celltype-annotation-fast

What problem does it solve?

Annotate cell types in spatial transcriptomics data by combining unsupervised clustering, marker gene analysis, and LLM-based labeling, enabling fast and interpretable identification of cellular composition within tissue sections.

Core Features & Use Cases

• Unsupervised clustering (Leiden) to identify cell populations.
• Marker gene analysis to derive cluster-specific markers.
• LLM-based annotation to assign precise cell type names using tissue context.
• Use Case: Quickly annotate tissue sections (e.g., breast cancer, brain) to explore cellular architecture and compare regions.

Quick Start

Provide a spatial dataset and tissue type, then run the annotation workflow to obtain cell-type predictions.