信息理论多尺度几何预训,用于增强分子性质预测
Xiaoyu Hu1, Xiuyuan Zhao2, Jiyuan Wang3
1Department of Chemical Engineering and Materials Science, Stevens Institute of Technology, Hoboken, New Jersey, United States of America.
PloS one
|October 6, 2025
概括
多尺度几何预训练 (MSG-Pre) 通过整合跨尺度的信息来改善分子表示学习. 这种新的框架增强了药物发现和纳米材料设计的预测.
科学领域:
- 计算化学是一种计算化学.
- 机器学习 机器学习
- 纳米技术纳米技术
背景情况:
- 有效的分子表示学习需要在结构尺度上最大限度地传输信息.
- 当前的图形神经网络在与多尺度分子几何学作斗争,阻碍了信息传播.
- 这限制了捕捉当地和全球结构特征的能力.
研究的目的:
- 引入多尺度几何预训练 (MSG-Pre),这是一个用于分子表示学习的信息理论框架.
- 解决现有方法在捕获多尺度分子信息方面的局限性.
- 提高药物发现和纳米材料设计的分子理解和预测能力.
主要方法:
- 开发了一个信息理论框架 (MSG-Pre),整合了原子,功能组和调整器级别.
- 采用了以为导向的机制,包括尺度适应性注意力和层次对比学习.
- 利用几何规律化策略来保持形状性质.
主要成果:
- 在14个分子基准数据集上实现了最先进的性能,改进率高达5.2%.
- 显著增强了用于纳米医学应用的信息提取,例如纳米粒子-蛋白质相互作用.
- 证明有效地最大化跨规模的相互信息和最大限度地减少规模内的冗余.
结论:
- MSG-Pre建立了几何学预训练的信息理论基础.
- 该框架优化了分子表示中的信息平衡.
- MSG-Pre提高了药物发现和纳米材料设计的分子理解和预测.
相关概念视频
Predicting Molecular Geometry
45.0K
VSEPR Theory for Determination of Electron Pair Geometries
45.0K
Molecular Geometry and Dipole Moments
18.1K
The VSEPR theory can be used to determine the electron pair geometries and molecular structures as follows:
18.1K
Molecular Models
43.5K
Physical models representing molecular architectures of chemical compounds play essential roles in understanding chemistry. The use of molecular models makes it easier to visualize the structures and shapes of atoms and molecules.
43.5K
Multi-species Conserved Sequences
4.6K
Next-generation sequencing technologies have created large genomic databases of a variety of animals and plants. Ever since the human genome project was completed, scientists studied the genome of primates, mammals, and other phylogenetically distant living beings. Such large-scale studies have provided new insights into the evolutionary relationship between organisms.
Although the genome of each species varies greatly from each other, a few sequences are highly conserved. Such conserved...
Although the genome of each species varies greatly from each other, a few sequences are highly conserved. Such conserved...
4.6K


