发表机构
The Hong Kong University of Science and Technology (Guangzhou); Jinan University（香港科技大学（广州）; 暨南大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
CAGenMol-2 通过单一掩码扩散模型统一药物设计任务，AdaFO 优化器在 CrossDocked2020 上将成功率从 30.2% 提升至 70.8%，实现高效局部优化与结构感知设计。
AI 中文摘要
药物设计将性质评估、条件生成、基于结构的设计和局部优化相结合，然而机器学习系统通常使用各自独立的任务特定模型来处理这些能力。我们提出了 CAGenMol-2，一种掩码扩散分子语言模型，它将分子、连续标量性质和 3D 蛋白质口袋表示在单个包装序列中。在这个预训练接口中，下游操作通过推理时观察或掩码的序列区域来选择，使得一个检查点能够在没有任务特定架构或骨干微调的情况下执行性质预测、性质和口袋条件生成以及部分约束设计。我们进一步提出了自适应片段优化（AdaFO），一种无梯度的掩码-再填充搜索，将掩码解码器转变为迭代的局部分子优化器。在 CrossDocked2020 上，AdaFO 将成功率从 30.2% 提高到 70.8%，这是该协议下报告的最佳结果，同时基本保持了药物相似性和多样性。最后，保持骨架的方向性编辑和 CRBN/VHL 案例研究证明了其在化合物设计工作流程中的用途，涵盖局部分子编辑、基于结构的优先级排序和下游基于模拟的筛选。
英文摘要
Drug design couples property evaluation, conditional generation, structure-based design, and local optimization, yet machine learning systems typically address these capabilities with separate task-specific models. We introduce CAGenMol-2, a masked diffusion molecular language model that represents molecules, continuous scalar properties, and 3D protein pockets within a single wrapped sequence. Within this pretrained interface, downstream operations are selected by which sequence regions are observed or masked at inference, allowing one checkpoint to perform property prediction, property- and pocket-conditioned generation, and partial-constraint design without task-specific architectures or backbone fine-tuning. We further propose Adaptive Fragment Optimization (AdaFO), a gradient-free mask-and-refill search that turns the masked decoder into an iterative local molecular optimizer. On CrossDocked2020, AdaFO increases Success Rate from 30.2\% to 70.8\%, the best reported under this protocol, while largely preserving drug-likeness and diversity. Finally, scaffold-preserving directional editing and CRBN/VHL case studies demonstrate its use in compound design workflows spanning local molecular editing, structure-based prioritization, and downstream simulation-based screening.
