AI 中文总结
提出TreeRef-BFN，一种基于树表示和贝叶斯流网络的从头分子生成方法，联合建模拓扑与局部三维几何，支持变尺寸条件生成，无需重训练，兼具高有效性与灵活性。
AI 中文摘要
从头三维分子生成联合建模分子大小、拓扑和几何结构。大多数方法预先采样分子大小并生成笛卡尔坐标，这限制了诸如片段补全和骨架修饰等变尺寸条件任务，且通常依赖等变架构。内部坐标方法避免了刚体冗余，但通常需要已知的分子图或自回归构建，这可能累积误差。我们提出TreeRef，一种基于树的分子表示，将分子拓扑和依赖于拓扑的局部三维几何分配给自然变尺寸的树。RingRef节点编码环闭合同时保持树结构，而Null节点允许分子大小直接从节点占用中产生。基于TreeRef，我们开发了TreeRef-BFN，一种具有标准Transformer主干网络的贝叶斯流网络，该网络全局耦合这些局部定义的变量，并联合生成离散分子变量和连续局部几何。单个预训练的TreeRef-BFN仅通过掩码即可支持无条件生成和变尺寸结构条件下的三维生成，无需重新训练。实证研究展示了强化学有效性、分子稳定性和多样性、准确的局部几何分布、快速采样以及有竞争力的性质条件生成，确立了TreeRef-BFN作为三维分子生成的高效灵活框架。
英文摘要
De novo 3D molecular generation jointly models molecular size, topology, and geometry. Most methods pre-sample molecular size and generate Cartesian coordinates, limiting variable-size conditional tasks such as fragment completion and scaffold decoration while often relying on equivariant architectures. Internal-coordinate methods avoid rigid-body redundancy but typically require a known molecular graph or autoregressive construction, which may accumulate errors. We propose TreeRef, a tree-based molecular representation that assigns molecular topology and topology-dependent local 3D geometry to a naturally variable-size tree. RingRef nodes encode ring closures while preserving the tree structure, while Null nodes allow molecular size to emerge directly from node occupancy. Based on TreeRef, we develop TreeRef-BFN, a Bayesian Flow Network with a standard Transformer backbone that globally couples these locally defined variables and jointly generates discrete molecular variables and continuous local geometry. A single pretrained TreeRef-BFN supports unconditional generation and variable-size structure-conditioned 3D generation through masking alone, without retraining. Empirical studies demonstrate strong chemical validity, molecular stability, and diversity, accurate local geometric distributions, fast sampling, and competitive property-conditioned generation, establishing TreeRef-BFN as an efficient and flexible framework for 3D molecular generation.
