Macrocyclization of linear molecules by deep learning to facilitate macrocyclic drug candidates discovery

• Published in: Nature communications Vol. 14; no. 1; p. 4552
• Main Authors: Diao, Yanyan, Liu, Dandan, Ge, Huan, Zhang, Rongrong, Jiang, Kexin, Bao, Runhui, Zhu, Xiaoqian, Bi, Hongjie, Liao, Wenjie, Chen, Ziqi, Zhang, Kai, Wang, Rui, Zhu, Lili, Zhao, Zhenjiang, Hu, Qiaoyu, Li, Honglin
• Format: Journal Article
• Language: English
• Published: London Nature Publishing Group UK 28.07.2023; Nature Publishing Group; Nature Portfolio
• Subjects: 119/118; 631/114/2397; 631/154/309/606; 692/308/153; Biochemistry; Biological activity; Biological properties; Data augmentation; Deep learning; Drug development; Humanities and Social Sciences; Janus kinase 2; Molecular docking; multidisciplinary; Pharmacology; Physicochemical properties; Scaffolds; Science; Science (multidisciplinary)
• ISSN: 2041-1723; 2041-1723
• DOI: 10.1038/s41467-023-40219-8

Interest in macrocycles as potential therapeutic agents has increased rapidly. Macrocyclization of bioactive acyclic molecules provides a potential avenue to yield novel chemical scaffolds, which can contribute to the improvement of the biological activity and physicochemical properties of these molecules. In this study, we propose a computational macrocyclization method based on Transformer architecture (which we name Macformer). Leveraging deep learning, Macformer explores the vast chemical space of macrocyclic analogues of a given acyclic molecule by adding diverse linkers compatible with the acyclic molecule. Macformer can efficiently learn the implicit relationships between acyclic and macrocyclic structures represented as SMILES strings and generate plenty of macrocycles with chemical diversity and structural novelty. In data augmentation scenarios using both internal ChEMBL and external ZINC test datasets, Macformer display excellent performance and generalisability. We showcase the utility of Macformer when combined with molecular docking simulations and wet lab based experimental validation, by applying it to the prospective design of macrocyclic JAK2 inhibitors. Macrocyclization of bioactive acyclic molecules provides a potential avenue to yield novel chemical scaffolds with improved pharmacological properties. Here, the authors propose a deep learning based macrocyclization method to generate diverse macrocycles from a given acyclic molecule.