HarmonyCell: 在语义和分布偏移下自动化单细胞扰动建模
HarmonyCell: Automating Single-Cell Perturbation Modeling under Semantic and Distribution Shifts
AI总结:
HarmonyCell通过语义统一和自适应搜索机制,在语义和分布偏移下实现单细胞扰动建模的自动化,有效执行率达95%并超越专家基线。
摘要:
单细胞扰动研究面临双重异质性瓶颈:(i)语义异质性——不同数据集下不兼容的元数据模式编码了相同生物概念;(ii)统计异质性——生物变异导致的分布偏移需要数据集特定的归纳偏差。我们提出了HarmonyCell,一个端到端的智能体框架,通过专门的机制解决每个挑战:一个由大语言模型驱动的语义统一器能够自动将不一致的元数据映射到一个标准接口,而一个自适应的蒙特卡洛树搜索引擎则在分层动作空间上操作,合成具有最佳统计归纳偏差的架构以应对分布偏移。在多样化的扰动任务中,既考虑语义又考虑分布偏移,HarmonyCell在异质输入数据集上实现了95%的有效执行率(相比之下通用智能体为0%),并且在严格的分布外评估中匹配或超过专家设计的基线。这种双轨协作使大规模自动虚拟细胞建模成为可能,而无需数据集特定的工程。
英文摘要:
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.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。