Data-driven identification of cell subtypes for single-cell transcriptomic data with Subtypist.

Subtypist identifies novel cell subtypes in scRNA-seq data with over 30% improved accuracy compared to existing methods, without relying on external references.

• Why it matters: Accurate discovery of new cell subtypes is essential for understanding disease mechanisms and developing targeted therapies, but current methods often depend on fixed reference labels that limit discovery.
• What they did: The authors developed Subtypist, a multiscale iterative algorithm that analyzes single-cell transcriptomic data in a fully data-driven manner, validated on both simulated and real datasets involving disease samples.
• The result: Subtypist successfully uncovers biologically meaningful new cell subtypes and elucidates cell-cell communication pathways in diseases like hepatocellular carcinoma, enabling more precise disease characterization.