通过几何学习和预训策略,通过突变改善对蛋白质稳定性变化的预测
Yunxin Xu1,2, Di Liu1,2, Haipeng Gong3,4
1MOE Key Laboratory of Bioinformatics, School of Life Sciences, Tsinghua University, Beijing, China.
Nature computational science
|October 25, 2024
概括
GeoStab套件介绍了三种几何学习模型,用于预测蛋白质突变效应. 这些模型,GeoFitness,GeoDDG和GeoDTm,在预测健身成绩和稳定性变化方面表现出卓越的表现.
科学领域:
- 计算生物学 计算生物学
- 结构生物信息学 结构生物信息学
- 机器学习在生物学中的应用
背景情况:
- 预测蛋白质突变效应对于蛋白质工程和设计至关重要.
- 现有方法面临的挑战是,对于特定预测的数据稀缺,例如 ΔΔG 和 ΔTm.
研究的目的:
- 开发GeoStab-suite,这是一个新的几何学习模型套件,用于预测蛋白质突变效应.
- 为了提高健身成绩的预测准确度, ΔΔG 和 ΔTm.
主要方法:
- 开发了使用几何学习的GeoFitness,GeoDDG和GeoDTm模型.
- 为 GeoFitness 采用专门的损失功能,以利用多标签的深度突变扫描数据.
- 利用 GeoDDG 和 GeoDTm 的 GeoFitness 编码器进行预训练策略,以解决数据限制.
主要成果:
- GeoFitness允许在广泛的健身数据上进行监督训练.
- 预培训策略显著提高了GeoDDG和GeoDTm的性能和通用性.
- 在斯皮尔曼相关性中,GeoDDG和GeoDTm的性能至少比最先进的方法高出30%和70%.
结论:
- GeoStab套件为预测蛋白质突变影响提供了一种强大而准确的方法.
- 拟议的预训练策略有效地克服了在预测蛋白质稳定性变化方面的数据短缺问题.
- 这些模型通过改进的预测能力推动了蛋白质工程和设计领域的发展.
相关概念视频
Protein Folding
7.8K
Proteins are chains of amino acids linked together by peptide bonds. Upon synthesis, a protein folds into a three-dimensional conformation, critical to its biological function. Interactions between its constituent amino acids guide protein folding, and hence the protein structure is primarily dependent on its amino acid sequence.
Protein Structure Is Critical to Its Biological Function
Proteins perform a wide range of biological functions such as catalyzing chemical reactions, providing...
Protein Structure Is Critical to Its Biological Function
Proteins perform a wide range of biological functions such as catalyzing chemical reactions, providing...
7.8K
Conserved Binding Sites
4.2K
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...
4.2K
Protein Organization
6.3K
Proteins are polymers of amino acid residues. They are versatile and responsible for different cellular functions, including DNA replication, molecular transport, catalysis, and structural support. Proteins have a hierarchical structure comprising at least three levels of organization: primary, secondary, and tertiary structure. Some large proteins have a quaternary structure where individual protein subunits are linked together.
The primary structure of a protein is its amino acid sequence....
The primary structure of a protein is its amino acid sequence....
6.3K
Protein Denaturation
4.0K
The function of proteins depends on their native three-dimensional structure, which is dictated by the amino acid sequence of the specific protein. Folding of the polypeptide chain takes place under specific conditions that energetically favor the folded conformation. In contrast, protein denaturation occurs spontaneously under unfavorable conditions that disrupt the integrity of the folded conformation. Thus, the chemical and physical environment of a protein, such as significant changes in pH...
4.0K
Mutations
80.6K
Overview
80.6K
Conservation of Protein Domains Over Different Proteins
10.8K
Protein domains are small structurally independent units that are part of a single amino acid chain. Although these domains are often structurally independent, they may rely on synergistic effects to perform their functions as part of a larger protein. Protein domains may be conserved within the same organism, as well as across different organisms.
A limited set of protein domains often duplicate and recombine during evolution. These domains can be organized in different combinations to...
A limited set of protein domains often duplicate and recombine during evolution. These domains can be organized in different combinations to...
10.8K


