发表机构
University of Connecticut; Hefei Comprehensive National Science Center（康涅狄格大学; 合肥综合性国家科学中心）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出预算商-残差引导（QRG），通过推理时修正使冻结分子扩散模型激活距离、接触等商目标，无需重训练，在CBGBench上提升有效性并保持新颖性与多样性。
AI 中文摘要
口袋条件分子扩散更新环境原子坐标，但许多先导优化目标表达在商特征上，如距离、接触和锚定子结构。我们引入预算商-残差引导（QRG），一种推理时修正方法，使这些商目标在不重新训练分子生成器的情况下被激活。QRG将商余向量提升到度量水平环境方向，并通过冻结采样器自身步长范数设定的信任预算传递它们：商几何选择方向，而采样器运动限制尺度。我们推导了水平提升、闭式采样器预算更新、围绕冻结反向步骤的KL/动力学解释、等变性条件，以及用于预算封顶截面和残差控制的乘积预算分割。受控商任务确认，采样器相对传递激活了原始局部商梯度未激活的信号。在冻结TargetDiff骨干上，官方seed-0 CBGBench配体生成/编辑扫描显示实际质量-运行时间收益：Local-QRG在片段生长上将有效性从0.815提高到0.864，在骨架跳跃上从0.664提高到0.707，在连接子设计上从0.681提高到0.712，而PredNext-QRG改善了片段/骨架并在连接子上保持接近中性。新颖性保持1.000，多样性在匹配的多种子分子切片中得以保留，实现了任务依赖的改进，无需采样器重训练或骨干修改。总体而言，QRG为冻结分子采样器提供了一条轻量级的商感知推理路径，并具有显式运行时间核算。
英文摘要
Pocket-conditioned molecular diffusion updates ambient atom coordinates, but many lead-optimization objectives are expressed on quotient features such as distances, contacts, and anchored substructures. We introduce budgeted quotient-residual guidance (QRG), an inference-time correction that makes these quotient objectives active without retraining the molecular generator. QRG lifts quotient covectors to metric-horizontal ambient directions and delivers them through a trust budget set by the frozen sampler's own step norm: quotient geometry chooses the direction, while sampler motion bounds the scale. We derive the horizontal lift, closed-form sampler-budget update, KL/kinetic interpretation around a frozen reverse step, equivariance conditions, and a product-budget split for budget-capped section and residual controls. Controlled quotient tasks confirm that sampler-relative delivery activates signals that raw local quotient gradients leave dormant. On frozen TargetDiff backbones, official seed-0 CBGBench ligand-generation/editing sweeps show practical quality-runtime gains: Local-QRG improves validity from 0.815 to 0.864 on fragment growing, 0.664 to 0.707 on scaffold hopping, and 0.681 to 0.712 on linker design, while PredNext-QRG improves fragment/scaffold and remains near-neutral on linker. Novelty remains 1.000 and diversity is preserved in the matched multi-seed molecular slice, giving task-dependent improvements without sampler retraining or backbone modification. Overall, QRG provides a lightweight route to quotient-aware inference for frozen molecular samplers with explicit runtime accounting.
Comments21 pages, 5 figures. Includes theoretical proofs and supplementary experimental results
