使用图形神经网络进行不确定性量化,以实现高效的分子设计
Lung-Yi Chen1, Yi-Pei Li2,3
1Department of Chemical Engineering, National Taiwan University, Taipei, Taiwan, ROC.
Nature communications
|April 5, 2025
概括
将不确定性量化 (UQ) 与定向消息传递神经网络 (D-MPNNs) 集成,可以在大型化学空间中提高分子设计优化. 这种方法提高了预测准确度,并平衡了计算辅助分子设计 (CAMD) 的竞争目标.
科学领域:
- 计算化学是一种计算化学.
- 机器学习在药物发现中的作用
- 材料科学是一种材料科学.
背景情况:
- 在大型化学空间中优化分子设计是具有挑战性的,原因是域移位和保持预测准确度.
- 现有的方法经常与广泛的,开放式的化学勘探作斗争.
- 计算辅助分子设计 (CAMD) 需要强大的优化策略.
研究的目的:
- 评估与定向消息传递神经网络 (D-MPNNs) 集成的不确定性量化 (UQ) 的有效性,以优化广的化学空间.
- 在分子设计中确定UQ增强的D-MPNNs的最佳实施策略.
- 评估UQ引导优化在单一和多目标任务中的性能.
主要方法:
- 不确定性量化 (UQ) 与定向消息传递神经网络 (D-MPNNs) 的整合.
- 利用遗传算法 (GA) 进行优化.
- 评估使用来自Tartarus和GuacaMol平台的基准.
- 对UQ集成应用概率改进优化 (PIO) 的应用.
主要成果:
- 通过概率改进优化 (PIO) 进行UQ集成,通常可以在各种化学领域提高优化成功率.
- 用UQ增强的D-MPNN在探索化学多样性的地区中表现出更高的可靠性.
- 在多目标优化任务中,PIO特别有利,有效地平衡竞争目标.
- 提出的方法在几个基准指标中优于不确定性不可知论方法.
结论:
- 不确定性量化显著提高了用于计算辅助分子设计 (CAMD) 的D-MPNNs的性能.
- 概率性改进优化 (PIO) 为导航复杂的化学环境和平衡多个目标提供了一个强大的策略.
- 本研究提供了在CAMD工作流程中实施UQ的实用指南,使得分子发现更加可靠和高效.
相关概念视频
02:00Molecular Models
37.6K
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.
37.6K
02:35Molecular Orbital Theory I
31.2K
Overview of Molecular Orbital Theory
31.2K
02:45The Quantum-Mechanical Model of an Atom
41.7K
Shortly after de Broglie published his ideas that the electron in a hydrogen atom could be better thought of as being a circular standing wave instead of a particle moving in quantized circular orbits, Erwin Schrödinger extended de Broglie’s work by deriving what is now known as the Schrödinger equation. When Schrödinger applied his equation to hydrogen-like atoms, he was able to reproduce Bohr’s expression for the energy and, thus, the Rydberg formula governing...
41.7K
03:51Molecular Orbital Theory II
18.7K
Molecular Orbital Energy Diagrams
18.7K
01:29Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving
34
Mechanistic models play a crucial role in algorithms for numerical problem-solving, particularly in nonlinear mixed effects modeling (NMEM). These models aim to minimize specific objective functions by evaluating various parameter estimates, leading to the development of systematic algorithms. In some cases, linearization techniques approximate the model using linear equations.
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...
34
02:40MO Theory and Covalent Bonding
10.2K
The molecular orbital theory describes the distribution of electrons in molecules in a manner similar to the distribution of electrons in atomic orbitals. The region of space in which a valence electron in a molecule is likely to be found is called a molecular orbital. Mathematically, the linear combination of atomic orbitals (LCAO) generates molecular orbitals. Combinations of in-phase atomic orbital wave functions result in regions with a high probability of electron density, while...
10.2K