用物理动力学高效优化蛋白序列，兼顾结构与功能
Efficient Protein Optimization via Structure-aware Hamiltonian Dynamics
- 引入哈密顿动力学模拟蛋白质结构约束下的序列演化
- 在多个指标上超越现有方法，实现更优的序列设计性能
- 适合需要结构-功能协同设计的生物工程与药物研发人员
蛋白质变体的工程化优化在生物技术和医学中具有变革性潜力。以往基于序列的方法因表观遗传效应和忽略结构约束，难以应对高维复杂性。为此，我们提出HADES，一种利用哈密顿动力学进行结构感知后验近似采样的贝叶斯优化方法。通过模拟物理运动中的动量与不确定性，该方法能快速将候选序列引导至有前景区域。采用位置离散化策略，从连续状态系统中生成离散蛋白序列。后验代理模型由两阶段编码器-解码器框架驱动，学习突变邻域间的结构-功能关系，从而构建平滑的可采样景观。大量仿真实验表明，本方法在多数指标上均优于当前最优基线。显著优势在于利用了蛋白质结构与序列间的相互约束，可设计出结构相似且性能优化的序列。代码与数据已公开于 https://github.com/GENTEL-lab/HADES。
原文摘要 · Abstract (English)
The ability to engineer optimized protein variants has transformative potential for biotechnology and medicine. Prior sequence-based optimization methods struggle with the high-dimensional complexities due to the epistasis effect and the disregard for structural constraints. To address this, we propose HADES, a Bayesian optimization method utilizing Hamiltonian dynamics to efficiently sample from a structure-aware approximated posterior. Leveraging momentum and uncertainty in the simulated physical movements, HADES enables rapid transition of proposals toward promising areas. A position discretization procedure is introduced to propose discrete protein sequences from such a continuous state system. The posterior surrogate is powered by a two-stage encoder-decoder framework to determine the structure and function relationships between mutant neighbors, consequently learning a smoothed landscape to sample from. Extensive experiments demonstrate that our method outperforms state-of-the-art baselines in in-silico evaluations across most metrics. Remarkably, our approach offers a unique advantage by leveraging the mutual constraints between protein structure and sequence, facilitating the design of protein sequences with similar structures and optimized properties. The code and data are publicly available at https://github.com/GENTEL-lab/HADES.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。