Search papers, labs, and topics across Lattice.
The paper introduces CellMaster, an AI agent leveraging LLMs (specifically GPT-4o) for zero-shot cell-type annotation in scRNA-seq data, addressing the limitations of existing methods that rely on pre-training or fixed marker databases. CellMaster generates on-the-fly annotations with interpretable rationales, mimicking expert annotation practices. Experiments across 9 datasets show CellMaster achieves a 7.1% accuracy improvement over state-of-the-art baselines in automatic mode, and an 18.6% improvement with human-in-the-loop refinement, particularly excelling in identifying rare and novel cell states.
Key contribution not extracted.
Single-cell RNA-seq (scRNA-seq) enables atlas-scale profiling of complex tissues, revealing rare lineages and transient states. Yet, assigning biologically valid cell identities remains a bottleneck because markers are tissue- and state-dependent, and novel states lack references. We present CellMaster, an AI agent that mimics expert practice for zero-shot cell-type annotation. Unlike existing automated tools, CellMaster leverages LLM-encoded knowledge (e.g., GPT-4o) to perform on-the-fly annotation with interpretable rationales, without pre-training or fixed marker databases. Across 9 datasets spanning 8 tissues, CellMaster improved accuracy by 7.1% over best-performing baselines (including CellTypist and scTab) in automatic mode. With human-in-the-loop refinement, this advantage increased to 18.6%, with a 22.1% gain on subtype populations. The system demonstrates particular strength in rare and novel cell states where baselines often fail. Source code and the web application are available at \href{https://github.com/AnonymousGym/CellMaster}{https://github.com/AnonymousGym/CellMaster}.
