[论文解读] Towards an AI co-scientist

Juraj Gottweis, Wei‐Hung Weng+32 more|ArXiv.org|Feb 26, 2025

Genomics and Rare Diseases被引用 25

一句话总结

本文提出一个 AI 共同科学家，是基于 Gemini 2.0 的多智能体系统，能够在科学家参与的协作下生成、辩论并演化新颖的生物医学假设与研究提案。

ABSTRACT

Scientific discovery relies on scientists generating novel hypotheses that undergo rigorous experimental validation. To augment this process, we introduce an AI co-scientist, a multi-agent system built on Gemini 2.0. The AI co-scientist is intended to help uncover new, original knowledge and to formulate demonstrably novel research hypotheses and proposals, building upon prior evidence and aligned to scientist-provided research objectives and guidance. The system's design incorporates a generate, debate, and evolve approach to hypothesis generation, inspired by the scientific method and accelerated by scaling test-time compute. Key contributions include: (1) a multi-agent architecture with an asynchronous task execution framework for flexible compute scaling; (2) a tournament evolution process for self-improving hypotheses generation. Automated evaluations show continued benefits of test-time compute, improving hypothesis quality. While general purpose, we focus development and validation in three biomedical areas: drug repurposing, novel target discovery, and explaining mechanisms of bacterial evolution and anti-microbial resistance. For drug repurposing, the system proposes candidates with promising validation findings, including candidates for acute myeloid leukemia that show tumor inhibition in vitro at clinically applicable concentrations. For novel target discovery, the AI co-scientist proposed new epigenetic targets for liver fibrosis, validated by anti-fibrotic activity and liver cell regeneration in human hepatic organoids. Finally, the AI co-scientist recapitulated unpublished experimental results via a parallel in silico discovery of a novel gene transfer mechanism in bacterial evolution. These results, detailed in separate, co-timed reports, demonstrate the potential to augment biomedical and scientific discovery and usher an era of AI empowered scientists.

研究动机与目标

• 激发并使 AI 支持的假设生成成为可能，从而加速生物医学领域的科学发现。
• 开发一个可扩展的多智能体架构，模仿科学方法进行推理与提案生成。
• 展示通过自然语言接口和可调整约束实现的科学家在环协作。
• 在药物重定位、新靶点发现以及抗菌药物耐药性机制等三个领域进行端到端验证。

提出的方法

• 提出一个基于 Gemini 2.0、带异步任务框架的多智能体系统。
• 使用专门的代理（Generation、Reflection、Ranking、Evolution、Proximity、Meta-review）在竞技场式的设定中生成、辩论并进化假设。
• 纳入上下文记忆以实现长时间尺度的迭代推理。
• 以文献引用和推理可解释性为输出提供支撑。
• 通过自然语言启用科学家反馈，并使输出符合约束和安全标准。
• 在三个生物医学领域提供端到端验证，并附有外部湿实验室验证报告。

实验结果

研究问题

• RQ1 AI 共同科学家是否能生成新颖、可验证的生物医学假设，并与科学家指定的目标保持一致？
• RQ2 通过自我改进的竞技框架扩大测试时的计算能力是否能提高假设的质量和新颖性？
• RQ3 科学家在环与 AI 代理协作以生成基于文献的、可执行的实验计划的效果如何？
• RQ4 有哪些证据支持 AI 驱动的假设生成在药物重定位、靶点发现和 AMR 机制方面的应用？

主要发现

• AI 共同科学家提出用于 AML 的新颖再利用候选药物，在临床相关浓度下对体外肿瘤具有抑制作用。
• 它识别出用于肝纤维化的新型表观遗传靶点，在人肝脏类器官中显示出抗纤维化活性。
• 通过提出一种与 AMR 相关的细菌进化中的新基因转移机制，它再现了未发表的实验发现。
• 在三个生物医学问题上的端到端验证显示出增强发现工作流程的潜力。
• 通过基于竞技的进化过程实现的自我改进循环在持续扩展计算时提升假设质量。