探索带有潜空间算法的分子异型编码器:原子描述符和分子运算符
Xinyue Gao1, Natalia Baimacheva2, Joao Aires-de-Sousa3
1Faculty of Sciences, Université Paris Cité, 75013 Paris, France.
Molecules (Basel, Switzerland)
|August 29, 2024
概括
本研究介绍了从使用循环神经网络的分子结构中衍生出的三角潜伏空间向量 (DLSV). 这些DLSV有效地预测-19NMR的化学转移,并使新的分子设计成为可能.
科学领域:
- 计算化学是一种计算化学.
- 机器学习在化学中的应用
- 药物发现 药物发现
背景情况:
- 开发新的原子描述器对于推进化学性质预测至关重要.
- 循环神经网络 (RNN) 和变异自编码器 (VAE) 为学习分子表示提供了强大的工具.
- 微笑符号提供了一种简洁的方式来表示分子结构用于计算分析.
研究的目的:
- 开发和验证一组新的原子描述器,三角形潜伏空间向量 (DLSVs),使用变异异型编码器.
- 评估DLSV用于预测19F NMR化学转移的实用性.
- 探索DLSVs作为分子运算器的应用,用于新的分子生成.
主要方法:
- 基于RNN的变异性异型编码器使用SMILES符号进行训练.
- 德尔塔潜伏空间向量 (DLSV) 是通过比较具有和没有特定原子修饰的分子的潜伏空间表示生成的.
- 机器学习模型,包括随机森林和梯度增强回归器,使用DLSV进行训练,以预测19F NMR化学转移.
- DLSV被用作潜伏空间操作员来执行虚拟化学反应,如化.
主要成果:
- 对DLSV的无监督映射显示了基于元素,杂交和芳香度等原子性质的聚类.
- 在DLSV上训练的机器学习模型在预测19F NMR化学转移方面取得了很高的准确性 (R2高达0.89,MAE高达5.5ppm).
- 使用DLSV作为分子操作器,成功生成了具有高有效性 (99%) 的新型化分子,并且在很大程度上包含 (75%).
结论:
- DLSV是有效的原子描述器,可以捕获基本的化学信息.
- 通过机器学习,DLSV可以准确预测19F NMR化学转移.
- DLSVs代表了生成化学的一个有前途的方法,促进了具有所需性质的新型分子的设计.
相关概念视频
02:35Molecular Orbital Theory I
31.8K
Overview of Molecular Orbital Theory
31.8K
03:35Hybridization of Atomic Orbitals II
31.9K
sp3d and sp3d 2 Hybridization
31.9K
03:24Hybridization of Atomic Orbitals I
46.7K
The mathematical expression known as the wave function, ψ, contains information about each orbital and the wavelike properties of electrons in an isolated atom. When atoms are bound together in a molecule, the wave functions combine to produce new mathematical descriptions that have different shapes. This process of combining the wave functions for atomic orbitals is called hybridization and is mathematically accomplished by the linear combination of atomic orbitals. The new orbitals that...
46.7K
03:51Molecular Orbital Theory II
19.0K
Molecular Orbital Energy Diagrams
19.0K
01:27¹H NMR: Long-Range Coupling
1.7K
The coupling interactions of nuclei across four or more bonds are usually weak, with J values less than 1 Hz. While these are usually not observed in spectra, the presence of multiple bonds along the coupling pathway can result in observable long-range coupling.
In alkenes, spin information is communicated via σ–π overlap, as seen in allylic (four-bond) and homoallylic (five-bond) couplings. These coupling interactions are stronger when the σ bond is parallel to the alkene...
In alkenes, spin information is communicated via σ–π overlap, as seen in allylic (four-bond) and homoallylic (five-bond) couplings. These coupling interactions are stronger when the σ bond is parallel to the alkene...
1.7K
01:24π Molecular Orbitals of 1,3-Butadiene
8.8K
Conjugated dienes have lower heats of hydrogenation than cumulated and isolated dienes, making them more stable. The enhanced stabilization of conjugated systems can be understood from their π molecular orbitals.
The simplest conjugated diene is 1,3-butadiene: a four-carbon system where each carbon is sp2-hybridized and has an unhybridized p orbital that contains an unpaired electron. According to molecular orbital theory, atomic orbitals combine to form molecular orbitals such that the number...
The simplest conjugated diene is 1,3-butadiene: a four-carbon system where each carbon is sp2-hybridized and has an unhybridized p orbital that contains an unpaired electron. According to molecular orbital theory, atomic orbitals combine to form molecular orbitals such that the number...
8.8K