
从诺奖项目到生成式药物设计,Latent Labs 创始人 Simon Kohl:AI 正在让生物学进入「可编程时代」 | CVPR 2026
Quick Answer
Simon Kohl, CEO of Latent Labs, presented at CVPR 2026, highlighting how generative AI, including models like Latent-X1 and Latent-Y, is revolutionizing drug design by drastically reducing development times and costs, achieving up to 90% success rates compared to traditional methods.
Quick Take
The transition from AlphaFold 2's structural predictions to autonomous design agents marks a pivotal shift towards programmable biology.
Key Points
- Latent-X1 achieves high affinity and hit rates, outperforming traditional trillion-scale screenings.
- Latent-X2 enables zero-shot antibody design, maintaining high affinity across various formats.
- Latent-Y is the first lab-validated antibody design agent, streamlining the drug development process.
- AI-driven methods reduce drug development time from years to weeks, significantly lowering costs.
- Protein dynamics and systemic toxicity predictions remain open challenges in AI drug design.
Source Excerpt
作者|吴思梦编辑|岑峰 2026年6月3日,计算机视觉与模式识别顶级会议(CVPR)在美国丹佛举行。 在大会特邀演讲环节,前 DeepMind 蛋白质设计团队核心成员、2024年诺贝尔化学奖获奖项目 AlphaFold 核心研究员,Latent Labs 创始人兼 CEO Simon Kohl 发表了题为“Programmable Biology:Generative AI for Molecular Design”的精彩演讲。 围绕当今药物发现领域最核心的痛点:一种新药从研发到上市平均耗时超过10年、花费超20亿美元,但九成候选药物最终失败。 而Simon Kohl认为,这一切的根源在于“我们从错误的分子出发”。 为此,他提出了一条从“结构预测”到“条件生成”再到“自主智能体”的技术跃迁路线。
演讲以AlphaFold 2为起点,回顾了蛋白质结构预测突破如何催生生成式药物设计;随后展示了Latent Labs的两代基础模型——Latent—X1(通用蛋白结合物设计)与Latent—X2(零样本抗体设计)——如何在湿实验室中实现媲美甚至超越传统万亿级筛选的命中率和亲和力;最终发布了全球首个实验室验证的抗体设计智能体Latent—Y,仅需一条自然语言提示,即可自主完成从靶点分析到分子设计的全流程。 总结而言,从AlphaFold 2解决“序列到结构”的预测问题,到生成式AI实现“靶点到药物”的条件设计,再到智能体接管“端到端”的自主设计闭环——计算药物设计正以指数级速度演进,Simon Kohl断言:生物学终将成为可编程的工程学科。 …
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from 雷峰网 AI
See more →
刚刚,GPT 5.6 发布会上,OpenAI 暴露了哪些 Agent 技术路线?
OpenAI's GPT 5.6 integrates ChatGPT and Codex, introducing a for complex task execution, with models Soul, Terra, and Luna for efficient workflow management. The release emphasizes task orchestration, contextual understanding, and robust security measures for enterprise applications.

