使用GNN属性预测器作为分子发生器
Félix Therrien1, Edward H Sargent1, Oleksandr Voznyy2
1University of Toronto, Ontario, Canada.
Nature communications
|May 9, 2025
概括
图形神经网络 (GNN) 现在可以直接生成具有特定电子特性的新型分子结构. 这种方法在没有额外的培训的情况下优化分子图以获得所需的属性,产生多样化和准确的结果.
科学领域:
- 计算化学和材料科学计算化学和材料科学
- 机器学习在药物发现和材料设计中的应用.
背景情况:
- 图形神经网络 (GNN) 对于预测材料和分子性质越来越重要.
- 自动化发现管道需要有效的方法来产生新的分子结构.
研究的目的:
- 利用GNN的可逆性来直接生成具有有针对性的电子特性的分子结构.
- 为了优化分子图向所需的属性使用梯度上升固定GNN重量.
主要方法:
- 利用预训练的GNN分子图输入的梯度上升来优化目标属性.
- 通过仔细的图形构造,确保严格遵守价值规则.
- 不需要对分子结构进行额外的培训,仅依靠属性预测器.
主要成果:
- 成功生成了具有特定能量差距 (通过DFT验证) 和八醇-水分割系数 (logP) 的分子.
- 实现了与最先进的生成模型可比或优于目标物业预测率.
- 创建了1617个新分子及其DFT计算属性的数据集,用于分发之外的测试.
结论:
- 可逆GNN提供了一种强大的,无需训练的方法,用于具有所需性质的de novo分子生成.
- 与现有模型相比,该方法表现出高效率,精度和优越的分子多样性.
- 生成的数据集为对比和验证QM9训练模型提供了宝贵的资源.
相关概念视频
Predicting Molecular Geometry
33.9K
VSEPR Theory for Determination of Electron Pair Geometries
33.9K
Predicting Reaction Outcomes
7.8K
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,...
7.8K
Predicting Products: SN1 vs. SN2
13.1K
Nucleophilic substitution reactions of alkyl halides can proceed via an SN1 or an SN2 mechanism. While in SN2 reactions, the nucleophile attacks the substrate simultaneously as the leaving group departs, in SN1 reactions, the substrate first dissociates to give the carbocation intermediate. Various factors such as the structure of the substrate, the strength of the nucleophile, and the nature of the solvent promote one mechanism over the other.
With increased substitution on the alkyl halide,...
With increased substitution on the alkyl halide,...
13.1K
Molecular Models
37.5K
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.
37.5K
Ziegler–Natta Chain-Growth Polymerization: Overview
3.2K
Ziegler–Natta polymerization is another form of addition or chain‐growth polymerization used for synthesizing linear polymers over branched polymers. The catalyst used for polymerization is the Ziegler–Natta catalyst, named after Karl Ziegler and Giulio Natta, who developed it in 1953. This catalyst is an organometallic complex of titanium tetrachloride and triethyl aluminum, with the active form of the catalyst being an alkyl titanium compound. Using the Ziegler–Natta...
3.2K
Newman Projections
16.1K
Different notations are used to represent the three-dimensional structure of molecules on two-dimensional surfaces. One of the most commonly used representations is the dash-wedge formula. The dashed wedges, solid wedges, and the plane lines indicate the groups situated behind the plane, coming out of the plane, and in the plane, respectively.
The organic molecules rotate across the single bonds leading to numerous temporary three-dimensional structures of varying energy known as...
The organic molecules rotate across the single bonds leading to numerous temporary three-dimensional structures of varying energy known as...
16.1K


