OmicVerse Single-Cell Batch Integration

Goal

Turn the notebook's post-preprocessing batch integration workflow into one reusable skill. Assume QC, normalization, HVG selection, and base PCA preparation are already handled upstream; this skill starts from a preprocessed AnnData with a batch column and focuses on integration backend selection, optional embedding visualization, and optional integration benchmarking.

Quick Workflow

1. Confirm that preprocessing is already done and that adata.obs contains the batch labels.
2. Choose an integration backend explicitly with methods=....
3. Validate the backend-specific prerequisites before calling ov.single.batch_correction(...).
4. Check which integrated embedding key was written to adata.obsm, and keep model/object returns when the backend returns more than adata.
5. Run optional embedding visualization only after the integrated embedding exists.
6. Run benchmarking only when at least one non-integrated reference embedding and one or more integrated embeddings are present.

Interface Summary