积极学习管道的分布外评估,用于分子性质预测
Tianzhixi Yin1, Peiyuan Gao1, Gihan Panapitiya1
1Pacific Northwest National Laboratory USA tianzhixi.yin@gmail.com.
RSC advances
|January 26, 2026
概括
积极学习 (AL) 通过战略性地选择数据来改善分子性质预测. 与AL一起的证据深度学习 (EDL) 在与随机抽样相比,在分布之外的数据上表现更好.
科学领域:
- 计算化学是一种计算化学.
- 机器学习是机器学习.
- 数据科学是数据科学.
背景情况:
- 积极学习 (AL) 最小化了机器学习 (ML) 模型的数据需求.
- 分子性质预测是数据密集型的,使得AL有价值.
- 对外分销 (OOD) 数据进行AL评估对于现实应用至关重要,但研究不足.
研究的目的:
- 评估积极学习 (AL) 用于分子性质预测,特别关注分布外 (OOD) 性能.
- 开发和评估使用证据深度学习 (EDL) 来预测溶解能量的AL框架.
- 分析数据多样性和数据集相似性对AL性能的影响.
主要方法:
- 开发了一个AL框架,利用证据深度学习 (EDL) 的预测不确定性.
- 训练模型在发行数据上,并与PubChem.采样的OOD数据进行增强.
- 使用随机抽样与EDL引导的选择研究AL性能.
- 通过从一个不那么多样化的分布式数据集开始,检查了概括.
主要成果:
- 基于深度学习 (EDL) 的积极学习 (AL) 证明了对OOD分子性质预测的随机抽样比较优异的性能.
- 分析表明,训练测试数据集的相似性如何影响AL的有效性.
- 研究了AL和随机抽样之间的分子选择的分布差异.
结论:
- 积极学习 (AL) 与证据深度学习 (EDL) 是增强分子性质预测的有希望的策略,特别是在OOD数据中.
- 该研究强调了考虑AL数据集相似性和分布特征的重要性.
- 基于EDL的AL提供了一个比随机抽样更有效的方法来导航OOD分子数据.
相关概念视频
Predicting Molecular Geometry
45.7K
VSEPR Theory for Determination of Electron Pair Geometries
45.7K
Distribution of Molecular Speeds
5.4K
The motion of molecules in a gas is random in magnitude and direction for individual molecules, but a gas of many molecules has a predictable distribution of molecular speeds. This predictable distribution of molecular speeds is known as the Maxwell-Boltzmann distribution. The distribution of molecular speeds in liquids is comparable to that of gases but not identical and can help to understand the phenomenon of the boiling and vapor pressure of a liquid. Consider that a molecule requires a...
5.4K
Polymers: Molecular Weight Distribution
4.8K
For any given polymer, the weight average molecular weight (Mw) is higher than, if not equal to, the number average molecular weight (Mn). The only situation in which the weight average molecular weight and the number average molecular weight are equal is when a polymer consists only of chains with equal molecular weight. However, this never happens in a synthetic polymer, since it is difficult to control the polymerization process up to a molecular level with accuracy to a hundred percent.
4.8K
Kinetic Molecular Theory and Gas Laws Explain Properties of Gas Molecules
37.4K
The test of the kinetic molecular theory (KMT) and its postulates is its ability to explain and describe the behavior of a gas. The various gas laws (Boyle’s, Charles’s, Gay-Lussac’s, Avogadro’s, and Dalton’s laws) can be derived from the assumptions of the KMT, which have led chemists to believe that the assumptions of the theory accurately represent the properties of gas molecules.
37.4K
Properties of Enantiomers and Optical Activity
21.6K
It is essential to understand the difference between chiral and achiral interactions and the implications thereof in optical activity and their applications. Just as our feet, which are chiral, interact uniquely with chiral objects, such as a pair of shoes, but identically with achiral socks, enantiomers of a molecule exhibit different properties only when they interact with other chiral media. An example of a significant implication from this facet is the phenomenon known as optical activity,...
21.6K
Molecular and Ionic Solids
20.0K
Crystalline solids are divided into four types: molecular, ionic, metallic, and covalent network based on the type of constituent units and their interparticle interactions.
Molecular Solids
Molecular crystalline solids, such as ice, sucrose (table sugar), and iodine, are solids that are composed of neutral molecules as their constituent units. These molecules are held together by weak intermolecular forces such as London dispersion forces, dipole-dipole interactions, or hydrogen bonds, which...
Molecular Solids
Molecular crystalline solids, such as ice, sucrose (table sugar), and iodine, are solids that are composed of neutral molecules as their constituent units. These molecules are held together by weak intermolecular forces such as London dispersion forces, dipole-dipole interactions, or hydrogen bonds, which...
20.0K


