通过图形神经网络和转移学习来准确预测蛋白质的分子特性
Spencer Wozniak1, Giacomo Janson1, Michael Feig1
1Department of Biochemistry and Molecular Biology, Michigan State University, East Lansing, Michigan 48824, United States.
Journal of chemical theory and computation
|April 24, 2025
概括
像GSnet这样的图形神经网络 (GNN) 从3D结构中预测蛋白质特性. 使用GSnet嵌入式的转移学习可以预测溶剂可访问的表面积和pKa值.
科学领域:
- 计算生物学 计算生物学
- 结构生物学 结构生物学
- 机器学习 机器学习
背景情况:
- 机器学习 (ML) 为实验和传统计算蛋白质性质预测的局限性提供了解决方案.
- 预测蛋白质特征对于理解生物功能和疾病至关重要.
研究的目的:
- 介绍GSnet,一个图形神经网络 (GNN),用于预测蛋白质的物理化学和几何性质.
- 使用转移学习调整预先训练的GSnet嵌入,以提高预测准确度.
主要方法:
- 开发了GSnet,一种利用3D蛋白质结构的GNN模型.
- 员工转移学习以微调GSnet嵌入式,以进行特定物业预测.
- 在各种数据集上评估模型性能,包括内在无序.
主要成果:
- GSnet准确地预测了没有溶解的能量,扩散常数和水力动力半径.
- 使用GSnet嵌入式的转移学习实现了高精度的溶剂可访问表面积 (SASA) 预测,优于现有方法.
- 一种变种,aLCnet,与基于模拟的方法相比,在残留物特定的pKa预测方面表现出具有竞争力的准确性.
结论:
- GSnet和转移学习为蛋白质性质预测提供了一个强大的和可扩展的框架.
- 基于GNN的嵌入可以推进蛋白质结构分析,并有可能进行全蛋白质组研究.
- 这种方法支持将预测模型集成到结构生物学管道中.
相关概念视频
Protein Networks
3.9K
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,...
3.9K
Protein-protein Interfaces
12.4K
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...
12.4K
Proteomics
7.1K
A proteome is the entire set of proteins that a cell type produces. We can study proteomes using the knowledge of genomes because genes code for mRNAs, and the mRNAs encode proteins. Although mRNA analysis is a step in the right direction, not all mRNAs are translated into proteins.
Proteomics is the study of proteomes' function. It involves the large-scale systematic study of the proteome to denote the protein complement expressed by a genome. Scientist Mark Wilkins coined the term...
Proteomics is the study of proteomes' function. It involves the large-scale systematic study of the proteome to denote the protein complement expressed by a genome. Scientist Mark Wilkins coined the term...
7.1K
Ligand Binding Sites
12.6K
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...
12.6K
Conserved Binding Sites
4.1K
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...
4.1K


