CellMaster: Collaborative Cell Type Annotation in Single-Cell Analysis
This addresses a bottleneck in single-cell analysis for researchers, offering a novel zero-shot annotation method with interpretable rationales, though it is incremental as it builds on existing automated tools.
The paper tackles the problem of assigning biologically valid cell identities in single-cell RNA-seq analysis, which is hindered by tissue- and state-dependent markers and lack of references for novel states, and presents CellMaster, an AI agent that improves accuracy by 7.1% over best-performing baselines in automatic mode and up to 18.6% with human-in-the-loop refinement.
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}.