通过力场重连图结构，提升低配位原子构象预测精度
REBIND: Enhancing ground-state molecular conformation via force-based graph rewiring
- 基于莱纳德-琼斯势重新连接分子图，增强非键作用建模
- 在各类分子中误差降低最高达20%，尤其改善低度原子预测
- 适合需要高精度分子构象生成的研究者使用
从二维分子图预测基态三维构象是计算化学中的关键问题，对分子性质有深远影响。深度学习方法近年来成为密度泛函理论等计算成本高昂的传统方法的有力替代。然而我们发现，现有深度学习方法因简单使用键和成对距离，未能充分建模原子间作用力，尤其是非键原子对的作用，导致低度原子（即低配位数）的构象预测误差显著。为此，我们提出REBIND框架，通过引入基于莱纳德-琼斯势的边来重连分子图，以捕捉低度原子的非键相互作用。实验表明，REBIND在多种分子尺寸下均显著优于当前最优方法，预测误差最高降低20%。
原文摘要 · Abstract (English)
Predicting the ground-state 3D molecular conformations from 2D molecular graphs is critical in computational chemistry due to its profound impact on molecular properties. Deep learning (DL) approaches have recently emerged as promising alternatives to computationally-heavy classical methods such as density functional theory (DFT). However, we discover that existing DL methods inadequately model inter-atomic forces, particularly for non-bonded atomic pairs, due to their naive usage of bonds and pairwise distances. Consequently, significant prediction errors occur for atoms with low degree (i.e., low coordination numbers) whose conformations are primarily influenced by non-bonded interactions. To address this, we propose REBIND, a novel framework that rewires molecular graphs by adding edges based on the Lennard-Jones potential to capture non-bonded interactions for low-degree atoms. Experimental results demonstrate that REBIND significantly outperforms state-of-the-art methods across various molecular sizes, achieving up to a 20\% reduction in prediction error.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。