用智能算法设计更稳定的环肽药物，还能精准调控关键性质。
APCyc: Property-Informed Design of Cyclic Peptides via Automated Cyclization
- 引入环化特异性信息建模，学习环肽生成规律。
- 可同时优化多个药物相关性质，提升设计成功率。
- 适合需要精准控制性质的药物研发人员使用。
环肽是现代药物研发中极具前景的治疗化合物，通常具备更高的稳定性和结合亲和力。然而，从头设计环肽仍具挑战性，因需同时识别适配口袋的环化模式与连接位点，并控制药物相关的理化性质。这一难题在近期主要基于线性肽数据训练的生成模型中尤为突出，它们难以捕捉环化特有的约束。为此，我们提出APCyc，一种目标感知的从头环肽生成框架，显式建模环化过程，并联合优化多种关键理化性质。通过扩展残基词汇表并显式编码环化位点与连接类型信息，APCyc学习环化感知表示，并利用贝叶斯后验引导实现采样，推动生成满足多属性目标的环肽。实验表明，该模型能学习目标依赖的环化偏好，有效实现环肽设计的可控多性质优化。代码已开源：https://github.com/HKUSTGZ-ML4Health-Lab/APCyc。
原文摘要 · Abstract (English)
Cyclic peptides represent a promising class of therapeutic compounds in modern drug discovery, often offering improved stability and binding affinity. However, the de novo design of cyclic peptides remains challenging because methods must identify pocket-adaptive cyclization patterns and linkage sites while simultaneously controlling drug-relevant properties. This challenge is particularly pronounced for recent generative models trained predominantly on linear peptide data, which may fail to capture cyclization-specific constraints. To address the limitation, we introduce APCyc, a target-aware de novo cyclic peptide generation framework that explicitly models cyclization and jointly optimizes multiple essential physicochemical properties. By using an expanded residue vocabulary and explicitly encoding cyclization-site and linkage-type information, APCyc learns cyclization-aware representations and leverages Bayesian posterior guidance to steer sampling toward cyclic peptides satisfying multiple property objectives. Experimental results demonstrate that our model learns target-dependent cyclization preferences, and enables effective and controllable multi-property optimization for cyclic peptide design. The source code of this paper is available at https://github.com/HKUSTGZ-ML4Health-Lab/APCyc.
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。