OmicVerse Single-Cell Differential Expression

Goal

Turn notebook-style OmicVerse DEG analysis into a compact execution spine for condition-vs-condition comparisons inside selected cell types. Keep this skill focused on DEG only; differential abundance and compositional analysis are a separate job with a different input contract and backend surface.

Quick Workflow

1. Inspect the input AnnData, the condition column, the cell-type column, and whether raw counts are available in adata.raw or adata.layers["counts"].
2. Choose a DEG backend before running anything: wilcoxon or t-test for the scanpy rank-gene path, memento-de for the count-aware memento path.
3. Subset to the required cell types with celltype_key and celltype_group; leave celltype_group=None only when you really want all cell types pooled into one DEG run.
4. Run DEG.run(...) with an explicit max_cells policy and method-specific kwargs when using memento.
5. Collect results with get_results(), then verify the expected statistical columns and expression-percentage columns before saving or plotting.

Interface Summary