对分子构成的深度对比学习,用于高效的属性预测
Yang Jeong Park1,2,3, HyunGi Kim4, Jeonghee Jo4,5
1Department of Electrical and Computer Engineering, Seoul National University, Seoul, Republic of Korea. parkyj@mit.edu.
Nature computational science
|January 4, 2024
概括
深度学习模型可以准确地预测分子特性,但需要一致的几何数据. 当地原子环境对比学习 (LACL) 通过调整模型以适应不同数据类型来克服这一问题,从而实现更广泛的应用.
科学领域:
- 计算化学的计算化学
- 机器学习 机器学习
- 深度学习 (Deep Learning) 是一种深度学习.
背景情况:
- 数据驱动的深度学习模型可以准确地预测分子特性,但受到几何放松约束的限制.
- 当使用具有成本效益的符合性生成方法时,会出现域移动问题,从而降低预测准确性.
研究的目的:
- 开发一种域适应方法,在分子性质预测中弥合不同几何构造之间的差距.
- 为了使深度学习模型能够在不同的几何放松水平上保持准确性.
主要方法:
- 提出了一种基于深度对比学习的域适应方法,称为局部原子环境对比学习 (LACL).
- 通过比较不同的构造生成方法来捕获局部原子环境语义,LACL学习了一个域无关的潜空间.
主要成果:
- 实际上,LACL有效地减轻了不同几何形状之间的分布差异.
- 在没有几何放松瓶的情况下实现了量子化学准确性.
- 在小型有机分子,生物链和药物分子中展示了普遍性.
结论:
- 通过LACL,可以独立于几何放松约束,准确地预测分子性质.
- 该方法有助于更广泛的应用,如反向分子工程和大规模查.
- 在计算化学中,LACL为各种分子结构提供了可概括的解决方案.
相关概念视频
Predicting Molecular Geometry
34.3K
VSEPR Theory for Determination of Electron Pair Geometries
34.3K
¹H NMR of Conformationally Flexible Molecules: Variable-Temperature NMR
1.1K
The axial and equatorial protons in cyclohexane can be distinguished by performing a variable-temperature NMR experiment. In this process, except for one proton, the remaining eleven protons are replaced by deuterium. The deuterium substitution avoids the possible peak splitting caused by the spin-spin coupling between the adjacent protons. The remaining proton flips between the axial and equatorial positions.
1.1K
¹H NMR of Conformationally Flexible Molecules: Temporal Resolution
847
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...
847
Conserved Binding Sites
4.2K
Many proteins’ biological role depends on their interactions with their ligands, small molecules that bind to specific locations on the protein known as ligand-binding sites. Ligand-binding sites are often conserved among homologous proteins as these sites are critical for protein function.
Binding sites are often located in large pockets, and if their location on a protein’s surface is unknown, it can be predicted using various approaches. The energetic method computationally...
Binding sites are often located in large pockets, and if their location on a protein’s surface is unknown, it can be predicted using various approaches. The energetic method computationally...
4.2K
Molecular Models
38.4K
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.
38.4K
Molecular Shape and Polarity
60.5K
Dipole Moment of a Molecule
60.5K


