文献类型：期刊文献

英文题名：Design of Protein and Peptide Macromolecular Drugs

作者：Li, Honglin[1,3]; Li, Shiliang[2]

机构：[1] Innovation Center for AI and Drug Discovery, School of Pharmacy, East China Normal University, Shanghai, China; [2] Innovation Center for AI and Drug Discovery, School of Pharmacy, East China Normal University, Shanghai, China; [3] Shanghai Key Laboratory of New Drug Design, State Key Laboratory of Bioreactor Engineering, School of Pharmacy, East China University of Science & Technology, Shanghai, China

年份：2025

起止页码：785

外文期刊名：Artificial Intelligence for Drug Design

收录：EI(收录号：20262620987589)

语种：英文

外文关键词：Bioactivity - Bioinformatics - Design - Drug discovery - Drug products - Learning systems - Macroinvertebrates - Macromolecules - Peptides

摘要：De novo protein design, where proteins are engineered from fundamental principles to achieve structures and functions beyond those found in nature, is being fundamentally transformed by the integration of deep learning into bioinformatics. This revolution, driven by artificial intelligence (AI), is not only enabling the creation of these novel proteins but also opening significant new possibilities for the design of both protein and peptide-based macromolecular drugs. AI’s growing capabilities in peptide sequence recognition, generation, and property prediction further contribute to this exciting era of biomolecular engineering. Compared to traditional experimental methods, AI-based design approaches can explore a broader protein sequence and structural space, avoiding druggability issues associated with natural peptides and proteins and facilitating the rapid acquisition of target protein and peptide molecules with biological activity. Significant progress has been made in the application of AI in the design of anticancer peptides, antimicrobial peptides, and drug-binding peptides. For instance, deep learning-based de novo design methods can generate peptides targeting specific receptors, and collaborations between companies such as Peptilogics and Cerebras have advanced AI-driven peptide drug development. Despite the tremendous potential of AI in peptide drug discovery, challenges remain, including data capacity, class imbalance, and data representation. Future research will focus on optimizing AI models to overcome these challenges, thereby promoting the development of novel peptide therapeutics. ? Chemical Industry Press 2026.