使用图形神经网络进行转移学习,以在多忠度设置中改进分子性质预测
David Buterez1, Jon Paul Janet2, Steven J Kiddle3
1Department of Computer Science and Technology, University of Cambridge, Cambridge, UK. db804@cam.ac.uk.
Nature communications
|February 26, 2024
概括
图形神经网络 (GNN) 可以通过使用低保真性数据进行转移学习来改善分子性质预测. 新的策略提高了稀疏数据集的性能,减少了昂贵的高保真度测量的需求.
科学领域:
- 计算化学是一种计算化学.
- 机器学习是机器学习.
- 药物发现 药物发现
背景情况:
- 分子性质预测对于药物发现和材料科学至关重要.
- 高准确度数据采集是昂贵和耗时的,导致数据集稀疏.
- 对于图形神经网络而言,现有的转移学习方法与多忠度数据布作斗争.
研究的目的:
- 在分子性质预测中开发和评估图形神经网络 (GNN) 的有效转移学习策略.
- 为了利用低保真度数据作为高保真度测量成本有效的代理.
- 在稀疏和昂贵的数据集上提高预测准确度.
主要方法:
- 为 GNN 提出了新的转移学习策略.
- 对传导式和归纳式学习环境的评估方法.
- 利用了大型数据集,包括2800万个蛋白质-连接体相互作用和QMugs量子性质.
主要成果:
- 转移学习显著提高了稀疏任务的性能,高达八倍.
- 使用一个数量级小的高保真数据实现了实质性的性能增长.
- 提出的方法在药物发现和量子力学数据集上表现优于现有的转移学习策略.
结论:
- 有效的转移学习策略可以利用多忠度数据进行分子性质预测.
- 这种方法提供了一种具有成本效益的方法,可以提高数据稀缺场景的准确性.
- 开发的方法在加速药物发现和材料科学研究方面非常有前途.
相关概念视频
Predicting Molecular Geometry
34.3K
VSEPR Theory for Determination of Electron Pair Geometries
34.3K
Predicting Reaction Outcomes
8.4K
Kinetics describes the rate and path by which a reaction occurs. In contrast, thermodynamics deals with state functions and describes the properties, behavior, and components of a system. It is not concerned with the path taken by the process and cannot address the rate at which a reaction occurs. Although it does provide information about what can happen during a reaction process, it does not describe the detailed steps of what appears on an atomic or a molecular level. On the other hand,...
8.4K
¹H NMR Chemical Shift Equivalence: Homotopic and Heterotopic Protons
2.4K
Protons in identical electronic environments within a molecule are chemically equivalent and have the same chemical shift. The replacement test is a useful tool to identify chemical equivalence and predict NMR spectra. A substituent replaces each of the protons being examined and the resulting molecules are compared. If the same molecule is obtained, the protons are equivalent or homotopic. Replacement of any hydrogens in ethane by chlorine yields chloroethane because all six protons are...
2.4K
Inductive Effects on Chemical Shift: Overview
1.1K
The protons in unsubstituted alkanes are strongly shielded with chemical shifts below 1.8 ppm. Methine, methylene, and methyl protons appear at approximately 1.7, 1.2 and 0.7 ppm, while the proton signal from methane appears at 0.23 ppm. An electronegative substituent, such as chlorine, withdraws the electron density from the protons, increasing their chemical shift. Progressive substitution of the hydrogens in methane by chlorine shifts the proton signals increasingly downfield, to 3.05 ppm in...
1.1K
¹H NMR of Conformationally Flexible Molecules: Temporal Resolution
841
At room temperature, the chair conformer of cyclohexane undergoes rapid ring flipping between two equivalent chair conformers at a rate of approximately 105 times per second. These two chair conformers are in equilibrium. The rapid ring flipping results in the interconversion of the axial proton to an equatorial proton and an equatorial to the axial proton. Such interconversions are too rapid and cannot be detected on the NMR timescale. Hence, the NMR spectrometer cannot distinguish between the...
841
2D NMR: Overview of Homonuclear Correlation Techniques
198
Homonuclear correlation spectroscopy (COSY) is a powerful technique used in Nuclear Magnetic Resonance (NMR) spectroscopy to study the correlations between nuclei of the same type within a molecule. It provides information about scalar couplings between adjacent nuclei, which helps determine connectivity and structural information. There are several COSY variants, each with its unique strengths and experimental parameters.
COSY90 is the standard two-dimensional (2D) COSY experiment that...
COSY90 is the standard two-dimensional (2D) COSY experiment that...
198


