总干事ATT:一个序列图交叉注意力表示架构用于分子性质预测
Yajie Hao1, Xing Chen1, Ailu Fei1
1School of Information Science and Technology, Nantong University, Nantong 226001, China.
Molecules (Basel, Switzerland)
|January 26, 2024
概括
这项研究引入了一种新的序列图交叉注意 (SG-ATT) 模型用于分子性质预测. SG-ATT通过结合SMILES序列和图形结构来增强分子表示,提高预测准确度.
科学领域:
- 计算化学计算化学
- 化学信息学 化学信息学
- 机器学习 机器学习
背景情况:
- 现有的分子编码方法,如SMILES和图形结构,难以捕获复杂的物理化学性质.
- 单个编码格式不足以表示分子的全部语义和结构信息.
研究的目的:
- 为分子性质预测提出一个序列图交叉注意 (SG-ATT) 表示架构.
- 通过将域知识与SMILES序列和分子图形结构集成来增强分子特征编码.
主要方法:
- 开发了SG-ATT架构,以从序列 (SMILES) 和图表表示中融合2D分子特征.
- 集成的领域知识,以改善功能编码,用于分子性质预测.
- 在九个不同的分子性质预测任务中测试了SG-ATT模型.
主要成果:
- 在BACE数据集上实现了4.5%的最大性能改进.
- 在所有测试的数据集中显示了1.83%的平均性能改善.
- 进行了用于体外验证的可解释性研究和案例研究.
结论:
- 该SG-ATT模型有效地整合了分子结构和语义信息,以提高属性预测.
- 开发的网络工具为分子性质预测研究人员提供了宝贵的资源.
- SG-ATT提供了一种有希望的方法来克服现有的分子表示方法的局限性.
相关概念视频
Protein Networks
4.0K
An organism can have thousands of different proteins, and these proteins must cooperate to ensure the health of an organism. Proteins bind to other proteins and form complexes to carry out their functions. Many proteins interact with multiple other proteins creating a complex network of protein interactions.
These interactions can be represented through maps depicting protein-protein interaction networks, represented as nodes and edges. Nodes are circles that are representative of a protein,...
These interactions can be represented through maps depicting protein-protein interaction networks, represented as nodes and edges. Nodes are circles that are representative of a protein,...
4.0K
Ligand Binding Sites
12.8K
Proteins are dynamic macromolecules that carry out a wide variety of essential processes; however, the activities of most proteins depend on their interactions with other molecules or ions, known as ligands.
Protein-ligand interactions are quite specific; even though numerous potential ligands surround a cellular protein at any given time, only a particular ligand can bind to that protein. Moreover, a ligand binds only to a dedicated area on the surface of the protein, known as the...
Protein-ligand interactions are quite specific; even though numerous potential ligands surround a cellular protein at any given time, only a particular ligand can bind to that protein. Moreover, a ligand binds only to a dedicated area on the surface of the protein, known as the...
12.8K
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
Protein-protein Interfaces
12.5K
Many proteins form complexes to carry out their functions, making protein-protein interactions (PPIs) essential for an organism's survival. Most PPIs are stabilized by numerous weak noncovalent chemical forces. The physical shape of the interfaces determines the way two proteins interact. Many globular proteins have closely-matching shapes on their surfaces, which form a large number of weak bonds. Additionally, many PPIs occur between two helices or between a surface cleft and a...
12.5K
G Protein-coupled Receptors
12.1K
G Protein-Coupled Receptors or GPCRs are membrane-bound receptors that transiently associate with heterotrimeric G proteins and induce an appropriate response to sensory stimuli such as light, odors, hormones, cytokines, or neurotransmitters.
GPCRs are also called heptahelical, 7TM, or serpentine receptors, and consist of seven (H1-H7) transmembrane alpha-helices that span the bilayer to form a cylindrical core. The transmembrane helices are connected by three extracellular loops and three...
GPCRs are also called heptahelical, 7TM, or serpentine receptors, and consist of seven (H1-H7) transmembrane alpha-helices that span the bilayer to form a cylindrical core. The transmembrane helices are connected by three extracellular loops and three...
12.1K


