KnoMol:一个知识增强的图形转换器用于分子性质预测
Jian Gao1,2, Zheyuan Shen1, Yan Lu3
1Hangzhou Institute of Innovative Medicine, Institute of Drug Discovery and Design, College of Pharmaceutical Sciences, Zhejiang University, Hangzhou 310058, China.
Journal of chemical information and modeling
|September 26, 2024
概括
这项研究介绍了KnoMol,这是一种新的深度学习框架,将化学知识集成到用于分子性质预测 (MPP) 的变压器中. 诺莫尔提高了准确性,减少了数据依赖,加速了药物发现.
科学领域:
- 计算化学是一种计算化学.
- 化学信息学 化学信息学
- 人工智能在药物发现中的作用
背景情况:
- 分子性质预测 (MPP) 对于有效的药物开发至关重要,但当前的深度学习模型在表示能力方面扎.
- 现有的方法往往需要大量的数据集,在数据稀缺的场景中带来挑战.
研究的目的:
- 开发一种基于知识的新型变压器框架,KnoMol,以提高分子结构的理解和提高MPP的准确性.
- 通过整合专家化学知识,解决MPP深度学习模型中数据稀缺的挑战.
主要方法:
- 开发了KnoMol,一个包含专家化学知识和多视角注意力机制的变压器框架.
- 在基准数据集 (MoleculeNet) 和小规模数据上评估KnoMol,将其性能与现有模型进行比较.
主要成果:
- KnoMol实现了最先进的性能,在MPP任务上的准确性和概括性方面超过了现有模型.
- 知识的整合大大减少了KnoMol对数据量的依赖,缓解了数据稀缺问题.
- 在一个案例研究中,KnoMol成功地确定了新的HER2抑制剂,展示了其实际适用性.
结论:
- KnoMol提供了一种强大且数据效率高的分子性质预测工具,推进了计算机辅助药物发现.
- 这项研究为将域知识嵌入到变压器模型中建立了一个成功的先例,有利于MPP算法开发的更广泛领域.
相关概念视频
Predicting Molecular Geometry
34.1K
VSEPR Theory for Determination of Electron Pair Geometries
34.1K
Predicting Reaction Outcomes
8.2K
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,...
8.2K
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
Properties of Transition Metals
25.2K
Transition metals are defined as those elements that have partially filled d orbitals. As shown in Figure 1, the d-block elements in groups 3–12 are transition elements. The f-block elements, also called inner transition metals (the lanthanides and actinides), also meet this criterion because the d orbital is partially occupied before the f orbitals.
25.2K
Molecular Orbital Theory II
19.0K
Molecular Orbital Energy Diagrams
19.0K
Molecular Orbital Theory I
31.8K
Overview of Molecular Orbital Theory
31.8K


