Intology 发布自动化科研系统 Locus，分子设计任务超越 Codex 与 Claude Code
Intology 做了个自动搞科研的系统 Locus，自己调模型做分子设计和抗体设计，成绩超过了 Codex 和 Claude Code 这类通用编程智能体，适合关注 AI for Science 的人看看。
Intology 推出自动化科研系统 Locus，可在私有和有限数据上自主优化分子设计相关模型。测试覆盖三个真实任务：训练分子性质预测模型、微调 Boltz-2 预测小分子效力、以及围绕 BoltzGen、Boltz-2、ESMC、ESMFold2 搭建抗体设计工作流。在这些任务上，Locus 的成绩超过现有 SOTA 基线和 Codex、Claude Code 等通用 LLM 智能体。它还在数据受限场景下表现出更强的泛化能力和样本效率。
Closed-loop discovery is starting to look real. This is autonomously optimizing models for molecular property prediction, potency, and antibody design on proprietary/limited data and beating generalist agents (Codex, Claude Code) on generalization and sample efficiency. So cool Intology @intology Locus sets the frontier for automating molecular design Our automated research system Locus develops scientific AI models that outperform SOTA expert solutions Unlocking the potential of scientific AI requires leveraging proprietary data. Locus achieves this autonomously 🧵👇 -- We test Locus across a number of tasks related to molecular scoring and design: training molecular property prediction models for a proprietary task, fine-tuning Boltz-2 to predict small-molecule potency, and building antibody design workflows around BoltzGen, Boltz-2, ESMC, and ESMFold2. Each of these settings are real-world AI for science use cases, where tasks are often out-of-distribution for existing foundation models and limited in data, while featuring expensive and noisy evaluators. Compared to state-of-the-art baselines and LLM agents set to optimize these tasks, Locus achieves higher performance. Additionally, Locus generalizes better despite limited data, finds more sample efficient solutions, and explores a higher diversity of solutions. 🔗 View Quoted Tweet 💬 2 🔄 0 ❤️ 6 👀 1514 📊 2 ⚡
