omicverse-single-cell-clustering-backends

What problem does it solve?

Converts a clustering notebook into a reusable, triggerable workflow that runs and compares multiple backends on a prepared AnnData embedding.

Core Features & Use Cases

• Run Leiden, Louvain, GMM, or scICE on a ready embedding to obtain comparable cluster assignments.
• Produce consistent output columns (e.g., gmm_cluster, mclust) for downstream validation and reporting.
• Smoke-testable via a minimal Python script that exercises the backend options and reports success.

Quick Start

Provide an AnnData with a PCA or other embedding and call the clustering wrapper to compare backends across a fixed set of parameters.