相关实验视频

Updated: Jan 17, 2026

Efficient and Site-specific Antibody Labeling by Strain-promoted Azide-alkyne Cycloaddition

Efficient and Site-specific Antibody Labeling by Strain-promoted Azide-alkyne Cycloaddition

Published on: December 23, 2016

abCAN:一个实用且新的关注网络,用于预测突变抗体亲和力

Chen Gong^1,2, Nan Weng², Hongjia Liu²

¹Jiangsu Key Laboratory of Intelligent Medical Image Computing, School of Artificial Intelligence, Nanjing University of Information Science and Technology, 219 Ning Liu Road, Nanjing 210044, China.

Briefings in bioinformatics

|September 18, 2025

概括

abCAN使用一种新的注意力网络准确地预测了对抗体-抗原结合亲和力的突变效应. 该方法通过系统地整合结构和序列数据来提高抗体工程和药物设计,以准确预测结合亲和力变化.

科学领域:

计算生物学计算生物学
结构生物学结构生物学
免疫信息学是指免疫信息学.

背景情况:

对抗体-抗原相互作用的突变效应的准确预测对于开发有效的基于抗体的治疗方法至关重要.
现有的方法往往难以捕捉影响结合亲和力的结构性和序列性特征之间的复杂相互作用.

研究的目的:

开发一种新的深度学习模型,abCAN,用于预测由于突变而导致的抗体-抗原结合亲和力的变化.
在抗体-抗原系统中建立一种新的突变效应预测的先进基准.

主要方法:

开发了abCAN,一个使用渐进编码集成结构,残留级和顺序信息的注意网络.
使用注意力机制来优先考虑接口残留物.
在抗体-抗原复杂结构和突变数据上训练模型,以预测结合亲和力变化.

主要成果:

在一组基准测试中,abCAN实现了1.460 (kcal/mol) 的平方根平均误差.
获得了0.731的皮尔森相关系数,证明了高预测准确度.
该模型为预测突变诱导的亲和力变化设定了新的最先进的性能.

结论:

abCAN提供了一种实用且准确的方法,用于预测对抗体-抗原结合亲和力的突变效应.
渐进编码方法有效地捕捉复杂的相互作用,推进抗体工程和药物设计.
开发的模型和相关资源是公开的,以促进进一步的研究.

关键词:

抗体亲和力抗体亲和力抗体抗原相互作用人工智能 (AI) 是一种人工智能.深度学习是一种深度学习.蛋白质结构表示蛋白质结构表示

更多相关视频

Author Spotlight: A Computational Approach to Decipher Amino Acid Preferences in Multispecific Protein-Protein Interactions

Author Spotlight: A Computational Approach to Decipher Amino Acid Preferences in Multispecific Protein-Protein Interactions

Published on: January 26, 2024

Detection of Antibodies That Neutralize the Cellular Uptake of Enzyme Replacement Therapies with a Cell-based Assay

Detection of Antibodies That Neutralize the Cellular Uptake of Enzyme Replacement Therapies with a Cell-based Assay

Published on: September 10, 2018

相关概念视频

Affinity and Avidity

Affinity and Avidity

Protein Networks

Protein Networks

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,...