Search research articles

关于 JoVE

概览领导团队博客 JoVE 帮助中心

作者

出版流程编辑委员会范围与政策同行评审常见问题投稿

图书馆员

用户评价订阅访问资源图书馆顾问委员会常见问题

研究

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments 存档

教育

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual 教师资源中心教师网站

使用条款与条件

相关概念视频

Hybridoma Technology

Hybridoma Technology

Hybridoma technology is used for the large-scale production of monoclonal antibodies. Monoclonal antibodies bind to only a single antigenic determinant or epitope. Such antibodies are used in research, diagnostics, and disease therapy. The hybridoma technology established in 1975 by Georges Köhler and Cesar Milstein was awarded the Nobel Prize in Medicine in 1984 for revolutionizing research and therapy.
Hybridoma Selection
Commonly used fusion techniques — electroporation,...

您也可能阅读

相关文章

通过共同作者、期刊和引用图与本文相关的文章。

排序

Same author

Mechanism of claudin-2 in RTECs apoptosis after renal obstruction.

Urolithiasis·2026

Same author

Pancreatic Metastasis from Intracranial Solitary Fibrous Tumor/Hemangiopericytoma Mimicking a Pancreatic Neuroendocrine Tumor: A Case Report and Focused Literature Review.

Current oncology (Toronto, Ont.)·2026

Same author

Explaining rural-urban disparities in child stunting in African least developed countries: a multi-country cross-sectional analysis.

International journal for equity in health·2026

Same author

Apoptosis, Pyroptosis, and Necroptosis (PANoptosis) may be Present in Renal Ischemic Injury.

Current medicinal chemistry·2026

Same author

Advances in Nanozyme Engineering for Precision Oral Health Management.

International dental journal·2026

Same author

Targeted Protein Degradation and Delivery Strategies in the Context of Neurological Disorders.

ACS nano·2026

Search research articles

相关实验视频

Updated: Jul 8, 2025

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

通过大型语言模型改进生成对抗网络的抗体优化能力.

Wenbin Zhao¹, Xiaowei Luo¹, Fan Tong¹

¹Academy of Military Medical Sciences, Beijing 100850, China.

Computational and structural biotechnology journal

|December 11, 2023

概括

我们开发了AbGAN-LMG,这是一个新的生成对抗网络 (GAN),它使用语言模型来创建高质量的抗体序列. 这种方法改善了抗体优化,并产生了多样化的,可开发的抗体,对SARS-CoV-2具有更高的结合亲和力.

关键词:

抗体优化优化抗体优化生成的对抗网络产生性的对抗网络语言模型语言模型

更多相关视频

Antigenic Liposomes for Generation of Disease-specific Antibodies

Antigenic Liposomes for Generation of Disease-specific Antibodies

Published on: October 25, 2018

Generation of Murine Monoclonal Antibodies by Hybridoma Technology

Generation of Murine Monoclonal Antibodies by Hybridoma Technology

Published on: January 2, 2017

相关实验视频

Last Updated: Jul 8, 2025

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

Antigenic Liposomes for Generation of Disease-specific Antibodies

Antigenic Liposomes for Generation of Disease-specific Antibodies

Published on: October 25, 2018

Generation of Murine Monoclonal Antibodies by Hybridoma Technology

Generation of Murine Monoclonal Antibodies by Hybridoma Technology

Published on: January 2, 2017

科学领域:

计算生物学计算生物学
免疫信息学是指免疫信息学.
人工智能在药物发现中的作用

背景情况:

生成对抗网络 (GAN) 可以创建功能蛋白序列,但往往缺乏特异性,阻碍了理想抗体的识别.
由于实验验证的高成本,通过计算优化抗体至关重要,但提高GAN以产生高质量的候选者仍然是一个挑战.

研究的目的:

引入和评估语言模型引导的抗体生成对抗网络 (AbGAN-LMG),以改进抗体序列生成.
利用语言模型的代表性力量来增强GANs生产高质量,可开发抗体候选者的能力.

主要方法:

开发了AbGAN-LMG,这是一个新的GAN架构,将语言模型作为输入.
通过生成针对SARS-CoV-2和MERS-CoV的抗体库和序列来评估AbGAN-LMG的性能.
通过分子对接来评估序列质量,库的多样性,可开发性和结合性亲和力.

主要成果:

AbGAN-LMG成功地学习了基本抗体特性,并增加了生成的抗体库的多样性.
与原始抗体相比,针对AZD-8895的产生的抗体序列中,超过50%的抗体呈现出优越的发育能力.
确定了70个候选抗体,它们与SARS-CoV-2受体结合域 (RBD) 的结合亲和力比AZD-8895高.

结论:

正如AbGAN-LMG所示,将语言模型与GAN集成,可以显著增强生成高质量的抗体库和候选序列.
AbGAN-LMG提高了抗体优化的效率,为抗体发现和开发提供了一个有前途的计算工具.
AbGAN-LMG模型是公开可用的,用于进一步的研究和应用在抗体工程.