片段级图编码让分子性质预测解释可对齐官能团
Fragment-Level Graph Encoding for Interpretable Molecular Property Prediction
这篇不改模型只改输入表示：把分子图拆成 BRICS 片段节点，GNN 的解释就直接落在官能团粒度上，化学家能看懂，精度还基本不掉。
该论文提出不改模型、只改输入表示：用 BRICS 分解将分子编码为片段级图，节点为合成上有意义的片段，特征取其原子特征的逐元素求和。在 4 种 GNN 架构、4 个预测任务和 2 种解释方法、scaffold 划分下，片段级编码在约 5 倍更小的图上达到与原子级相当的测试精度。Integrated-Gradients 归因在 BACE 和 PTR1 两个酶靶点上分别以 1.5 倍和 3.2 倍于随机概率恢复已知药效团。与聚合原子级基线相比，后处理聚合的 BACE 命中率随两个任意聚合选择波动，而片段级训练可无预测损失地产出单一、无约定依赖的归因。代码已在 GitHub 开源。
Fragment-Level Graph Encoding for Interpretable Molecular Property Prediction
Graph neural networks (GNNs) are among the standard tools for molecular property prediction, but the atom-level explanations of their predictions are hard for medicinal chemists to act on. We propose a change of input representation rather than a new model: molecules are encoded as fragment-level graphs from BRICS decomposition, where each node is a synthetically meaningful fragment whose features are the element-wise sum of its atoms' features. Because only the representation changes, any message-passing GNN and any post-hoc attribution method produces explanations at the resolution of functional groups instead of single atoms. Across four architectures, four prediction tasks, and two explainers under scaffold splits, fragment-level encoding matches atom-level test accuracy on roughly five-fold smaller graphs. Integrated-Gradients attributions recover known pharmacophores above chance on two enzyme targets, namely BACE at 1.5 times the chance rate, and PTR1 at 3.2 times. A like-for-like comparison against an aggregated atom-level baseline shows that post-hoc aggregation is not a stable substitute: its BACE hit rate range both exceeds and falls below the fragment model's hit rate depending on two arbitrary aggregation choices, whereas fragment-level training yields a single convention-free attribution at no predictive cost. The code is available at: https://github.com/4D-Lab/frame