用于分子图学习的变分量子注意力

中文摘要 AI 辅助

分子性质预测是计算药物发现的核心任务，其中图神经网络在消息传递过程中学习对相邻原子环境进行加权。然而，变分量子电路如何改变分子图中的学习注意力行为仍不清楚。我们提出了一种用于分子图学习的边感知变分量子注意力机制，其中接收原子、相邻原子和连接键共同决定量子注意力状态。在五个分子性质和生物活性预测任务中，QGAT相对于GATv2取得了具有竞争力的性能，并在所有六个评估的电路拟设中对BBBP任务实现了一致的改进。我们进一步比较了量子与经典注意力分数在准确性之外对分子结构的加权方式。在Verubecestat BACE1抑制剂系列中，QGAT获得了比GATv2更高的Spearman相关性，并对若干与已报道的构效关系（SARs）一致的结构变化赋予了正向归因。该案例研究表明，两种注意力机制在结构相关的BACE1类似物上可以表现出不同的预测和归因行为，而需要更广泛的验证来确定这些差异在化学系列和靶点间的一致性程度。电路消融进一步表明性能依赖于电路设计。总之，这些结果表明变分量子注意力可以作为可行的替代分子注意力参数化方式，同时引发与匹配的经典评分器不同的、依赖于电路和化学性质的行为。

英文摘要

Molecular property prediction is central to computational drug discovery, where graph neural networks learn to weight neighboring atomic environments during message passing. Yet it remains unclear how variational quantum circuits alter learned attention behavior in molecular graphs. We introduce an edge-aware variational quantum attention mechanism for molecular graph learning, in which the receiving atom, neighboring atom, and connecting bond jointly determine the quantum attention state. Across five molecular property and bioactivity prediction tasks, QGAT achieves competitive performance relative to GATv2, with a consistent improvement on BBBP across all six evaluated circuit ansatzes. We further compare how the quantum and classical attention scores weight molecular structure beyond accuracy. In the Verubecestat BACE1 inhibitor series, QGAT achieves a higher Spearman correlation than GATv2 and assigns positive attributions to several structural changes consistent with reported structure-activity relationships (SARs). This case study shows that the two attention mechanisms can exhibit different prediction and attribution behavior across structurally related BACE1 analogues, while broader validation is required to determine how consistently these differences generalize across chemical series and targets. Circuit ablations further show that performance depends on the circuit design. Together, these results show that variational quantum attention can serve as a viable alternative molecular attention parameterization while inducing circuit- and chemistry-dependent behavior distinct from a matched classical scorer.

发表机构

• National Yang Ming Chiao Tung University（国立阳明交通大学）
• Korea Advanced Institute of Science and Technology (KAIST)（韩国科学技术院）
• Brookhaven National Laboratory（布鲁克海文国家实验室）
• Taipei Medical University（台北医学大学）

机构由 AI 辅助整理，请以论文原文为准。