Put output_compression argument in base

CHANGELOG.md

@@ -12,6 +12,8 @@
 
 * Remove `workflows` directory (PR #993). The workflows which were at one point in this directory were all deprecated and moved to `src/workflows`.
 
+* Move output file compression argument for AnnData and MuData files to a base config file (`src/base/h5_compression_argument.yaml`) (PR #1017).
+
 ## BUG FIXES
 
 * Bump viash to 0.9.4. This adds support for nextflow versions starting major version 25.01 and fixes an issue where an integer being passed to a argument with `type: double` resulted in an error (PR #1016).

src/annotate/celltypist/config.vsh.yaml

@@ -109,11 +109,6 @@ argument_groups:
         description: Output h5mu file.
         direction: output
         example: output.h5mu
-      - name: "--output_compression"
-        type: string
-        choices: ["gzip", "lzf"]
-        required: false
-        example: "gzip"
       - name: "--output_obs_predictions"
         type: string
         default: celltypist_pred
@@ -126,6 +121,7 @@ argument_groups:
         required: false
         description: |
           In which `.obs` slots to store the probability of the predictions.
+    __merge__: [., /src/base/h5_compression_argument.yaml]
 
 resources:
   - type: python_script

src/annotate/onclass/config.vsh.yaml

@@ -98,11 +98,6 @@ argument_groups:
         description: Output h5mu file.
         direction: output
         example: output.h5mu
-      - name: "--output_compression"
-        type: string
-        choices: ["gzip", "lzf"]
-        required: false
-        example: "gzip"
       - name: "--output_obs_predictions"
         type: string
         default: onclass_pred
@@ -115,6 +110,7 @@ argument_groups:
         required: false
         description: |
           In which `.obs` slots to store the probability of the predictions.
+    __merge__: [., /src/base/h5_compression_argument.yaml]
 
   - name: Model arguments
     description: Model arguments

src/annotate/popv/config.vsh.yaml

@@ -80,11 +80,8 @@ argument_groups:
         direction: output
         required: true
         example: output.h5mu
-      - name: "--output_compression"
-        type: string
-        choices: ["gzip", "lzf"]
-        required: false
-        example: "gzip"
+    __merge__: [., /src/base/h5_compression_argument.yaml]
+
       # - name: "--output_models"
       #   type: file
       #   direction: output

src/annotate/random_forest_annotation/config.vsh.yaml

@@ -71,11 +71,6 @@ argument_groups:
         description: Output h5mu file.
         direction: output
         example: output.h5mu
-      - name: "--output_compression"
-        type: string
-        choices: ["gzip", "lzf"]
-        required: false
-        example: "gzip"
       - name: "--output_obs_predictions"
         type: string
         default: random_forest_pred
@@ -88,6 +83,7 @@ argument_groups:
         required: false
         description: |
           In which `.obs` slots to store the probability of the predictions.
+    __merge__: [., /src/base/h5_compression_argument.yaml]
 
   - name: Model arguments
     description: Model arguments.

src/annotate/scanvi/config.vsh.yaml

@@ -68,12 +68,6 @@ argument_groups:
         description: Folder where the state of the trained model will be saved to.
         required: false
         direction: output
-      - name: "--output_compression"
-        type: string
-        description: The compression format to be used on the output h5mu object.
-        choices: ["gzip", "lzf"]
-        required: false
-        example: "gzip"
       - name: "--obsm_output"
         type: string
         default: "X_scanvi_integrated"
@@ -87,7 +81,8 @@ argument_groups:
         type: string
         default: scanvi_proba
         description: "In which. obs slot to store the probabilities of the predicted labels."
-
+    __merge__: [., /src/base/h5_compression_argument.yaml]
+
   - name: "scANVI training arguments"
     arguments:
       - name: "--early_stopping"

src/annotate/svm_annotation/config.vsh.yaml

@@ -71,11 +71,6 @@ argument_groups:
         description: Output h5mu file.
         direction: output
         example: output.h5mu
-      - name: "--output_compression"
-        type: string
-        choices: ["gzip", "lzf"]
-        required: false
-        example: "gzip"
       - name: "--output_obs_prediction"
         type: string
         default: svm_pred
@@ -88,6 +83,7 @@ argument_groups:
         required: false
         description: |
           In which `.obs` slots to store the probability of the predictions.
+    __merge__: [., /src/base/h5_compression_argument.yaml]
 
   - name: Model arguments
     description: Model arguments.

src/base/h5_compression_argument.yaml

@@ -0,0 +1,9 @@
+arguments:
+  - name: "--output_compression"
+    description: |
+      Compression format to use for the output AnnData and/or Mudata objects.
+      By default no compression is applied.
+    type: string
+    choices: ["gzip", "lzf"]
+    required: false
+    example: "gzip"

src/cluster/leiden/config.vsh.yaml

@@ -41,13 +41,6 @@ arguments:
     direction: output
     required: true
     example: output.h5mu
-
-  - name: "--output_compression"
-    type: string
-    choices: ["gzip", "lzf"]
-    required: false
-    example: "gzip"
-
   - name: "--obsm_name"
     type: string
     description: |
@@ -67,6 +60,8 @@ arguments:
     default: [1]
     required: true
     multiple: true
+__merge__: [., /src/base/h5_compression_argument.yaml]
+
 resources:
   - type: python_script
     path: script.py

src/convert/from_10xh5_to_h5mu/config.vsh.yaml

@@ -28,15 +28,12 @@ argument_groups:
         example: output.h5mu
         direction: output
         __merge__: api_output.yaml
-      - name: "--output_compression"
-        type: string
-        choices: ["gzip", "lzf"]
-        required: false
-        example: "gzip"
       - name: "--uns_metrics"
         type: string
         description: Name of the .uns slot under which to QC metrics (if any).
         default: "metrics_cellranger"
+    __merge__: [., /src/base/h5_compression_argument.yaml]
+
   - name: Arguments
     arguments:
       - name: "--min_genes"

src/convert/from_10xmtx_to_h5mu/config.vsh.yaml

@@ -19,11 +19,8 @@ arguments:
     description: Output h5mu file.
     example: output.h5mu
     direction: output
-  - name: "--output_compression"
-    type: string
-    choices: ["gzip", "lzf"]
-    required: false
-    example: "gzip"
+__merge__: [., /src/base/h5_compression_argument.yaml]
+
 resources:
   - type: python_script
     path: script.py

src/convert/from_bdrhap_to_h5mu/config.vsh.yaml

@@ -30,11 +30,8 @@ argument_groups:
         description: "Output h5mu file."
         required: true
         example: output.h5mu
-      - name: "--output_compression"
-        type: string
-        choices: ["gzip", "lzf"]
-        required: false
-        example: "gzip"
+__merge__: [., /src/base/h5_compression_argument.yaml]
+
 resources:
   - type: python_script
     path: script.py

src/convert/from_cellranger_multi_to_h5mu/config.vsh.yaml

@@ -41,15 +41,12 @@ arguments:
     description: CSV file describing the sample name per output file
     direction: output
     example: "samples.csv"
-  - name: "--output_compression"
-    type: string
-    choices: ["gzip", "lzf"]
-    required: false
-    example: "gzip"
   - name: "--uns_metrics"
     type: string
     description: Name of the .uns slot under which to QC metrics (if any).
     default: "metrics_cellranger"
+__merge__: [., /src/base/h5_compression_argument.yaml]
+
 resources:
   - type: python_script
     path: script.py

src/convert/from_h5ad_to_h5mu/config.vsh.yaml

@@ -25,11 +25,9 @@ arguments:
     description: Output MuData file.
     default: output.h5mu
     direction: output
-  - name: "--output_compression"
-    type: string
-    choices: ["gzip", "lzf"]
-    required: false
-    example: "gzip"
+__merge__: [., /src/base/h5_compression_argument.yaml]
+
+
 resources:
   - type: python_script
     path: script.py

src/convert/from_h5mu_to_h5ad/config.vsh.yaml

@@ -23,11 +23,9 @@ arguments:
     description: Output AnnData file.
     default: output.h5ad
     direction: output
-  - name: "--output_compression"
-    type: string
-    description: The compression format to be used on the final h5ad object.
-    default: "gzip"
-    choices: ["gzip", "lzf"]
+__merge__: [., /src/base/h5_compression_argument.yaml]
+
+
 resources:
   - type: python_script
     path: script.py

src/correction/cellbender_remove_background/config.vsh.yaml

@@ -32,11 +32,6 @@ argument_groups:
         direction: output
         required: true
         example: output.h5mu
-      - name: "--output_compression"
-        type: string
-        choices: ["gzip", "lzf"]
-        required: false
-        example: "gzip"
       - name: "--layer_output"
         description: Output layer
         type: string
@@ -62,6 +57,8 @@ argument_groups:
       - name: "--obsm_gene_expression_encoding"
         type: string
         default: "cellbender_gene_expression_encoding"
+    __merge__: [., /src/base/h5_compression_argument.yaml]
+
   - name: Arguments
     arguments:
       # custom arg

src/correction/cellbender_remove_background_v0_2/config.vsh.yaml

@@ -32,11 +32,6 @@ argument_groups:
         direction: output
         required: true
         example: output.h5mu
-      - name: "--output_compression"
-        type: string
-        choices: ["gzip", "lzf"]
-        required: false
-        example: "gzip"
       - name: "--layer_output"
         description: Output layer
         type: string
@@ -56,6 +51,8 @@ argument_groups:
       - name: "--obsm_latent_gene_encoding"
         type: string
         default: "cellbender_latent_gene_encoding"
+    __merge__: [., /src/base/h5_compression_argument.yaml]
+
   - name: Arguments
     arguments:
       - name: "--expected_cells"

src/dataflow/concatenate_h5mu/config.vsh.yaml

@@ -31,12 +31,6 @@ arguments:
     type: file
     direction: output
     example: "output.h5mu"
-  - name: "--output_compression"
-    type: string
-    description: The compression format to be used on the output h5mu object.
-    choices: ["gzip", "lzf"]
-    required: false
-    example: "gzip"
   - name: "--obs_sample_name"
     type: string
     description: Name of the .obs key under which to add the sample names.
@@ -66,6 +60,7 @@ arguments:
     type: string
     choices: ["same", "unique", "first", "only", "make_unique"]
     default: make_unique
+__merge__: [., /src/base/h5_compression_argument.yaml]
 
 resources:
   - type: python_script

src/dataflow/split_h5mu/config.vsh.yaml

@@ -36,18 +36,14 @@ argument_groups:
     direction: output
     example: "/path/to/output"
     description: Output directory containing multiple h5mu files.
-  - name: "--output_compression"
-    type: string
-    description: The compression format to be used on the output h5mu object.
-    choices: ["gzip", "lzf"]
-    required: false
-    example: "gzip"
   - name: "--output_files"
     type: file
     required: true
     direction: output
     example: sample_files.csv
     description: A csv containing the base filename and obs feature by which it was split.
+  __merge__: [., /src/base/h5_compression_argument.yaml]
+
 
 resources:
   - type: python_script

src/dataflow/split_modalities/config.vsh.yaml

@@ -21,18 +21,14 @@ arguments:
     direction: output
     example: "/path/to/output"
     description: Output directory containing multiple h5mu files.
-  - name: "--output_compression"
-    type: string
-    description: The compression format to be used on the output h5mu object.
-    choices: ["gzip", "lzf"]
-    required: false
-    example: "gzip"
   - name: "--output_types"
     type: file
     required: true
     direction: output
     example: types.csv
     description: A csv containing the base filename and modality type per output file.
+__merge__: [., /src/base/h5_compression_argument.yaml]
+
 resources:
   - type: python_script
     path: script.py

src/dimred/densmap/config.vsh.yaml

@@ -42,17 +42,12 @@ argument_groups:
         required: true
         example: output.h5mu
 
-      - name: "--output_compression"
-        type: string
-        description: The compression format to be used on the output h5mu object.
-        choices: ["gzip", "lzf"]
-        required: false
-        example: "gzip"
-
       - name: "--obsm_output"
         type: string
         description: The .obsm key to use for storing the densMAP results..
         default: "X_densmap"
+    __merge__: [., /src/base/h5_compression_argument.yaml]
+
 
   - name: Arguments UMAP
     arguments: