使用蛋白质语言模型和图形神经网络预测裂部位
Paula Cifuentes1,2, Ramon Adàlia3,4, Ismael Zamora3
1Universitat Pompeu Fabra, 08003, Barcelona, Spain. paula.cifuentes01@estudiant.upf.edu.
Scientific reports
|October 31, 2025
概括
预测裂部位对于药物开发至关重要. 使用蛋白质语言模型和图形神经网络的新in silico方法提高了准确性,特别是在含有非天然氨基酸的复杂循环上.
科学领域:
- 制药科学 制药科学
- 计算生物学 计算生物学
- 生物技术是生物技术.
背景情况:
- 类治疗药物具有很高的选择性和有效性,但由于其低生物可用性和蛋白酶敏感性,在口服时面临挑战.
- 目前用于预测裂部位的in silico方法依赖于手动特征工程,限制了它们分析复杂结构的能力,例如循环或非天然氨基酸含.
研究的目的:
- 开发新的in silico方法来准确预测裂部位,克服现有方法的局限性.
- 通过改进in silico分析工具来加强基于的治疗药物的开发.
主要方法:
- 微调蛋白质语言模型 (ESM-2) 以利用已学习的结构嵌入来预测裂变部位,而无需手动特征工程.
- 使用图形神经网络 (GNN) 与等级原子和氨基酸水平图表来表示和分析复杂的结构,包括含非天然氨基酸的循环.
主要成果:
- 蛋白质语言模型方法通过利用预训练的结构嵌入来有效地预测裂变部位.
- 该GNN方法证明了处理复杂的循环结构的能力,通过一项案例研究验证,将in silico预测与非天然氨基酸含有循环的实验数据进行比较.
结论:
- 新的in silico方法,包括蛋白质语言模型和图形神经网络,在裂部位预测方面取得了重大进展.
- 这些改进的计算工具对于优化类药物开发至关重要,特别是对于复杂的类模式.
相关概念视频
Ligand Binding Sites
14.9K
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...
14.9K
Protein-protein Interfaces
14.4K
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...
14.4K
Protein Networks
4.5K
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,...
4.5K
Protein Networks
2.8K
2.8K
Peptide Bonds
81.9K
A peptide bond covalently attaches amino acids through a dehydration reaction. One amino acid's carboxyl group and another amino acid's amino group combine, releasing a water molecule. The resulting bond is the peptide bond. The products that such linkages form are peptides. As more amino acids join this growing chain, the resulting chain is a polypeptide. Each polypeptide has a free amino group at one end. This end has the N-terminal, or the amino-terminal, and the other end has a free...
81.9K
Conserved Binding Sites
5.0K
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...
5.0K


