Added op3loader

src/datasets/loaders/scrnaseq/op3_loader/config.vsh.yaml

@@ -0,0 +1,107 @@
+name: op3_loader
+namespace: datasets/loaders/scrnaseq
+description: |
+  "Loads and preprocesses the OP3 dataset from GEO accession GSE279945."
+
+argument_groups:
+  - name: Input
+    arguments:
+      - name: "--input"
+        type: string
+        description: "Input url to the .h5ad file."
+        direction: input
+        required: false
+        default: https://ftp.ncbi.nlm.nih.gov/geo/series/GSE279nnn/GSE279945/suppl/GSE279945_sc_counts_processed.h5ad
+        example: https://ftp.ncbi.nlm.nih.gov/geo/series/GSE279nnn/GSE279945/suppl/GSE279945_sc_counts_processed.h5ad
+      - name: "--var_feature_name"
+        type: string
+        description: "Location of where to find the feature names. Can be set to index if the feature names are the index."
+        default: index
+  - name: Data Filtering
+    description: "Arguments for filtering the dataset"
+    arguments:
+      - name: "--donor_id"
+        type: string
+        description: "Donor ID to filter for (1, 2, or 3). If not specified, all donors are included."
+        required: false
+      - name: "--cell_type"
+        type: string
+        description: "Cell type to filter for (T cells, B cells, NK cells, or Myeloid). If not specified, all cell types are included."
+        required: false
+      - name: "--perturbation"
+        type: string
+        description: "Perturbation to filter for. If not specified, all perturbations are included."
+        required: false
+
+  - name: Dataset Metadata
+    description: "Metadata about the dataset"
+    arguments:
+      - name: "--dataset_id"
+        type: string
+        description: "Unique identifier for the dataset"
+        default: "op3"
+      - name: "--dataset_name"
+        type: string
+        description: "Human-readable name for the dataset"
+        default: "OP3: single-cell multimodal dataset in PBMCs for perturbation prediction benchmarking"
+      - name: "--dataset_summary"
+        type: string
+        description: "Short summary of the dataset"
+        default: "The Open Problems Perurbation Prediction (OP3) dataset with small molecule perturbations in PBMCs"
+      - name: "--dataset_description"
+        type: string
+        description: "Detailed description of the dataset"
+        default: "The OP3 dataset is to-date the largest single-cell small molecule perturbation dataset in primary tissue with multiple donor replicates."
+      - name: "dataset_reference"
+        type: string
+        description: "Bibtex reference of the paper in which the dataset was published."
+        required: false
+        default: GSE279945
+      - name: "--dataset_url"
+        type: string
+        description: "Link to the original source of the dataset."
+        required: false
+        default: https://ftp.ncbi.nlm.nih.gov/geo/series/GSE279nnn/GSE279945/suppl/GSE279945_sc_counts_processed.h5ad
+
+  - name: Output
+    description: "Output parameters"
+    arguments:
+      - name: "--output"
+        type: file
+        description: "Output h5ad file."
+        direction: output
+        required: true
+      - name: "--output_compression"
+        type: string
+        choices: [gzip, lzf]
+        required: false
+        default: "gzip"
+
+resources:
+  - type: python_script
+    path: script.py
+
+engines:
+  - type: docker
+    image: python:3.11
+    setup:
+      - type: python
+        packages:
+          - scanpy
+          - anndata
+          - pandas
+          - numpy
+          - requests
+    test_setup:
+      - type: python
+        packages:
+          - viashpy
+
+runners:
+  - type: executable
+  - type: nextflow
+
+test_resources:
+  - type: python_script
+    path: test.py
+