Exploring the macrocyclic chemical space for heuristic drug design with deep learning models

Le résumé fourni par la source

Macrocyclic compounds hold great promise as therapeutic agents. However, their structural optimization remains constrained by the limited availability of bioactive candidates, which in turn hampers the systematic exploration of structure-activity relationships. Here we introduce CycleGPT, a generative chemical language model designed specifically to address these challenges. CycleGPT is characterized by a progressive transfer learning paradigm that incrementally transfers knowledge from pre-trained chemical language models to specialized macrocycle generation, thereby overcoming the data shortage issue. Meanwhile, it adopts an innovative probabilistic sampling strategy that effectively improves the structural novelty of generated macrocycles while ensuring domain-specific adaptability. In a prospective drug design based on CycleGPT and a JAK2 activity prediction model, we successfully developed a new JAK2 drug candidate with a good selectivity profile (inhibiting 17 wild-type kinases) and promising potential for treating polycythemia in vivo, demonstrating the practicality of deep learning methods in macrocyclic drug design. Macrocyclic compounds hold promise as therapeutic agents, yet their structural optimization is hindered by a scarcity of bioactive candidates. Here, the authors present CycleGPT, a generative chemical language model that enhances macrocycle design through innovative transfer learning and sampling strategies, leading to potent JAK2 inhibitors with promising in vivo efficacy.

Ce résumé expose les affirmations des auteurs. BNTIC ne l’interprète pas comme une validation indépendante des résultats.