Scholarlink

<p>This study systematically compares six deep learning architectures—three graph neural networks (MPNN, GAT, GIN) and three physics-informed variants (PhysNet, PhysNet-ens5, PhysNet-Lite)—for molecular dipole moment prediction. Models are first evaluated on the QM9 benchmark, then assessed for generalization to a curated set of 50 Traditional Chinese Medicine molecules (27 overlapping with QM9, 23 structurally novel). While physics-informed models achieved the highest accuracy on QM9, GAT demonstrated the most robust transfer to unseen TCM structures, with the lowest performance degradation (gap ratio: 1.48 ×). Physics-informed models showed potential but exhibited varying generalization behavior, indicating that architectural design and hyperparameter optimization significantly influence out-of-distribution performance. This comparative analysis provides practical guidance for model selection in TCM property prediction and establishes a framework for evaluating generalization in molecular machine learning.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Dipole moment prediction with graph neural networks and physics-informed models: a comparative evaluation on QM9 and traditional Chinese medicine molecules

  • 期刊论文

  • 发表日期：

    2026年2月2日

查看全文
  • Xiong Li,
  • Guoqiang Bian,
  • Tao Yang,
  • Kongfa Hu,
  • Renli Xu,
  • Zuojian Zhou,
  • Chenjun Hu

摘要

This study systematically compares six deep learning architectures—three graph neural networks (MPNN, GAT, GIN) and three physics-informed variants (PhysNet, PhysNet-ens5, PhysNet-Lite)—for molecular dipole moment prediction. Models are first evaluated on the QM9 benchmark, then assessed for generalization to a curated set of 50 Traditional Chinese Medicine molecules (27 overlapping with QM9, 23 structurally novel). While physics-informed models achieved the highest accuracy on QM9, GAT demonstrated the most robust transfer to unseen TCM structures, with the lowest performance degradation (gap ratio: 1.48 ×). Physics-informed models showed potential but exhibited varying generalization behavior, indicating that architectural design and hyperparameter optimization significantly influence out-of-distribution performance. This comparative analysis provides practical guidance for model selection in TCM property prediction and establishes a framework for evaluating generalization in molecular machine learning.