Geylan Gökçe, Janet Jon Paul, Tibo Alessandro, He Jiazhen, Patronov Atanas, Kabeshov Mikhail, Czechtizky Werngard, David Florian, Engkvist Ola, De Maria Leonardo
Molecular AI, Discovery Sciences, BioPharmaceuticals R&D, AstraZeneca Gothenburg Sweden
Division of Systems and Synthetic Biology, Department of Life Sciences, Chalmers University of Technology Gothenburg Sweden.
Chem Sci. 2025 Apr 16;16(20):8682-8696. doi: 10.1039/d4sc07642g. eCollection 2025 May 21.
Peptides play a crucial role in drug design and discovery whether as a therapeutic modality or a delivery agent. Non-natural amino acids (NNAAs) have been used to enhance the peptide properties such as binding affinity, plasma stability and permeability. Incorporating novel NNAAs facilitates the design of more effective peptides with improved properties. The generative models used in the field have focused on navigating the peptide sequence space. The sequence space is formed by combinations of a predefined set of amino acids. However, there is still a need for a tool to explore the peptide landscape beyond this enumerated space to unlock and effectively incorporate the design of new amino acids. To thoroughly explore the theoretical chemical space of peptides, we present PepINVENT, a novel generative AI-based tool as an extension to the small molecule molecular design platform, REINVENT. PepINVENT navigates the vast space of natural and non-natural amino acids to propose valid, novel, and diverse peptide designs. The generative model can serve as a central tool for peptide-related tasks, as it was not trained on peptides with specific properties or topologies. The prior was trained to understand the granularity of peptides and to design amino acids for filling the masked positions within a peptide. PepINVENT coupled with reinforcement learning enables the goal-oriented design of peptides using its chemistry-informed generative capabilities. This study demonstrates PepINVENT's ability to explore the peptide space with unique and novel designs and its capacity for property optimization in the context of therapeutically relevant peptides. Our tool can be employed for multi-parameter learning objectives, peptidomimetics, lead optimization, and a variety of other tasks within the peptide domain.
无论是作为一种治疗方式还是一种递送剂，肽在药物设计和发现中都起着至关重要的作用。非天然氨基酸（NNAAs）已被用于增强肽的性质，如结合亲和力、血浆稳定性和通透性。纳入新型非天然氨基酸有助于设计出具有更好性质的更有效肽。该领域中使用的生成模型专注于探索肽序列空间。序列空间由一组预定义氨基酸的组合形成。然而，仍然需要一种工具来探索超出这个枚举空间的肽格局，以解锁并有效纳入新氨基酸的设计。为了全面探索肽的理论化学空间，我们提出了PepINVENT，这是一种基于生成式人工智能的新型工具，作为小分子分子设计平台REINVENT的扩展。PepINVENT在天然和非天然氨基酸的广阔空间中导航，以提出有效的、新颖的和多样化的肽设计。该生成模型可以作为肽相关任务的核心工具，因为它没有针对具有特定性质或拓扑结构的肽进行训练。先验模型经过训练以理解肽的粒度，并设计用于填充肽内掩蔽位置的氨基酸。PepINVENT与强化学习相结合，利用其化学信息生成能力实现肽的目标导向设计。本研究展示了PepINVENT以独特新颖的设计探索肽空间的能力及其在治疗相关肽背景下进行性质优化的能力。我们的工具可用于多参数学习目标、肽模拟物、先导优化以及肽领域内的各种其他任务。
