" : "openpipeline",
         "repo" : "openpipeline",
-        "tag" : "v4.0.3"
+        "tag" : "v4.1.0"
       }
     ],
-    "viash_version" : "0.9.4",
+    "viash_version" : "0.9.7",
     "source" : "/workdir/root/repo/src",
     "target" : "/workdir/root/repo/target",
     "config_mods" : [

target/_test/executable/test_workflows/ingestion/spaceranger_mapping_test/.config.vsh.yaml

@@ -48,7 +48,7 @@ repositories:
 - type: "vsh"
   name: "openpipeline"
   repo: "openpipeline"
-  tag: "v4.0.3"
+  tag: "v4.1.0"
 links:
   repository: "https://github.com/openpipelines-bio/openpipeline_spatial"
   docker_registry: "ghcr.io"
@@ -135,10 +135,11 @@ engines:
   - type: "python"
     user: false
     packages:
-    - "anndata~=0.12.7"
+    - "anndata~=0.12.16"
     - "awkward"
-    - "mudata~=0.3.2"
+    - "scipy~=1.17.1"
-    - "viashpy==0.9.0"
+    - "mudata~=0.3.8"
+    - "viashpy==0.10.0"
     github:
     - "openpipelines-bio/core#subdirectory=packages/python/openpipeline_testutils"
     script:
@@ -156,8 +157,8 @@ build_info:
   engine: "docker|native"
   output: "target/_test/executable/test_workflows/ingestion/spaceranger_mapping_test"
   executable: "target/_test/executable/test_workflows/ingestion/spaceranger_mapping_test/spaceranger_mapping_test"
-  viash_version: "0.9.4"
+  viash_version: "0.9.7"
-  git_commit: "e087099616271bd0f11e825b7817ec14ebef62d7"
+  git_commit: "4449aa6094a686af0a5fbe99b9aaafd01ae75aff"
   git_remote: "https://github.com/openpipelines-bio/openpipeline_spatial"
 package_config:
   name: "openpipeline_spatial"
@@ -171,8 +172,8 @@ package_config:
   - type: "vsh"
     name: "openpipeline"
     repo: "openpipeline"
-    tag: "v4.0.3"
+    tag: "v4.1.0"
-  viash_version: "0.9.4"
+  viash_version: "0.9.7"
   source: "src"
   target: "target"
   config_mods:

target/_test/executable/test_workflows/ingestion/spaceranger_mapping_test/spaceranger_mapping_test

@@ -2,7 +2,7 @@
 
 # spaceranger_mapping_test main
 # 
-# This wrapper script is auto-generated by viash 0.9.4 and is thus a derivative
+# This wrapper script is auto-generated by viash 0.9.7 and is thus a derivative
 # work thereof. This software comes with ABSOLUTELY NO WARRANTY from Data
 # Intuitive.
 # 
@@ -453,15 +453,15 @@ RUN apt-get update && \
   rm -rf /var/lib/apt/lists/*
 
 RUN pip install --upgrade pip && \
-  pip install --upgrade --no-cache-dir "anndata~=0.12.7" "awkward" "mudata~=0.3.2" "viashpy==0.9.0" && \
+  pip install --upgrade --no-cache-dir "anndata~=0.12.16" "awkward" "scipy~=1.17.1" "mudata~=0.3.8" "viashpy==0.10.0" && \
   pip install --upgrade --no-cache-dir "git+https://github.com/openpipelines-bio/core#subdirectory=packages/python/openpipeline_testutils" && \
   python -c 'exec("try:\n  import zarr; from importlib.metadata import version\nexcept ModuleNotFoundError:\n  exit(0)\nelse:  assert int(version(\"zarr\").partition(\".\")[0]) > 2")'
 
 LABEL org.opencontainers.image.authors="Dorien Roosen"
 LABEL org.opencontainers.image.description="Companion container for running component test_workflows/ingestion spaceranger_mapping_test"
-LABEL org.opencontainers.image.created="2026-05-22T11:53:09Z"
+LABEL org.opencontainers.image.created="2026-06-01T12:50:39Z"
 LABEL org.opencontainers.image.source="https://github.com/openpipelines-bio/openpipeline_spatial"
-LABEL org.opencontainers.image.revision="e087099616271bd0f11e825b7817ec14ebef62d7"
+LABEL org.opencontainers.image.revision="4449aa6094a686af0a5fbe99b9aaafd01ae75aff"
 LABEL org.opencontainers.image.version="main"
 
 VIASHDOCKER

target/_test/nextflow/test_workflows/ingestion/spaceranger_mapping_test/.config.vsh.yaml

@@ -48,7 +48,7 @@ repositories:
 - type: "vsh"
   name: "openpipeline"
   repo: "openpipeline"
-  tag: "v4.0.3"
+  tag: "v4.1.0"
 links:
   repository: "https://github.com/openpipelines-bio/openpipeline_spatial"
   docker_registry: "ghcr.io"
@@ -135,10 +135,11 @@ engines:
   - type: "python"
     user: false
     packages:
-    - "anndata~=0.12.7"
+    - "anndata~=0.12.16"
     - "awkward"
-    - "mudata~=0.3.2"
+    - "scipy~=1.17.1"
-    - "viashpy==0.9.0"
+    - "mudata~=0.3.8"
+    - "viashpy==0.10.0"
     github:
     - "openpipelines-bio/core#subdirectory=packages/python/openpipeline_testutils"
     script:
@@ -156,8 +157,8 @@ build_info:
   engine: "docker|native"
   output: "target/_test/nextflow/test_workflows/ingestion/spaceranger_mapping_test"
   executable: "target/_test/nextflow/test_workflows/ingestion/spaceranger_mapping_test/main.nf"
-  viash_version: "0.9.4"
+  viash_version: "0.9.7"
-  git_commit: "e087099616271bd0f11e825b7817ec14ebef62d7"
+  git_commit: "4449aa6094a686af0a5fbe99b9aaafd01ae75aff"
   git_remote: "https://github.com/openpipelines-bio/openpipeline_spatial"
 package_config:
   name: "openpipeline_spatial"
@@ -171,8 +172,8 @@ package_config:
   - type: "vsh"
     name: "openpipeline"
     repo: "openpipeline"
-    tag: "v4.0.3"
+    tag: "v4.1.0"
-  viash_version: "0.9.4"
+  viash_version: "0.9.7"
   source: "src"
   target: "target"
   config_mods:

target/_test/nextflow/test_workflows/ingestion/spaceranger_mapping_test/main.nf

@@ -1,6 +1,6 @@
 // spaceranger_mapping_test main
 // 
-// This wrapper script is auto-generated by viash 0.9.4 and is thus a derivative
+// This wrapper script is auto-generated by viash 0.9.7 and is thus a derivative
 // work thereof. This software comes with ABSOLUTELY NO WARRANTY from Data
 // Intuitive.
 // 
@@ -1353,47 +1353,42 @@ def readCsv(file_path) {
   def splitRegex = java.util.regex.Pattern.compile(''',(?=(?:[^"]*"[^"]*")*[^"]*$)''')
   def removeQuote = java.util.regex.Pattern.compile('''"(.*)"''')
 
-  def br = java.nio.file.Files.newBufferedReader(inputFile)
+  java.nio.file.Files.newBufferedReader(inputFile).withCloseable { br ->
+    def row = 0
+    def header = null
+    def line
 
-  def row = -1
+    while (header == null && (line = br.readLine()) != null) {
-  def header = null
+      if (!line.startsWith("#")) {
-  while (br.ready() && header == null) {
+        header = splitRegex.split(line, -1).collect { field ->
-    def line = br.readLine()
+          def m = removeQuote.matcher(field)
-    row++
+          m.find() ? m.replaceFirst('$1') : field
-    if (!line.startsWith("#")) {
-      header = splitRegex.split(line, -1).collect{field ->
-        m = removeQuote.matcher(field)
-        m.find() ? m.replaceFirst('$1') : field
-      }
-    }
-  }
-  assert header != null: "CSV file should contain a header"
-
-  while (br.ready()) {
-    def line = br.readLine()
-    row++
-    if (line == null) {
-      br.close()
-      break
-    }
-
-    if (!line.startsWith("#")) {
-      def predata = splitRegex.split(line, -1)
-      def data = predata.collect{field ->
-        if (field == "") {
-          return null
-        }
-        def m = removeQuote.matcher(field)
-        if (m.find()) {
-          return m.replaceFirst('$1')
-        } else {
-          return field
         }
       }
-      assert header.size() == data.size(): "Row $row should contain the same number as fields as the header"
+      row++
-      
+    }
-      def dataMap = [header, data].transpose().collectEntries().findAll{it.value != null}
+    assert header != null : "CSV file should contain a header"
-      output.add(dataMap)
+
+    while ((line = br.readLine()) != null) {
+      row++
+      if (!line.startsWith("#")) {
+        def predata = splitRegex.split(line, -1)
+        def data = predata.collect { field ->
+          if (field == "") {
+            return null
+          }
+          def m = removeQuote.matcher(field)
+          if (m.find()) {
+            return m.replaceFirst('$1')
+          } else {
+            return field
+          }
+        }
+        assert header.size() == data.size() : "Row $row should contain the same number as fields as the header"
+
+        def dataMap = [header, data].transpose().collectEntries().findAll { it.value != null }
+        output.add(dataMap)
+      }
     }
   }
 
@@ -1709,10 +1704,25 @@ process publishFilesProc {
   ]
     .transpose()
     .collectMany{infile, outfile ->
-      if (infile.toString() != outfile.toString()) {
+      def infileString = infile.toString()
+      def outfileString = outfile.toString()
+      if (infileString != outfileString) {
+        /* Trailing slashes are removed from both the source and destination arguments.
+           From source arguments, this is useful when a source argument may have a trailing slash
+           and specify a symbolic link to a directory. Without removing the slash, cp will dereference
+           the symbolic link. 
+           See https://www.gnu.org/software/coreutils/manual/html_node/Trailing-slashes.html#Trailing-slashes-1
+
+           For the destination path addding a trailing slash is a problem when publishing directories: 
+           it requires the destination directory to exist. This fails because we only create the parent
+           directories first.
+        */
+        def regexTrailingSlashes = ~/\/+$/
+        def infileNoTrailingSlash = infileString - regexTrailingSlashes
+        def outfileNoTrailingSlash = outfileString - regexTrailingSlashes
         [
-          "[ -d \"\$(dirname '${outfile.toString()}')\" ] || mkdir -p \"\$(dirname '${outfile.toString()}')\"",
+          "[ -d \"\$(dirname '${outfileNoTrailingSlash}')\" ] || mkdir -p \"\$(dirname '${outfileNoTrailingSlash}')\"",
-          "cp -r '${infile.toString()}' '${outfile.toString()}'"
+          "cp -a '${infileNoTrailingSlash}' '${outfileNoTrailingSlash}'"
         ]
       } else {
         // no need to copy if infile is the same as outfile
@@ -3104,7 +3114,7 @@ meta = [
       "type" : "vsh",
       "name" : "openpipeline",
       "repo" : "openpipeline",
-      "tag" : "v4.0.3"
+      "tag" : "v4.1.0"
     }
   ],
   "links" : {
@@ -3209,10 +3219,11 @@ meta = [
           "type" : "python",
           "user" : false,
           "packages" : [
-            "anndata~=0.12.7",
+            "anndata~=0.12.16",
             "awkward",
-            "mudata~=0.3.2",
+            "scipy~=1.17.1",
-            "viashpy==0.9.0"
+            "mudata~=0.3.8",
+            "viashpy==0.10.0"
           ],
           "github" : [
             "openpipelines-bio/core#subdirectory=packages/python/openpipeline_testutils"
@@ -3234,8 +3245,8 @@ meta = [
     "runner" : "nextflow",
     "engine" : "docker|native",
     "output" : "/workdir/root/repo/target/_test/nextflow/test_workflows/ingestion/spaceranger_mapping_test",
-    "viash_version" : "0.9.4",
+    "viash_version" : "0.9.7",
-    "git_commit" : "e087099616271bd0f11e825b7817ec14ebef62d7",
+    "git_commit" : "4449aa6094a686af0a5fbe99b9aaafd01ae75aff",
     "git_remote" : "https://github.com/openpipelines-bio/openpipeline_spatial"
   },
   "package_config" : {
@@ -3255,10 +3266,10 @@ meta = [
         "type" : "vsh",
         "name" : "openpipeline",
         "repo" : "openpipeline",
-        "tag" : "v4.0.3"
+        "tag" : "v4.1.0"
       }
     ],
-    "viash_version" : "0.9.4",
+    "viash_version" : "0.9.7",
     "source" : "/workdir/root/repo/src",
     "target" : "/workdir/root/repo/target",
     "config_mods" : [

target/dependencies/vsh/vsh/openpipeline/v4.0.3/nextflow/feature_annotation/highly_variable_features_scanpy/subset_vars.py

@@ -1,31 +0,0 @@
-def subset_vars(adata, subset_col):
-    """Subset AnnData object on highly variable genes
-
-    Parameters
-    ----------
-    adata : AnnData
-        Annotated data object
-    subset_col : str
-        Name of the boolean column in `adata.var` that contains the information if features should be used or not
-
-    Returns
-    -------
-    AnnData
-        Copy of `adata` with subsetted features
-    """
-    if subset_col not in adata.var.columns:
-        raise ValueError(
-            f"Requested to use .var column '{subset_col}' as a selection of genes, but the column is not available."
-        )
-
-    if adata.var[subset_col].dtype == "boolean":
-        assert adata.var[subset_col].isna().sum() == 0, (
-            f"The .var column `{subset_col}` contains NaN values. Can not subset data."
-        )
-        adata.var[subset_col] = adata.var[subset_col].astype("bool")
-
-    assert adata.var[subset_col].dtype == "bool", (
-        f"Expected dtype of .var column '{subset_col}' to be `bool`, but found {adata.var[subset_col].dtype}. Can not subset data."
-    )
-
-    return adata[:, adata.var[subset_col]].copy()

target/dependencies/vsh/vsh/openpipeline/v4.1.0/_private/nextflow/workflows/multiomics/process_singlesample_base/.config.vsh.yaml

@@ -0,0 +1,567 @@
+name: "process_singlesample_base"
+namespace: "workflows/multiomics"
+version: "v4.1.0"
+authors:
+- name: "Dorien Roosen"
+  roles:
+  - "author"
+  info:
+    role: "Core Team Member"
+    links:
+      email: "dorien@data-intuitive.com"
+      github: "dorien-er"
+      linkedin: "dorien-roosen"
+    organizations:
+    - name: "Data Intuitive"
+      href: "https://www.data-intuitive.com"
+      role: "Data Scientist"
+argument_groups:
+- name: "Output State"
+  arguments:
+  - type: "string"
+    name: "--output_modality"
+    info: null
+    required: false
+    direction: "output"
+    multiple: false
+    multiple_sep: ";"
+- name: "Inputs"
+  arguments:
+  - type: "file"
+    name: "--input"
+    alternatives:
+    - "-i"
+    description: "Path to the sample."
+    info: null
+    example:
+    - "input.h5mu"
+    must_exist: true
+    create_parent: true
+    required: true
+    direction: "input"
+    multiple: false
+    multiple_sep: ";"
+  - type: "string"
+    name: "--rna_layer"
+    description: "Input layer for the gene expression modality. If not specified,\
+      \ .X is used."
+    info: null
+    required: false
+    direction: "input"
+    multiple: false
+    multiple_sep: ";"
+  - type: "string"
+    name: "--prot_layer"
+    description: "Input layer for the antibody capture modality. If not specified,\
+      \ .X is used."
+    info: null
+    required: false
+    direction: "input"
+    multiple: false
+    multiple_sep: ";"
+  - type: "string"
+    name: "--gdo_layer"
+    description: "Input layer for the guide-derived oligonucleotide (GDO) data. If\
+      \ not specified, .X is used."
+    info: null
+    required: false
+    direction: "input"
+    multiple: false
+    multiple_sep: ";"
+- name: "Outputs"
+  arguments:
+  - type: "file"
+    name: "--output"
+    description: "Destination path to the output."
+    info: null
+    example:
+    - "output.h5mu"
+    must_exist: true
+    create_parent: true
+    required: true
+    direction: "output"
+    multiple: false
+    multiple_sep: ";"
+- name: "Sample ID options"
+  description: "Options for adding the id to .obs on the MuData object. Having a sample\
+    \ \nid present in a requirement of several components for this pipeline.\n"
+  arguments:
+  - type: "boolean"
+    name: "--add_id_to_obs"
+    description: "Add the value passed with --id to .obs."
+    info: null
+    default:
+    - true
+    required: false
+    direction: "input"
+    multiple: false
+    multiple_sep: ";"
+  - type: "string"
+    name: "--add_id_obs_output"
+    description: ".Obs column to add the sample IDs to. Required and only used when\
+      \ \n--add_id_to_obs is set to 'true'\n"
+    info: null
+    default:
+    - "sample_id"
+    required: false
+    direction: "input"
+    multiple: false
+    multiple_sep: ";"
+  - type: "boolean"
+    name: "--add_id_make_observation_keys_unique"
+    description: "Join the id to the .obs index (.obs_names). \nOnly used when --add_id_to_obs\
+      \ is set to 'true'.\n"
+    info: null
+    default:
+    - true
+    required: false
+    direction: "input"
+    multiple: false
+    multiple_sep: ";"
+- name: "RNA filtering options"
+  arguments:
+  - type: "integer"
+    name: "--rna_min_counts"
+    description: "Minimum number of counts captured per cell."
+    info: null
+    example:
+    - 200
+    required: false
+    direction: "input"
+    multiple: false
+    multiple_sep: ";"
+  - type: "integer"
+    name: "--rna_max_counts"
+    description: "Maximum number of counts captured per cell."
+    info: null
+    example:
+    - 5000000
+    required: false
+    direction: "input"
+    multiple: false
+    multiple_sep: ";"
+  - type: "integer"
+    name: "--rna_min_genes_per_cell"
+    description: "Minimum of non-zero values per cell."
+    info: null
+    example:
+    - 200
+    required: false
+    direction: "input"
+    multiple: false
+    multiple_sep: ";"
+  - type: "integer"
+    name: "--rna_max_genes_per_cell"
+    description: "Maximum of non-zero values per cell."
+    info: null
+    example:
+    - 1500000
+    required: false
+    direction: "input"
+    multiple: false
+    multiple_sep: ";"
+  - type: "integer"
+    name: "--rna_min_cells_per_gene"
+    description: "Minimum of non-zero values per gene."
+    info: null
+    example:
+    - 3
+    required: false
+    direction: "input"
+    multiple: false
+    multiple_sep: ";"
+  - type: "double"
+    name: "--rna_min_fraction_mito"
+    description: "Minimum fraction of UMIs that are mitochondrial."
+    info: null
+    example:
+    - 0.0
+    required: false
+    direction: "input"
+    multiple: false
+    multiple_sep: ";"
+  - type: "double"
+    name: "--rna_max_fraction_mito"
+    description: "Maximum fraction of UMIs that are mitochondrial."
+    info: null
+    example:
+    - 0.2
+    required: false
+    direction: "input"
+    multiple: false
+    multiple_sep: ";"
+  - type: "double"
+    name: "--rna_min_fraction_ribo"
+    description: "Minimum fraction of UMIs that are mitochondrial."
+    info: null
+    example:
+    - 0.0
+    required: false
+    direction: "input"
+    multiple: false
+    multiple_sep: ";"
+  - type: "double"
+    name: "--rna_max_fraction_ribo"
+    description: "Maximum fraction of UMIs that are mitochondrial."
+    info: null
+    example:
+    - 0.2
+    required: false
+    direction: "input"
+    multiple: false
+    multiple_sep: ";"
+  - type: "boolean_true"
+    name: "--skip_scrublet_doublet_detection"
+    description: "Skip the scrublet doublet detection step."
+    info: null
+    direction: "input"
+- name: "CITE-seq filtering options"
+  arguments:
+  - type: "integer"
+    name: "--prot_min_counts"
+    description: "Minimum number of counts per cell."
+    info: null
+    example:
+    - 3
+    required: false
+    direction: "input"
+    multiple: false
+    multiple_sep: ";"
+  - type: "integer"
+    name: "--prot_max_counts"
+    description: "Minimum number of counts per cell."
+    info: null
+    example:
+    - 5000000
+    required: false
+    direction: "input"
+    multiple: false
+    multiple_sep: ";"
+  - type: "integer"
+    name: "--prot_min_proteins_per_cell"
+    description: "Minimum of non-zero values per cell."
+    info: null
+    example:
+    - 200
+    required: false
+    direction: "input"
+    multiple: false
+    multiple_sep: ";"
+  - type: "integer"
+    name: "--prot_max_proteins_per_cell"
+    description: "Maximum of non-zero values per cell."
+    info: null
+    example:
+    - 100000000
+    required: false
+    direction: "input"
+    multiple: false
+    multiple_sep: ";"
+  - type: "integer"
+    name: "--prot_min_cells_per_protein"
+    description: "Minimum of non-zero values per protein."
+    info: null
+    example:
+    - 3
+    required: false
+    direction: "input"
+    multiple: false
+    multiple_sep: ";"
+- name: "GDO filtering options"
+  arguments:
+  - type: "integer"
+    name: "--gdo_min_counts"
+    description: "Minimum number of counts per cell."
+    info: null
+    example:
+    - 3
+    required: false
+    direction: "input"
+    multiple: false
+    multiple_sep: ";"
+  - type: "integer"
+    name: "--gdo_max_counts"
+    description: "Minimum number of counts per cell."
+    info: null
+    example:
+    - 5000000
+    required: false
+    direction: "input"
+    multiple: false
+    multiple_sep: ";"
+  - type: "integer"
+    name: "--gdo_min_guides_per_cell"
+    description: "Minimum of non-zero values per cell."
+    info: null
+    example:
+    - 200
+    required: false
+    direction: "input"
+    multiple: false
+    multiple_sep: ";"
+  - type: "integer"
+    name: "--gdo_max_guides_per_cell"
+    description: "Maximum of non-zero values per cell."
+    info: null
+    example:
+    - 100000000
+    required: false
+    direction: "input"
+    multiple: false
+    multiple_sep: ";"
+  - type: "integer"
+    name: "--gdo_min_cells_per_guide"
+    description: "Minimum of non-zero values per guide."
+    info: null
+    example:
+    - 3
+    required: false
+    direction: "input"
+    multiple: false
+    multiple_sep: ";"
+- name: "Cross-modality filtering"
+  arguments:
+  - type: "boolean_true"
+    name: "--intersect_obs"
+    description: "After per-modality filtering, remove observations that are not present\n\
+      in all processed modalities so that each modality shares the same set of cells.\n"
+    info: null
+    direction: "input"
+- name: "Mitochondrial & Ribosomal Gene Detection"
+  arguments:
+  - type: "string"
+    name: "--var_gene_names"
+    description: ".var column name to be used to detect mitochondrial/ribosomal genes\
+      \ instead of .var_names (default if not set).\nGene names matching with the\
+      \ regex value from --mitochondrial_gene_regex or --ribosomal_gene_regex will\
+      \ be \nidentified as mitochondrial or ribosomal genes, respectively. \n"
+    info: null
+    example:
+    - "gene_symbol"
+    required: false
+    direction: "input"
+    multiple: false
+    multiple_sep: ";"
+  - type: "string"
+    name: "--var_name_mitochondrial_genes"
+    description: "In which .var slot to store a boolean array corresponding the mitochondrial\
+      \ genes.\n"
+    info: null
+    required: false
+    direction: "input"
+    multiple: false
+    multiple_sep: ";"
+  - type: "string"
+    name: "--obs_name_mitochondrial_fraction"
+    description: "When specified, write the fraction of counts originating from mitochondrial\
+      \ genes \n(based on --mitochondrial_gene_regex) to an .obs column with the specified\
+      \ name.\nRequires --var_name_mitochondrial_genes.\n"
+    info: null
+    required: false
+    direction: "input"
+    multiple: false
+    multiple_sep: ";"
+  - type: "string"
+    name: "--mitochondrial_gene_regex"
+    description: "Regex string that identifies mitochondrial genes from --var_gene_names.\n\
+      By default will detect human and mouse mitochondrial genes from a gene symbol.\n"
+    info: null
+    default:
+    - "^[mM][tT]-"
+    required: false
+    direction: "input"
+    multiple: false
+    multiple_sep: ";"
+  - type: "string"
+    name: "--var_name_ribosomal_genes"
+    description: "In which .var slot to store a boolean array corresponding the ribosomal\
+      \ genes.\n"
+    info: null
+    required: false
+    direction: "input"
+    multiple: false
+    multiple_sep: ";"
+  - type: "string"
+    name: "--obs_name_ribosomal_fraction"
+    description: "When specified, write the fraction of counts originating from ribosomal\
+      \ genes \n(based on --ribosomal_gene_regex) to an .obs column with the specified\
+      \ name.\nRequires --var_name_ribosomal_genes.\n"
+    info: null
+    required: false
+    direction: "input"
+    multiple: false
+    multiple_sep: ";"
+  - type: "string"
+    name: "--ribosomal_gene_regex"
+    description: "Regex string that identifies ribosomal genes from --var_gene_names.\n\
+      By default will detect human and mouse ribosomal genes from a gene symbol.\n"
+    info: null
+    default:
+    - "^[Mm]?[Rr][Pp][LlSs]"
+    required: false
+    direction: "input"
+    multiple: false
+    multiple_sep: ";"
+resources:
+- type: "nextflow_script"
+  path: "main.nf"
+  is_executable: true
+  entrypoint: "run_wf"
+- type: "file"
+  path: "utils"
+- type: "file"
+  path: "nextflow_labels.config"
+  dest: "nextflow_labels.config"
+description: "A pipeline to analyse a single multiomics sample."
+info: null
+status: "enabled"
+scope:
+  image: "private"
+  target: "private"
+dependencies:
+- name: "metadata/add_id"
+  repository:
+    type: "local"
+- name: "workflows/multiomics/split_modalities"
+  alias: "split_modalities_workflow"
+  repository:
+    type: "local"
+- name: "workflows/rna/rna_singlesample"
+  repository:
+    type: "local"
+- name: "workflows/prot/prot_singlesample"
+  repository:
+    type: "local"
+- name: "workflows/gdo/gdo_singlesample"
+  repository:
+    type: "local"
+license: "MIT"
+links:
+  repository: "https://github.com/openpipelines-bio/openpipeline"
+  docker_registry: "ghcr.io"
+runners:
+- type: "nextflow"
+  id: "nextflow"
+  directives:
+    tag: "$id"
+  auto:
+    simplifyInput: true
+    simplifyOutput: false
+    transcript: false
+    publish: false
+  config:
+    labels:
+      mem1gb: "memory = 1000000000.B"
+      mem2gb: "memory = 2000000000.B"
+      mem5gb: "memory = 5000000000.B"
+      mem10gb: "memory = 10000000000.B"
+      mem20gb: "memory = 20000000000.B"
+      mem50gb: "memory = 50000000000.B"
+      mem100gb: "memory = 100000000000.B"
+      mem200gb: "memory = 200000000000.B"
+      mem500gb: "memory = 500000000000.B"
+      mem1tb: "memory = 1000000000000.B"
+      mem2tb: "memory = 2000000000000.B"
+      mem5tb: "memory = 5000000000000.B"
+      mem10tb: "memory = 10000000000000.B"
+      mem20tb: "memory = 20000000000000.B"
+      mem50tb: "memory = 50000000000000.B"
+      mem100tb: "memory = 100000000000000.B"
+      mem200tb: "memory = 200000000000000.B"
+      mem500tb: "memory = 500000000000000.B"
+      mem1gib: "memory = 1073741824.B"
+      mem2gib: "memory = 2147483648.B"
+      mem4gib: "memory = 4294967296.B"
+      mem8gib: "memory = 8589934592.B"
+      mem16gib: "memory = 17179869184.B"
+      mem32gib: "memory = 34359738368.B"
+      mem64gib: "memory = 68719476736.B"
+      mem128gib: "memory = 137438953472.B"
+      mem256gib: "memory = 274877906944.B"
+      mem512gib: "memory = 549755813888.B"
+      mem1tib: "memory = 1099511627776.B"
+      mem2tib: "memory = 2199023255552.B"
+      mem4tib: "memory = 4398046511104.B"
+      mem8tib: "memory = 8796093022208.B"
+      mem16tib: "memory = 17592186044416.B"
+      mem32tib: "memory = 35184372088832.B"
+      mem64tib: "memory = 70368744177664.B"
+      mem128tib: "memory = 140737488355328.B"
+      mem256tib: "memory = 281474976710656.B"
+      mem512tib: "memory = 562949953421312.B"
+      cpu1: "cpus = 1"
+      cpu2: "cpus = 2"
+      cpu5: "cpus = 5"
+      cpu10: "cpus = 10"
+      cpu20: "cpus = 20"
+      cpu50: "cpus = 50"
+      cpu100: "cpus = 100"
+      cpu200: "cpus = 200"
+      cpu500: "cpus = 500"
+      cpu1000: "cpus = 1000"
+    script:
+    - "includeConfig(\"nextflow_labels.config\")"
+  debug: false
+  container: "docker"
+engines:
+- type: "native"
+  id: "native"
+build_info:
+  config: "src/workflows/multiomics/process_singlesample_base/config.vsh.yaml"
+  runner: "nextflow"
+  engine: "native"
+  output: "target/_private/nextflow/workflows/multiomics/process_singlesample_base"
+  executable: "target/_private/nextflow/workflows/multiomics/process_singlesample_base/main.nf"
+  viash_version: "0.9.7"
+  git_commit: "a6499fddaa8553874585c747370f919f4d7b729c"
+  git_remote: "https://github.com/openpipelines-bio/openpipeline"
+  dependencies:
+  - "target/nextflow/metadata/add_id"
+  - "target/_private/nextflow/workflows/multiomics/split_modalities"
+  - "target/nextflow/workflows/rna/rna_singlesample"
+  - "target/nextflow/workflows/prot/prot_singlesample"
+  - "target/nextflow/workflows/gdo/gdo_singlesample"
+package_config:
+  name: "openpipeline"
+  version: "v4.1.0"
+  summary: "Best-practice workflows for single-cell multi-omics analyses.\n"
+  description: "OpenPipelines are extensible single cell analysis pipelines for reproducible\
+    \ and large-scale single cell processing using [Viash](https://viash.io) and [Nextflow](https://www.nextflow.io/).\n\
+    \nIn terms of workflows, the following has been made available, but keep in mind\
+    \ that\nindividual tools and functionality can be executed as standalone components\
+    \ as well.\n\n  * Demultiplexing: conversion of raw sequencing data to FASTQ objects.\n\
+    \  * Ingestion: Read mapping and generating a count matrix.\n  * Single sample\
+    \ processing: cell filtering and doublet detection.\n  * Multisample processing:\
+    \ Count transformation, normalization, QC metric calulations.\n  * Integration:\
+    \ Clustering, integration and batch correction using single and multimodal methods.\n\
+    \  * Downstream analysis workflows\n"
+  info:
+    test_resources:
+    - type: "s3"
+      path: "s3://openpipelines-data"
+      dest: "resources_test"
+    nextflow_labels_ci:
+    - path: "src/workflows/utils/labels_ci.config"
+      description: "Adds the correct memory and CPU labels when running on the Viash\
+        \ Hub CI."
+  viash_version: "0.9.7"
+  source: "src"
+  target: "target"
+  config_mods:
+  - ".resources += {path: '/src/workflows/utils/labels.config', dest: 'nextflow_labels.config'}\n\
+    .runners[.type == 'nextflow'].config.script := 'includeConfig(\"nextflow_labels.config\"\
+    )'"
+  - ".engines += { type: \"native\" }"
+  - ".engines[.type == 'docker'].target_registry := 'images.viash-hub.com'"
+  - ".engines[.type == 'docker'].target_tag := 'v4.1.0'"
+  keywords:
+  - "single-cell"
+  - "multimodal"
+  license: "MIT"
+  organization: "vsh"
+  links:
+    repository: "https://github.com/openpipelines-bio/openpipeline"
+    docker_registry: "ghcr.io"
+    homepage: "https://openpipelines.bio"
+    documentation: "https://openpipelines.bio/fundamentals"
+    issue_tracker: "https://github.com/openpipelines-bio/openpipeline/issues"

target/dependencies/vsh/vsh/openpipeline/v4.1.0/_private/nextflow/workflows/multiomics/process_singlesample_base/nextflow.config

@@ -0,0 +1,126 @@
+manifest {
+  name = 'workflows/multiomics/process_singlesample_base'
+  mainScript = 'main.nf'
+  nextflowVersion = '!>=20.12.1-edge'
+  version = 'v4.1.0'
+  description = 'A pipeline to analyse a single multiomics sample.'
+  author = 'Dorien Roosen'
+}
+
+process.container = 'nextflow/bash:latest'
+
+// detect tempdir
+tempDir = java.nio.file.Paths.get(
+  System.getenv('NXF_TEMP') ?:
+    System.getenv('VIASH_TEMP') ?: 
+    System.getenv('TEMPDIR') ?: 
+    System.getenv('TMPDIR') ?: 
+    '/tmp'
+).toAbsolutePath()
+
+profiles {
+  no_publish {
+    process {
+      withName: '.*' {
+        publishDir = [
+          enabled: false
+        ]
+      }
+    }
+  }
+  mount_temp {
+    docker.temp            = tempDir
+    podman.temp            = tempDir
+    charliecloud.temp      = tempDir
+  }
+  docker {
+    docker.enabled         = true
+    // docker.userEmulation   = true
+    singularity.enabled    = false
+    podman.enabled         = false
+    shifter.enabled        = false
+    charliecloud.enabled   = false
+  }
+  singularity {
+    singularity.enabled    = true
+    singularity.autoMounts = true
+    docker.enabled         = false
+    podman.enabled         = false
+    shifter.enabled        = false
+    charliecloud.enabled   = false
+  }
+  podman {
+    podman.enabled         = true
+    docker.enabled         = false
+    singularity.enabled    = false
+    shifter.enabled        = false
+    charliecloud.enabled   = false
+  }
+  shifter {
+    shifter.enabled        = true
+    docker.enabled         = false
+    singularity.enabled    = false
+    podman.enabled         = false
+    charliecloud.enabled   = false
+  }
+  charliecloud {
+    charliecloud.enabled   = true
+    docker.enabled         = false
+    singularity.enabled    = false
+    podman.enabled         = false
+    shifter.enabled        = false
+  }
+}
+
+process{
+  withLabel: mem1gb { memory = 1000000000.B }
+  withLabel: mem2gb { memory = 2000000000.B }
+  withLabel: mem5gb { memory = 5000000000.B }
+  withLabel: mem10gb { memory = 10000000000.B }
+  withLabel: mem20gb { memory = 20000000000.B }
+  withLabel: mem50gb { memory = 50000000000.B }
+  withLabel: mem100gb { memory = 100000000000.B }
+  withLabel: mem200gb { memory = 200000000000.B }
+  withLabel: mem500gb { memory = 500000000000.B }
+  withLabel: mem1tb { memory = 1000000000000.B }
+  withLabel: mem2tb { memory = 2000000000000.B }
+  withLabel: mem5tb { memory = 5000000000000.B }
+  withLabel: mem10tb { memory = 10000000000000.B }
+  withLabel: mem20tb { memory = 20000000000000.B }
+  withLabel: mem50tb { memory = 50000000000000.B }
+  withLabel: mem100tb { memory = 100000000000000.B }
+  withLabel: mem200tb { memory = 200000000000000.B }
+  withLabel: mem500tb { memory = 500000000000000.B }
+  withLabel: mem1gib { memory = 1073741824.B }
+  withLabel: mem2gib { memory = 2147483648.B }
+  withLabel: mem4gib { memory = 4294967296.B }
+  withLabel: mem8gib { memory = 8589934592.B }
+  withLabel: mem16gib { memory = 17179869184.B }
+  withLabel: mem32gib { memory = 34359738368.B }
+  withLabel: mem64gib { memory = 68719476736.B }
+  withLabel: mem128gib { memory = 137438953472.B }
+  withLabel: mem256gib { memory = 274877906944.B }
+  withLabel: mem512gib { memory = 549755813888.B }
+  withLabel: mem1tib { memory = 1099511627776.B }
+  withLabel: mem2tib { memory = 2199023255552.B }
+  withLabel: mem4tib { memory = 4398046511104.B }
+  withLabel: mem8tib { memory = 8796093022208.B }
+  withLabel: mem16tib { memory = 17592186044416.B }
+  withLabel: mem32tib { memory = 35184372088832.B }
+  withLabel: mem64tib { memory = 70368744177664.B }
+  withLabel: mem128tib { memory = 140737488355328.B }
+  withLabel: mem256tib { memory = 281474976710656.B }
+  withLabel: mem512tib { memory = 562949953421312.B }
+  withLabel: cpu1 { cpus = 1 }
+  withLabel: cpu2 { cpus = 2 }
+  withLabel: cpu5 { cpus = 5 }
+  withLabel: cpu10 { cpus = 10 }
+  withLabel: cpu20 { cpus = 20 }
+  withLabel: cpu50 { cpus = 50 }
+  withLabel: cpu100 { cpus = 100 }
+  withLabel: cpu200 { cpus = 200 }
+  withLabel: cpu500 { cpus = 500 }
+  withLabel: cpu1000 { cpus = 1000 }
+}
+
+includeConfig("nextflow_labels.config")

target/dependencies/vsh/vsh/openpipeline/v4.1.0/_private/nextflow/workflows/multiomics/split_modalities/.config.vsh.yaml

@@ -1,6 +1,6 @@
 name: "split_modalities"
 namespace: "workflows/multiomics"
-version: "v4.0.3"
+version: "v4.1.0"
 authors:
 - name: "Dries Schaumont"
   roles:
@@ -182,14 +182,14 @@ build_info:
   engine: "native"
   output: "target/_private/nextflow/workflows/multiomics/split_modalities"
   executable: "target/_private/nextflow/workflows/multiomics/split_modalities/main.nf"
-  viash_version: "0.9.4"
+  viash_version: "0.9.7"
-  git_commit: "7bfad4ea12f87eca59213be3ab08deff67cc4206"
+  git_commit: "a6499fddaa8553874585c747370f919f4d7b729c"
   git_remote: "https://github.com/openpipelines-bio/openpipeline"
   dependencies:
   - "target/nextflow/dataflow/split_modalities"
 package_config:
   name: "openpipeline"
-  version: "v4.0.3"
+  version: "v4.1.0"
   summary: "Best-practice workflows for single-cell multi-omics analyses.\n"
   description: "OpenPipelines are extensible single cell analysis pipelines for reproducible\
     \ and large-scale single cell processing using [Viash](https://viash.io) and [Nextflow](https://www.nextflow.io/).\n\
@@ -210,7 +210,7 @@ package_config:
     - path: "src/workflows/utils/labels_ci.config"
       description: "Adds the correct memory and CPU labels when running on the Viash\
         \ Hub CI."
-  viash_version: "0.9.4"
+  viash_version: "0.9.7"
   source: "src"
   target: "target"
   config_mods:
@@ -219,7 +219,7 @@ package_config:
     )'"
   - ".engines += { type: \"native\" }"
   - ".engines[.type == 'docker'].target_registry := 'images.viash-hub.com'"
-  - ".engines[.type == 'docker'].target_tag := 'v4.0.3'"
+  - ".engines[.type == 'docker'].target_tag := 'v4.1.0'"
   keywords:
   - "single-cell"
   - "multimodal"

target/dependencies/vsh/vsh/openpipeline/v4.1.0/_private/nextflow/workflows/multiomics/split_modalities/main.nf

@@ -1,6 +1,6 @@
-// split_modalities v4.0.3
+// split_modalities v4.1.0
 // 
-// This wrapper script is auto-generated by viash 0.9.4 and is thus a derivative
+// This wrapper script is auto-generated by viash 0.9.7 and is thus a derivative
 // work thereof. This software comes with ABSOLUTELY NO WARRANTY from Data
 // Intuitive.
 // 
@@ -1353,47 +1353,42 @@ def readCsv(file_path) {
   def splitRegex = java.util.regex.Pattern.compile(''',(?=(?:[^"]*"[^"]*")*[^"]*$)''')
   def removeQuote = java.util.regex.Pattern.compile('''"(.*)"''')
 
-  def br = java.nio.file.Files.newBufferedReader(inputFile)
+  java.nio.file.Files.newBufferedReader(inputFile).withCloseable { br ->
+    def row = 0
+    def header = null
+    def line
 
-  def row = -1
+    while (header == null && (line = br.readLine()) != null) {
-  def header = null
+      if (!line.startsWith("#")) {
-  while (br.ready() && header == null) {
+        header = splitRegex.split(line, -1).collect { field ->
-    def line = br.readLine()
+          def m = removeQuote.matcher(field)
-    row++
+          m.find() ? m.replaceFirst('$1') : field
-    if (!line.startsWith("#")) {
-      header = splitRegex.split(line, -1).collect{field ->
-        m = removeQuote.matcher(field)
-        m.find() ? m.replaceFirst('$1') : field
-      }
-    }
-  }
-  assert header != null: "CSV file should contain a header"
-
-  while (br.ready()) {
-    def line = br.readLine()
-    row++
-    if (line == null) {
-      br.close()
-      break
-    }
-
-    if (!line.startsWith("#")) {
-      def predata = splitRegex.split(line, -1)
-      def data = predata.collect{field ->
-        if (field == "") {
-          return null
-        }
-        def m = removeQuote.matcher(field)
-        if (m.find()) {
-          return m.replaceFirst('$1')
-        } else {
-          return field
         }
       }
-      assert header.size() == data.size(): "Row $row should contain the same number as fields as the header"
+      row++
-      
+    }
-      def dataMap = [header, data].transpose().collectEntries().findAll{it.value != null}
+    assert header != null : "CSV file should contain a header"
-      output.add(dataMap)
+
+    while ((line = br.readLine()) != null) {
+      row++
+      if (!line.startsWith("#")) {
+        def predata = splitRegex.split(line, -1)
+        def data = predata.collect { field ->
+          if (field == "") {
+            return null
+          }
+          def m = removeQuote.matcher(field)
+          if (m.find()) {
+            return m.replaceFirst('$1')
+          } else {
+            return field
+          }
+        }
+        assert header.size() == data.size() : "Row $row should contain the same number as fields as the header"
+
+        def dataMap = [header, data].transpose().collectEntries().findAll { it.value != null }
+        output.add(dataMap)
+      }
     }
   }
 
@@ -1709,10 +1704,25 @@ process publishFilesProc {
   ]
     .transpose()
     .collectMany{infile, outfile ->
-      if (infile.toString() != outfile.toString()) {
+      def infileString = infile.toString()
+      def outfileString = outfile.toString()
+      if (infileString != outfileString) {
+        /* Trailing slashes are removed from both the source and destination arguments.
+           From source arguments, this is useful when a source argument may have a trailing slash
+           and specify a symbolic link to a directory. Without removing the slash, cp will dereference
+           the symbolic link. 
+           See https://www.gnu.org/software/coreutils/manual/html_node/Trailing-slashes.html#Trailing-slashes-1
+
+           For the destination path addding a trailing slash is a problem when publishing directories: 
+           it requires the destination directory to exist. This fails because we only create the parent
+           directories first.
+        */
+        def regexTrailingSlashes = ~/\/+$/
+        def infileNoTrailingSlash = infileString - regexTrailingSlashes
+        def outfileNoTrailingSlash = outfileString - regexTrailingSlashes
         [
-          "[ -d \"\$(dirname '${outfile.toString()}')\" ] || mkdir -p \"\$(dirname '${outfile.toString()}')\"",
+          "[ -d \"\$(dirname '${outfileNoTrailingSlash}')\" ] || mkdir -p \"\$(dirname '${outfileNoTrailingSlash}')\"",
-          "cp -r '${infile.toString()}' '${outfile.toString()}'"
+          "cp -a '${infileNoTrailingSlash}' '${outfileNoTrailingSlash}'"
         ]
       } else {
         // no need to copy if infile is the same as outfile
@@ -3035,7 +3045,7 @@ meta = [
   "config": processConfig(readJsonBlob('''{
   "name" : "split_modalities",
   "namespace" : "workflows/multiomics",
-  "version" : "v4.0.3",
+  "version" : "v4.1.0",
   "authors" : [
     {
       "name" : "Dries Schaumont",
@@ -3273,13 +3283,13 @@ meta = [
     "runner" : "nextflow",
     "engine" : "native",
     "output" : "/workdir/root/repo/target/_private/nextflow/workflows/multiomics/split_modalities",
-    "viash_version" : "0.9.4",
+    "viash_version" : "0.9.7",
-    "git_commit" : "7bfad4ea12f87eca59213be3ab08deff67cc4206",
+    "git_commit" : "a6499fddaa8553874585c747370f919f4d7b729c",
     "git_remote" : "https://github.com/openpipelines-bio/openpipeline"
   },
   "package_config" : {
     "name" : "openpipeline",
-    "version" : "v4.0.3",
+    "version" : "v4.1.0",
     "summary" : "Best-practice workflows for single-cell multi-omics analyses.\n",
     "description" : "OpenPipelines are extensible single cell analysis pipelines for reproducible and large-scale single cell processing using [Viash](https://viash.io) and [Nextflow](https://www.nextflow.io/).\n\nIn terms of workflows, the following has been made available, but keep in mind that\nindividual tools and functionality can be executed as standalone components as well.\n\n  * Demultiplexing: conversion of raw sequencing data to FASTQ objects.\n  * Ingestion: Read mapping and generating a count matrix.\n  * Single sample processing: cell filtering and doublet detection.\n  * Multisample processing: Count transformation, normalization, QC metric calulations.\n  * Integration: Clustering, integration and batch correction using single and multimodal methods.\n  * Downstream analysis workflows\n",
     "info" : {
@@ -3297,14 +3307,14 @@ meta = [
         }
       ]
     },
-    "viash_version" : "0.9.4",
+    "viash_version" : "0.9.7",
     "source" : "/workdir/root/repo/src",
     "target" : "/workdir/root/repo/target",
     "config_mods" : [
       ".resources += {path: '/src/workflows/utils/labels.config', dest: 'nextflow_labels.config'}\n.runners[.type == 'nextflow'].config.script := 'includeConfig(\\"nextflow_labels.config\\")'",
       ".engines += { type: \\"native\\" }",
       ".engines[.type == 'docker'].target_registry := 'images.viash-hub.com'",
-      ".engines[.type == 'docker'].target_tag := 'v4.0.3'"
+      ".engines[.type == 'docker'].target_tag := 'v4.1.0'"
     ],
     "keywords" : [
       "single-cell",

target/dependencies/vsh/vsh/openpipeline/v4.1.0/_private/nextflow/workflows/multiomics/split_modalities/nextflow.config

@@ -2,7 +2,7 @@ manifest {
   name = 'workflows/multiomics/split_modalities'
   mainScript = 'main.nf'
   nextflowVersion = '!>=20.12.1-edge'
-  version = 'v4.0.3'
+  version = 'v4.1.0'
   description = 'A pipeline to split a multimodal mudata files into several unimodal mudata files.'
   author = 'Dries Schaumont'
 }

target/dependencies/vsh/vsh/openpipeline/v4.1.0/_private/nextflow/workflows/rna/log_normalize/.config.vsh.yaml

@@ -1,6 +1,6 @@
 name: "log_normalize"
 namespace: "workflows/rna"
-version: "v4.0.3"
+version: "v4.1.0"
 authors:
 - name: "Dries Schaumont"
   roles:
@@ -197,8 +197,8 @@ build_info:
   engine: "native"
   output: "target/_private/nextflow/workflows/rna/log_normalize"
   executable: "target/_private/nextflow/workflows/rna/log_normalize/main.nf"
-  viash_version: "0.9.4"
+  viash_version: "0.9.7"
-  git_commit: "7bfad4ea12f87eca59213be3ab08deff67cc4206"
+  git_commit: "a6499fddaa8553874585c747370f919f4d7b729c"
   git_remote: "https://github.com/openpipelines-bio/openpipeline"
   dependencies:
   - "target/nextflow/transform/normalize_total"
@@ -206,7 +206,7 @@ build_info:
   - "target/nextflow/transform/delete_layer"
 package_config:
   name: "openpipeline"
-  version: "v4.0.3"
+  version: "v4.1.0"
   summary: "Best-practice workflows for single-cell multi-omics analyses.\n"
   description: "OpenPipelines are extensible single cell analysis pipelines for reproducible\
     \ and large-scale single cell processing using [Viash](https://viash.io) and [Nextflow](https://www.nextflow.io/).\n\
@@ -227,7 +227,7 @@ package_config:
     - path: "src/workflows/utils/labels_ci.config"
       description: "Adds the correct memory and CPU labels when running on the Viash\
         \ Hub CI."
-  viash_version: "0.9.4"
+  viash_version: "0.9.7"
   source: "src"
   target: "target"
   config_mods:
@@ -236,7 +236,7 @@ package_config:
     )'"
   - ".engines += { type: \"native\" }"
   - ".engines[.type == 'docker'].target_registry := 'images.viash-hub.com'"
-  - ".engines[.type == 'docker'].target_tag := 'v4.0.3'"
+  - ".engines[.type == 'docker'].target_tag := 'v4.1.0'"
   keywords:
   - "single-cell"
   - "multimodal"

target/dependencies/vsh/vsh/openpipeline/v4.1.0/_private/nextflow/workflows/rna/log_normalize/main.nf

@@ -1,6 +1,6 @@
-// log_normalize v4.0.3
+// log_normalize v4.1.0
 // 
-// This wrapper script is auto-generated by viash 0.9.4 and is thus a derivative
+// This wrapper script is auto-generated by viash 0.9.7 and is thus a derivative
 // work thereof. This software comes with ABSOLUTELY NO WARRANTY from Data
 // Intuitive.
 // 
@@ -1353,47 +1353,42 @@ def readCsv(file_path) {
   def splitRegex = java.util.regex.Pattern.compile(''',(?=(?:[^"]*"[^"]*")*[^"]*$)''')
   def removeQuote = java.util.regex.Pattern.compile('''"(.*)"''')
 
-  def br = java.nio.file.Files.newBufferedReader(inputFile)
+  java.nio.file.Files.newBufferedReader(inputFile).withCloseable { br ->
+    def row = 0
+    def header = null
+    def line
 
-  def row = -1
+    while (header == null && (line = br.readLine()) != null) {
-  def header = null
+      if (!line.startsWith("#")) {
-  while (br.ready() && header == null) {
+        header = splitRegex.split(line, -1).collect { field ->
-    def line = br.readLine()
+          def m = removeQuote.matcher(field)
-    row++
+          m.find() ? m.replaceFirst('$1') : field
-    if (!line.startsWith("#")) {
-      header = splitRegex.split(line, -1).collect{field ->
-        m = removeQuote.matcher(field)
-        m.find() ? m.replaceFirst('$1') : field
-      }
-    }
-  }
-  assert header != null: "CSV file should contain a header"
-
-  while (br.ready()) {
-    def line = br.readLine()
-    row++
-    if (line == null) {
-      br.close()
-      break
-    }
-
-    if (!line.startsWith("#")) {
-      def predata = splitRegex.split(line, -1)
-      def data = predata.collect{field ->
-        if (field == "") {
-          return null
-        }
-        def m = removeQuote.matcher(field)
-        if (m.find()) {
-          return m.replaceFirst('$1')
-        } else {
-          return field
         }
       }
-      assert header.size() == data.size(): "Row $row should contain the same number as fields as the header"
+      row++
-      
+    }
-      def dataMap = [header, data].transpose().collectEntries().findAll{it.value != null}
+    assert header != null : "CSV file should contain a header"
-      output.add(dataMap)
+
+    while ((line = br.readLine()) != null) {
+      row++
+      if (!line.startsWith("#")) {
+        def predata = splitRegex.split(line, -1)
+        def data = predata.collect { field ->
+          if (field == "") {
+            return null
+          }
+          def m = removeQuote.matcher(field)
+          if (m.find()) {
+            return m.replaceFirst('$1')
+          } else {
+            return field
+          }
+        }
+        assert header.size() == data.size() : "Row $row should contain the same number as fields as the header"
+
+        def dataMap = [header, data].transpose().collectEntries().findAll { it.value != null }
+        output.add(dataMap)
+      }
     }
   }
 
@@ -1709,10 +1704,25 @@ process publishFilesProc {
   ]
     .transpose()
     .collectMany{infile, outfile ->
-      if (infile.toString() != outfile.toString()) {
+      def infileString = infile.toString()
+      def outfileString = outfile.toString()
+      if (infileString != outfileString) {
+        /* Trailing slashes are removed from both the source and destination arguments.
+           From source arguments, this is useful when a source argument may have a trailing slash
+           and specify a symbolic link to a directory. Without removing the slash, cp will dereference
+           the symbolic link. 
+           See https://www.gnu.org/software/coreutils/manual/html_node/Trailing-slashes.html#Trailing-slashes-1
+
+           For the destination path addding a trailing slash is a problem when publishing directories: 
+           it requires the destination directory to exist. This fails because we only create the parent
+           directories first.
+        */
+        def regexTrailingSlashes = ~/\/+$/
+        def infileNoTrailingSlash = infileString - regexTrailingSlashes
+        def outfileNoTrailingSlash = outfileString - regexTrailingSlashes
         [
-          "[ -d \"\$(dirname '${outfile.toString()}')\" ] || mkdir -p \"\$(dirname '${outfile.toString()}')\"",
+          "[ -d \"\$(dirname '${outfileNoTrailingSlash}')\" ] || mkdir -p \"\$(dirname '${outfileNoTrailingSlash}')\"",
-          "cp -r '${infile.toString()}' '${outfile.toString()}'"
+          "cp -a '${infileNoTrailingSlash}' '${outfileNoTrailingSlash}'"
         ]
       } else {
         // no need to copy if infile is the same as outfile
@@ -3035,7 +3045,7 @@ meta = [
   "config": processConfig(readJsonBlob('''{
   "name" : "log_normalize",
   "namespace" : "workflows/rna",
-  "version" : "v4.0.3",
+  "version" : "v4.1.0",
   "authors" : [
     {
       "name" : "Dries Schaumont",
@@ -3293,13 +3303,13 @@ meta = [
     "runner" : "nextflow",
     "engine" : "native",
     "output" : "/workdir/root/repo/target/_private/nextflow/workflows/rna/log_normalize",
-    "viash_version" : "0.9.4",
+    "viash_version" : "0.9.7",
-    "git_commit" : "7bfad4ea12f87eca59213be3ab08deff67cc4206",
+    "git_commit" : "a6499fddaa8553874585c747370f919f4d7b729c",
     "git_remote" : "https://github.com/openpipelines-bio/openpipeline"
   },
   "package_config" : {
     "name" : "openpipeline",
-    "version" : "v4.0.3",
+    "version" : "v4.1.0",
     "summary" : "Best-practice workflows for single-cell multi-omics analyses.\n",
     "description" : "OpenPipelines are extensible single cell analysis pipelines for reproducible and large-scale single cell processing using [Viash](https://viash.io) and [Nextflow](https://www.nextflow.io/).\n\nIn terms of workflows, the following has been made available, but keep in mind that\nindividual tools and functionality can be executed as standalone components as well.\n\n  * Demultiplexing: conversion of raw sequencing data to FASTQ objects.\n  * Ingestion: Read mapping and generating a count matrix.\n  * Single sample processing: cell filtering and doublet detection.\n  * Multisample processing: Count transformation, normalization, QC metric calulations.\n  * Integration: Clustering, integration and batch correction using single and multimodal methods.\n  * Downstream analysis workflows\n",
     "info" : {
@@ -3317,14 +3327,14 @@ meta = [
         }
       ]
     },
-    "viash_version" : "0.9.4",
+    "viash_version" : "0.9.7",
     "source" : "/workdir/root/repo/src",
     "target" : "/workdir/root/repo/target",
     "config_mods" : [
       ".resources += {path: '/src/workflows/utils/labels.config', dest: 'nextflow_labels.config'}\n.runners[.type == 'nextflow'].config.script := 'includeConfig(\\"nextflow_labels.config\\")'",
       ".engines += { type: \\"native\\" }",
       ".engines[.type == 'docker'].target_registry := 'images.viash-hub.com'",
-      ".engines[.type == 'docker'].target_tag := 'v4.0.3'"
+      ".engines[.type == 'docker'].target_tag := 'v4.1.0'"
     ],
     "keywords" : [
       "single-cell",

target/dependencies/vsh/vsh/openpipeline/v4.1.0/_private/nextflow/workflows/rna/log_normalize/nextflow.config

@@ -2,7 +2,7 @@ manifest {
   name = 'workflows/rna/log_normalize'
   mainScript = 'main.nf'
   nextflowVersion = '!>=20.12.1-edge'
-  version = 'v4.0.3'
+  version = 'v4.1.0'
   description = 'Performs normalization and subsequent log-transformation of raw count data.'
   author = 'Dries Schaumont'
 }

target/dependencies/vsh/vsh/openpipeline/v4.1.0/nextflow/cluster/leiden/.config.vsh.yaml

@@ -1,6 +1,6 @@
 name: "leiden"
 namespace: "cluster"
-version: "v4.0.3"
+version: "v4.1.0"
 authors:
 - name: "Dries De Maeyer"
   roles:
@@ -77,6 +77,41 @@ argument_groups:
     direction: "input"
     multiple: false
     multiple_sep: ";"
+  - type: "string"
+    name: "--flavor"
+    description: "Which package's implementation to use.\n"
+    info: null
+    default:
+    - "leidenalg"
+    required: false
+    choices:
+    - "leidenalg"
+    - "igraph"
+    direction: "input"
+    multiple: false
+    multiple_sep: ";"
+  - type: "integer"
+    name: "--n_iterations"
+    description: "How many iterations of the Leiden clustering algorithm to perform.\n\
+      When defined, positive values above 2 define the total number of iterations\
+      \ to perform.\nWhen not set, the algorithm will run until it reaches its optimal\
+      \ clustering.\n"
+    info: null
+    required: false
+    min: 1
+    direction: "input"
+    multiple: false
+    multiple_sep: ";"
+  - type: "integer"
+    name: "--seed"
+    description: "Fix the initialization of the optimization. Can be used to increase\
+      \ reproducibility.\n"
+    info: null
+    required: false
+    min: 0
+    direction: "input"
+    multiple: false
+    multiple_sep: ";"
   - type: "double"
     name: "--resolution"
     description: "A parameter value controlling the coarseness of the clustering.\
@@ -91,8 +126,8 @@ argument_groups:
     multiple_sep: ";"
   - type: "string"
     name: "--output_compression"
-    description: "Compression format to use for the output AnnData and/or Mudata objects.\n\
+    description: "Compression format to use for the output AnnData and/or Mudata H5\
-      By default no compression is applied.\n"
+      \ files.\nBy default no compression is applied.\n"
     info: null
     example:
     - "gzip"
@@ -215,7 +250,7 @@ engines:
   id: "docker"
   image: "python:3.13-slim"
   target_registry: "images.viash-hub.com"
-  target_tag: "v4.0.3"
+  target_tag: "v4.1.0"
   namespace_separator: "/"
   setup:
   - type: "apt"
@@ -225,11 +260,12 @@ engines:
   - type: "python"
     user: false
     packages:
-    - "anndata~=0.12.7"
+    - "anndata~=0.12.16"
     - "awkward"
-    - "mudata~=0.3.2"
+    - "scipy~=1.17.1"
+    - "mudata~=0.3.8"
     - "scanpy~=1.11.4"
-    - "leidenalg~=0.10.0"
+    - "leidenalg~=0.11.0"
     script:
     - "exec(\"try:\\n  import zarr; from importlib.metadata import version\\nexcept\
       \ ModuleNotFoundError:\\n  exit(0)\\nelse:  assert int(version(\\\"zarr\\\"\
@@ -243,7 +279,7 @@ engines:
   - type: "python"
     user: false
     packages:
-    - "viashpy==0.8.0"
+    - "viashpy==0.10.0"
     github:
     - "openpipelines-bio/core#subdirectory=packages/python/openpipeline_testutils"
     upgrade: true
@@ -257,12 +293,12 @@ build_info:
   engine: "docker|native"
   output: "target/nextflow/cluster/leiden"
   executable: "target/nextflow/cluster/leiden/main.nf"
-  viash_version: "0.9.4"
+  viash_version: "0.9.7"
-  git_commit: "7bfad4ea12f87eca59213be3ab08deff67cc4206"
+  git_commit: "a6499fddaa8553874585c747370f919f4d7b729c"
   git_remote: "https://github.com/openpipelines-bio/openpipeline"
 package_config:
   name: "openpipeline"
-  version: "v4.0.3"
+  version: "v4.1.0"
   summary: "Best-practice workflows for single-cell multi-omics analyses.\n"
   description: "OpenPipelines are extensible single cell analysis pipelines for reproducible\
     \ and large-scale single cell processing using [Viash](https://viash.io) and [Nextflow](https://www.nextflow.io/).\n\
@@ -283,7 +319,7 @@ package_config:
     - path: "src/workflows/utils/labels_ci.config"
       description: "Adds the correct memory and CPU labels when running on the Viash\
         \ Hub CI."
-  viash_version: "0.9.4"
+  viash_version: "0.9.7"
   source: "src"
   target: "target"
   config_mods:
@@ -292,7 +328,7 @@ package_config:
     )'"
   - ".engines += { type: \"native\" }"
   - ".engines[.type == 'docker'].target_registry := 'images.viash-hub.com'"
-  - ".engines[.type == 'docker'].target_tag := 'v4.0.3'"
+  - ".engines[.type == 'docker'].target_tag := 'v4.1.0'"
   keywords:
   - "single-cell"
   - "multimodal"

target/dependencies/vsh/vsh/openpipeline/v4.1.0/nextflow/cluster/leiden/main.nf

@@ -1,6 +1,6 @@
-// leiden v4.0.3
+// leiden v4.1.0
 // 
-// This wrapper script is auto-generated by viash 0.9.4 and is thus a derivative
+// This wrapper script is auto-generated by viash 0.9.7 and is thus a derivative
 // work thereof. This software comes with ABSOLUTELY NO WARRANTY from Data
 // Intuitive.
 // 
@@ -1353,47 +1353,42 @@ def readCsv(file_path) {
   def splitRegex = java.util.regex.Pattern.compile(''',(?=(?:[^"]*"[^"]*")*[^"]*$)''')
   def removeQuote = java.util.regex.Pattern.compile('''"(.*)"''')
 
-  def br = java.nio.file.Files.newBufferedReader(inputFile)
+  java.nio.file.Files.newBufferedReader(inputFile).withCloseable { br ->
+    def row = 0
+    def header = null
+    def line
 
-  def row = -1
+    while (header == null && (line = br.readLine()) != null) {
-  def header = null
+      if (!line.startsWith("#")) {
-  while (br.ready() && header == null) {
+        header = splitRegex.split(line, -1).collect { field ->
-    def line = br.readLine()
+          def m = removeQuote.matcher(field)
-    row++
+          m.find() ? m.replaceFirst('$1') : field
-    if (!line.startsWith("#")) {
-      header = splitRegex.split(line, -1).collect{field ->
-        m = removeQuote.matcher(field)
-        m.find() ? m.replaceFirst('$1') : field
-      }
-    }
-  }
-  assert header != null: "CSV file should contain a header"
-
-  while (br.ready()) {
-    def line = br.readLine()
-    row++
-    if (line == null) {
-      br.close()
-      break
-    }
-
-    if (!line.startsWith("#")) {
-      def predata = splitRegex.split(line, -1)
-      def data = predata.collect{field ->
-        if (field == "") {
-          return null
-        }
-        def m = removeQuote.matcher(field)
-        if (m.find()) {
-          return m.replaceFirst('$1')
-        } else {
-          return field
         }
       }
-      assert header.size() == data.size(): "Row $row should contain the same number as fields as the header"
+      row++
-      
+    }
-      def dataMap = [header, data].transpose().collectEntries().findAll{it.value != null}
+    assert header != null : "CSV file should contain a header"
-      output.add(dataMap)
+
+    while ((line = br.readLine()) != null) {
+      row++
+      if (!line.startsWith("#")) {
+        def predata = splitRegex.split(line, -1)
+        def data = predata.collect { field ->
+          if (field == "") {
+            return null
+          }
+          def m = removeQuote.matcher(field)
+          if (m.find()) {
+            return m.replaceFirst('$1')
+          } else {
+            return field
+          }
+        }
+        assert header.size() == data.size() : "Row $row should contain the same number as fields as the header"
+
+        def dataMap = [header, data].transpose().collectEntries().findAll { it.value != null }
+        output.add(dataMap)
+      }
     }
   }
 
@@ -1709,10 +1704,25 @@ process publishFilesProc {
   ]
     .transpose()
     .collectMany{infile, outfile ->
-      if (infile.toString() != outfile.toString()) {
+      def infileString = infile.toString()
+      def outfileString = outfile.toString()
+      if (infileString != outfileString) {
+        /* Trailing slashes are removed from both the source and destination arguments.
+           From source arguments, this is useful when a source argument may have a trailing slash
+           and specify a symbolic link to a directory. Without removing the slash, cp will dereference
+           the symbolic link. 
+           See https://www.gnu.org/software/coreutils/manual/html_node/Trailing-slashes.html#Trailing-slashes-1
+
+           For the destination path addding a trailing slash is a problem when publishing directories: 
+           it requires the destination directory to exist. This fails because we only create the parent
+           directories first.
+        */
+        def regexTrailingSlashes = ~/\/+$/
+        def infileNoTrailingSlash = infileString - regexTrailingSlashes
+        def outfileNoTrailingSlash = outfileString - regexTrailingSlashes
         [
-          "[ -d \"\$(dirname '${outfile.toString()}')\" ] || mkdir -p \"\$(dirname '${outfile.toString()}')\"",
+          "[ -d \"\$(dirname '${outfileNoTrailingSlash}')\" ] || mkdir -p \"\$(dirname '${outfileNoTrailingSlash}')\"",
-          "cp -r '${infile.toString()}' '${outfile.toString()}'"
+          "cp -a '${infileNoTrailingSlash}' '${outfileNoTrailingSlash}'"
         ]
       } else {
         // no need to copy if infile is the same as outfile
@@ -3035,7 +3045,7 @@ meta = [
   "config": processConfig(readJsonBlob('''{
   "name" : "leiden",
   "namespace" : "cluster",
-  "version" : "v4.0.3",
+  "version" : "v4.1.0",
   "authors" : [
     {
       "name" : "Dries De Maeyer",
@@ -3133,6 +3143,42 @@ meta = [
           "multiple" : false,
           "multiple_sep" : ";"
         },
+        {
+          "type" : "string",
+          "name" : "--flavor",
+          "description" : "Which package's implementation to use.\n",
+          "default" : [
+            "leidenalg"
+          ],
+          "required" : false,
+          "choices" : [
+            "leidenalg",
+            "igraph"
+          ],
+          "direction" : "input",
+          "multiple" : false,
+          "multiple_sep" : ";"
+        },
+        {
+          "type" : "integer",
+          "name" : "--n_iterations",
+          "description" : "How many iterations of the Leiden clustering algorithm to perform.\nWhen defined, positive values above 2 define the total number of iterations to perform.\nWhen not set, the algorithm will run until it reaches its optimal clustering.\n",
+          "required" : false,
+          "min" : 1,
+          "direction" : "input",
+          "multiple" : false,
+          "multiple_sep" : ";"
+        },
+        {
+          "type" : "integer",
+          "name" : "--seed",
+          "description" : "Fix the initialization of the optimization. Can be used to increase reproducibility.\n",
+          "required" : false,
+          "min" : 0,
+          "direction" : "input",
+          "multiple" : false,
+          "multiple_sep" : ";"
+        },
         {
           "type" : "double",
           "name" : "--resolution",
@@ -3148,7 +3194,7 @@ meta = [
         {
           "type" : "string",
           "name" : "--output_compression",
-          "description" : "Compression format to use for the output AnnData and/or Mudata objects.\nBy default no compression is applied.\n",
+          "description" : "Compression format to use for the output AnnData and/or Mudata H5 files.\nBy default no compression is applied.\n",
           "example" : [
             "gzip"
           ],
@@ -3294,7 +3340,7 @@ meta = [
       "id" : "docker",
       "image" : "python:3.13-slim",
       "target_registry" : "images.viash-hub.com",
-      "target_tag" : "v4.0.3",
+      "target_tag" : "v4.1.0",
       "namespace_separator" : "/",
       "setup" : [
         {
@@ -3308,11 +3354,12 @@ meta = [
           "type" : "python",
           "user" : false,
           "packages" : [
-            "anndata~=0.12.7",
+            "anndata~=0.12.16",
             "awkward",
-            "mudata~=0.3.2",
+            "scipy~=1.17.1",
+            "mudata~=0.3.8",
             "scanpy~=1.11.4",
-            "leidenalg~=0.10.0"
+            "leidenalg~=0.11.0"
           ],
           "script" : [
             "exec(\\"try:\\\\n  import zarr; from importlib.metadata import version\\\\nexcept ModuleNotFoundError:\\\\n  exit(0)\\\\nelse:  assert int(version(\\\\\\"zarr\\\\\\").partition(\\\\\\".\\\\\\")[0]) > 2\\")"
@@ -3332,7 +3379,7 @@ meta = [
           "type" : "python",
           "user" : false,
           "packages" : [
-            "viashpy==0.8.0"
+            "viashpy==0.10.0"
           ],
           "github" : [
             "openpipelines-bio/core#subdirectory=packages/python/openpipeline_testutils"
@@ -3351,13 +3398,13 @@ meta = [
     "runner" : "nextflow",
     "engine" : "docker|native",
     "output" : "/workdir/root/repo/target/nextflow/cluster/leiden",
-    "viash_version" : "0.9.4",
+    "viash_version" : "0.9.7",
-    "git_commit" : "7bfad4ea12f87eca59213be3ab08deff67cc4206",
+    "git_commit" : "a6499fddaa8553874585c747370f919f4d7b729c",
     "git_remote" : "https://github.com/openpipelines-bio/openpipeline"
   },
   "package_config" : {
     "name" : "openpipeline",
-    "version" : "v4.0.3",
+    "version" : "v4.1.0",
     "summary" : "Best-practice workflows for single-cell multi-omics analyses.\n",
     "description" : "OpenPipelines are extensible single cell analysis pipelines for reproducible and large-scale single cell processing using [Viash](https://viash.io) and [Nextflow](https://www.nextflow.io/).\n\nIn terms of workflows, the following has been made available, but keep in mind that\nindividual tools and functionality can be executed as standalone components as well.\n\n  * Demultiplexing: conversion of raw sequencing data to FASTQ objects.\n  * Ingestion: Read mapping and generating a count matrix.\n  * Single sample processing: cell filtering and doublet detection.\n  * Multisample processing: Count transformation, normalization, QC metric calulations.\n  * Integration: Clustering, integration and batch correction using single and multimodal methods.\n  * Downstream analysis workflows\n",
     "info" : {
@@ -3375,14 +3422,14 @@ meta = [
         }
       ]
     },
-    "viash_version" : "0.9.4",
+    "viash_version" : "0.9.7",
     "source" : "/workdir/root/repo/src",
     "target" : "/workdir/root/repo/target",
     "config_mods" : [
       ".resources += {path: '/src/workflows/utils/labels.config', dest: 'nextflow_labels.config'}\n.runners[.type == 'nextflow'].config.script := 'includeConfig(\\"nextflow_labels.config\\")'",
       ".engines += { type: \\"native\\" }",
       ".engines[.type == 'docker'].target_registry := 'images.viash-hub.com'",
-      ".engines[.type == 'docker'].target_tag := 'v4.0.3'"
+      ".engines[.type == 'docker'].target_tag := 'v4.1.0'"
     ],
     "keywords" : [
       "single-cell",
@@ -3416,7 +3463,6 @@ import os
 import time
 import logging
 import logging.handlers
-import warnings
 import h5py
 import mudata as mu
 import pandas as pd
@@ -3438,6 +3484,9 @@ par = {
   'obsp_connectivities': $( if [ ! -z ${VIASH_PAR_OBSP_CONNECTIVITIES+x} ]; then echo "r'${VIASH_PAR_OBSP_CONNECTIVITIES//\\'/\\'\\"\\'\\"r\\'}'"; else echo None; fi ),
   'output': $( if [ ! -z ${VIASH_PAR_OUTPUT+x} ]; then echo "r'${VIASH_PAR_OUTPUT//\\'/\\'\\"\\'\\"r\\'}'"; else echo None; fi ),
   'obsm_name': $( if [ ! -z ${VIASH_PAR_OBSM_NAME+x} ]; then echo "r'${VIASH_PAR_OBSM_NAME//\\'/\\'\\"\\'\\"r\\'}'"; else echo None; fi ),
+  'flavor': $( if [ ! -z ${VIASH_PAR_FLAVOR+x} ]; then echo "r'${VIASH_PAR_FLAVOR//\\'/\\'\\"\\'\\"r\\'}'"; else echo None; fi ),
+  'n_iterations': $( if [ ! -z ${VIASH_PAR_N_ITERATIONS+x} ]; then echo "int(r'${VIASH_PAR_N_ITERATIONS//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ),
+  'seed': $( if [ ! -z ${VIASH_PAR_SEED+x} ]; then echo "int(r'${VIASH_PAR_SEED//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ),
   'resolution': $( if [ ! -z ${VIASH_PAR_RESOLUTION+x} ]; then echo "list(map(float, r'${VIASH_PAR_RESOLUTION//\\'/\\'\\"\\'\\"r\\'}'.split(';')))"; else echo None; fi ),
   'output_compression': $( if [ ! -z ${VIASH_PAR_OUTPUT_COMPRESSION+x} ]; then echo "r'${VIASH_PAR_OUTPUT_COMPRESSION//\\'/\\'\\"\\'\\"r\\'}'"; else echo None; fi )
 }
@@ -3473,6 +3522,9 @@ from compress_h5mu import compress_h5mu
 
 _shared_logger_name = "leiden"
 
+if not par["n_iterations"]:
+    par["n_iterations"] = -1
+
 
 # Function to check available space in /dev/shm
 def get_available_shared_memory():
@@ -3571,18 +3623,18 @@ def run_single_resolution(shared_csr_matrix, obs_names, resolution):
     try:
         connectivities = shared_csr_matrix.to_csr_matrix()
         adata = create_empty_anndata_with_connectivities(connectivities, obs_names)
-        with warnings.catch_warnings():
+        sc.tl.leiden(
-            # In the future, the default backend for leiden will be igraph instead of leidenalg.
+            adata,
-            warnings.simplefilter(action="ignore", category=FutureWarning)
+            resolution=resolution,
-            adata_out = sc.tl.leiden(
+            key_added=str(resolution),
-                adata,
+            obsp="connectivities",
-                resolution=resolution,
+            flavor=par["flavor"],
-                key_added=str(resolution),
+            n_iterations=par["n_iterations"],
-                obsp="connectivities",
+            random_state=par["seed"],
-                copy=True,
+            copy=False,  # A copy was already created above
-            )
+        )
         logger.info(f"Returning result for resolution {resolution}")
-        return adata_out.obs[str(resolution)]
+        return adata.obs[str(resolution)]
     finally:
         obs_names.shm.close()
         shared_csr_matrix.close()
@@ -4147,7 +4199,7 @@ meta["defaults"] = [
   "container" : {
     "registry" : "images.viash-hub.com",
     "image" : "vsh/openpipeline/cluster/leiden",
-    "tag" : "v4.0.3"
+    "tag" : "v4.1.0"
   },
   "label" : [
     "highcpu",

target/dependencies/vsh/vsh/openpipeline/v4.1.0/nextflow/cluster/leiden/nextflow.config

@@ -2,7 +2,7 @@ manifest {
   name = 'cluster/leiden'
   mainScript = 'main.nf'
   nextflowVersion = '!>=20.12.1-edge'
-  version = 'v4.0.3'
+  version = 'v4.1.0'
   description = 'Cluster cells using the [Leiden algorithm] [Traag18] implemented in the [Scanpy framework] [Wolf18]. \nLeiden is an improved version of the [Louvain algorithm] [Blondel08]. \nIt has been proposed for single-cell analysis by [Levine15] [Levine15]. \nThis requires having ran `neighbors/find_neighbors` or `neighbors/bbknn` first.\n\n[Blondel08]: Blondel et al. (2008), Fast unfolding of communities in large networks, J. Stat. Mech.  \n[Levine15]: Levine et al. (2015), Data-Driven Phenotypic Dissection of AML Reveals Progenitor-like Cells that Correlate with Prognosis, Cell.  \n[Traag18]: Traag et al. (2018), From Louvain to Leiden: guaranteeing well-connected communities arXiv.  \n[Wolf18]: Wolf et al. (2018), Scanpy: large-scale single-cell gene expression data analysis, Genome Biology.  \n'
   author = 'Dries De Maeyer'
 }

target/dependencies/vsh/vsh/openpipeline/v4.1.0/nextflow/cluster/leiden/nextflow_schema.json

@@ -41,6 +41,26 @@
           "help_text": "Type: `string`, multiple: `False`, default: `\"leiden\"`. ",
           "default": "leiden"
         },
+        "flavor": {
+          "type": "string",
+          "description": "Which package's implementation to use.\n",
+          "help_text": "Type: `string`, multiple: `False`, default: `\"leidenalg\"`, choices: ``leidenalg`, `igraph``. ",
+          "enum": [
+            "leidenalg",
+            "igraph"
+          ],
+          "default": "leidenalg"
+        },
+        "n_iterations": {
+          "type": "integer",
+          "description": "How many iterations of the Leiden clustering algorithm to perform.\nWhen defined, positive values above 2 define the total number of iterations to perform.\nWhen not set, the algorithm will run until it reaches its optimal clustering.\n",
+          "help_text": "Type: `integer`, multiple: `False`. "
+        },
+        "seed": {
+          "type": "integer",
+          "description": "Fix the initialization of the optimization",
+          "help_text": "Type: `integer`, multiple: `False`. "
+        },
         "resolution": {
           "type": "array",
           "items": {
@@ -54,7 +74,7 @@
         },
         "output_compression": {
           "type": "string",
-          "description": "Compression format to use for the output AnnData and/or Mudata objects.\nBy default no compression is applied.\n",
+          "description": "Compression format to use for the output AnnData and/or Mudata H5 files.\nBy default no compression is applied.\n",
           "help_text": "Type: `string`, multiple: `False`, example: `\"gzip\"`, choices: ``gzip`, `lzf``. ",
           "enum": [
             "gzip",

target/dependencies/vsh/vsh/openpipeline/v4.1.0/nextflow/dataflow/concatenate_h5mu/.config.vsh.yaml

@@ -1,6 +1,6 @@
 name: "concatenate_h5mu"
 namespace: "dataflow"
-version: "v4.0.3"
+version: "v4.1.0"
 authors:
 - name: "Dries Schaumont"
   roles:
@@ -136,8 +136,8 @@ argument_groups:
     multiple_sep: ";"
   - type: "string"
     name: "--output_compression"
-    description: "Compression format to use for the output AnnData and/or Mudata objects.\n\
+    description: "Compression format to use for the output AnnData and/or Mudata H5\
-      By default no compression is applied.\n"
+      \ files.\nBy default no compression is applied.\n"
     info: null
     example:
     - "gzip"
@@ -253,7 +253,7 @@ engines:
   id: "docker"
   image: "python:3.13-slim"
   target_registry: "images.viash-hub.com"
-  target_tag: "v4.0.3"
+  target_tag: "v4.1.0"
   namespace_separator: "/"
   setup:
   - type: "apt"
@@ -263,9 +263,10 @@ engines:
   - type: "python"
     user: false
     packages:
-    - "anndata~=0.12.7"
+    - "anndata~=0.12.16"
     - "awkward"
-    - "mudata~=0.3.2"
+    - "scipy~=1.17.1"
+    - "mudata~=0.3.8"
     script:
     - "exec(\"try:\\n  import zarr; from importlib.metadata import version\\nexcept\
       \ ModuleNotFoundError:\\n  exit(0)\\nelse:  assert int(version(\\\"zarr\\\"\
@@ -279,14 +280,14 @@ engines:
   - type: "python"
     user: false
     packages:
-    - "viashpy==0.8.0"
+    - "viashpy==0.10.0"
     github:
     - "openpipelines-bio/core#subdirectory=packages/python/openpipeline_testutils"
     upgrade: true
   - type: "python"
     user: false
     packages:
-    - "viashpy==0.8.0"
+    - "viashpy==0.10.0"
     - "pytest-benchmark"
     upgrade: true
   entrypoint: []
@@ -299,12 +300,12 @@ build_info:
   engine: "docker|native"
   output: "target/nextflow/dataflow/concatenate_h5mu"
   executable: "target/nextflow/dataflow/concatenate_h5mu/main.nf"
-  viash_version: "0.9.4"
+  viash_version: "0.9.7"
-  git_commit: "7bfad4ea12f87eca59213be3ab08deff67cc4206"
+  git_commit: "a6499fddaa8553874585c747370f919f4d7b729c"
   git_remote: "https://github.com/openpipelines-bio/openpipeline"
 package_config:
   name: "openpipeline"
-  version: "v4.0.3"
+  version: "v4.1.0"
   summary: "Best-practice workflows for single-cell multi-omics analyses.\n"
   description: "OpenPipelines are extensible single cell analysis pipelines for reproducible\
     \ and large-scale single cell processing using [Viash](https://viash.io) and [Nextflow](https://www.nextflow.io/).\n\
@@ -325,7 +326,7 @@ package_config:
     - path: "src/workflows/utils/labels_ci.config"
       description: "Adds the correct memory and CPU labels when running on the Viash\
         \ Hub CI."
-  viash_version: "0.9.4"
+  viash_version: "0.9.7"
   source: "src"
   target: "target"
   config_mods:
@@ -334,7 +335,7 @@ package_config:
     )'"
   - ".engines += { type: \"native\" }"
   - ".engines[.type == 'docker'].target_registry := 'images.viash-hub.com'"
-  - ".engines[.type == 'docker'].target_tag := 'v4.0.3'"
+  - ".engines[.type == 'docker'].target_tag := 'v4.1.0'"
   keywords:
   - "single-cell"
   - "multimodal"

target/dependencies/vsh/vsh/openpipeline/v4.1.0/nextflow/dataflow/concatenate_h5mu/main.nf

@@ -1,6 +1,6 @@
-// concatenate_h5mu v4.0.3
+// concatenate_h5mu v4.1.0
 // 
-// This wrapper script is auto-generated by viash 0.9.4 and is thus a derivative
+// This wrapper script is auto-generated by viash 0.9.7 and is thus a derivative
 // work thereof. This software comes with ABSOLUTELY NO WARRANTY from Data
 // Intuitive.
 // 
@@ -1353,47 +1353,42 @@ def readCsv(file_path) {
   def splitRegex = java.util.regex.Pattern.compile(''',(?=(?:[^"]*"[^"]*")*[^"]*$)''')
   def removeQuote = java.util.regex.Pattern.compile('''"(.*)"''')
 
-  def br = java.nio.file.Files.newBufferedReader(inputFile)
+  java.nio.file.Files.newBufferedReader(inputFile).withCloseable { br ->
+    def row = 0
+    def header = null
+    def line
 
-  def row = -1
+    while (header == null && (line = br.readLine()) != null) {
-  def header = null
+      if (!line.startsWith("#")) {
-  while (br.ready() && header == null) {
+        header = splitRegex.split(line, -1).collect { field ->
-    def line = br.readLine()
+          def m = removeQuote.matcher(field)
-    row++
+          m.find() ? m.replaceFirst('$1') : field
-    if (!line.startsWith("#")) {
-      header = splitRegex.split(line, -1).collect{field ->
-        m = removeQuote.matcher(field)
-        m.find() ? m.replaceFirst('$1') : field
-      }
-    }
-  }
-  assert header != null: "CSV file should contain a header"
-
-  while (br.ready()) {
-    def line = br.readLine()
-    row++
-    if (line == null) {
-      br.close()
-      break
-    }
-
-    if (!line.startsWith("#")) {
-      def predata = splitRegex.split(line, -1)
-      def data = predata.collect{field ->
-        if (field == "") {
-          return null
-        }
-        def m = removeQuote.matcher(field)
-        if (m.find()) {
-          return m.replaceFirst('$1')
-        } else {
-          return field
         }
       }
-      assert header.size() == data.size(): "Row $row should contain the same number as fields as the header"
+      row++
-      
+    }
-      def dataMap = [header, data].transpose().collectEntries().findAll{it.value != null}
+    assert header != null : "CSV file should contain a header"
-      output.add(dataMap)
+
+    while ((line = br.readLine()) != null) {
+      row++
+      if (!line.startsWith("#")) {
+        def predata = splitRegex.split(line, -1)
+        def data = predata.collect { field ->
+          if (field == "") {
+            return null
+          }
+          def m = removeQuote.matcher(field)
+          if (m.find()) {
+            return m.replaceFirst('$1')
+          } else {
+            return field
+          }
+        }
+        assert header.size() == data.size() : "Row $row should contain the same number as fields as the header"
+
+        def dataMap = [header, data].transpose().collectEntries().findAll { it.value != null }
+        output.add(dataMap)
+      }
     }
   }
 
@@ -1709,10 +1704,25 @@ process publishFilesProc {
   ]
     .transpose()
     .collectMany{infile, outfile ->
-      if (infile.toString() != outfile.toString()) {
+      def infileString = infile.toString()
+      def outfileString = outfile.toString()
+      if (infileString != outfileString) {
+        /* Trailing slashes are removed from both the source and destination arguments.
+           From source arguments, this is useful when a source argument may have a trailing slash
+           and specify a symbolic link to a directory. Without removing the slash, cp will dereference
+           the symbolic link. 
+           See https://www.gnu.org/software/coreutils/manual/html_node/Trailing-slashes.html#Trailing-slashes-1
+
+           For the destination path addding a trailing slash is a problem when publishing directories: 
+           it requires the destination directory to exist. This fails because we only create the parent
+           directories first.
+        */
+        def regexTrailingSlashes = ~/\/+$/
+        def infileNoTrailingSlash = infileString - regexTrailingSlashes
+        def outfileNoTrailingSlash = outfileString - regexTrailingSlashes
         [
-          "[ -d \"\$(dirname '${outfile.toString()}')\" ] || mkdir -p \"\$(dirname '${outfile.toString()}')\"",
+          "[ -d \"\$(dirname '${outfileNoTrailingSlash}')\" ] || mkdir -p \"\$(dirname '${outfileNoTrailingSlash}')\"",
-          "cp -r '${infile.toString()}' '${outfile.toString()}'"
+          "cp -a '${infileNoTrailingSlash}' '${outfileNoTrailingSlash}'"
         ]
       } else {
         // no need to copy if infile is the same as outfile
@@ -3035,7 +3045,7 @@ meta = [
   "config": processConfig(readJsonBlob('''{
   "name" : "concatenate_h5mu",
   "namespace" : "dataflow",
-  "version" : "v4.0.3",
+  "version" : "v4.1.0",
   "authors" : [
     {
       "name" : "Dries Schaumont",
@@ -3179,7 +3189,7 @@ meta = [
         {
           "type" : "string",
           "name" : "--output_compression",
-          "description" : "Compression format to use for the output AnnData and/or Mudata objects.\nBy default no compression is applied.\n",
+          "description" : "Compression format to use for the output AnnData and/or Mudata H5 files.\nBy default no compression is applied.\n",
           "example" : [
             "gzip"
           ],
@@ -3328,7 +3338,7 @@ meta = [
       "id" : "docker",
       "image" : "python:3.13-slim",
       "target_registry" : "images.viash-hub.com",
-      "target_tag" : "v4.0.3",
+      "target_tag" : "v4.1.0",
       "namespace_separator" : "/",
       "setup" : [
         {
@@ -3342,9 +3352,10 @@ meta = [
           "type" : "python",
           "user" : false,
           "packages" : [
-            "anndata~=0.12.7",
+            "anndata~=0.12.16",
             "awkward",
-            "mudata~=0.3.2"
+            "scipy~=1.17.1",
+            "mudata~=0.3.8"
           ],
           "script" : [
             "exec(\\"try:\\\\n  import zarr; from importlib.metadata import version\\\\nexcept ModuleNotFoundError:\\\\n  exit(0)\\\\nelse:  assert int(version(\\\\\\"zarr\\\\\\").partition(\\\\\\".\\\\\\")[0]) > 2\\")"
@@ -3364,7 +3375,7 @@ meta = [
           "type" : "python",
           "user" : false,
           "packages" : [
-            "viashpy==0.8.0"
+            "viashpy==0.10.0"
           ],
           "github" : [
             "openpipelines-bio/core#subdirectory=packages/python/openpipeline_testutils"
@@ -3375,7 +3386,7 @@ meta = [
           "type" : "python",
           "user" : false,
           "packages" : [
-            "viashpy==0.8.0",
+            "viashpy==0.10.0",
             "pytest-benchmark"
           ],
           "upgrade" : true
@@ -3392,13 +3403,13 @@ meta = [
     "runner" : "nextflow",
     "engine" : "docker|native",
     "output" : "/workdir/root/repo/target/nextflow/dataflow/concatenate_h5mu",
-    "viash_version" : "0.9.4",
+    "viash_version" : "0.9.7",
-    "git_commit" : "7bfad4ea12f87eca59213be3ab08deff67cc4206",
+    "git_commit" : "a6499fddaa8553874585c747370f919f4d7b729c",
     "git_remote" : "https://github.com/openpipelines-bio/openpipeline"
   },
   "package_config" : {
     "name" : "openpipeline",
-    "version" : "v4.0.3",
+    "version" : "v4.1.0",
     "summary" : "Best-practice workflows for single-cell multi-omics analyses.\n",
     "description" : "OpenPipelines are extensible single cell analysis pipelines for reproducible and large-scale single cell processing using [Viash](https://viash.io) and [Nextflow](https://www.nextflow.io/).\n\nIn terms of workflows, the following has been made available, but keep in mind that\nindividual tools and functionality can be executed as standalone components as well.\n\n  * Demultiplexing: conversion of raw sequencing data to FASTQ objects.\n  * Ingestion: Read mapping and generating a count matrix.\n  * Single sample processing: cell filtering and doublet detection.\n  * Multisample processing: Count transformation, normalization, QC metric calulations.\n  * Integration: Clustering, integration and batch correction using single and multimodal methods.\n  * Downstream analysis workflows\n",
     "info" : {
@@ -3416,14 +3427,14 @@ meta = [
         }
       ]
     },
-    "viash_version" : "0.9.4",
+    "viash_version" : "0.9.7",
     "source" : "/workdir/root/repo/src",
     "target" : "/workdir/root/repo/target",
     "config_mods" : [
       ".resources += {path: '/src/workflows/utils/labels.config', dest: 'nextflow_labels.config'}\n.runners[.type == 'nextflow'].config.script := 'includeConfig(\\"nextflow_labels.config\\")'",
       ".engines += { type: \\"native\\" }",
       ".engines[.type == 'docker'].target_registry := 'images.viash-hub.com'",
-      ".engines[.type == 'docker'].target_tag := 'v4.0.3'"
+      ".engines[.type == 'docker'].target_tag := 'v4.1.0'"
     ],
     "keywords" : [
       "single-cell",
@@ -4266,7 +4277,7 @@ meta["defaults"] = [
   "container" : {
     "registry" : "images.viash-hub.com",
     "image" : "vsh/openpipeline/dataflow/concatenate_h5mu",
-    "tag" : "v4.0.3"
+    "tag" : "v4.1.0"
   },
   "label" : [
     "midcpu",

target/dependencies/vsh/vsh/openpipeline/v4.1.0/nextflow/dataflow/concatenate_h5mu/nextflow.config

@@ -2,7 +2,7 @@ manifest {
   name = 'dataflow/concatenate_h5mu'
   mainScript = 'main.nf'
   nextflowVersion = '!>=20.12.1-edge'
-  version = 'v4.0.3'
+  version = 'v4.1.0'
   description = 'Concatenate observations from samples in several (uni- and/or multi-modal) MuData files into a single file.\n'
   author = 'Dries Schaumont'
 }

target/dependencies/vsh/vsh/openpipeline/v4.1.0/nextflow/dataflow/concatenate_h5mu/nextflow_schema.json

@@ -85,7 +85,7 @@
         },
         "output_compression": {
           "type": "string",
-          "description": "Compression format to use for the output AnnData and/or Mudata objects.\nBy default no compression is applied.\n",
+          "description": "Compression format to use for the output AnnData and/or Mudata H5 files.\nBy default no compression is applied.\n",
           "help_text": "Type: `string`, multiple: `False`, example: `\"gzip\"`, choices: ``gzip`, `lzf``. ",
           "enum": [
             "gzip",

target/dependencies/vsh/vsh/openpipeline/v4.1.0/nextflow/dataflow/merge/.config.vsh.yaml

@@ -1,6 +1,6 @@
 name: "merge"
 namespace: "dataflow"
-version: "v4.0.3"
+version: "v4.1.0"
 authors:
 - name: "Dries Schaumont"
   roles:
@@ -25,6 +25,9 @@ argument_groups:
     - "-i"
     description: "Paths to the single-modality .h5mu files that need to be combined"
     info: null
+    example:
+    - "/path/to/modality_1.h5mu"
+    - "/path/to/modality_2.h5mu"
     default:
     - "sample_paths"
     must_exist: true
@@ -163,7 +166,7 @@ engines:
   id: "docker"
   image: "python:3.12-slim"
   target_registry: "images.viash-hub.com"
-  target_tag: "v4.0.3"
+  target_tag: "v4.1.0"
   namespace_separator: "/"
   setup:
   - type: "apt"
@@ -173,9 +176,10 @@ engines:
   - type: "python"
     user: false
     packages:
-    - "anndata~=0.12.7"
+    - "anndata~=0.12.16"
     - "awkward"
-    - "mudata~=0.3.2"
+    - "scipy~=1.17.1"
+    - "mudata~=0.3.8"
     script:
     - "exec(\"try:\\n  import zarr; from importlib.metadata import version\\nexcept\
       \ ModuleNotFoundError:\\n  exit(0)\\nelse:  assert int(version(\\\"zarr\\\"\
@@ -189,7 +193,7 @@ engines:
   - type: "python"
     user: false
     packages:
-    - "viashpy==0.8.0"
+    - "viashpy==0.10.0"
     github:
     - "openpipelines-bio/core#subdirectory=packages/python/openpipeline_testutils"
     upgrade: true
@@ -203,12 +207,12 @@ build_info:
   engine: "docker|native"
   output: "target/nextflow/dataflow/merge"
   executable: "target/nextflow/dataflow/merge/main.nf"
-  viash_version: "0.9.4"
+  viash_version: "0.9.7"
-  git_commit: "7bfad4ea12f87eca59213be3ab08deff67cc4206"
+  git_commit: "a6499fddaa8553874585c747370f919f4d7b729c"
   git_remote: "https://github.com/openpipelines-bio/openpipeline"
 package_config:
   name: "openpipeline"
-  version: "v4.0.3"
+  version: "v4.1.0"
   summary: "Best-practice workflows for single-cell multi-omics analyses.\n"
   description: "OpenPipelines are extensible single cell analysis pipelines for reproducible\
     \ and large-scale single cell processing using [Viash](https://viash.io) and [Nextflow](https://www.nextflow.io/).\n\
@@ -229,7 +233,7 @@ package_config:
     - path: "src/workflows/utils/labels_ci.config"
       description: "Adds the correct memory and CPU labels when running on the Viash\
         \ Hub CI."
-  viash_version: "0.9.4"
+  viash_version: "0.9.7"
   source: "src"
   target: "target"
   config_mods:
@@ -238,7 +242,7 @@ package_config:
     )'"
   - ".engines += { type: \"native\" }"
   - ".engines[.type == 'docker'].target_registry := 'images.viash-hub.com'"
-  - ".engines[.type == 'docker'].target_tag := 'v4.0.3'"
+  - ".engines[.type == 'docker'].target_tag := 'v4.1.0'"
   keywords:
   - "single-cell"
   - "multimodal"

target/dependencies/vsh/vsh/openpipeline/v4.1.0/nextflow/dataflow/merge/main.nf

@@ -1,6 +1,6 @@
-// merge v4.0.3
+// merge v4.1.0
 // 
-// This wrapper script is auto-generated by viash 0.9.4 and is thus a derivative
+// This wrapper script is auto-generated by viash 0.9.7 and is thus a derivative
 // work thereof. This software comes with ABSOLUTELY NO WARRANTY from Data
 // Intuitive.
 // 
@@ -1353,47 +1353,42 @@ def readCsv(file_path) {
   def splitRegex = java.util.regex.Pattern.compile(''',(?=(?:[^"]*"[^"]*")*[^"]*$)''')
   def removeQuote = java.util.regex.Pattern.compile('''"(.*)"''')
 
-  def br = java.nio.file.Files.newBufferedReader(inputFile)
+  java.nio.file.Files.newBufferedReader(inputFile).withCloseable { br ->
+    def row = 0
+    def header = null
+    def line
 
-  def row = -1
+    while (header == null && (line = br.readLine()) != null) {
-  def header = null
+      if (!line.startsWith("#")) {
-  while (br.ready() && header == null) {
+        header = splitRegex.split(line, -1).collect { field ->
-    def line = br.readLine()
+          def m = removeQuote.matcher(field)
-    row++
+          m.find() ? m.replaceFirst('$1') : field
-    if (!line.startsWith("#")) {
-      header = splitRegex.split(line, -1).collect{field ->
-        m = removeQuote.matcher(field)
-        m.find() ? m.replaceFirst('$1') : field
-      }
-    }
-  }
-  assert header != null: "CSV file should contain a header"
-
-  while (br.ready()) {
-    def line = br.readLine()
-    row++
-    if (line == null) {
-      br.close()
-      break
-    }
-
-    if (!line.startsWith("#")) {
-      def predata = splitRegex.split(line, -1)
-      def data = predata.collect{field ->
-        if (field == "") {
-          return null
-        }
-        def m = removeQuote.matcher(field)
-        if (m.find()) {
-          return m.replaceFirst('$1')
-        } else {
-          return field
         }
       }
-      assert header.size() == data.size(): "Row $row should contain the same number as fields as the header"
+      row++
-      
+    }
-      def dataMap = [header, data].transpose().collectEntries().findAll{it.value != null}
+    assert header != null : "CSV file should contain a header"
-      output.add(dataMap)
+
+    while ((line = br.readLine()) != null) {
+      row++
+      if (!line.startsWith("#")) {
+        def predata = splitRegex.split(line, -1)
+        def data = predata.collect { field ->
+          if (field == "") {
+            return null
+          }
+          def m = removeQuote.matcher(field)
+          if (m.find()) {
+            return m.replaceFirst('$1')
+          } else {
+            return field
+          }
+        }
+        assert header.size() == data.size() : "Row $row should contain the same number as fields as the header"
+
+        def dataMap = [header, data].transpose().collectEntries().findAll { it.value != null }
+        output.add(dataMap)
+      }
     }
   }
 
@@ -1709,10 +1704,25 @@ process publishFilesProc {
   ]
     .transpose()
     .collectMany{infile, outfile ->
-      if (infile.toString() != outfile.toString()) {
+      def infileString = infile.toString()
+      def outfileString = outfile.toString()
+      if (infileString != outfileString) {
+        /* Trailing slashes are removed from both the source and destination arguments.
+           From source arguments, this is useful when a source argument may have a trailing slash
+           and specify a symbolic link to a directory. Without removing the slash, cp will dereference
+           the symbolic link. 
+           See https://www.gnu.org/software/coreutils/manual/html_node/Trailing-slashes.html#Trailing-slashes-1
+
+           For the destination path addding a trailing slash is a problem when publishing directories: 
+           it requires the destination directory to exist. This fails because we only create the parent
+           directories first.
+        */
+        def regexTrailingSlashes = ~/\/+$/
+        def infileNoTrailingSlash = infileString - regexTrailingSlashes
+        def outfileNoTrailingSlash = outfileString - regexTrailingSlashes
         [
-          "[ -d \"\$(dirname '${outfile.toString()}')\" ] || mkdir -p \"\$(dirname '${outfile.toString()}')\"",
+          "[ -d \"\$(dirname '${outfileNoTrailingSlash}')\" ] || mkdir -p \"\$(dirname '${outfileNoTrailingSlash}')\"",
-          "cp -r '${infile.toString()}' '${outfile.toString()}'"
+          "cp -a '${infileNoTrailingSlash}' '${outfileNoTrailingSlash}'"
         ]
       } else {
         // no need to copy if infile is the same as outfile
@@ -3035,7 +3045,7 @@ meta = [
   "config": processConfig(readJsonBlob('''{
   "name" : "merge",
   "namespace" : "dataflow",
-  "version" : "v4.0.3",
+  "version" : "v4.1.0",
   "authors" : [
     {
       "name" : "Dries Schaumont",
@@ -3071,6 +3081,10 @@ meta = [
             "-i"
           ],
           "description" : "Paths to the single-modality .h5mu files that need to be combined",
+          "example" : [
+            "/path/to/modality_1.h5mu",
+            "/path/to/modality_2.h5mu"
+          ],
           "default" : [
             "sample_paths"
           ],
@@ -3246,7 +3260,7 @@ meta = [
       "id" : "docker",
       "image" : "python:3.12-slim",
       "target_registry" : "images.viash-hub.com",
-      "target_tag" : "v4.0.3",
+      "target_tag" : "v4.1.0",
       "namespace_separator" : "/",
       "setup" : [
         {
@@ -3260,9 +3274,10 @@ meta = [
           "type" : "python",
           "user" : false,
           "packages" : [
-            "anndata~=0.12.7",
+            "anndata~=0.12.16",
             "awkward",
-            "mudata~=0.3.2"
+            "scipy~=1.17.1",
+            "mudata~=0.3.8"
           ],
           "script" : [
             "exec(\\"try:\\\\n  import zarr; from importlib.metadata import version\\\\nexcept ModuleNotFoundError:\\\\n  exit(0)\\\\nelse:  assert int(version(\\\\\\"zarr\\\\\\").partition(\\\\\\".\\\\\\")[0]) > 2\\")"
@@ -3282,7 +3297,7 @@ meta = [
           "type" : "python",
           "user" : false,
           "packages" : [
-            "viashpy==0.8.0"
+            "viashpy==0.10.0"
           ],
           "github" : [
             "openpipelines-bio/core#subdirectory=packages/python/openpipeline_testutils"
@@ -3301,13 +3316,13 @@ meta = [
     "runner" : "nextflow",
     "engine" : "docker|native",
     "output" : "/workdir/root/repo/target/nextflow/dataflow/merge",
-    "viash_version" : "0.9.4",
+    "viash_version" : "0.9.7",
-    "git_commit" : "7bfad4ea12f87eca59213be3ab08deff67cc4206",
+    "git_commit" : "a6499fddaa8553874585c747370f919f4d7b729c",
     "git_remote" : "https://github.com/openpipelines-bio/openpipeline"
   },
   "package_config" : {
     "name" : "openpipeline",
-    "version" : "v4.0.3",
+    "version" : "v4.1.0",
     "summary" : "Best-practice workflows for single-cell multi-omics analyses.\n",
     "description" : "OpenPipelines are extensible single cell analysis pipelines for reproducible and large-scale single cell processing using [Viash](https://viash.io) and [Nextflow](https://www.nextflow.io/).\n\nIn terms of workflows, the following has been made available, but keep in mind that\nindividual tools and functionality can be executed as standalone components as well.\n\n  * Demultiplexing: conversion of raw sequencing data to FASTQ objects.\n  * Ingestion: Read mapping and generating a count matrix.\n  * Single sample processing: cell filtering and doublet detection.\n  * Multisample processing: Count transformation, normalization, QC metric calulations.\n  * Integration: Clustering, integration and batch correction using single and multimodal methods.\n  * Downstream analysis workflows\n",
     "info" : {
@@ -3325,14 +3340,14 @@ meta = [
         }
       ]
     },
-    "viash_version" : "0.9.4",
+    "viash_version" : "0.9.7",
     "source" : "/workdir/root/repo/src",
     "target" : "/workdir/root/repo/target",
     "config_mods" : [
       ".resources += {path: '/src/workflows/utils/labels.config', dest: 'nextflow_labels.config'}\n.runners[.type == 'nextflow'].config.script := 'includeConfig(\\"nextflow_labels.config\\")'",
       ".engines += { type: \\"native\\" }",
       ".engines[.type == 'docker'].target_registry := 'images.viash-hub.com'",
-      ".engines[.type == 'docker'].target_tag := 'v4.0.3'"
+      ".engines[.type == 'docker'].target_tag := 'v4.1.0'"
     ],
     "keywords" : [
       "single-cell",
@@ -3847,7 +3862,7 @@ meta["defaults"] = [
   "container" : {
     "registry" : "images.viash-hub.com",
     "image" : "vsh/openpipeline/dataflow/merge",
-    "tag" : "v4.0.3"
+    "tag" : "v4.1.0"
   },
   "label" : [
     "singlecpu",

target/dependencies/vsh/vsh/openpipeline/v4.1.0/nextflow/dataflow/merge/nextflow.config

@@ -2,7 +2,7 @@ manifest {
   name = 'dataflow/merge'
   mainScript = 'main.nf'
   nextflowVersion = '!>=20.12.1-edge'
-  version = 'v4.0.3'
+  version = 'v4.1.0'
   description = 'Combine one or more single-modality .h5mu files together into one .h5mu file.\n'
   author = 'Dries Schaumont'
 }

target/dependencies/vsh/vsh/openpipeline/v4.1.0/nextflow/dataflow/merge/nextflow_schema.json

@@ -17,7 +17,7 @@
           "format": "path",
           "exists": true,
           "description": "Paths to the single-modality .h5mu files that need to be combined",
-          "help_text": "Type: `file`, multiple: `True`, required, default: `[\"sample_paths\"]`, direction: `input`. ",
+          "help_text": "Type: `file`, multiple: `True`, required, default: `[\"sample_paths\"]`, direction: `input`, example: `[\"/path/to/modality_1.h5mu\";\"/path/to/modality_2.h5mu\"]`. ",
           "default": [
             "sample_paths"
           ]

target/dependencies/vsh/vsh/openpipeline/v4.1.0/nextflow/dataflow/split_modalities/.config.vsh.yaml

@@ -1,6 +1,6 @@
 name: "split_modalities"
 namespace: "dataflow"
-version: "v4.0.3"
+version: "v4.1.0"
 authors:
 - name: "Dries Schaumont"
   roles:
@@ -42,6 +42,8 @@ argument_groups:
     - "-i"
     description: "Path to a single .h5mu file."
     info: null
+    example:
+    - "input.h5mu"
     default:
     - "sample_path"
     must_exist: true
@@ -79,8 +81,8 @@ argument_groups:
     multiple_sep: ";"
   - type: "string"
     name: "--output_compression"
-    description: "Compression format to use for the output AnnData and/or Mudata objects.\n\
+    description: "Compression format to use for the output AnnData and/or Mudata H5\
-      By default no compression is applied.\n"
+      \ files.\nBy default no compression is applied.\n"
     info: null
     example:
     - "gzip"
@@ -97,6 +99,8 @@ resources:
   is_executable: true
 - type: "file"
   path: "setup_logger.py"
+- type: "file"
+  path: "mudata_opener.py"
 - type: "file"
   path: "nextflow_labels.config"
   dest: "nextflow_labels.config"
@@ -190,7 +194,7 @@ engines:
   id: "docker"
   image: "python:3.12-slim"
   target_registry: "images.viash-hub.com"
-  target_tag: "v4.0.3"
+  target_tag: "v4.1.0"
   namespace_separator: "/"
   setup:
   - type: "apt"
@@ -200,9 +204,10 @@ engines:
   - type: "python"
     user: false
     packages:
-    - "anndata~=0.12.7"
+    - "anndata~=0.12.16"
     - "awkward"
-    - "mudata~=0.3.2"
+    - "scipy~=1.17.1"
+    - "mudata~=0.3.8"
     script:
     - "exec(\"try:\\n  import zarr; from importlib.metadata import version\\nexcept\
       \ ModuleNotFoundError:\\n  exit(0)\\nelse:  assert int(version(\\\"zarr\\\"\
@@ -216,7 +221,7 @@ engines:
   - type: "python"
     user: false
     packages:
-    - "viashpy==0.8.0"
+    - "viashpy==0.10.0"
     github:
     - "openpipelines-bio/core#subdirectory=packages/python/openpipeline_testutils"
     upgrade: true
@@ -230,12 +235,12 @@ build_info:
   engine: "docker|native"
   output: "target/nextflow/dataflow/split_modalities"
   executable: "target/nextflow/dataflow/split_modalities/main.nf"
-  viash_version: "0.9.4"
+  viash_version: "0.9.7"
-  git_commit: "7bfad4ea12f87eca59213be3ab08deff67cc4206"
+  git_commit: "a6499fddaa8553874585c747370f919f4d7b729c"
   git_remote: "https://github.com/openpipelines-bio/openpipeline"
 package_config:
   name: "openpipeline"
-  version: "v4.0.3"
+  version: "v4.1.0"
   summary: "Best-practice workflows for single-cell multi-omics analyses.\n"
   description: "OpenPipelines are extensible single cell analysis pipelines for reproducible\
     \ and large-scale single cell processing using [Viash](https://viash.io) and [Nextflow](https://www.nextflow.io/).\n\
@@ -256,7 +261,7 @@ package_config:
     - path: "src/workflows/utils/labels_ci.config"
       description: "Adds the correct memory and CPU labels when running on the Viash\
         \ Hub CI."
-  viash_version: "0.9.4"
+  viash_version: "0.9.7"
   source: "src"
   target: "target"
   config_mods:
@@ -265,7 +270,7 @@ package_config:
     )'"
   - ".engines += { type: \"native\" }"
   - ".engines[.type == 'docker'].target_registry := 'images.viash-hub.com'"
-  - ".engines[.type == 'docker'].target_tag := 'v4.0.3'"
+  - ".engines[.type == 'docker'].target_tag := 'v4.1.0'"
   keywords:
   - "single-cell"
   - "multimodal"

target/dependencies/vsh/vsh/openpipeline/v4.1.0/nextflow/dataflow/split_modalities/main.nf

@@ -1,6 +1,6 @@
-// split_modalities v4.0.3
+// split_modalities v4.1.0
 // 
-// This wrapper script is auto-generated by viash 0.9.4 and is thus a derivative
+// This wrapper script is auto-generated by viash 0.9.7 and is thus a derivative
 // work thereof. This software comes with ABSOLUTELY NO WARRANTY from Data
 // Intuitive.
 // 
@@ -1354,47 +1354,42 @@ def readCsv(file_path) {
   def splitRegex = java.util.regex.Pattern.compile(''',(?=(?:[^"]*"[^"]*")*[^"]*$)''')
   def removeQuote = java.util.regex.Pattern.compile('''"(.*)"''')
 
-  def br = java.nio.file.Files.newBufferedReader(inputFile)
+  java.nio.file.Files.newBufferedReader(inputFile).withCloseable { br ->
+    def row = 0
+    def header = null
+    def line
 
-  def row = -1
+    while (header == null && (line = br.readLine()) != null) {
-  def header = null
+      if (!line.startsWith("#")) {
-  while (br.ready() && header == null) {
+        header = splitRegex.split(line, -1).collect { field ->
-    def line = br.readLine()
+          def m = removeQuote.matcher(field)
-    row++
+          m.find() ? m.replaceFirst('$1') : field
-    if (!line.startsWith("#")) {
-      header = splitRegex.split(line, -1).collect{field ->
-        m = removeQuote.matcher(field)
-        m.find() ? m.replaceFirst('$1') : field
-      }
-    }
-  }
-  assert header != null: "CSV file should contain a header"
-
-  while (br.ready()) {
-    def line = br.readLine()
-    row++
-    if (line == null) {
-      br.close()
-      break
-    }
-
-    if (!line.startsWith("#")) {
-      def predata = splitRegex.split(line, -1)
-      def data = predata.collect{field ->
-        if (field == "") {
-          return null
-        }
-        def m = removeQuote.matcher(field)
-        if (m.find()) {
-          return m.replaceFirst('$1')
-        } else {
-          return field
         }
       }
-      assert header.size() == data.size(): "Row $row should contain the same number as fields as the header"
+      row++
-      
+    }
-      def dataMap = [header, data].transpose().collectEntries().findAll{it.value != null}
+    assert header != null : "CSV file should contain a header"
-      output.add(dataMap)
+
+    while ((line = br.readLine()) != null) {
+      row++
+      if (!line.startsWith("#")) {
+        def predata = splitRegex.split(line, -1)
+        def data = predata.collect { field ->
+          if (field == "") {
+            return null
+          }
+          def m = removeQuote.matcher(field)
+          if (m.find()) {
+            return m.replaceFirst('$1')
+          } else {
+            return field
+          }
+        }
+        assert header.size() == data.size() : "Row $row should contain the same number as fields as the header"
+
+        def dataMap = [header, data].transpose().collectEntries().findAll { it.value != null }
+        output.add(dataMap)
+      }
     }
   }
 
@@ -1710,10 +1705,25 @@ process publishFilesProc {
   ]
     .transpose()
     .collectMany{infile, outfile ->
-      if (infile.toString() != outfile.toString()) {
+      def infileString = infile.toString()
+      def outfileString = outfile.toString()
+      if (infileString != outfileString) {
+        /* Trailing slashes are removed from both the source and destination arguments.
+           From source arguments, this is useful when a source argument may have a trailing slash
+           and specify a symbolic link to a directory. Without removing the slash, cp will dereference
+           the symbolic link. 
+           See https://www.gnu.org/software/coreutils/manual/html_node/Trailing-slashes.html#Trailing-slashes-1
+
+           For the destination path addding a trailing slash is a problem when publishing directories: 
+           it requires the destination directory to exist. This fails because we only create the parent
+           directories first.
+        */
+        def regexTrailingSlashes = ~/\/+$/
+        def infileNoTrailingSlash = infileString - regexTrailingSlashes
+        def outfileNoTrailingSlash = outfileString - regexTrailingSlashes
         [
-          "[ -d \"\$(dirname '${outfile.toString()}')\" ] || mkdir -p \"\$(dirname '${outfile.toString()}')\"",
+          "[ -d \"\$(dirname '${outfileNoTrailingSlash}')\" ] || mkdir -p \"\$(dirname '${outfileNoTrailingSlash}')\"",
-          "cp -r '${infile.toString()}' '${outfile.toString()}'"
+          "cp -a '${infileNoTrailingSlash}' '${outfileNoTrailingSlash}'"
         ]
       } else {
         // no need to copy if infile is the same as outfile
@@ -3036,7 +3046,7 @@ meta = [
   "config": processConfig(readJsonBlob('''{
   "name" : "split_modalities",
   "namespace" : "dataflow",
-  "version" : "v4.0.3",
+  "version" : "v4.1.0",
   "authors" : [
     {
       "name" : "Dries Schaumont",
@@ -3099,6 +3109,9 @@ meta = [
             "-i"
           ],
           "description" : "Path to a single .h5mu file.",
+          "example" : [
+            "input.h5mu"
+          ],
           "default" : [
             "sample_path"
           ],
@@ -3143,7 +3156,7 @@ meta = [
         {
           "type" : "string",
           "name" : "--output_compression",
-          "description" : "Compression format to use for the output AnnData and/or Mudata objects.\nBy default no compression is applied.\n",
+          "description" : "Compression format to use for the output AnnData and/or Mudata H5 files.\nBy default no compression is applied.\n",
           "example" : [
             "gzip"
           ],
@@ -3169,6 +3182,10 @@ meta = [
       "type" : "file",
       "path" : "/src/utils/setup_logger.py"
     },
+    {
+      "type" : "file",
+      "path" : "/src/utils/mudata_opener.py"
+    },
     {
       "type" : "file",
       "path" : "/src/workflows/utils/labels.config",
@@ -3280,7 +3297,7 @@ meta = [
       "id" : "docker",
       "image" : "python:3.12-slim",
       "target_registry" : "images.viash-hub.com",
-      "target_tag" : "v4.0.3",
+      "target_tag" : "v4.1.0",
       "namespace_separator" : "/",
       "setup" : [
         {
@@ -3294,9 +3311,10 @@ meta = [
           "type" : "python",
           "user" : false,
           "packages" : [
-            "anndata~=0.12.7",
+            "anndata~=0.12.16",
             "awkward",
-            "mudata~=0.3.2"
+            "scipy~=1.17.1",
+            "mudata~=0.3.8"
           ],
           "script" : [
             "exec(\\"try:\\\\n  import zarr; from importlib.metadata import version\\\\nexcept ModuleNotFoundError:\\\\n  exit(0)\\\\nelse:  assert int(version(\\\\\\"zarr\\\\\\").partition(\\\\\\".\\\\\\")[0]) > 2\\")"
@@ -3316,7 +3334,7 @@ meta = [
           "type" : "python",
           "user" : false,
           "packages" : [
-            "viashpy==0.8.0"
+            "viashpy==0.10.0"
           ],
           "github" : [
             "openpipelines-bio/core#subdirectory=packages/python/openpipeline_testutils"
@@ -3335,13 +3353,13 @@ meta = [
     "runner" : "nextflow",
     "engine" : "docker|native",
     "output" : "/workdir/root/repo/target/nextflow/dataflow/split_modalities",
-    "viash_version" : "0.9.4",
+    "viash_version" : "0.9.7",
-    "git_commit" : "7bfad4ea12f87eca59213be3ab08deff67cc4206",
+    "git_commit" : "a6499fddaa8553874585c747370f919f4d7b729c",
     "git_remote" : "https://github.com/openpipelines-bio/openpipeline"
   },
   "package_config" : {
     "name" : "openpipeline",
-    "version" : "v4.0.3",
+    "version" : "v4.1.0",
     "summary" : "Best-practice workflows for single-cell multi-omics analyses.\n",
     "description" : "OpenPipelines are extensible single cell analysis pipelines for reproducible and large-scale single cell processing using [Viash](https://viash.io) and [Nextflow](https://www.nextflow.io/).\n\nIn terms of workflows, the following has been made available, but keep in mind that\nindividual tools and functionality can be executed as standalone components as well.\n\n  * Demultiplexing: conversion of raw sequencing data to FASTQ objects.\n  * Ingestion: Read mapping and generating a count matrix.\n  * Single sample processing: cell filtering and doublet detection.\n  * Multisample processing: Count transformation, normalization, QC metric calulations.\n  * Integration: Clustering, integration and batch correction using single and multimodal methods.\n  * Downstream analysis workflows\n",
     "info" : {
@@ -3359,14 +3377,14 @@ meta = [
         }
       ]
     },
-    "viash_version" : "0.9.4",
+    "viash_version" : "0.9.7",
     "source" : "/workdir/root/repo/src",
     "target" : "/workdir/root/repo/target",
     "config_mods" : [
       ".resources += {path: '/src/workflows/utils/labels.config', dest: 'nextflow_labels.config'}\n.runners[.type == 'nextflow'].config.script := 'includeConfig(\\"nextflow_labels.config\\")'",
       ".engines += { type: \\"native\\" }",
       ".engines[.type == 'docker'].target_registry := 'images.viash-hub.com'",
-      ".engines[.type == 'docker'].target_tag := 'v4.0.3'"
+      ".engines[.type == 'docker'].target_tag := 'v4.1.0'"
     ],
     "keywords" : [
       "single-cell",
@@ -3395,11 +3413,14 @@ def innerWorkflowFactory(args) {
 tempscript=".viash_script.py"
 cat > "$tempscript" << VIASHMAIN
 from __future__ import annotations
+from functools import partial
 import sys
 import mudata as md
+import anndata as ad
 from pathlib import Path
 import pandas as pd
 
+
 ### VIASH START
 # The following code has been auto-generated by Viash.
 par = {
@@ -3436,6 +3457,7 @@ dep = {
 
 sys.path.append(meta["resources_dir"])
 from setup_logger import setup_logger
+from mudata_opener import mudata_opener
 
 logger = setup_logger()
 
@@ -3447,36 +3469,54 @@ def main() -> None:
         logger.info("Creating %s", output_dir)
         output_dir.mkdir(parents=True)
 
-    logger.info("Reading input file '%s'", par["input"])
+    input_file = Path(par["input"])
-    input_file = Path(par["input"].strip())
+    logger.info("Checking which modalities exist for '%s'", par["input"])
-    sample = md.read_h5mu(input_file)
+    with mudata_opener(input_file, mode="r") as (open_mudata, input_is_zarr):
-
-    logger.info("Creating output types CSV.")
-    modalities = list(sample.mod.keys())
-
-    logger.info("Found the following modalities:\\\\n%s", "\\\\n".join(modalities))
-    names = {mod_name: f"{input_file.stem}_{mod_name}.h5mu" for mod_name in modalities}
-    output_files = list(names.values())
-    logger.info(
-        "Will be creating the following output .h5mu files:\\\\n%s",
-        "\\\\n".join(output_files),
-    )
-    df = pd.DataFrame({"name": modalities, "filename": output_files})
-    logger.info("Writing output_types CSV file to '%s'.", par["output_types"])
-    df.to_csv(par["output_types"], index=False)
-
-    logger.info("Splitting input file into unimodal output files.")
-    for mod_name, mod in sample.mod.items():
-        logger.info("Processing modality '%s'", mod_name)
-        new_sample = md.MuData({mod_name: mod})
         logger.info(
-            "Writing to '%s', with compression '%s'",
+            "Opened %s in %s format.", par["input"], "zarr" if input_is_zarr else "h5"
-            names[mod_name],
-            par["output_compression"],
         )
-        new_sample.write_h5mu(
+
-            output_dir / names[mod_name], compression=par["output_compression"]
+        modalities = list(open_mudata["mod"].keys())
+        logger.info("Found the following modalities:\\\\n%s", "\\\\n".join(modalities))
+
+        logger.info("Creating output types CSV.")
+        output_extension = "zarr" if input_is_zarr else "h5mu"
+        names = {
+            mod_name: f"{input_file.stem}_{mod_name}.{output_extension}"
+            for mod_name in modalities
+        }
+        output_files = list(names.values())
+        logger.info(
+            "Will be creating the following output .%s files:\\\\n%s",
+            output_extension,
+            "\\\\n".join(output_files),
         )
+        df = pd.DataFrame({"name": modalities, "filename": output_files})
+        logger.info("Writing output_types CSV file to '%s'.", par["output_types"])
+        df.to_csv(par["output_types"], index=False)
+
+        logger.info("Splitting input file into unimodal output files.")
+        for mod_name in modalities:
+            logger.info("Processing modality '%s'", mod_name)
+            elem_key = f"/mod/{mod_name}"
+            elem = open_mudata[elem_key]
+            logger.info("Reading %s", elem_key)
+            new_ad = ad.io.read_elem(elem)
+            logger.info("Creating MuData object.")
+            new_sample = md.MuData({mod_name: new_ad})
+            logger.info(
+                "Writing to '%s', with compression '%s'",
+                names[mod_name],
+                par["output_compression"],
+            )
+            writer = (
+                partial(md.MuData.write_zarr, zarr_format=3)
+                if input_is_zarr
+                else partial(
+                    md.MuData.write_h5mu, compression=par["output_compression"]
+                )
+            )
+            writer(new_sample, output_dir / names[mod_name])
         logger.info("Done writing output file.")
     logger.info("Finished")
 
@@ -3865,7 +3905,7 @@ meta["defaults"] = [
   "container" : {
     "registry" : "images.viash-hub.com",
     "image" : "vsh/openpipeline/dataflow/split_modalities",
-    "tag" : "v4.0.3"
+    "tag" : "v4.1.0"
   },
   "label" : [
     "singlecpu",

target/dependencies/vsh/vsh/openpipeline/v4.1.0/nextflow/dataflow/split_modalities/mudata_opener.py

@@ -0,0 +1,27 @@
+import zarr
+import h5py
+from contextlib import contextmanager
+
+
+@contextmanager
+def mudata_opener(file_loc, mode=None):
+    open_mudata = None
+    input_is_zarr = False
+    try:
+        open_mudata = zarr.open(file_loc, zarr_format=3, mode=mode)
+        input_is_zarr = True
+        yield open_mudata, input_is_zarr
+    except (zarr.errors.GroupNotFoundError, NotADirectoryError):
+        try:
+            open_mudata = h5py.File(file_loc, mode=mode)
+            yield open_mudata, input_is_zarr
+        except (FileNotFoundError, IsADirectoryError, KeyError) as e:
+            e.add_note(f"Could not open file {file_loc}.")
+            raise e
+        finally:
+            try:
+                if open_mudata:
+                    open_mudata.close()
+                    del open_mudata
+            except (AttributeError, UnboundLocalError):
+                pass

target/dependencies/vsh/vsh/openpipeline/v4.1.0/nextflow/dataflow/split_modalities/nextflow.config

@@ -2,7 +2,7 @@ manifest {
   name = 'dataflow/split_modalities'
   mainScript = 'main.nf'
   nextflowVersion = '!>=20.12.1-edge'
-  version = 'v4.0.3'
+  version = 'v4.1.0'
   description = 'Split the modalities from a single .h5mu multimodal sample into seperate .h5mu files. \n'
   author = 'Dries Schaumont, Robrecht Cannoodt'
 }

target/dependencies/vsh/vsh/openpipeline/v4.1.0/nextflow/dataflow/split_modalities/nextflow_schema.json

@@ -14,7 +14,7 @@
           "format": "path",
           "exists": true,
           "description": "Path to a single .h5mu file.",
-          "help_text": "Type: `file`, multiple: `False`, required, default: `\"sample_path\"`, direction: `input`. ",
+          "help_text": "Type: `file`, multiple: `False`, required, default: `\"sample_path\"`, direction: `input`, example: `\"input.h5mu\"`. ",
           "default": "sample_path"
         },
         "output": {
@@ -33,7 +33,7 @@
         },
         "output_compression": {
           "type": "string",
-          "description": "Compression format to use for the output AnnData and/or Mudata objects.\nBy default no compression is applied.\n",
+          "description": "Compression format to use for the output AnnData and/or Mudata H5 files.\nBy default no compression is applied.\n",
           "help_text": "Type: `string`, multiple: `False`, example: `\"gzip\"`, choices: ``gzip`, `lzf``. ",
           "enum": [
             "gzip",

target/dependencies/vsh/vsh/openpipeline/v4.1.0/nextflow/dimred/pca/.config.vsh.yaml

@@ -1,6 +1,6 @@
 name: "pca"
 namespace: "dimred"
-version: "v4.0.3"
+version: "v4.1.0"
 authors:
 - name: "Dries De Maeyer"
   roles:
@@ -17,6 +17,22 @@ authors:
       role: "Principal Scientist"
 argument_groups:
 - name: "Arguments"
+  arguments:
+  - type: "string"
+    name: "--output_compression"
+    description: "Compression format to use for the output AnnData and/or Mudata H5\
+      \ files.\nBy default no compression is applied.\n"
+    info: null
+    example:
+    - "gzip"
+    required: false
+    choices:
+    - "gzip"
+    - "lzf"
+    direction: "input"
+    multiple: false
+    multiple_sep: ";"
+- name: "inputs"
   arguments:
   - type: "file"
     name: "--input"
@@ -62,6 +78,47 @@ argument_groups:
     direction: "input"
     multiple: false
     multiple_sep: ";"
+- name: "Options"
+  arguments:
+  - type: "integer"
+    name: "--num_components"
+    description: "Number of principal components to compute. Defaults to 50, or 1\
+      \ - minimum dimension size of selected representation."
+    info: null
+    example:
+    - 25
+    required: false
+    direction: "input"
+    multiple: false
+    multiple_sep: ";"
+  - type: "boolean_true"
+    name: "--chunked"
+    description: "If True, perform an incremental PCA on segments of a predefined\
+      \ size. Setting this flag automatically implies zero centering.\nMust be specified\
+      \ together with --chunk_size.\n"
+    info: null
+    direction: "input"
+  - type: "integer"
+    name: "--chunk_size"
+    description: "Number of observations to include in each chunk. Required if chunked=True\
+      \ was passed.\n"
+    info: null
+    required: false
+    min: 2
+    direction: "input"
+    multiple: false
+    multiple_sep: ";"
+  - type: "integer"
+    name: "--seed"
+    description: "Used to set the initial states for the optimization. \n"
+    info: null
+    required: false
+    min: 0
+    direction: "input"
+    multiple: false
+    multiple_sep: ";"
+- name: "Outputs"
+  arguments:
   - type: "file"
     name: "--output"
     alternatives:
@@ -106,36 +163,11 @@ argument_groups:
     direction: "input"
     multiple: false
     multiple_sep: ";"
-  - type: "integer"
-    name: "--num_components"
-    description: "Number of principal components to compute. Defaults to 50, or 1\
-      \ - minimum dimension size of selected representation."
-    info: null
-    example:
-    - 25
-    required: false
-    direction: "input"
-    multiple: false
-    multiple_sep: ";"
   - type: "boolean_true"
     name: "--overwrite"
     description: "Allow overwriting .obsm, .varm and .uns slots."
     info: null
     direction: "input"
-  - type: "string"
-    name: "--output_compression"
-    description: "Compression format to use for the output AnnData and/or Mudata objects.\n\
-      By default no compression is applied.\n"
-    info: null
-    example:
-    - "gzip"
-    required: false
-    choices:
-    - "gzip"
-    - "lzf"
-    direction: "input"
-    multiple: false
-    multiple_sep: ";"
 resources:
 - type: "python_script"
   path: "script.py"
@@ -147,8 +179,7 @@ resources:
 - type: "file"
   path: "nextflow_labels.config"
   dest: "nextflow_labels.config"
-description: "Computes PCA coordinates, loadings and variance decomposition. Uses\
+description: "Computes PCA coordinates, loadings and variance decomposition.\n"
-  \ the implementation of scikit-learn [Pedregosa11].\n"
 test_resources:
 - type: "python_script"
   path: "test.py"
@@ -238,9 +269,9 @@ runners:
 engines:
 - type: "docker"
   id: "docker"
-  image: "python:3.12-slim"
+  image: "python:3.13-slim"
   target_registry: "images.viash-hub.com"
-  target_tag: "v4.0.3"
+  target_tag: "v4.1.0"
   namespace_separator: "/"
   setup:
   - type: "apt"
@@ -250,9 +281,10 @@ engines:
   - type: "python"
     user: false
     packages:
-    - "anndata~=0.12.7"
+    - "anndata~=0.12.16"
     - "awkward"
-    - "mudata~=0.3.2"
+    - "scipy~=1.17.1"
+    - "mudata~=0.3.8"
     - "scanpy~=1.11.4"
     script:
     - "exec(\"try:\\n  import zarr; from importlib.metadata import version\\nexcept\
@@ -260,10 +292,16 @@ engines:
       ).partition(\\\".\\\")[0]) > 2\")"
     upgrade: true
   test_setup:
+  - type: "apt"
+    packages:
+    - "git"
+    interactive: false
   - type: "python"
     user: false
     packages:
-    - "viashpy==0.8.0"
+    - "viashpy==0.10.0"
+    github:
+    - "openpipelines-bio/core#subdirectory=packages/python/openpipeline_testutils"
     upgrade: true
   entrypoint: []
   cmd: null
@@ -275,12 +313,12 @@ build_info:
   engine: "docker|native"
   output: "target/nextflow/dimred/pca"
   executable: "target/nextflow/dimred/pca/main.nf"
-  viash_version: "0.9.4"
+  viash_version: "0.9.7"
-  git_commit: "7bfad4ea12f87eca59213be3ab08deff67cc4206"
+  git_commit: "a6499fddaa8553874585c747370f919f4d7b729c"
   git_remote: "https://github.com/openpipelines-bio/openpipeline"
 package_config:
   name: "openpipeline"
-  version: "v4.0.3"
+  version: "v4.1.0"
   summary: "Best-practice workflows for single-cell multi-omics analyses.\n"
   description: "OpenPipelines are extensible single cell analysis pipelines for reproducible\
     \ and large-scale single cell processing using [Viash](https://viash.io) and [Nextflow](https://www.nextflow.io/).\n\
@@ -301,7 +339,7 @@ package_config:
     - path: "src/workflows/utils/labels_ci.config"
       description: "Adds the correct memory and CPU labels when running on the Viash\
         \ Hub CI."
-  viash_version: "0.9.4"
+  viash_version: "0.9.7"
   source: "src"
   target: "target"
   config_mods:
@@ -310,7 +348,7 @@ package_config:
     )'"
   - ".engines += { type: \"native\" }"
   - ".engines[.type == 'docker'].target_registry := 'images.viash-hub.com'"
-  - ".engines[.type == 'docker'].target_tag := 'v4.0.3'"
+  - ".engines[.type == 'docker'].target_tag := 'v4.1.0'"
   keywords:
   - "single-cell"
   - "multimodal"

target/dependencies/vsh/vsh/openpipeline/v4.1.0/nextflow/dimred/pca/main.nf

@@ -1,6 +1,6 @@
-// pca v4.0.3
+// pca v4.1.0
 // 
-// This wrapper script is auto-generated by viash 0.9.4 and is thus a derivative
+// This wrapper script is auto-generated by viash 0.9.7 and is thus a derivative
 // work thereof. This software comes with ABSOLUTELY NO WARRANTY from Data
 // Intuitive.
 // 
@@ -1353,47 +1353,42 @@ def readCsv(file_path) {
   def splitRegex = java.util.regex.Pattern.compile(''',(?=(?:[^"]*"[^"]*")*[^"]*$)''')
   def removeQuote = java.util.regex.Pattern.compile('''"(.*)"''')
 
-  def br = java.nio.file.Files.newBufferedReader(inputFile)
+  java.nio.file.Files.newBufferedReader(inputFile).withCloseable { br ->
+    def row = 0
+    def header = null
+    def line
 
-  def row = -1
+    while (header == null && (line = br.readLine()) != null) {
-  def header = null
+      if (!line.startsWith("#")) {
-  while (br.ready() && header == null) {
+        header = splitRegex.split(line, -1).collect { field ->
-    def line = br.readLine()
+          def m = removeQuote.matcher(field)
-    row++
+          m.find() ? m.replaceFirst('$1') : field
-    if (!line.startsWith("#")) {
-      header = splitRegex.split(line, -1).collect{field ->
-        m = removeQuote.matcher(field)
-        m.find() ? m.replaceFirst('$1') : field
-      }
-    }
-  }
-  assert header != null: "CSV file should contain a header"
-
-  while (br.ready()) {
-    def line = br.readLine()
-    row++
-    if (line == null) {
-      br.close()
-      break
-    }
-
-    if (!line.startsWith("#")) {
-      def predata = splitRegex.split(line, -1)
-      def data = predata.collect{field ->
-        if (field == "") {
-          return null
-        }
-        def m = removeQuote.matcher(field)
-        if (m.find()) {
-          return m.replaceFirst('$1')
-        } else {
-          return field
         }
       }
-      assert header.size() == data.size(): "Row $row should contain the same number as fields as the header"
+      row++
-      
+    }
-      def dataMap = [header, data].transpose().collectEntries().findAll{it.value != null}
+    assert header != null : "CSV file should contain a header"
-      output.add(dataMap)
+
+    while ((line = br.readLine()) != null) {
+      row++
+      if (!line.startsWith("#")) {
+        def predata = splitRegex.split(line, -1)
+        def data = predata.collect { field ->
+          if (field == "") {
+            return null
+          }
+          def m = removeQuote.matcher(field)
+          if (m.find()) {
+            return m.replaceFirst('$1')
+          } else {
+            return field
+          }
+        }
+        assert header.size() == data.size() : "Row $row should contain the same number as fields as the header"
+
+        def dataMap = [header, data].transpose().collectEntries().findAll { it.value != null }
+        output.add(dataMap)
+      }
     }
   }
 
@@ -1709,10 +1704,25 @@ process publishFilesProc {
   ]
     .transpose()
     .collectMany{infile, outfile ->
-      if (infile.toString() != outfile.toString()) {
+      def infileString = infile.toString()
+      def outfileString = outfile.toString()
+      if (infileString != outfileString) {
+        /* Trailing slashes are removed from both the source and destination arguments.
+           From source arguments, this is useful when a source argument may have a trailing slash
+           and specify a symbolic link to a directory. Without removing the slash, cp will dereference
+           the symbolic link. 
+           See https://www.gnu.org/software/coreutils/manual/html_node/Trailing-slashes.html#Trailing-slashes-1
+
+           For the destination path addding a trailing slash is a problem when publishing directories: 
+           it requires the destination directory to exist. This fails because we only create the parent
+           directories first.
+        */
+        def regexTrailingSlashes = ~/\/+$/
+        def infileNoTrailingSlash = infileString - regexTrailingSlashes
+        def outfileNoTrailingSlash = outfileString - regexTrailingSlashes
         [
-          "[ -d \"\$(dirname '${outfile.toString()}')\" ] || mkdir -p \"\$(dirname '${outfile.toString()}')\"",
+          "[ -d \"\$(dirname '${outfileNoTrailingSlash}')\" ] || mkdir -p \"\$(dirname '${outfileNoTrailingSlash}')\"",
-          "cp -r '${infile.toString()}' '${outfile.toString()}'"
+          "cp -a '${infileNoTrailingSlash}' '${outfileNoTrailingSlash}'"
         ]
       } else {
         // no need to copy if infile is the same as outfile
@@ -3035,7 +3045,7 @@ meta = [
   "config": processConfig(readJsonBlob('''{
   "name" : "pca",
   "namespace" : "dimred",
-  "version" : "v4.0.3",
+  "version" : "v4.1.0",
   "authors" : [
     {
       "name" : "Dries De Maeyer",
@@ -3062,6 +3072,27 @@ meta = [
   "argument_groups" : [
     {
       "name" : "Arguments",
+      "arguments" : [
+        {
+          "type" : "string",
+          "name" : "--output_compression",
+          "description" : "Compression format to use for the output AnnData and/or Mudata H5 files.\nBy default no compression is applied.\n",
+          "example" : [
+            "gzip"
+          ],
+          "required" : false,
+          "choices" : [
+            "gzip",
+            "lzf"
+          ],
+          "direction" : "input",
+          "multiple" : false,
+          "multiple_sep" : ";"
+        }
+      ]
+    },
+    {
+      "name" : "inputs",
       "arguments" : [
         {
           "type" : "file",
@@ -3112,7 +3143,55 @@ meta = [
           "direction" : "input",
           "multiple" : false,
           "multiple_sep" : ";"
+        }
+      ]
+    },
+    {
+      "name" : "Options",
+      "arguments" : [
+        {
+          "type" : "integer",
+          "name" : "--num_components",
+          "description" : "Number of principal components to compute. Defaults to 50, or 1 - minimum dimension size of selected representation.",
+          "example" : [
+            25
+          ],
+          "required" : false,
+          "direction" : "input",
+          "multiple" : false,
+          "multiple_sep" : ";"
         },
+        {
+          "type" : "boolean_true",
+          "name" : "--chunked",
+          "description" : "If True, perform an incremental PCA on segments of a predefined size. Setting this flag automatically implies zero centering.\nMust be specified together with --chunk_size.\n",
+          "direction" : "input"
+        },
+        {
+          "type" : "integer",
+          "name" : "--chunk_size",
+          "description" : "Number of observations to include in each chunk. Required if chunked=True was passed.\n",
+          "required" : false,
+          "min" : 2,
+          "direction" : "input",
+          "multiple" : false,
+          "multiple_sep" : ";"
+        },
+        {
+          "type" : "integer",
+          "name" : "--seed",
+          "description" : "Used to set the initial states for the optimization. \n",
+          "required" : false,
+          "min" : 0,
+          "direction" : "input",
+          "multiple" : false,
+          "multiple_sep" : ";"
+        }
+      ]
+    },
+    {
+      "name" : "Outputs",
+      "arguments" : [
         {
           "type" : "file",
           "name" : "--output",
@@ -3166,39 +3245,11 @@ meta = [
           "multiple" : false,
           "multiple_sep" : ";"
         },
-        {
-          "type" : "integer",
-          "name" : "--num_components",
-          "description" : "Number of principal components to compute. Defaults to 50, or 1 - minimum dimension size of selected representation.",
-          "example" : [
-            25
-          ],
-          "required" : false,
-          "direction" : "input",
-          "multiple" : false,
-          "multiple_sep" : ";"
-        },
         {
           "type" : "boolean_true",
           "name" : "--overwrite",
           "description" : "Allow overwriting .obsm, .varm and .uns slots.",
           "direction" : "input"
-        },
-        {
-          "type" : "string",
-          "name" : "--output_compression",
-          "description" : "Compression format to use for the output AnnData and/or Mudata objects.\nBy default no compression is applied.\n",
-          "example" : [
-            "gzip"
-          ],
-          "required" : false,
-          "choices" : [
-            "gzip",
-            "lzf"
-          ],
-          "direction" : "input",
-          "multiple" : false,
-          "multiple_sep" : ";"
         }
       ]
     }
@@ -3223,7 +3274,7 @@ meta = [
       "dest" : "nextflow_labels.config"
     }
   ],
-  "description" : "Computes PCA coordinates, loadings and variance decomposition. Uses the implementation of scikit-learn [Pedregosa11].\n",
+  "description" : "Computes PCA coordinates, loadings and variance decomposition.\n",
   "test_resources" : [
     {
       "type" : "python_script",
@@ -3331,9 +3382,9 @@ meta = [
     {
       "type" : "docker",
       "id" : "docker",
-      "image" : "python:3.12-slim",
+      "image" : "python:3.13-slim",
       "target_registry" : "images.viash-hub.com",
-      "target_tag" : "v4.0.3",
+      "target_tag" : "v4.1.0",
       "namespace_separator" : "/",
       "setup" : [
         {
@@ -3347,9 +3398,10 @@ meta = [
           "type" : "python",
           "user" : false,
           "packages" : [
-            "anndata~=0.12.7",
+            "anndata~=0.12.16",
             "awkward",
-            "mudata~=0.3.2",
+            "scipy~=1.17.1",
+            "mudata~=0.3.8",
             "scanpy~=1.11.4"
           ],
           "script" : [
@@ -3359,11 +3411,21 @@ meta = [
         }
       ],
       "test_setup" : [
+        {
+          "type" : "apt",
+          "packages" : [
+            "git"
+          ],
+          "interactive" : false
+        },
         {
           "type" : "python",
           "user" : false,
           "packages" : [
-            "viashpy==0.8.0"
+            "viashpy==0.10.0"
+          ],
+          "github" : [
+            "openpipelines-bio/core#subdirectory=packages/python/openpipeline_testutils"
           ],
           "upgrade" : true
         }
@@ -3379,13 +3441,13 @@ meta = [
     "runner" : "nextflow",
     "engine" : "docker|native",
     "output" : "/workdir/root/repo/target/nextflow/dimred/pca",
-    "viash_version" : "0.9.4",
+    "viash_version" : "0.9.7",
-    "git_commit" : "7bfad4ea12f87eca59213be3ab08deff67cc4206",
+    "git_commit" : "a6499fddaa8553874585c747370f919f4d7b729c",
     "git_remote" : "https://github.com/openpipelines-bio/openpipeline"
   },
   "package_config" : {
     "name" : "openpipeline",
-    "version" : "v4.0.3",
+    "version" : "v4.1.0",
     "summary" : "Best-practice workflows for single-cell multi-omics analyses.\n",
     "description" : "OpenPipelines are extensible single cell analysis pipelines for reproducible and large-scale single cell processing using [Viash](https://viash.io) and [Nextflow](https://www.nextflow.io/).\n\nIn terms of workflows, the following has been made available, but keep in mind that\nindividual tools and functionality can be executed as standalone components as well.\n\n  * Demultiplexing: conversion of raw sequencing data to FASTQ objects.\n  * Ingestion: Read mapping and generating a count matrix.\n  * Single sample processing: cell filtering and doublet detection.\n  * Multisample processing: Count transformation, normalization, QC metric calulations.\n  * Integration: Clustering, integration and batch correction using single and multimodal methods.\n  * Downstream analysis workflows\n",
     "info" : {
@@ -3403,14 +3465,14 @@ meta = [
         }
       ]
     },
-    "viash_version" : "0.9.4",
+    "viash_version" : "0.9.7",
     "source" : "/workdir/root/repo/src",
     "target" : "/workdir/root/repo/target",
     "config_mods" : [
       ".resources += {path: '/src/workflows/utils/labels.config', dest: 'nextflow_labels.config'}\n.runners[.type == 'nextflow'].config.script := 'includeConfig(\\"nextflow_labels.config\\")'",
       ".engines += { type: \\"native\\" }",
       ".engines[.type == 'docker'].target_registry := 'images.viash-hub.com'",
-      ".engines[.type == 'docker'].target_tag := 'v4.0.3'"
+      ".engines[.type == 'docker'].target_tag := 'v4.1.0'"
     ],
     "keywords" : [
       "single-cell",
@@ -3441,22 +3503,26 @@ cat > "$tempscript" << VIASHMAIN
 import scanpy as sc
 import mudata as mu
 import sys
+import pandas as pd
 from anndata import AnnData
 
 ## VIASH START
 # The following code has been auto-generated by Viash.
 par = {
+  'output_compression': $( if [ ! -z ${VIASH_PAR_OUTPUT_COMPRESSION+x} ]; then echo "r'${VIASH_PAR_OUTPUT_COMPRESSION//\\'/\\'\\"\\'\\"r\\'}'"; else echo None; fi ),
   'input': $( if [ ! -z ${VIASH_PAR_INPUT+x} ]; then echo "r'${VIASH_PAR_INPUT//\\'/\\'\\"\\'\\"r\\'}'"; else echo None; fi ),
   'modality': $( if [ ! -z ${VIASH_PAR_MODALITY+x} ]; then echo "r'${VIASH_PAR_MODALITY//\\'/\\'\\"\\'\\"r\\'}'"; else echo None; fi ),
   'layer': $( if [ ! -z ${VIASH_PAR_LAYER+x} ]; then echo "r'${VIASH_PAR_LAYER//\\'/\\'\\"\\'\\"r\\'}'"; else echo None; fi ),
   'var_input': $( if [ ! -z ${VIASH_PAR_VAR_INPUT+x} ]; then echo "r'${VIASH_PAR_VAR_INPUT//\\'/\\'\\"\\'\\"r\\'}'"; else echo None; fi ),
+  'num_components': $( if [ ! -z ${VIASH_PAR_NUM_COMPONENTS+x} ]; then echo "int(r'${VIASH_PAR_NUM_COMPONENTS//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ),
+  'chunked': $( if [ ! -z ${VIASH_PAR_CHUNKED+x} ]; then echo "r'${VIASH_PAR_CHUNKED//\\'/\\'\\"\\'\\"r\\'}'.lower() == 'true'"; else echo None; fi ),
+  'chunk_size': $( if [ ! -z ${VIASH_PAR_CHUNK_SIZE+x} ]; then echo "int(r'${VIASH_PAR_CHUNK_SIZE//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ),
+  'seed': $( if [ ! -z ${VIASH_PAR_SEED+x} ]; then echo "int(r'${VIASH_PAR_SEED//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ),
   'output': $( if [ ! -z ${VIASH_PAR_OUTPUT+x} ]; then echo "r'${VIASH_PAR_OUTPUT//\\'/\\'\\"\\'\\"r\\'}'"; else echo None; fi ),
   'obsm_output': $( if [ ! -z ${VIASH_PAR_OBSM_OUTPUT+x} ]; then echo "r'${VIASH_PAR_OBSM_OUTPUT//\\'/\\'\\"\\'\\"r\\'}'"; else echo None; fi ),
   'varm_output': $( if [ ! -z ${VIASH_PAR_VARM_OUTPUT+x} ]; then echo "r'${VIASH_PAR_VARM_OUTPUT//\\'/\\'\\"\\'\\"r\\'}'"; else echo None; fi ),
   'uns_output': $( if [ ! -z ${VIASH_PAR_UNS_OUTPUT+x} ]; then echo "r'${VIASH_PAR_UNS_OUTPUT//\\'/\\'\\"\\'\\"r\\'}'"; else echo None; fi ),
-  'num_components': $( if [ ! -z ${VIASH_PAR_NUM_COMPONENTS+x} ]; then echo "int(r'${VIASH_PAR_NUM_COMPONENTS//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ),
+  'overwrite': $( if [ ! -z ${VIASH_PAR_OVERWRITE+x} ]; then echo "r'${VIASH_PAR_OVERWRITE//\\'/\\'\\"\\'\\"r\\'}'.lower() == 'true'"; else echo None; fi )
-  'overwrite': $( if [ ! -z ${VIASH_PAR_OVERWRITE+x} ]; then echo "r'${VIASH_PAR_OVERWRITE//\\'/\\'\\"\\'\\"r\\'}'.lower() == 'true'"; else echo None; fi ),
-  'output_compression': $( if [ ! -z ${VIASH_PAR_OUTPUT_COMPRESSION+x} ]; then echo "r'${VIASH_PAR_OUTPUT_COMPRESSION//\\'/\\'\\"\\'\\"r\\'}'"; else echo None; fi )
 }
 meta = {
   'name': $( if [ ! -z ${VIASH_META_NAME+x} ]; then echo "r'${VIASH_META_NAME//\\'/\\'\\"\\'\\"r\\'}'"; else echo None; fi ),
@@ -3496,11 +3562,24 @@ data = mu.read_h5ad(par["input"], mod=par["modality"])
 logger.info("Computing PCA components for modality '%s'", par["modality"])
 if par["layer"] and par["layer"] not in data.layers:
     raise ValueError(f"{par['layer']} was not found in modality {par['modality']}.")
-layer = data.X if not par["layer"] else data.layers[par["layer"]]
-adata_input_layer = AnnData(layer)
-adata_input_layer.var.index = data.var.index
 
-use_highly_variable = False
+chunked, chunk_size = par["chunked"], par["chunk_size"]
+if chunked:
+    if not chunk_size:
+        raise ValueError(
+            "Requested to perform an incremental PCA "
+            "('chunked'), but the chunk size is not set."
+        )
+    if chunk_size < par["num_components"]:
+        raise ValueError(
+            f"The requested chunk size ({chunk_size}) must not be smaller "
+            f"than the number of components ({par['num_components']})"
+        )
+
+layer = data.X if not par["layer"] else data.layers[par["layer"]]
+adata_input_layer = AnnData(layer, var=pd.DataFrame([], index=data.var.index))
+
+mask_var = None
 if par["var_input"]:
     if par["var_input"] not in data.var.columns:
         raise ValueError(
@@ -3508,15 +3587,18 @@ if par["var_input"]:
             "as a selection of genes to run the PCA on, "
             f"but the column is not available for modality {par['modality']}"
         )
-    use_highly_variable = True
+    mask_var = data.var[par["var_input"]]
-    adata_input_layer.var["highly_variable"] = data.var[par["var_input"]]
 
 # run pca
-output_adata = sc.tl.pca(
+sc.tl.pca(
     adata_input_layer,
     n_comps=par["num_components"],
-    copy=True,
+    copy=False,  # A copy was already created
-    use_highly_variable=use_highly_variable,
+    return_info=True,
+    mask_var=mask_var,
+    chunked=chunked,
+    chunk_size=chunk_size,
+    random_state=par["seed"],
 )
 
 # store output in specific objects
@@ -3535,11 +3617,11 @@ for parameter_name, field in check_exist_dict.items():
             )
         del getattr(data, field)[par[parameter_name]]
 
-data.obsm[par["obsm_output"]] = output_adata.obsm["X_pca"]
+data.obsm[par["obsm_output"]] = adata_input_layer.obsm["X_pca"]
-data.varm[par["varm_output"]] = output_adata.varm["PCs"]
+data.varm[par["varm_output"]] = adata_input_layer.varm["PCs"]
 data.uns[par["uns_output"]] = {
-    "variance": output_adata.uns["pca"]["variance"],
+    "variance": adata_input_layer.uns["pca"]["variance"],
-    "variance_ratio": output_adata.uns["pca"]["variance_ratio"],
+    "variance_ratio": adata_input_layer.uns["pca"]["variance_ratio"],
 }
 
 
@@ -3933,7 +4015,7 @@ meta["defaults"] = [
   "container" : {
     "registry" : "images.viash-hub.com",
     "image" : "vsh/openpipeline/dimred/pca",
-    "tag" : "v4.0.3"
+    "tag" : "v4.1.0"
   },
   "label" : [
     "highcpu",

target/dependencies/vsh/vsh/openpipeline/v4.1.0/nextflow/dimred/pca/nextflow.config

@@ -2,8 +2,8 @@ manifest {
   name = 'dimred/pca'
   mainScript = 'main.nf'
   nextflowVersion = '!>=20.12.1-edge'
-  version = 'v4.0.3'
+  version = 'v4.1.0'
-  description = 'Computes PCA coordinates, loadings and variance decomposition. Uses the implementation of scikit-learn [Pedregosa11].\n'
+  description = 'Computes PCA coordinates, loadings and variance decomposition.\n'
   author = 'Dries De Maeyer'
 }
 

target/dependencies/vsh/vsh/openpipeline/v4.1.0/nextflow/dimred/pca/nextflow_schema.json

@@ -1,37 +1,14 @@
 {
   "$schema": "https://json-schema.org/draft/2020-12/schema",
   "title": "pca",
-  "description": "Computes PCA coordinates, loadings and variance decomposition. Uses the implementation of scikit-learn [Pedregosa11].\n",
+  "description": "Computes PCA coordinates, loadings and variance decomposition.\n",
   "type": "object",
   "$defs": {
-    "arguments": {
+    "outputs": {
-      "title": "Arguments",
+      "title": "Outputs",
       "type": "object",
       "description": "No description",
       "properties": {
-        "input": {
-          "type": "string",
-          "format": "path",
-          "exists": true,
-          "description": "Input h5mu file",
-          "help_text": "Type: `file`, multiple: `False`, required, direction: `input`, example: `\"input.h5mu\"`. "
-        },
-        "modality": {
-          "type": "string",
-          "description": "Which modality from the input MuData file to process.\n",
-          "help_text": "Type: `string`, multiple: `False`, default: `\"rna\"`. ",
-          "default": "rna"
-        },
-        "layer": {
-          "type": "string",
-          "description": "Use specified layer for expression values instead of the .X object from the modality.",
-          "help_text": "Type: `string`, multiple: `False`. "
-        },
-        "var_input": {
-          "type": "string",
-          "description": "Column name in .var matrix that will be used to select which genes to run the PCA on.",
-          "help_text": "Type: `string`, multiple: `False`, example: `\"filter_with_hvg\"`. "
-        },
         "output": {
           "type": "string",
           "format": "path",
@@ -57,20 +34,22 @@
           "help_text": "Type: `string`, multiple: `False`, default: `\"pca_variance\"`. ",
           "default": "pca_variance"
         },
-        "num_components": {
-          "type": "integer",
-          "description": "Number of principal components to compute",
-          "help_text": "Type: `integer`, multiple: `False`, example: `25`. "
-        },
         "overwrite": {
           "type": "boolean",
           "description": "Allow overwriting .obsm, .varm and .uns slots.",
           "help_text": "Type: `boolean_true`, multiple: `False`, default: `false`. ",
           "default": false
-        },
+        }
+      }
+    },
+    "arguments": {
+      "title": "Arguments",
+      "type": "object",
+      "description": "No description",
+      "properties": {
         "output_compression": {
           "type": "string",
-          "description": "Compression format to use for the output AnnData and/or Mudata objects.\nBy default no compression is applied.\n",
+          "description": "Compression format to use for the output AnnData and/or Mudata H5 files.\nBy default no compression is applied.\n",
           "help_text": "Type: `string`, multiple: `False`, example: `\"gzip\"`, choices: ``gzip`, `lzf``. ",
           "enum": [
             "gzip",
@@ -79,6 +58,64 @@
         }
       }
     },
+    "inputs": {
+      "title": "inputs",
+      "type": "object",
+      "description": "No description",
+      "properties": {
+        "input": {
+          "type": "string",
+          "format": "path",
+          "exists": true,
+          "description": "Input h5mu file",
+          "help_text": "Type: `file`, multiple: `False`, required, direction: `input`, example: `\"input.h5mu\"`. "
+        },
+        "modality": {
+          "type": "string",
+          "description": "Which modality from the input MuData file to process.\n",
+          "help_text": "Type: `string`, multiple: `False`, default: `\"rna\"`. ",
+          "default": "rna"
+        },
+        "layer": {
+          "type": "string",
+          "description": "Use specified layer for expression values instead of the .X object from the modality.",
+          "help_text": "Type: `string`, multiple: `False`. "
+        },
+        "var_input": {
+          "type": "string",
+          "description": "Column name in .var matrix that will be used to select which genes to run the PCA on.",
+          "help_text": "Type: `string`, multiple: `False`, example: `\"filter_with_hvg\"`. "
+        }
+      }
+    },
+    "options": {
+      "title": "Options",
+      "type": "object",
+      "description": "No description",
+      "properties": {
+        "num_components": {
+          "type": "integer",
+          "description": "Number of principal components to compute",
+          "help_text": "Type: `integer`, multiple: `False`, example: `25`. "
+        },
+        "chunked": {
+          "type": "boolean",
+          "description": "If True, perform an incremental PCA on segments of a predefined size",
+          "help_text": "Type: `boolean_true`, multiple: `False`, default: `false`. ",
+          "default": false
+        },
+        "chunk_size": {
+          "type": "integer",
+          "description": "Number of observations to include in each chunk",
+          "help_text": "Type: `integer`, multiple: `False`. "
+        },
+        "seed": {
+          "type": "integer",
+          "description": "Used to set the initial states for the optimization",
+          "help_text": "Type: `integer`, multiple: `False`. "
+        }
+      }
+    },
     "nextflow input-output arguments": {
       "title": "Nextflow input-output arguments",
       "type": "object",
@@ -93,9 +130,18 @@
     }
   },
   "allOf": [
+    {
+      "$ref": "#/$defs/outputs"
+    },
     {
       "$ref": "#/$defs/arguments"
     },
+    {
+      "$ref": "#/$defs/inputs"
+    },
+    {
+      "$ref": "#/$defs/options"
+    },
     {
       "$ref": "#/$defs/nextflow input-output arguments"
     }

target/dependencies/vsh/vsh/openpipeline/v4.1.0/nextflow/dimred/umap/.config.vsh.yaml

@@ -1,6 +1,6 @@
 name: "umap"
 namespace: "dimred"
-version: "v4.0.3"
+version: "v4.1.0"
 authors:
 - name: "Dries De Maeyer"
   roles:
@@ -78,8 +78,8 @@ argument_groups:
     multiple_sep: ";"
   - type: "string"
     name: "--output_compression"
-    description: "Compression format to use for the output AnnData and/or Mudata objects.\n\
+    description: "Compression format to use for the output AnnData and/or Mudata H5\
-      By default no compression is applied.\n"
+      \ files.\nBy default no compression is applied.\n"
     info: null
     example:
     - "gzip"
@@ -294,7 +294,7 @@ engines:
   id: "docker"
   image: "python:3.12-slim"
   target_registry: "images.viash-hub.com"
-  target_tag: "v4.0.3"
+  target_tag: "v4.1.0"
   namespace_separator: "/"
   setup:
   - type: "apt"
@@ -304,9 +304,10 @@ engines:
   - type: "python"
     user: false
     packages:
-    - "anndata~=0.12.7"
+    - "anndata~=0.12.16"
     - "awkward"
-    - "mudata~=0.3.2"
+    - "scipy~=1.17.1"
+    - "mudata~=0.3.8"
     - "scanpy~=1.11.4"
     script:
     - "exec(\"try:\\n  import zarr; from importlib.metadata import version\\nexcept\
@@ -317,7 +318,7 @@ engines:
   - type: "python"
     user: false
     packages:
-    - "viashpy==0.8.0"
+    - "viashpy==0.10.0"
     upgrade: true
   entrypoint: []
   cmd: null
@@ -329,12 +330,12 @@ build_info:
   engine: "docker|native"
   output: "target/nextflow/dimred/umap"
   executable: "target/nextflow/dimred/umap/main.nf"
-  viash_version: "0.9.4"
+  viash_version: "0.9.7"
-  git_commit: "7bfad4ea12f87eca59213be3ab08deff67cc4206"
+  git_commit: "a6499fddaa8553874585c747370f919f4d7b729c"
   git_remote: "https://github.com/openpipelines-bio/openpipeline"
 package_config:
   name: "openpipeline"
-  version: "v4.0.3"
+  version: "v4.1.0"
   summary: "Best-practice workflows for single-cell multi-omics analyses.\n"
   description: "OpenPipelines are extensible single cell analysis pipelines for reproducible\
     \ and large-scale single cell processing using [Viash](https://viash.io) and [Nextflow](https://www.nextflow.io/).\n\
@@ -355,7 +356,7 @@ package_config:
     - path: "src/workflows/utils/labels_ci.config"
       description: "Adds the correct memory and CPU labels when running on the Viash\
         \ Hub CI."
-  viash_version: "0.9.4"
+  viash_version: "0.9.7"
   source: "src"
   target: "target"
   config_mods:
@@ -364,7 +365,7 @@ package_config:
     )'"
   - ".engines += { type: \"native\" }"
   - ".engines[.type == 'docker'].target_registry := 'images.viash-hub.com'"
-  - ".engines[.type == 'docker'].target_tag := 'v4.0.3'"
+  - ".engines[.type == 'docker'].target_tag := 'v4.1.0'"
   keywords:
   - "single-cell"
   - "multimodal"

target/dependencies/vsh/vsh/openpipeline/v4.1.0/nextflow/dimred/umap/main.nf

@@ -1,6 +1,6 @@
-// umap v4.0.3
+// umap v4.1.0
 // 
-// This wrapper script is auto-generated by viash 0.9.4 and is thus a derivative
+// This wrapper script is auto-generated by viash 0.9.7 and is thus a derivative
 // work thereof. This software comes with ABSOLUTELY NO WARRANTY from Data
 // Intuitive.
 // 
@@ -1353,47 +1353,42 @@ def readCsv(file_path) {
   def splitRegex = java.util.regex.Pattern.compile(''',(?=(?:[^"]*"[^"]*")*[^"]*$)''')
   def removeQuote = java.util.regex.Pattern.compile('''"(.*)"''')
 
-  def br = java.nio.file.Files.newBufferedReader(inputFile)
+  java.nio.file.Files.newBufferedReader(inputFile).withCloseable { br ->
+    def row = 0
+    def header = null
+    def line
 
-  def row = -1
+    while (header == null && (line = br.readLine()) != null) {
-  def header = null
+      if (!line.startsWith("#")) {
-  while (br.ready() && header == null) {
+        header = splitRegex.split(line, -1).collect { field ->
-    def line = br.readLine()
+          def m = removeQuote.matcher(field)
-    row++
+          m.find() ? m.replaceFirst('$1') : field
-    if (!line.startsWith("#")) {
-      header = splitRegex.split(line, -1).collect{field ->
-        m = removeQuote.matcher(field)
-        m.find() ? m.replaceFirst('$1') : field
-      }
-    }
-  }
-  assert header != null: "CSV file should contain a header"
-
-  while (br.ready()) {
-    def line = br.readLine()
-    row++
-    if (line == null) {
-      br.close()
-      break
-    }
-
-    if (!line.startsWith("#")) {
-      def predata = splitRegex.split(line, -1)
-      def data = predata.collect{field ->
-        if (field == "") {
-          return null
-        }
-        def m = removeQuote.matcher(field)
-        if (m.find()) {
-          return m.replaceFirst('$1')
-        } else {
-          return field
         }
       }
-      assert header.size() == data.size(): "Row $row should contain the same number as fields as the header"
+      row++
-      
+    }
-      def dataMap = [header, data].transpose().collectEntries().findAll{it.value != null}
+    assert header != null : "CSV file should contain a header"
-      output.add(dataMap)
+
+    while ((line = br.readLine()) != null) {
+      row++
+      if (!line.startsWith("#")) {
+        def predata = splitRegex.split(line, -1)
+        def data = predata.collect { field ->
+          if (field == "") {
+            return null
+          }
+          def m = removeQuote.matcher(field)
+          if (m.find()) {
+            return m.replaceFirst('$1')
+          } else {
+            return field
+          }
+        }
+        assert header.size() == data.size() : "Row $row should contain the same number as fields as the header"
+
+        def dataMap = [header, data].transpose().collectEntries().findAll { it.value != null }
+        output.add(dataMap)
+      }
     }
   }
 
@@ -1709,10 +1704,25 @@ process publishFilesProc {
   ]
     .transpose()
     .collectMany{infile, outfile ->
-      if (infile.toString() != outfile.toString()) {
+      def infileString = infile.toString()
+      def outfileString = outfile.toString()
+      if (infileString != outfileString) {
+        /* Trailing slashes are removed from both the source and destination arguments.
+           From source arguments, this is useful when a source argument may have a trailing slash
+           and specify a symbolic link to a directory. Without removing the slash, cp will dereference
+           the symbolic link. 
+           See https://www.gnu.org/software/coreutils/manual/html_node/Trailing-slashes.html#Trailing-slashes-1
+
+           For the destination path addding a trailing slash is a problem when publishing directories: 
+           it requires the destination directory to exist. This fails because we only create the parent
+           directories first.
+        */
+        def regexTrailingSlashes = ~/\/+$/
+        def infileNoTrailingSlash = infileString - regexTrailingSlashes
+        def outfileNoTrailingSlash = outfileString - regexTrailingSlashes
         [
-          "[ -d \"\$(dirname '${outfile.toString()}')\" ] || mkdir -p \"\$(dirname '${outfile.toString()}')\"",
+          "[ -d \"\$(dirname '${outfileNoTrailingSlash}')\" ] || mkdir -p \"\$(dirname '${outfileNoTrailingSlash}')\"",
-          "cp -r '${infile.toString()}' '${outfile.toString()}'"
+          "cp -a '${infileNoTrailingSlash}' '${outfileNoTrailingSlash}'"
         ]
       } else {
         // no need to copy if infile is the same as outfile
@@ -3035,7 +3045,7 @@ meta = [
   "config": processConfig(readJsonBlob('''{
   "name" : "umap",
   "namespace" : "dimred",
-  "version" : "v4.0.3",
+  "version" : "v4.1.0",
   "authors" : [
     {
       "name" : "Dries De Maeyer",
@@ -3138,7 +3148,7 @@ meta = [
         {
           "type" : "string",
           "name" : "--output_compression",
-          "description" : "Compression format to use for the output AnnData and/or Mudata objects.\nBy default no compression is applied.\n",
+          "description" : "Compression format to use for the output AnnData and/or Mudata H5 files.\nBy default no compression is applied.\n",
           "example" : [
             "gzip"
           ],
@@ -3382,7 +3392,7 @@ meta = [
       "id" : "docker",
       "image" : "python:3.12-slim",
       "target_registry" : "images.viash-hub.com",
-      "target_tag" : "v4.0.3",
+      "target_tag" : "v4.1.0",
       "namespace_separator" : "/",
       "setup" : [
         {
@@ -3396,9 +3406,10 @@ meta = [
           "type" : "python",
           "user" : false,
           "packages" : [
-            "anndata~=0.12.7",
+            "anndata~=0.12.16",
             "awkward",
-            "mudata~=0.3.2",
+            "scipy~=1.17.1",
+            "mudata~=0.3.8",
             "scanpy~=1.11.4"
           ],
           "script" : [
@@ -3412,7 +3423,7 @@ meta = [
           "type" : "python",
           "user" : false,
           "packages" : [
-            "viashpy==0.8.0"
+            "viashpy==0.10.0"
           ],
           "upgrade" : true
         }
@@ -3428,13 +3439,13 @@ meta = [
     "runner" : "nextflow",
     "engine" : "docker|native",
     "output" : "/workdir/root/repo/target/nextflow/dimred/umap",
-    "viash_version" : "0.9.4",
+    "viash_version" : "0.9.7",
-    "git_commit" : "7bfad4ea12f87eca59213be3ab08deff67cc4206",
+    "git_commit" : "a6499fddaa8553874585c747370f919f4d7b729c",
     "git_remote" : "https://github.com/openpipelines-bio/openpipeline"
   },
   "package_config" : {
     "name" : "openpipeline",
-    "version" : "v4.0.3",
+    "version" : "v4.1.0",
     "summary" : "Best-practice workflows for single-cell multi-omics analyses.\n",
     "description" : "OpenPipelines are extensible single cell analysis pipelines for reproducible and large-scale single cell processing using [Viash](https://viash.io) and [Nextflow](https://www.nextflow.io/).\n\nIn terms of workflows, the following has been made available, but keep in mind that\nindividual tools and functionality can be executed as standalone components as well.\n\n  * Demultiplexing: conversion of raw sequencing data to FASTQ objects.\n  * Ingestion: Read mapping and generating a count matrix.\n  * Single sample processing: cell filtering and doublet detection.\n  * Multisample processing: Count transformation, normalization, QC metric calulations.\n  * Integration: Clustering, integration and batch correction using single and multimodal methods.\n  * Downstream analysis workflows\n",
     "info" : {
@@ -3452,14 +3463,14 @@ meta = [
         }
       ]
     },
-    "viash_version" : "0.9.4",
+    "viash_version" : "0.9.7",
     "source" : "/workdir/root/repo/src",
     "target" : "/workdir/root/repo/target",
     "config_mods" : [
       ".resources += {path: '/src/workflows/utils/labels.config', dest: 'nextflow_labels.config'}\n.runners[.type == 'nextflow'].config.script := 'includeConfig(\\"nextflow_labels.config\\")'",
       ".engines += { type: \\"native\\" }",
       ".engines[.type == 'docker'].target_registry := 'images.viash-hub.com'",
-      ".engines[.type == 'docker'].target_tag := 'v4.0.3'"
+      ".engines[.type == 'docker'].target_tag := 'v4.1.0'"
     ],
     "keywords" : [
       "single-cell",
@@ -3971,7 +3982,7 @@ meta["defaults"] = [
   "container" : {
     "registry" : "images.viash-hub.com",
     "image" : "vsh/openpipeline/dimred/umap",
-    "tag" : "v4.0.3"
+    "tag" : "v4.1.0"
   },
   "label" : [
     "highcpu",

target/dependencies/vsh/vsh/openpipeline/v4.1.0/nextflow/dimred/umap/nextflow.config

@@ -2,7 +2,7 @@ manifest {
   name = 'dimred/umap'
   mainScript = 'main.nf'
   nextflowVersion = '!>=20.12.1-edge'
-  version = 'v4.0.3'
+  version = 'v4.1.0'
   description = 'UMAP (Uniform Manifold Approximation and Projection) is a manifold learning technique suitable for visualizing high-dimensional data. Besides tending to be faster than tSNE, it optimizes the embedding such that it best reflects the topology of the data, which we represent throughout Scanpy using a neighborhood graph. tSNE, by contrast, optimizes the distribution of nearest-neighbor distances in the embedding such that these best match the distribution of distances in the high-dimensional space. We use the implementation of umap-learn [McInnes18]. For a few comparisons of UMAP with tSNE, see this preprint.\n'
   author = 'Dries De Maeyer'
 }

target/dependencies/vsh/vsh/openpipeline/v4.1.0/nextflow/dimred/umap/nextflow_schema.json

@@ -50,7 +50,7 @@
         },
         "output_compression": {
           "type": "string",
-          "description": "Compression format to use for the output AnnData and/or Mudata objects.\nBy default no compression is applied.\n",
+          "description": "Compression format to use for the output AnnData and/or Mudata H5 files.\nBy default no compression is applied.\n",
           "help_text": "Type: `string`, multiple: `False`, example: `\"gzip\"`, choices: ``gzip`, `lzf``. ",
           "enum": [
             "gzip",

target/dependencies/vsh/vsh/openpipeline/v4.1.0/nextflow/feature_annotation/highly_variable_features_scanpy/.config.vsh.yaml

@@ -1,6 +1,6 @@
 name: "highly_variable_features_scanpy"
 namespace: "feature_annotation"
-version: "v4.0.3"
+version: "v4.1.0"
 authors:
 - name: "Dries De Maeyer"
   roles:
@@ -75,6 +75,20 @@ argument_groups:
     direction: "input"
     multiple: false
     multiple_sep: ";"
+  - type: "string"
+    name: "--features_to_exclude"
+    description: "User-defined list of feature names to exclude before HVG calculation.\
+      \ \nThese features will be excluded from HVG selection but will remain in the\
+      \ output data.\n"
+    info: null
+    example:
+    - "MT-CO1"
+    - "MT-CO2"
+    - "MT-ND1"
+    required: false
+    direction: "input"
+    multiple: true
+    multiple_sep: ";"
   - type: "file"
     name: "--output"
     description: "Output h5mu file."
@@ -214,8 +228,8 @@ argument_groups:
     multiple_sep: ";"
   - type: "string"
     name: "--output_compression"
-    description: "Compression format to use for the output AnnData and/or Mudata objects.\n\
+    description: "Compression format to use for the output AnnData and/or Mudata H5\
-      By default no compression is applied.\n"
+      \ files.\nBy default no compression is applied.\n"
     info: null
     example:
     - "gzip"
@@ -342,15 +356,16 @@ engines:
   id: "docker"
   image: "python:3.12"
   target_registry: "images.viash-hub.com"
-  target_tag: "v4.0.3"
+  target_tag: "v4.1.0"
   namespace_separator: "/"
   setup:
   - type: "python"
     user: false
     packages:
-    - "anndata~=0.12.7"
+    - "anndata~=0.12.16"
     - "awkward"
-    - "mudata~=0.3.2"
+    - "scipy~=1.17.1"
+    - "mudata~=0.3.8"
     - "scanpy~=1.11.4"
     - "scikit-misc"
     script:
@@ -366,7 +381,7 @@ engines:
   - type: "python"
     user: false
     packages:
-    - "viashpy==0.8.0"
+    - "viashpy==0.10.0"
     github:
     - "openpipelines-bio/core#subdirectory=packages/python/openpipeline_testutils"
     upgrade: true
@@ -380,12 +395,12 @@ build_info:
   engine: "docker|native"
   output: "target/nextflow/feature_annotation/highly_variable_features_scanpy"
   executable: "target/nextflow/feature_annotation/highly_variable_features_scanpy/main.nf"
-  viash_version: "0.9.4"
+  viash_version: "0.9.7"
-  git_commit: "7bfad4ea12f87eca59213be3ab08deff67cc4206"
+  git_commit: "a6499fddaa8553874585c747370f919f4d7b729c"
   git_remote: "https://github.com/openpipelines-bio/openpipeline"
 package_config:
   name: "openpipeline"
-  version: "v4.0.3"
+  version: "v4.1.0"
   summary: "Best-practice workflows for single-cell multi-omics analyses.\n"
   description: "OpenPipelines are extensible single cell analysis pipelines for reproducible\
     \ and large-scale single cell processing using [Viash](https://viash.io) and [Nextflow](https://www.nextflow.io/).\n\
@@ -406,7 +421,7 @@ package_config:
     - path: "src/workflows/utils/labels_ci.config"
       description: "Adds the correct memory and CPU labels when running on the Viash\
         \ Hub CI."
-  viash_version: "0.9.4"
+  viash_version: "0.9.7"
   source: "src"
   target: "target"
   config_mods:
@@ -415,7 +430,7 @@ package_config:
     )'"
   - ".engines += { type: \"native\" }"
   - ".engines[.type == 'docker'].target_registry := 'images.viash-hub.com'"
-  - ".engines[.type == 'docker'].target_tag := 'v4.0.3'"
+  - ".engines[.type == 'docker'].target_tag := 'v4.1.0'"
   keywords:
   - "single-cell"
   - "multimodal"

target/dependencies/vsh/vsh/openpipeline/v4.1.0/nextflow/feature_annotation/highly_variable_features_scanpy/main.nf

@@ -1,6 +1,6 @@
-// highly_variable_features_scanpy v4.0.3
+// highly_variable_features_scanpy v4.1.0
 // 
-// This wrapper script is auto-generated by viash 0.9.4 and is thus a derivative
+// This wrapper script is auto-generated by viash 0.9.7 and is thus a derivative
 // work thereof. This software comes with ABSOLUTELY NO WARRANTY from Data
 // Intuitive.
 // 
@@ -1354,47 +1354,42 @@ def readCsv(file_path) {
   def splitRegex = java.util.regex.Pattern.compile(''',(?=(?:[^"]*"[^"]*")*[^"]*$)''')
   def removeQuote = java.util.regex.Pattern.compile('''"(.*)"''')
 
-  def br = java.nio.file.Files.newBufferedReader(inputFile)
+  java.nio.file.Files.newBufferedReader(inputFile).withCloseable { br ->
+    def row = 0
+    def header = null
+    def line
 
-  def row = -1
+    while (header == null && (line = br.readLine()) != null) {
-  def header = null
+      if (!line.startsWith("#")) {
-  while (br.ready() && header == null) {
+        header = splitRegex.split(line, -1).collect { field ->
-    def line = br.readLine()
+          def m = removeQuote.matcher(field)
-    row++
+          m.find() ? m.replaceFirst('$1') : field
-    if (!line.startsWith("#")) {
-      header = splitRegex.split(line, -1).collect{field ->
-        m = removeQuote.matcher(field)
-        m.find() ? m.replaceFirst('$1') : field
-      }
-    }
-  }
-  assert header != null: "CSV file should contain a header"
-
-  while (br.ready()) {
-    def line = br.readLine()
-    row++
-    if (line == null) {
-      br.close()
-      break
-    }
-
-    if (!line.startsWith("#")) {
-      def predata = splitRegex.split(line, -1)
-      def data = predata.collect{field ->
-        if (field == "") {
-          return null
-        }
-        def m = removeQuote.matcher(field)
-        if (m.find()) {
-          return m.replaceFirst('$1')
-        } else {
-          return field
         }
       }
-      assert header.size() == data.size(): "Row $row should contain the same number as fields as the header"
+      row++
-      
+    }
-      def dataMap = [header, data].transpose().collectEntries().findAll{it.value != null}
+    assert header != null : "CSV file should contain a header"
-      output.add(dataMap)
+
+    while ((line = br.readLine()) != null) {
+      row++
+      if (!line.startsWith("#")) {
+        def predata = splitRegex.split(line, -1)
+        def data = predata.collect { field ->
+          if (field == "") {
+            return null
+          }
+          def m = removeQuote.matcher(field)
+          if (m.find()) {
+            return m.replaceFirst('$1')
+          } else {
+            return field
+          }
+        }
+        assert header.size() == data.size() : "Row $row should contain the same number as fields as the header"
+
+        def dataMap = [header, data].transpose().collectEntries().findAll { it.value != null }
+        output.add(dataMap)
+      }
     }
   }
 
@@ -1710,10 +1705,25 @@ process publishFilesProc {
   ]
     .transpose()
     .collectMany{infile, outfile ->
-      if (infile.toString() != outfile.toString()) {
+      def infileString = infile.toString()
+      def outfileString = outfile.toString()
+      if (infileString != outfileString) {
+        /* Trailing slashes are removed from both the source and destination arguments.
+           From source arguments, this is useful when a source argument may have a trailing slash
+           and specify a symbolic link to a directory. Without removing the slash, cp will dereference
+           the symbolic link. 
+           See https://www.gnu.org/software/coreutils/manual/html_node/Trailing-slashes.html#Trailing-slashes-1
+
+           For the destination path addding a trailing slash is a problem when publishing directories: 
+           it requires the destination directory to exist. This fails because we only create the parent
+           directories first.
+        */
+        def regexTrailingSlashes = ~/\/+$/
+        def infileNoTrailingSlash = infileString - regexTrailingSlashes
+        def outfileNoTrailingSlash = outfileString - regexTrailingSlashes
         [
-          "[ -d \"\$(dirname '${outfile.toString()}')\" ] || mkdir -p \"\$(dirname '${outfile.toString()}')\"",
+          "[ -d \"\$(dirname '${outfileNoTrailingSlash}')\" ] || mkdir -p \"\$(dirname '${outfileNoTrailingSlash}')\"",
-          "cp -r '${infile.toString()}' '${outfile.toString()}'"
+          "cp -a '${infileNoTrailingSlash}' '${outfileNoTrailingSlash}'"
         ]
       } else {
         // no need to copy if infile is the same as outfile
@@ -3036,7 +3046,7 @@ meta = [
   "config": processConfig(readJsonBlob('''{
   "name" : "highly_variable_features_scanpy",
   "namespace" : "feature_annotation",
-  "version" : "v4.0.3",
+  "version" : "v4.1.0",
   "authors" : [
     {
       "name" : "Dries De Maeyer",
@@ -3136,6 +3146,20 @@ meta = [
           "multiple" : false,
           "multiple_sep" : ";"
         },
+        {
+          "type" : "string",
+          "name" : "--features_to_exclude",
+          "description" : "User-defined list of feature names to exclude before HVG calculation. \nThese features will be excluded from HVG selection but will remain in the output data.\n",
+          "example" : [
+            "MT-CO1",
+            "MT-CO2",
+            "MT-ND1"
+          ],
+          "required" : false,
+          "direction" : "input",
+          "multiple" : true,
+          "multiple_sep" : ";"
+        },
         {
           "type" : "file",
           "name" : "--output",
@@ -3281,7 +3305,7 @@ meta = [
         {
           "type" : "string",
           "name" : "--output_compression",
-          "description" : "Compression format to use for the output AnnData and/or Mudata objects.\nBy default no compression is applied.\n",
+          "description" : "Compression format to use for the output AnnData and/or Mudata H5 files.\nBy default no compression is applied.\n",
           "example" : [
             "gzip"
           ],
@@ -3430,16 +3454,17 @@ meta = [
       "id" : "docker",
       "image" : "python:3.12",
       "target_registry" : "images.viash-hub.com",
-      "target_tag" : "v4.0.3",
+      "target_tag" : "v4.1.0",
       "namespace_separator" : "/",
       "setup" : [
         {
           "type" : "python",
           "user" : false,
           "packages" : [
-            "anndata~=0.12.7",
+            "anndata~=0.12.16",
             "awkward",
-            "mudata~=0.3.2",
+            "scipy~=1.17.1",
+            "mudata~=0.3.8",
             "scanpy~=1.11.4",
             "scikit-misc"
           ],
@@ -3461,7 +3486,7 @@ meta = [
           "type" : "python",
           "user" : false,
           "packages" : [
-            "viashpy==0.8.0"
+            "viashpy==0.10.0"
           ],
           "github" : [
             "openpipelines-bio/core#subdirectory=packages/python/openpipeline_testutils"
@@ -3480,13 +3505,13 @@ meta = [
     "runner" : "nextflow",
     "engine" : "docker|native",
     "output" : "/workdir/root/repo/target/nextflow/feature_annotation/highly_variable_features_scanpy",
-    "viash_version" : "0.9.4",
+    "viash_version" : "0.9.7",
-    "git_commit" : "7bfad4ea12f87eca59213be3ab08deff67cc4206",
+    "git_commit" : "a6499fddaa8553874585c747370f919f4d7b729c",
     "git_remote" : "https://github.com/openpipelines-bio/openpipeline"
   },
   "package_config" : {
     "name" : "openpipeline",
-    "version" : "v4.0.3",
+    "version" : "v4.1.0",
     "summary" : "Best-practice workflows for single-cell multi-omics analyses.\n",
     "description" : "OpenPipelines are extensible single cell analysis pipelines for reproducible and large-scale single cell processing using [Viash](https://viash.io) and [Nextflow](https://www.nextflow.io/).\n\nIn terms of workflows, the following has been made available, but keep in mind that\nindividual tools and functionality can be executed as standalone components as well.\n\n  * Demultiplexing: conversion of raw sequencing data to FASTQ objects.\n  * Ingestion: Read mapping and generating a count matrix.\n  * Single sample processing: cell filtering and doublet detection.\n  * Multisample processing: Count transformation, normalization, QC metric calulations.\n  * Integration: Clustering, integration and batch correction using single and multimodal methods.\n  * Downstream analysis workflows\n",
     "info" : {
@@ -3504,14 +3529,14 @@ meta = [
         }
       ]
     },
-    "viash_version" : "0.9.4",
+    "viash_version" : "0.9.7",
     "source" : "/workdir/root/repo/src",
     "target" : "/workdir/root/repo/target",
     "config_mods" : [
       ".resources += {path: '/src/workflows/utils/labels.config', dest: 'nextflow_labels.config'}\n.runners[.type == 'nextflow'].config.script := 'includeConfig(\\"nextflow_labels.config\\")'",
       ".engines += { type: \\"native\\" }",
       ".engines[.type == 'docker'].target_registry := 'images.viash-hub.com'",
-      ".engines[.type == 'docker'].target_tag := 'v4.0.3'"
+      ".engines[.type == 'docker'].target_tag := 'v4.1.0'"
     ],
     "keywords" : [
       "single-cell",
@@ -3553,6 +3578,7 @@ par = {
   'modality': $( if [ ! -z ${VIASH_PAR_MODALITY+x} ]; then echo "r'${VIASH_PAR_MODALITY//\\'/\\'\\"\\'\\"r\\'}'"; else echo None; fi ),
   'layer': $( if [ ! -z ${VIASH_PAR_LAYER+x} ]; then echo "r'${VIASH_PAR_LAYER//\\'/\\'\\"\\'\\"r\\'}'"; else echo None; fi ),
   'var_input': $( if [ ! -z ${VIASH_PAR_VAR_INPUT+x} ]; then echo "r'${VIASH_PAR_VAR_INPUT//\\'/\\'\\"\\'\\"r\\'}'"; else echo None; fi ),
+  'features_to_exclude': $( if [ ! -z ${VIASH_PAR_FEATURES_TO_EXCLUDE+x} ]; then echo "r'${VIASH_PAR_FEATURES_TO_EXCLUDE//\\'/\\'\\"\\'\\"r\\'}'.split(';')"; else echo None; fi ),
   'output': $( if [ ! -z ${VIASH_PAR_OUTPUT+x} ]; then echo "r'${VIASH_PAR_OUTPUT//\\'/\\'\\"\\'\\"r\\'}'"; else echo None; fi ),
   'var_name_filter': $( if [ ! -z ${VIASH_PAR_VAR_NAME_FILTER+x} ]; then echo "r'${VIASH_PAR_VAR_NAME_FILTER//\\'/\\'\\"\\'\\"r\\'}'"; else echo None; fi ),
   'varm_name': $( if [ ! -z ${VIASH_PAR_VARM_NAME+x} ]; then echo "r'${VIASH_PAR_VARM_NAME//\\'/\\'\\"\\'\\"r\\'}'"; else echo None; fi ),
@@ -3651,6 +3677,38 @@ if par["var_input"]:
     input_anndata.var[par["var_input"]] = data.var[par["var_input"]]
     input_anndata = subset_vars(input_anndata, par["var_input"])
 
+# Exclude user-specified features from HVG calculation
+excluded_features_mask = None
+if par.get("features_to_exclude"):
+    features_to_exclude = set(par["features_to_exclude"])
+    logger.info(
+        "\\\\tExcluding %d specified features from HVG calculation",
+        len(features_to_exclude),
+    )
+    excluded_features_mask = input_anndata.var_names.isin(features_to_exclude)
+    n_excluded = excluded_features_mask.sum()
+    n_not_found = len(features_to_exclude) - n_excluded
+    if n_not_found > 0:
+        not_found = features_to_exclude - set(
+            input_anndata.var_names[excluded_features_mask]
+        )
+        logger.warning(
+            "\\\\t%d features to exclude were not found in the data: %s",
+            n_not_found,
+            list(not_found)[:10],
+        )
+    logger.info("\\\\tExcluding %d features from HVG calculation", n_excluded)
+    if n_excluded == input_anndata.n_vars:
+        raise ValueError(
+            f"All features ({n_excluded}) are in the exclusion list. "
+            "Please check your --features_to_exclude list."
+        )
+    # Store original var_names for later reindexing
+    original_var_names = input_anndata.var_names.copy()
+    # Subset to non-excluded features for HVG calculation using subset_vars
+    input_anndata = subset_vars(input_anndata, ~excluded_features_mask)
+    logger.info("\\\\t%d features remaining for HVG calculation", input_anndata.n_vars)
+
 logger.info("\\\\tUnfiltered data: %s", data)
 
 logger.info("\\\\tComputing hvg")
@@ -3695,6 +3753,17 @@ try:
         assert (out.index == data.var.index).all(), (
             "Expected output index values to be equivalent to the input index"
         )
+    elif par.get("features_to_exclude") is not None:
+        # Reindex to include excluded features, marking them as non-HVG
+        out.index = input_anndata.var.index
+        out = out.reindex(index=original_var_names, method=None)
+        out.highly_variable = out.highly_variable.fillna(False)
+        # Further reindex to match data.var.index (for consistency with var_input path)
+        out = out.reindex(index=data.var.index, method=None)
+        out.highly_variable = out.highly_variable.fillna(False)
+        assert (out.index == data.var.index).all(), (
+            "Expected output index values to be equivalent to the input index"
+        )
     elif par["obs_batch_key"] is not None:
         out = out.reindex(index=data.var.index, method=None)
         assert (out.index == data.var.index).all(), (
@@ -4110,7 +4179,7 @@ meta["defaults"] = [
   "container" : {
     "registry" : "images.viash-hub.com",
     "image" : "vsh/openpipeline/feature_annotation/highly_variable_features_scanpy",
-    "tag" : "v4.0.3"
+    "tag" : "v4.1.0"
   },
   "label" : [
     "singlecpu",

target/dependencies/vsh/vsh/openpipeline/v4.1.0/nextflow/feature_annotation/highly_variable_features_scanpy/nextflow.config

@@ -2,7 +2,7 @@ manifest {
   name = 'feature_annotation/highly_variable_features_scanpy'
   mainScript = 'main.nf'
   nextflowVersion = '!>=20.12.1-edge'
-  version = 'v4.0.3'
+  version = 'v4.1.0'
   description = 'Annotate highly variable features [Satija15] [Zheng17] [Stuart19].\n\nExpects logarithmized data, except when flavor=\'seurat_v3\' in which count data is expected.\n\nDepending on flavor, this reproduces the R-implementations of Seurat [Satija15], Cell Ranger [Zheng17], and Seurat v3 [Stuart19].\n\nFor the dispersion-based methods ([Satija15] and [Zheng17]), the normalized dispersion is obtained by scaling with the mean and standard deviation of the dispersions for features falling into a given bin for mean expression of features. This means that for each bin of mean expression, highly variable features are selected.\n\nFor [Stuart19], a normalized variance for each feature is computed. First, the data are standardized (i.e., z-score normalization per feature) with a regularized standard deviation. Next, the normalized variance is computed as the variance of each feature after the transformation. Features are ranked by the normalized variance.\n'
   author = 'Dries De Maeyer, Robrecht Cannoodt'
 }

target/dependencies/vsh/vsh/openpipeline/v4.1.0/nextflow/feature_annotation/highly_variable_features_scanpy/nextflow_schema.json

@@ -32,6 +32,14 @@
           "description": "If specified, use boolean array in adata.var[var_input] to calculate hvg on subset of vars.\n",
           "help_text": "Type: `string`, multiple: `False`. "
         },
+        "features_to_exclude": {
+          "type": "array",
+          "items": {
+            "type": "string"
+          },
+          "description": "User-defined list of feature names to exclude before HVG calculation",
+          "help_text": "Type: `string`, multiple: `True`, example: `[\"MT-CO1\";\"MT-CO2\";\"MT-ND1\"]`. "
+        },
         "output": {
           "type": "string",
           "format": "path",
@@ -109,7 +117,7 @@
         },
         "output_compression": {
           "type": "string",
-          "description": "Compression format to use for the output AnnData and/or Mudata objects.\nBy default no compression is applied.\n",
+          "description": "Compression format to use for the output AnnData and/or Mudata H5 files.\nBy default no compression is applied.\n",
           "help_text": "Type: `string`, multiple: `False`, example: `\"gzip\"`, choices: ``gzip`, `lzf``. ",
           "enum": [
             "gzip",

target/dependencies/vsh/vsh/openpipeline/v4.1.0/nextflow/feature_annotation/highly_variable_features_scanpy/subset_vars.py

@@ -0,0 +1,49 @@
+def subset_vars(adata, subset_col):
+    """
+    Subset AnnData object on highly variable genes or a boolean mask.
+
+    Parameters
+    ----------
+    adata : AnnData
+        Annotated data object
+    subset_col : str, pd.Series, pd.Index, or np.ndarray
+        Name of the boolean column in `adata.var` that contains the information if features should be used or not,
+        or a boolean mask (same length as adata.var)
+
+    Returns
+    -------
+    AnnData
+        Copy of `adata` with subsetted features
+    """
+    import pandas as pd
+    import numpy as np
+
+    # Convert all input types to a pandas Series
+    if isinstance(subset_col, str):
+        if subset_col not in adata.var.columns:
+            raise ValueError(
+                f"Requested to use .var column '{subset_col}' as a selection of genes, but the column is not available."
+            )
+        mask = adata.var[subset_col]
+    elif isinstance(subset_col, pd.Series):
+        mask = subset_col
+    elif isinstance(subset_col, (pd.Index, np.ndarray, list)):
+        mask = pd.Series(subset_col, index=adata.var.index)
+    else:
+        raise TypeError(
+            "subset_col must be a string (column name) or a boolean mask (Series, Index, ndarray, or list)."
+        )
+
+    # Validate mask
+    if not pd.api.types.is_bool_dtype(mask):
+        raise ValueError(
+            f"Expected mask to be boolean, but found {mask.dtype}. Can not subset data."
+        )
+    if mask.isna().sum() > 0:
+        raise ValueError("Mask contains NaN values. Can not subset data.")
+    if len(mask) != adata.n_vars:
+        raise ValueError(
+            f"Mask length {len(mask)} does not match number of variables {adata.n_vars}."
+        )
+
+    return adata[:, mask].copy()

target/dependencies/vsh/vsh/openpipeline/v4.1.0/nextflow/filter/delimit_fraction/.config.vsh.yaml

@@ -1,6 +1,6 @@
 name: "delimit_fraction"
 namespace: "filter"
-version: "v4.0.3"
+version: "v4.1.0"
 authors:
 - name: "Dries Schaumont"
   roles:
@@ -78,8 +78,8 @@ argument_groups:
     multiple_sep: ";"
   - type: "string"
     name: "--output_compression"
-    description: "Compression format to use for the output AnnData and/or Mudata objects.\n\
+    description: "Compression format to use for the output AnnData and/or Mudata H5\
-      By default no compression is applied.\n"
+      \ files.\nBy default no compression is applied.\n"
     info: null
     example:
     - "gzip"
@@ -219,7 +219,7 @@ engines:
   id: "docker"
   image: "python:3.12-slim"
   target_registry: "images.viash-hub.com"
-  target_tag: "v4.0.3"
+  target_tag: "v4.1.0"
   namespace_separator: "/"
   setup:
   - type: "apt"
@@ -229,9 +229,10 @@ engines:
   - type: "python"
     user: false
     packages:
-    - "anndata~=0.12.7"
+    - "anndata~=0.12.16"
     - "awkward"
-    - "mudata~=0.3.2"
+    - "scipy~=1.17.1"
+    - "mudata~=0.3.8"
     script:
     - "exec(\"try:\\n  import zarr; from importlib.metadata import version\\nexcept\
       \ ModuleNotFoundError:\\n  exit(0)\\nelse:  assert int(version(\\\"zarr\\\"\
@@ -245,7 +246,7 @@ engines:
   - type: "python"
     user: false
     packages:
-    - "viashpy==0.8.0"
+    - "viashpy==0.10.0"
     github:
     - "openpipelines-bio/core#subdirectory=packages/python/openpipeline_testutils"
     upgrade: true
@@ -259,12 +260,12 @@ build_info:
   engine: "docker|native"
   output: "target/nextflow/filter/delimit_fraction"
   executable: "target/nextflow/filter/delimit_fraction/main.nf"
-  viash_version: "0.9.4"
+  viash_version: "0.9.7"
-  git_commit: "7bfad4ea12f87eca59213be3ab08deff67cc4206"
+  git_commit: "a6499fddaa8553874585c747370f919f4d7b729c"
   git_remote: "https://github.com/openpipelines-bio/openpipeline"
 package_config:
   name: "openpipeline"
-  version: "v4.0.3"
+  version: "v4.1.0"
   summary: "Best-practice workflows for single-cell multi-omics analyses.\n"
   description: "OpenPipelines are extensible single cell analysis pipelines for reproducible\
     \ and large-scale single cell processing using [Viash](https://viash.io) and [Nextflow](https://www.nextflow.io/).\n\
@@ -285,7 +286,7 @@ package_config:
     - path: "src/workflows/utils/labels_ci.config"
       description: "Adds the correct memory and CPU labels when running on the Viash\
         \ Hub CI."
-  viash_version: "0.9.4"
+  viash_version: "0.9.7"
   source: "src"
   target: "target"
   config_mods:
@@ -294,7 +295,7 @@ package_config:
     )'"
   - ".engines += { type: \"native\" }"
   - ".engines[.type == 'docker'].target_registry := 'images.viash-hub.com'"
-  - ".engines[.type == 'docker'].target_tag := 'v4.0.3'"
+  - ".engines[.type == 'docker'].target_tag := 'v4.1.0'"
   keywords:
   - "single-cell"
   - "multimodal"

target/dependencies/vsh/vsh/openpipeline/v4.1.0/nextflow/filter/delimit_fraction/main.nf

@@ -1,6 +1,6 @@
-// delimit_fraction v4.0.3
+// delimit_fraction v4.1.0
 // 
-// This wrapper script is auto-generated by viash 0.9.4 and is thus a derivative
+// This wrapper script is auto-generated by viash 0.9.7 and is thus a derivative
 // work thereof. This software comes with ABSOLUTELY NO WARRANTY from Data
 // Intuitive.
 // 
@@ -1353,47 +1353,42 @@ def readCsv(file_path) {
   def splitRegex = java.util.regex.Pattern.compile(''',(?=(?:[^"]*"[^"]*")*[^"]*$)''')
   def removeQuote = java.util.regex.Pattern.compile('''"(.*)"''')
 
-  def br = java.nio.file.Files.newBufferedReader(inputFile)
+  java.nio.file.Files.newBufferedReader(inputFile).withCloseable { br ->
+    def row = 0
+    def header = null
+    def line
 
-  def row = -1
+    while (header == null && (line = br.readLine()) != null) {
-  def header = null
+      if (!line.startsWith("#")) {
-  while (br.ready() && header == null) {
+        header = splitRegex.split(line, -1).collect { field ->
-    def line = br.readLine()
+          def m = removeQuote.matcher(field)
-    row++
+          m.find() ? m.replaceFirst('$1') : field
-    if (!line.startsWith("#")) {
-      header = splitRegex.split(line, -1).collect{field ->
-        m = removeQuote.matcher(field)
-        m.find() ? m.replaceFirst('$1') : field
-      }
-    }
-  }
-  assert header != null: "CSV file should contain a header"
-
-  while (br.ready()) {
-    def line = br.readLine()
-    row++
-    if (line == null) {
-      br.close()
-      break
-    }
-
-    if (!line.startsWith("#")) {
-      def predata = splitRegex.split(line, -1)
-      def data = predata.collect{field ->
-        if (field == "") {
-          return null
-        }
-        def m = removeQuote.matcher(field)
-        if (m.find()) {
-          return m.replaceFirst('$1')
-        } else {
-          return field
         }
       }
-      assert header.size() == data.size(): "Row $row should contain the same number as fields as the header"
+      row++
-      
+    }
-      def dataMap = [header, data].transpose().collectEntries().findAll{it.value != null}
+    assert header != null : "CSV file should contain a header"
-      output.add(dataMap)
+
+    while ((line = br.readLine()) != null) {
+      row++
+      if (!line.startsWith("#")) {
+        def predata = splitRegex.split(line, -1)
+        def data = predata.collect { field ->
+          if (field == "") {
+            return null
+          }
+          def m = removeQuote.matcher(field)
+          if (m.find()) {
+            return m.replaceFirst('$1')
+          } else {
+            return field
+          }
+        }
+        assert header.size() == data.size() : "Row $row should contain the same number as fields as the header"
+
+        def dataMap = [header, data].transpose().collectEntries().findAll { it.value != null }
+        output.add(dataMap)
+      }
     }
   }
 
@@ -1709,10 +1704,25 @@ process publishFilesProc {
   ]
     .transpose()
     .collectMany{infile, outfile ->
-      if (infile.toString() != outfile.toString()) {
+      def infileString = infile.toString()
+      def outfileString = outfile.toString()
+      if (infileString != outfileString) {
+        /* Trailing slashes are removed from both the source and destination arguments.
+           From source arguments, this is useful when a source argument may have a trailing slash
+           and specify a symbolic link to a directory. Without removing the slash, cp will dereference
+           the symbolic link. 
+           See https://www.gnu.org/software/coreutils/manual/html_node/Trailing-slashes.html#Trailing-slashes-1
+
+           For the destination path addding a trailing slash is a problem when publishing directories: 
+           it requires the destination directory to exist. This fails because we only create the parent
+           directories first.
+        */
+        def regexTrailingSlashes = ~/\/+$/
+        def infileNoTrailingSlash = infileString - regexTrailingSlashes
+        def outfileNoTrailingSlash = outfileString - regexTrailingSlashes
         [
-          "[ -d \"\$(dirname '${outfile.toString()}')\" ] || mkdir -p \"\$(dirname '${outfile.toString()}')\"",
+          "[ -d \"\$(dirname '${outfileNoTrailingSlash}')\" ] || mkdir -p \"\$(dirname '${outfileNoTrailingSlash}')\"",
-          "cp -r '${infile.toString()}' '${outfile.toString()}'"
+          "cp -a '${infileNoTrailingSlash}' '${outfileNoTrailingSlash}'"
         ]
       } else {
         // no need to copy if infile is the same as outfile
@@ -3035,7 +3045,7 @@ meta = [
   "config": processConfig(readJsonBlob('''{
   "name" : "delimit_fraction",
   "namespace" : "filter",
-  "version" : "v4.0.3",
+  "version" : "v4.1.0",
   "authors" : [
     {
       "name" : "Dries Schaumont",
@@ -3134,7 +3144,7 @@ meta = [
         {
           "type" : "string",
           "name" : "--output_compression",
-          "description" : "Compression format to use for the output AnnData and/or Mudata objects.\nBy default no compression is applied.\n",
+          "description" : "Compression format to use for the output AnnData and/or Mudata H5 files.\nBy default no compression is applied.\n",
           "example" : [
             "gzip"
           ],
@@ -3312,7 +3322,7 @@ meta = [
       "id" : "docker",
       "image" : "python:3.12-slim",
       "target_registry" : "images.viash-hub.com",
-      "target_tag" : "v4.0.3",
+      "target_tag" : "v4.1.0",
       "namespace_separator" : "/",
       "setup" : [
         {
@@ -3326,9 +3336,10 @@ meta = [
           "type" : "python",
           "user" : false,
           "packages" : [
-            "anndata~=0.12.7",
+            "anndata~=0.12.16",
             "awkward",
-            "mudata~=0.3.2"
+            "scipy~=1.17.1",
+            "mudata~=0.3.8"
           ],
           "script" : [
             "exec(\\"try:\\\\n  import zarr; from importlib.metadata import version\\\\nexcept ModuleNotFoundError:\\\\n  exit(0)\\\\nelse:  assert int(version(\\\\\\"zarr\\\\\\").partition(\\\\\\".\\\\\\")[0]) > 2\\")"
@@ -3348,7 +3359,7 @@ meta = [
           "type" : "python",
           "user" : false,
           "packages" : [
-            "viashpy==0.8.0"
+            "viashpy==0.10.0"
           ],
           "github" : [
             "openpipelines-bio/core#subdirectory=packages/python/openpipeline_testutils"
@@ -3367,13 +3378,13 @@ meta = [
     "runner" : "nextflow",
     "engine" : "docker|native",
     "output" : "/workdir/root/repo/target/nextflow/filter/delimit_fraction",
-    "viash_version" : "0.9.4",
+    "viash_version" : "0.9.7",
-    "git_commit" : "7bfad4ea12f87eca59213be3ab08deff67cc4206",
+    "git_commit" : "a6499fddaa8553874585c747370f919f4d7b729c",
     "git_remote" : "https://github.com/openpipelines-bio/openpipeline"
   },
   "package_config" : {
     "name" : "openpipeline",
-    "version" : "v4.0.3",
+    "version" : "v4.1.0",
     "summary" : "Best-practice workflows for single-cell multi-omics analyses.\n",
     "description" : "OpenPipelines are extensible single cell analysis pipelines for reproducible and large-scale single cell processing using [Viash](https://viash.io) and [Nextflow](https://www.nextflow.io/).\n\nIn terms of workflows, the following has been made available, but keep in mind that\nindividual tools and functionality can be executed as standalone components as well.\n\n  * Demultiplexing: conversion of raw sequencing data to FASTQ objects.\n  * Ingestion: Read mapping and generating a count matrix.\n  * Single sample processing: cell filtering and doublet detection.\n  * Multisample processing: Count transformation, normalization, QC metric calulations.\n  * Integration: Clustering, integration and batch correction using single and multimodal methods.\n  * Downstream analysis workflows\n",
     "info" : {
@@ -3391,14 +3402,14 @@ meta = [
         }
       ]
     },
-    "viash_version" : "0.9.4",
+    "viash_version" : "0.9.7",
     "source" : "/workdir/root/repo/src",
     "target" : "/workdir/root/repo/target",
     "config_mods" : [
       ".resources += {path: '/src/workflows/utils/labels.config', dest: 'nextflow_labels.config'}\n.runners[.type == 'nextflow'].config.script := 'includeConfig(\\"nextflow_labels.config\\")'",
       ".engines += { type: \\"native\\" }",
       ".engines[.type == 'docker'].target_registry := 'images.viash-hub.com'",
-      ".engines[.type == 'docker'].target_tag := 'v4.0.3'"
+      ".engines[.type == 'docker'].target_tag := 'v4.1.0'"
     ],
     "keywords" : [
       "single-cell",
@@ -3928,7 +3939,7 @@ meta["defaults"] = [
   "container" : {
     "registry" : "images.viash-hub.com",
     "image" : "vsh/openpipeline/filter/delimit_fraction",
-    "tag" : "v4.0.3"
+    "tag" : "v4.1.0"
   },
   "label" : [
     "singlecpu",

target/dependencies/vsh/vsh/openpipeline/v4.1.0/nextflow/filter/delimit_fraction/nextflow.config

@@ -2,7 +2,7 @@ manifest {
   name = 'filter/delimit_fraction'
   mainScript = 'main.nf'
   nextflowVersion = '!>=20.12.1-edge'
-  version = 'v4.0.3'
+  version = 'v4.1.0'
   description = 'Turns a column containing values between 0 and 1 into a boolean column based on thresholds.\n'
   author = 'Dries Schaumont'
 }

target/dependencies/vsh/vsh/openpipeline/v4.1.0/nextflow/filter/delimit_fraction/nextflow_schema.json

@@ -48,7 +48,7 @@
         },
         "output_compression": {
           "type": "string",
-          "description": "Compression format to use for the output AnnData and/or Mudata objects.\nBy default no compression is applied.\n",
+          "description": "Compression format to use for the output AnnData and/or Mudata H5 files.\nBy default no compression is applied.\n",
           "help_text": "Type: `string`, multiple: `False`, example: `\"gzip\"`, choices: ``gzip`, `lzf``. ",
           "enum": [
             "gzip",

target/dependencies/vsh/vsh/openpipeline/v4.1.0/nextflow/filter/do_filter/.config.vsh.yaml

@@ -1,6 +1,6 @@
 name: "do_filter"
 namespace: "filter"
-version: "v4.0.3"
+version: "v4.1.0"
 authors:
 - name: "Robrecht Cannoodt"
   roles:
@@ -79,8 +79,8 @@ argument_groups:
     multiple_sep: ";"
   - type: "string"
     name: "--output_compression"
-    description: "Compression format to use for the output AnnData and/or Mudata objects.\n\
+    description: "Compression format to use for the output AnnData and/or Mudata H5\
-      By default no compression is applied.\n"
+      \ files.\nBy default no compression is applied.\n"
     info: null
     example:
     - "gzip"
@@ -193,7 +193,7 @@ engines:
   id: "docker"
   image: "python:3.12-slim"
   target_registry: "images.viash-hub.com"
-  target_tag: "v4.0.3"
+  target_tag: "v4.1.0"
   namespace_separator: "/"
   setup:
   - type: "apt"
@@ -203,9 +203,10 @@ engines:
   - type: "python"
     user: false
     packages:
-    - "anndata~=0.12.7"
+    - "anndata~=0.12.16"
     - "awkward"
-    - "mudata~=0.3.2"
+    - "scipy~=1.17.1"
+    - "mudata~=0.3.8"
     script:
     - "exec(\"try:\\n  import zarr; from importlib.metadata import version\\nexcept\
       \ ModuleNotFoundError:\\n  exit(0)\\nelse:  assert int(version(\\\"zarr\\\"\
@@ -215,7 +216,7 @@ engines:
   - type: "python"
     user: false
     packages:
-    - "viashpy==0.8.0"
+    - "viashpy==0.10.0"
     upgrade: true
   entrypoint: []
   cmd: null
@@ -227,12 +228,12 @@ build_info:
   engine: "docker|native"
   output: "target/nextflow/filter/do_filter"
   executable: "target/nextflow/filter/do_filter/main.nf"
-  viash_version: "0.9.4"
+  viash_version: "0.9.7"
-  git_commit: "7bfad4ea12f87eca59213be3ab08deff67cc4206"
+  git_commit: "a6499fddaa8553874585c747370f919f4d7b729c"
   git_remote: "https://github.com/openpipelines-bio/openpipeline"
 package_config:
   name: "openpipeline"
-  version: "v4.0.3"
+  version: "v4.1.0"
   summary: "Best-practice workflows for single-cell multi-omics analyses.\n"
   description: "OpenPipelines are extensible single cell analysis pipelines for reproducible\
     \ and large-scale single cell processing using [Viash](https://viash.io) and [Nextflow](https://www.nextflow.io/).\n\
@@ -253,7 +254,7 @@ package_config:
     - path: "src/workflows/utils/labels_ci.config"
       description: "Adds the correct memory and CPU labels when running on the Viash\
         \ Hub CI."
-  viash_version: "0.9.4"
+  viash_version: "0.9.7"
   source: "src"
   target: "target"
   config_mods:
@@ -262,7 +263,7 @@ package_config:
     )'"
   - ".engines += { type: \"native\" }"
   - ".engines[.type == 'docker'].target_registry := 'images.viash-hub.com'"
-  - ".engines[.type == 'docker'].target_tag := 'v4.0.3'"
+  - ".engines[.type == 'docker'].target_tag := 'v4.1.0'"
   keywords:
   - "single-cell"
   - "multimodal"

target/dependencies/vsh/vsh/openpipeline/v4.1.0/nextflow/filter/do_filter/main.nf

@@ -1,6 +1,6 @@
-// do_filter v4.0.3
+// do_filter v4.1.0
 // 
-// This wrapper script is auto-generated by viash 0.9.4 and is thus a derivative
+// This wrapper script is auto-generated by viash 0.9.7 and is thus a derivative
 // work thereof. This software comes with ABSOLUTELY NO WARRANTY from Data
 // Intuitive.
 // 
@@ -1353,47 +1353,42 @@ def readCsv(file_path) {
   def splitRegex = java.util.regex.Pattern.compile(''',(?=(?:[^"]*"[^"]*")*[^"]*$)''')
   def removeQuote = java.util.regex.Pattern.compile('''"(.*)"''')
 
-  def br = java.nio.file.Files.newBufferedReader(inputFile)
+  java.nio.file.Files.newBufferedReader(inputFile).withCloseable { br ->
+    def row = 0
+    def header = null
+    def line
 
-  def row = -1
+    while (header == null && (line = br.readLine()) != null) {
-  def header = null
+      if (!line.startsWith("#")) {
-  while (br.ready() && header == null) {
+        header = splitRegex.split(line, -1).collect { field ->
-    def line = br.readLine()
+          def m = removeQuote.matcher(field)
-    row++
+          m.find() ? m.replaceFirst('$1') : field
-    if (!line.startsWith("#")) {
-      header = splitRegex.split(line, -1).collect{field ->
-        m = removeQuote.matcher(field)
-        m.find() ? m.replaceFirst('$1') : field
-      }
-    }
-  }
-  assert header != null: "CSV file should contain a header"
-
-  while (br.ready()) {
-    def line = br.readLine()
-    row++
-    if (line == null) {
-      br.close()
-      break
-    }
-
-    if (!line.startsWith("#")) {
-      def predata = splitRegex.split(line, -1)
-      def data = predata.collect{field ->
-        if (field == "") {
-          return null
-        }
-        def m = removeQuote.matcher(field)
-        if (m.find()) {
-          return m.replaceFirst('$1')
-        } else {
-          return field
         }
       }
-      assert header.size() == data.size(): "Row $row should contain the same number as fields as the header"
+      row++
-      
+    }
-      def dataMap = [header, data].transpose().collectEntries().findAll{it.value != null}
+    assert header != null : "CSV file should contain a header"
-      output.add(dataMap)
+
+    while ((line = br.readLine()) != null) {
+      row++
+      if (!line.startsWith("#")) {
+        def predata = splitRegex.split(line, -1)
+        def data = predata.collect { field ->
+          if (field == "") {
+            return null
+          }
+          def m = removeQuote.matcher(field)
+          if (m.find()) {
+            return m.replaceFirst('$1')
+          } else {
+            return field
+          }
+        }
+        assert header.size() == data.size() : "Row $row should contain the same number as fields as the header"
+
+        def dataMap = [header, data].transpose().collectEntries().findAll { it.value != null }
+        output.add(dataMap)
+      }
     }
   }
 
@@ -1709,10 +1704,25 @@ process publishFilesProc {
   ]
     .transpose()
     .collectMany{infile, outfile ->
-      if (infile.toString() != outfile.toString()) {
+      def infileString = infile.toString()
+      def outfileString = outfile.toString()
+      if (infileString != outfileString) {
+        /* Trailing slashes are removed from both the source and destination arguments.
+           From source arguments, this is useful when a source argument may have a trailing slash
+           and specify a symbolic link to a directory. Without removing the slash, cp will dereference
+           the symbolic link. 
+           See https://www.gnu.org/software/coreutils/manual/html_node/Trailing-slashes.html#Trailing-slashes-1
+
+           For the destination path addding a trailing slash is a problem when publishing directories: 
+           it requires the destination directory to exist. This fails because we only create the parent
+           directories first.
+        */
+        def regexTrailingSlashes = ~/\/+$/
+        def infileNoTrailingSlash = infileString - regexTrailingSlashes
+        def outfileNoTrailingSlash = outfileString - regexTrailingSlashes
         [
-          "[ -d \"\$(dirname '${outfile.toString()}')\" ] || mkdir -p \"\$(dirname '${outfile.toString()}')\"",
+          "[ -d \"\$(dirname '${outfileNoTrailingSlash}')\" ] || mkdir -p \"\$(dirname '${outfileNoTrailingSlash}')\"",
-          "cp -r '${infile.toString()}' '${outfile.toString()}'"
+          "cp -a '${infileNoTrailingSlash}' '${outfileNoTrailingSlash}'"
         ]
       } else {
         // no need to copy if infile is the same as outfile
@@ -3035,7 +3045,7 @@ meta = [
   "config": processConfig(readJsonBlob('''{
   "name" : "do_filter",
   "namespace" : "filter",
-  "version" : "v4.0.3",
+  "version" : "v4.1.0",
   "authors" : [
     {
       "name" : "Robrecht Cannoodt",
@@ -3137,7 +3147,7 @@ meta = [
         {
           "type" : "string",
           "name" : "--output_compression",
-          "description" : "Compression format to use for the output AnnData and/or Mudata objects.\nBy default no compression is applied.\n",
+          "description" : "Compression format to use for the output AnnData and/or Mudata H5 files.\nBy default no compression is applied.\n",
           "example" : [
             "gzip"
           ],
@@ -3282,7 +3292,7 @@ meta = [
       "id" : "docker",
       "image" : "python:3.12-slim",
       "target_registry" : "images.viash-hub.com",
-      "target_tag" : "v4.0.3",
+      "target_tag" : "v4.1.0",
       "namespace_separator" : "/",
       "setup" : [
         {
@@ -3296,9 +3306,10 @@ meta = [
           "type" : "python",
           "user" : false,
           "packages" : [
-            "anndata~=0.12.7",
+            "anndata~=0.12.16",
             "awkward",
-            "mudata~=0.3.2"
+            "scipy~=1.17.1",
+            "mudata~=0.3.8"
           ],
           "script" : [
             "exec(\\"try:\\\\n  import zarr; from importlib.metadata import version\\\\nexcept ModuleNotFoundError:\\\\n  exit(0)\\\\nelse:  assert int(version(\\\\\\"zarr\\\\\\").partition(\\\\\\".\\\\\\")[0]) > 2\\")"
@@ -3311,7 +3322,7 @@ meta = [
           "type" : "python",
           "user" : false,
           "packages" : [
-            "viashpy==0.8.0"
+            "viashpy==0.10.0"
           ],
           "upgrade" : true
         }
@@ -3327,13 +3338,13 @@ meta = [
     "runner" : "nextflow",
     "engine" : "docker|native",
     "output" : "/workdir/root/repo/target/nextflow/filter/do_filter",
-    "viash_version" : "0.9.4",
+    "viash_version" : "0.9.7",
-    "git_commit" : "7bfad4ea12f87eca59213be3ab08deff67cc4206",
+    "git_commit" : "a6499fddaa8553874585c747370f919f4d7b729c",
     "git_remote" : "https://github.com/openpipelines-bio/openpipeline"
   },
   "package_config" : {
     "name" : "openpipeline",
-    "version" : "v4.0.3",
+    "version" : "v4.1.0",
     "summary" : "Best-practice workflows for single-cell multi-omics analyses.\n",
     "description" : "OpenPipelines are extensible single cell analysis pipelines for reproducible and large-scale single cell processing using [Viash](https://viash.io) and [Nextflow](https://www.nextflow.io/).\n\nIn terms of workflows, the following has been made available, but keep in mind that\nindividual tools and functionality can be executed as standalone components as well.\n\n  * Demultiplexing: conversion of raw sequencing data to FASTQ objects.\n  * Ingestion: Read mapping and generating a count matrix.\n  * Single sample processing: cell filtering and doublet detection.\n  * Multisample processing: Count transformation, normalization, QC metric calulations.\n  * Integration: Clustering, integration and batch correction using single and multimodal methods.\n  * Downstream analysis workflows\n",
     "info" : {
@@ -3351,14 +3362,14 @@ meta = [
         }
       ]
     },
-    "viash_version" : "0.9.4",
+    "viash_version" : "0.9.7",
     "source" : "/workdir/root/repo/src",
     "target" : "/workdir/root/repo/target",
     "config_mods" : [
       ".resources += {path: '/src/workflows/utils/labels.config', dest: 'nextflow_labels.config'}\n.runners[.type == 'nextflow'].config.script := 'includeConfig(\\"nextflow_labels.config\\")'",
       ".engines += { type: \\"native\\" }",
       ".engines[.type == 'docker'].target_registry := 'images.viash-hub.com'",
-      ".engines[.type == 'docker'].target_tag := 'v4.0.3'"
+      ".engines[.type == 'docker'].target_tag := 'v4.1.0'"
     ],
     "keywords" : [
       "single-cell",
@@ -3851,7 +3862,7 @@ meta["defaults"] = [
   "container" : {
     "registry" : "images.viash-hub.com",
     "image" : "vsh/openpipeline/filter/do_filter",
-    "tag" : "v4.0.3"
+    "tag" : "v4.1.0"
   },
   "label" : [
     "singlecpu",