基于结构的预测,由蛋白质语言模型和深度学习对符合B细胞表皮质的预测
Yuhao Zhang1, Zhaoqian Su1,2, Felipe Vilicich3
1Data Science Institute, Vanderbilt University, Nashville, 37212, TN, USA.
bioRxiv : the preprint server for biology
|November 24, 2025
概括
一个新的以补丁为中心的框架使用蛋白质语言模型 (PLM) 准确地预测抗原上的B细胞表位. 该方法通过识别抗原结构上的关键结合区域来帮助抗体发现,工程和疫苗设计.
科学领域:
- 免疫学 免疫学 免疫学
- 计算生物学 计算生物学
- 结构生物学 结构生物学
背景情况:
- 绘制B细胞表位对抗体发现至关重要,但由于实验成本和当前计算工具的局限性,仍然具有挑战性.
- 现有的计算方法经常在抗体-抗原识别方面扎,在特定接口上表现不佳.
- 准确的表位预测对于推进抗体工程和疫苗开发至关重要.
研究的目的:
- 引入一种新的以补丁为中心的计算框架,用于直接在抗原结构上预测B细胞表位.
- 评估蛋白质语言模型 (PLM) 方法与卷积神经网络 (CNN) 基线进行表位预测的性能.
- 开发一种可解释的方法来识别和优先考虑B细胞表位,以帮助抗体发现和疫苗设计.
主要方法:
- 开发了一个以补丁为中心的框架,将表观物定义为捕捉局部形状和化学成分的邻近残留物三元体.
- 评估了两个分类器:一个PLM (ESM-2嵌入) 和一个CNN使用手工制作的功能.
- 从AbDb数据库中对1,151个抗体-抗原复合体进行了训练和验证模型,使用五倍交叉验证.
主要成果:
- 在补丁级别上,PLM分类器的表现明显优于CNN (F1 ≈ 0.986,ROC-AUC ≈ 0.998).
- 从补丁得分汇总的残留智能性能显示了PLM的优异结果 (ROC-AUC 0.689±0.072与0.548±0.018对比).
- 在基准数据集上,PLM实现了最先进的性能,并且很好地对外部复合体进行了概括 (ROC-AUC 0.663).
结论:
- 以补丁为中心的PLM框架为B细胞表位预测提供了一种强大而准确的方法.
- 该模型提供可解释的表位概率图,促进抗原优先级和抗体工程.
- 这种方法代表了抗体发现,疫苗设计和相关生物技术应用的实际进步.
相关概念视频
02:50Conjugated Proteins
27.4K
Simple proteins and protein complexes contain only amino acids. In contrast, many other proteins, called conjugated proteins, covalently bond with non-protein moieties.
Nucleoproteins are protein complexes that contain nucleic acids, categorized as deoxyribonucleoproteins (DNPs) or ribonucleoproteins (RNPs) respectively. The nucleosome is a typical example of a DNP where nuclear DNA is associated with histone proteins. The major antigen for the Covid-19 virus SARS-CoV is an RNP that is critical...
Nucleoproteins are protein complexes that contain nucleic acids, categorized as deoxyribonucleoproteins (DNPs) or ribonucleoproteins (RNPs) respectively. The nucleosome is a typical example of a DNP where nuclear DNA is associated with histone proteins. The major antigen for the Covid-19 virus SARS-CoV is an RNP that is critical...
27.4K
01:49Conserved 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
02:40Ligand Binding Sites
14.8K
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...
14.8K
01:24B Cell Activation and Differentiation
15.8K
The adaptive immune response, a sophisticated defense mechanism, relies on the activation and differentiation of B lymphocytes, or B cells. These processes enable our bodies to mount a tailored response against specific pathogens such as bacteria, free virus particles, toxins, and parasites.
When naive B cells encounter a specific antigen that can bind to the B cell receptor (BCR) on their surface, they undergo sensitization to respond to the antigen's presence. Sensitization begins with...
When naive B cells encounter a specific antigen that can bind to the B cell receptor (BCR) on their surface, they undergo sensitization to respond to the antigen's presence. Sensitization begins with...
15.8K
01:24Protein Organization
9.0K
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....
9.0K