The dissociation rate constant (k_off) significantly impacts the drug potency and dosing frequency. This work proposes a powerful optimization-based framework for de novo drug design guided by k_off. First, a comprehensive database containing 2,773 unique k_off values is created. Based on the database, a novel generic dissociation kinetic model is developed with a mixture-of-experts architecture, enabling high-throughput predictions of k_off with high accuracy. The developed model is then integrated with an optimization-based mathematical programming approach to design drug candidates with low k_off. Finally, the τ-RAMD method is utilized to rigorously verify the designed potential drug candidates. In a case study, the framework successfully identified numerous new potential HSP90 inhibitor candidates, achieving a maximum 45.7% improvement in residence time (τ = 1/k_off) compared to that of a known exceptional HSP90 inhibitor. These findings demonstrate the feasibility and effectiveness of the kinetics-guided optimization-based de novo drug design framework in designing drug candidates with prolonged τ.

中文翻译：

---

基于专家混合的解离动力学模型，用于延长停留时间的 HSP90 抑制剂的从头设计


解离速率常数 （k_off） 显着影响药物效力和给药频率。这项工作提出了一个强大的基于优化的框架，用于以 k_off 为指导的从头药物设计。首先，创建一个包含 2,773 个唯一 k_off 值的综合数据库。基于该数据库，开发了一种新的通用解离动力学模型，该模型采用专家混合架构，能够以高精度对 k_off 进行高通量预测。然后将开发的模型与基于优化的数学规划方法集成，以设计具有低 k_off 的候选药物。最后，利用 τ-RAMD 方法严格验证设计的潜在候选药物。在案例研究中，该框架成功确定了许多新的潜在 HSP90 抑制剂候选物，与已知的特殊 HSP90 抑制剂相比，停留时间最多缩短了 45.7% （τ = 1/k_off）。这些发现证明了基于动力学引导优化的从头药物设计框架在设计具有延长 τ 的候选药物方面的可行性和有效性。