Accurate prediction of protein-ligand binding structures, a task known as molecular docking is crucial for drug design but remains challenging. While deep learning has shown promise, existing methods often depend on holo-protein structures (docked, and not accessible in realistic tasks) or neglect pocket sidechain conformations, leading to limited practical utility and unrealistic conformation predictions. To fill these gaps, we introduce an under-explored task, named flexible docking to predict poses of ligand and pocket sidechains simultaneously and introduce Re-Dock, a novel diffusion bridge generative model extended to geometric manifolds. Specifically, we propose energy-to-geometry mapping inspired by the Newton-Euler equation to co-model the binding energy and conformations for reflecting the energy-constrained docking generative process. Comprehensive experiments on designed benchmark datasets including apo-dock and cross-dock demonstrate our model's superior effectiveness and efficiency over current methods.

翻译：蛋白质-配体结合结构的精确预测（即分子对接）对药物设计至关重要，但仍具挑战性。尽管深度学习已展现潜力，现有方法通常依赖全息蛋白质结构（已对接但实际任务中无法获取）或忽略口袋侧链构象，导致实际应用受限且构象预测不真实。为弥补这些不足，我们提出一项未充分研究的任务——"柔性对接"以同时预测配体与口袋侧链的位姿，并引入Re-Dock——一种扩展至几何流形的新型扩散桥生成模型。具体而言，我们提出基于牛顿-欧拉方程的能量-几何映射方法，通过联合建模结合能与构象来反映能量约束下的对接生成过程。在包含apo-dock和cross-dock的基准数据集上的全面实验表明，我们的模型在有效性和效率上均优于现有方法。