add process_dataset config file [WIP]

src/dataset_processors/process_dataset/config.vsh.yaml

@@ -0,0 +1,34 @@
+__merge__: ../../api/comp_data_processor.yaml
+name: process_dataset
+arguments:
+  - name: "--method"
+    type: "string"
+    description: "The process method to assign train/test."
+    choices: ["batch", "random"]
+    default: "batch"
+  - name: "--obs_label"
+    type: "string"
+    description: "Which .obs slot to use as label."
+    default: "cell_type"
+  - name: "--obs_batch"
+    type: "string"
+    description: "Which .obs slot to use as batch covariate."
+    default: "batch"
+  - name: "--seed"
+    type: "integer"
+    description: "A seed for the subsampling."
+    example: 123
+resources:
+  - type: python_script
+    path: script.py
+  - path: common/helper_functions/subset_anndata.py
+
+engines:
+  - type: docker
+    image: ghcr.io/openproblems-bio/base_images/python:1.1.0
+
+runners:
+  - type: executable
+  - type: nextflow
+    directives:
+      label: [highmem,midcpu,midtime]