This paper demonstrates that language models are strong structure-based protein designers. We present LM-Design, a generic approach to reprogramming sequence-based protein language models (pLMs), that have learned massive sequential evolutionary knowledge from the universe of natural protein sequences, to acquire an immediate capability to design preferable protein sequences for given folds. We conduct a structural surgery on pLMs, where a lightweight structural adapter is implanted into pLMs and endows it with structural awareness. During inference, iterative refinement is performed to effectively optimize the generated protein sequences. Experiments show that our approach outperforms the state-of-the-art methods by a large margin, leading to up to 4% to 12% accuracy gains in sequence recovery (e.g., 55.65% and 56.63% on CATH 4.2 and 4.3 single-chain benchmarks, and >60% when designing protein complexes). We provide extensive and in-depth analyses, which verify that LM-Design can (1) indeed leverage both structural and sequential knowledge to accurately handle structurally non-deterministic regions, (2) benefit from scaling data and model size, and (3) generalize to other proteins (e.g., antibodies and de novo proteins)

翻译：本文证明语言模型是强大的基于结构的蛋白质设计工具。我们提出LM-Design方法——一种通用性重编程策略，通过改造基于序列的蛋白质语言模型（pLMs），使其在保留从天然蛋白质序列宇宙中习得的庞大序列进化知识的同时，获得为给定蛋白质骨架设计优选蛋白质序列的即时能力。我们对pLMs实施结构外科手术：向其植入轻量级结构适配器，赋予其结构感知能力。在推理阶段，通过迭代精炼有效优化生成的蛋白质序列。实验表明，该方法大幅超越现有最优技术，在序列恢复准确率上提升4%-12%（例如：在CATH 4.2和4.3单链基准测试中分别达到55.65%和56.63%，在蛋白质复合物设计任务中超过60%）。我们通过全面深入的分析验证：LM-Design能够（1）真正利用结构与序列知识精准处理结构非确定性区域，（2）受益于数据和模型规模的扩展，（3）泛化至抗体和从头设计蛋白等其他蛋白质类型。