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.
- Feng Hu
- Xiaotong Jia
- Honglin Li