HarmonyCell: Automating Single-Cell Perturbation Modeling under Semantic and Distribution Shifts

TL;DR

HarmonyCell is proposed, an end-to-end agent framework resolving each challenge through a dedicated mechanism: an LLM-driven Semantic Unifier autonomously maps disparate metadata into a canonical interface without manual intervention; and an adaptive Monte Carlo Tree Search engine operates over a hierarchical action space to synthesize architectures with optimal statistical inductive biases for distribution shifts.

Abstract

Single-cell perturbation studies face dual heterogeneity bottlenecks: (i) semantic heterogeneity--identical biological concepts encoded under incompatible metadata schemas across datasets; and (ii) statistical heterogeneity--distribution shifts from biological variation demanding dataset-specific inductive biases. We propose HarmonyCell, an end-to-end agent framework resolving each challenge through a dedicated mechanism: an LLM-driven Semantic Unifier autonomously maps disparate metadata into a canonical interface without manual intervention; and an adaptive Monte Carlo Tree Search engine operates over a hierarchical action space to synthesize architectures with optimal statistical inductive biases for distribution shifts. Evaluated across diverse perturbation tasks under both semantic and distribution shifts, HarmonyCell achieves a 95% valid execution rate on heterogeneous input datasets (versus 0% for general agents) while matching or even exceeding expert-designed baselines in rigorous out-of-distribution evaluations. This dual-track orchestration enables scalable automatic virtual cell modeling without dataset-specific engineering.

Figures (6)

• Figure 1: Uniqueness of HarmonyCell. Existing task-specific LLM agents (CellForge etc.) but require rigid data input format, while general-purpose agents often lack biological knowledge. HarmonyCell can enhance its capabilities through biological priors, and also handle the problem of data heterogeneity.
• Figure 2: Architecture of HarmonyCell. The system integrates: (1) an LLM-driven Semantic Unifier to canonicalize heterogeneous h5ad inputs; (2) a Retrieval-Augmented Agent for meta-initialization using historical strategies; and (3) an Executor Agent guided by MCTS over a hierarchical action space (bottom panel). This hierarchical decomposition significantly bolsters search stability by proactively pruning branches that lead to erroneous 'bug' nodes before full execution. While runtime failures trigger a ReAct-style debugging loop, successfully validated pipelines are stored in a persistent knowledge base for future reuse.
• Figure 3: HarmonyCell successfully handles semantic heterogeneity, and enables synergistic dataset scaling. We compared the generalization performance of models trained on single-source Adamson adamson2016multiplexed and Replogle replogle2022mapping datasets against the joint dataset harmonized by HarmonyCell's Semantic Unifier. Models were evaluated on held-out test sets under a unified separate cross-validation protocol.
• Figure 4: Ablation Study: Necessity of Semantic Unifier. During execution, HarmonyCell containing the Semantic Unifier exhibits a more stable and error-free execution workflow compared to agents without the module.
• Figure 5: Ablation Study: Necessity of Hierarchical Action Space. HarmonyCell achieves superior convergence speed and accuracy compared to the non-hierarchical ablated agents, effectively surpasses the state-of-the-art specialized baseline models.