arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2606.01042cs.LGcs.AI
收藏

似真性不是预测:基于LLM的细胞扰动推理的对比证据

Plausibility Is Not Prediction: Contrastive Evidence for LLM-Based Cellular Perturbation Reasoning

Mila - Québec AI Institute(魁北克人工智能研究所);University of Montréal(蒙特利尔大学);HEC Montréal(蒙特利尔HEC商学院);University of Ottawa(渥太华大学);National Research Council of Canada(加拿大国家研究理事会);CIFAR AI Chair(CIFAR人工智能 chair)

Xinyu Yuan, Xixian Liu, Jianan Zhao, Yashi Zhang, Hongyu Guo, Jian Tang

AI总结:

本文发现基于大语言模型的细胞扰动推理虽能生成生物上合理的解释,但实际预测性能差,并提出CORE方法通过对比证据组织来提升扰动特异性预测。

摘要:

扰动实验对于理解细胞机制至关重要,但成本高昂且稀疏,因此需要预测未观察条件下的基因表达响应。最近一个有前景的方向是利用大语言模型(LLM)作为“虚拟细胞”模拟器——通过逐步的、基于知识的机械推理来推断差异表达——指向一种可解释的、知识驱动的范式,超越了纯粹的数据驱动方法。然而,我们发现似真性不是预测:尽管产生了生物上合理的解释,这些方法未能捕捉扰动特异性效应:系统性地高估差异表达,在聚合评估中通常表现不如简单的基因频率基线,并且在每个基因水平上降至随机水平。这揭示了对内在基因响应倾向的依赖,而非真正的扰动推理。我们将这一失败追溯到证据呈现方式:现有方法孤立地评估扰动-基因对,而不揭示相关扰动对同一基因的影响差异。为解决这一局限性,我们引入了CORE(对比关系证据组织),通过将证据组织成来自相关扰动的正面和负面结果,将预测重新定义为比较任务。使用生物医学知识图谱进行证据检索,CORE在基于LLM和非LLM的设置中均改善了校准并大幅提升了扰动特异性预测:例如,在药物扰动数据上,CORE-Reasoning将Qwen3.5-9B的聚合指标提升了高达28.6%;而在通用扰动数据上,CORE-Voting将四个细胞系的每个基因平均AUROC从随机水平提高到0.703。这突显了对比证据组织对于可靠的基于LLM的扰动推理至关重要。

英文摘要:

Perturbation experiments are central to understanding cellular mechanisms, but remain costly and sparse, motivating prediction of gene expression responses for unobserved conditions. A promising recent direction leverages large language models (LLMs) as "virtual cell" simulators-using stepwise, knowledge-grounded mechanistic reasoning to infer differential expression-pointing toward an interpretable, knowledge-driven paradigm that transcends purely data-driven approaches. However, we find that plausibility is not prediction: despite producing biologically plausible explanations, these methods fail to capture perturbation-specific effects: systematically overestimating differential expression, often underperforming a simple gene-frequency baseline in aggregate evaluations, and collapsing to chance-level performance at the per-gene level. This reveals a reliance on intrinsic gene response tendencies rather than true perturbation reasoning. We trace this failure to how evidence is presented: existing methods evaluate perturbation-gene pairs in isolation, without exposing how related perturbations differ in their effects on the same gene. To address this limitation, we introduce CORE (Contrastive Organization of Relational Evidence), which reframes prediction as a comparison task by organizing evidence into positive and negative outcomes from related perturbations. Using a biomedical knowledge graph for evidence retrieval, CORE improves calibration and substantially boosts perturbation-specific prediction in both LLM-based and non-LLM settings: for example, on drug-perturbation data, CORE-Reasoning improves Qwen3.5-9B aggregate metrics by up to 28.6%, while on generic perturbation data, CORE-Voting raises macro-per-gene AUROC from chance to 0.703 in average across four cell lines. This highlights contrastive evidence organization as essential to reliable LLM-based perturbation reasoning

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。

↑