相关实验视频

Updated: Sep 17, 2025

Peptide Scanning-assisted Identification of a Monoclonal Antibody-recognized Linear B-cell Epitope

Peptide Scanning-assisted Identification of a Monoclonal Antibody-recognized Linear B-cell Epitope

Published on: March 24, 2017

抗BMPNN:结构引导图形神经网络用于精密抗体工程

Ze-Yu Sun^1,2, Jiayi Yuan², Divya Jaiswal²

¹College of Pharmacology Sciences, Zhejiang University of Technology, Hangzhou, 310014, P. R. China.

Advanced science (Weinheim, Baden-Wurttemberg, Germany)

|June 27, 2025

概括

与现有方法相比,新的深度学习框架AntiBMPNN显著提高了抗体序列设计准确性和结合亲和力. 这一进步为开发更有效的治疗抗体带来了巨大的潜力.

科学领域:

生物技术是生物技术.
计算生物学计算生物学
免疫学免疫学免疫学

背景情况:

传统的抗体序列设计方法是低效的.
抗体对于各种医疗应用至关重要.

研究的目的:

介绍AntiBMPNN,一个新的深度学习框架,用于高精度的抗体序列设计.
评估AntiBMPNN的性能与现有的最先进的方法相比.

主要方法:

利用一种针对抗体的3D数据集和一个微调的消息传递神经网络 (MPNN).
加入了基于频率的评分功能和AlphaFold 3用于序列优先级.
用于单点抗体设计和结合亲和度评估的实验验证.

主要成果:

抗BMPNN实现了80%以上的序列恢复和1.5的困难度,超过了ProteinMPNN.
在单点抗体设计中表现出75%的成功率.
设计的序列具有显著增强的结合亲和力,特别是特定纳米体的CDR1,CDR2和CDR3区域,超过了多个基准.

结论:

抗BMPNN代表了抗体序列设计的重大进步,提供了卓越的准确性和结合能力.
该框架能够设计高亲和度抗体,并通过实验验证,这突显了其在治疗性抗体开发方面具有革命性的潜力.

关键词:

深度学习是一种深度学习.传递信息的神经元网络 (MPNN)精确抗体工程精确抗体工程序列设计设计的设计.

更多相关视频

Rapid Antibody Glycoengineering in Chinese Hamster Ovary Cells

Rapid Antibody Glycoengineering in Chinese Hamster Ovary Cells

Published on: June 2, 2022

Scalable High Throughput Selection From Phage-displayed Synthetic Antibody Libraries

Scalable High Throughput Selection From Phage-displayed Synthetic Antibody Libraries

Published on: January 17, 2015

相关概念视频

Antibody Structure

Antibody Structure

Overview
Antibodies, also known as immunoglobulins (Ig), are essential players of the adaptive immune system. These antigen-binding proteins are produced by B cells and make up 20 percent of the total blood plasma by weight. In mammals, antibodies fall into five different classes, which each elicits a different biological response upon antigen binding.
The Y-Shaped Structure of Antibodies Consists of Four Polypeptide Chains
Antibodies consist of four polypeptide chains: two identical heavy...