[论文解读] DecompOpt: Controllable and Decomposed Diffusion Models for Structure-based Molecular Optimization
DecompOpt 将可控且分解的扩散与迭代优化结合,用于设计和优化基于结构的配体,实现从头设计和可控生成(R-Group 设计与骨架跳跃),并提高对接亲和力与药物样性质。
Recently, 3D generative models have shown promising performances in structure-based drug design by learning to generate ligands given target binding sites. However, only modeling the target-ligand distribution can hardly fulfill one of the main goals in drug discovery -- designing novel ligands with desired properties, e.g., high binding affinity, easily synthesizable, etc. This challenge becomes particularly pronounced when the target-ligand pairs used for training do not align with these desired properties. Moreover, most existing methods aim at solving extit{de novo} design task, while many generative scenarios requiring flexible controllability, such as R-group optimization and scaffold hopping, have received little attention. In this work, we propose DecompOpt, a structure-based molecular optimization method based on a controllable and decomposed diffusion model. DecompOpt presents a new generation paradigm which combines optimization with conditional diffusion models to achieve desired properties while adhering to the molecular grammar. Additionally, DecompOpt offers a unified framework covering both extit{de novo} design and controllable generation. To achieve so, ligands are decomposed into substructures which allows fine-grained control and local optimization. Experiments show that DecompOpt can efficiently generate molecules with improved properties than strong de novo baselines, and demonstrate great potential in controllable generation tasks.
研究动机与目标
- 激发基于结构的分子设计,协同优化结合亲和力和药物样性质。
- 开发一个可控扩散框架,将配体分解为臂和骨架以实现细粒度控制。
- 在分解扩散范式中统一从头设计和可控生成。
- 展示以优化驱动的生成,在CrossDocked2020上能超越强基线。
提出的方法
- 引入一个可控且分解的扩散模型,根据蛋白质子口袋和参考臂条件生成配体。
- 将配体分解为骨架和臂;通过对臂-口袋对的SE(3)-等变编码器对臂层特征进行条件化。
- 使用带分解先验和条件特征的基于扩散的解码器,在保留分子文法的同时实现控制。
- 通过迭代优化,用更高分数的候选臂替换现有臂;将对接/评估整合为优化循环的一部分。
- 采用多目标评分(QED、SA、Vina Min)并进行Z分数归一化,以引导跨子口袋的臂层选择。
实验结果
研究问题
- RQ1可控的分解扩散模型在遵循分子文法的同时,是否能生成高亲和力的配体?
- RQ2臂层优化是否比分子层级优化或纯生成方法在效率和多样性方面更优?
- RQ3该框架能否在三维结构基础设计中支持如R-Group设计和骨架跳跃等可控任务?
- RQ4将优化与生成整合对比基线,如何影响结合亲和力和药物性指标?
主要发现
- 与强基线相比,DecompOpt在CrossDocked2020上实现了更高的亲和力相关指标和更高的成功率。
- 对于从头设计,DecompOpt达到平均Vina Dock分数为-8.98,平均成功率52.5%,优于若干基线。
- 臂层级优化在效率和性质提升方面优于分子层级优化,凸显了分解优化的优势。
- 可控性使得R-Group设计和骨架跳跃成为可能,骨架跳跃在有效性和完整率方面更高,并促进多样性。
- 平均而言,DecompOpt 提升了 QED 和 SA,并在对接方面实现了更深的提升(如 Vina Dock 和 Vina Min 相对于 DecompDiff 基线)。
更好的研究,从现在开始
从论文设计到论文写作,大幅缩短您的研究时间。
无需绑定信用卡
本解读由 AI 生成,并经人工编辑审核。