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

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

GSK3α functions as a stemness checkpoint across multiple stem cell states.

Cell research·2026

Same author

Catalytic role of the axial cysteine ligand in nitrile hydratases.

Journal of inorganic biochemistry·2026

Same author

Structural and mechanistic insights into the sulfur transfer protein SufU from Staphylococcus aureus.

Journal of inorganic biochemistry·2025

Same author

H3K27me3 chromatin heterogeneity reveals variable cell responses to estrogen and endocrine treatment.

bioRxiv : the preprint server for biology·2025

Same author

Cnot3 is required for male germ cell development and spermatogonial stem cell maintenance.

Development (Cambridge, England)·2025

Same author

Trimethylamine-<i>N</i>-Oxide Affects Cell Type-Specific Pathways and Networks in Mouse Aorta to Promote Atherosclerotic Plaque Vulnerability.

Arteriosclerosis, thrombosis, and vascular biology·2025

Search research articles

相关实验视频

Updated: Jun 22, 2025

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

基于序列的粘度预测用于快速抗体工程.

Bram Estes¹, Mani Jain¹, Lei Jia¹

¹Amgen Research, Protein Therapeutics, Thousand Oaks, CA 91320, USA.

|June 27, 2024

概括

此摘要是机器生成的。

机器学习确定了抗体序列与性质的相关性,创建了一个粘度预测模型. 这种模型加速了治疗抗体的工程,在16种变体中将粘度降低了62%.

关键词:

免疫球蛋白G (IgG) 是一种干白素13 (IL-13) 是一种干白素.mAbAb 在线观看机器学习是机器学习.预测模型是一个预测模型.蛋白质工程工程蛋白质工程蛋白质结构蛋白质结构治疗性抗体治疗性抗体粘度粘度粘度粘度粘度

更多相关视频

A High Throughput MHC II Binding Assay for Quantitative Analysis of Peptide Epitopes

A High Throughput MHC II Binding Assay for Quantitative Analysis of Peptide Epitopes

Published on: March 25, 2014

Identification of Mouse and Human Antibody Repertoires by Next-Generation Sequencing

Identification of Mouse and Human Antibody Repertoires by Next-Generation Sequencing

Published on: March 15, 2019

相关实验视频

Last Updated: Jun 22, 2025

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

A High Throughput MHC II Binding Assay for Quantitative Analysis of Peptide Epitopes

A High Throughput MHC II Binding Assay for Quantitative Analysis of Peptide Epitopes

Published on: March 25, 2014

Identification of Mouse and Human Antibody Repertoires by Next-Generation Sequencing

Identification of Mouse and Human Antibody Repertoires by Next-Generation Sequencing

Published on: March 15, 2019

科学领域:

生物技术是生物技术.
蛋白质工程是指蛋白质工程.
计算生物学计算生物学

背景情况:

高蛋白度配方对于有效的治疗提供至关重要.
抗体聚合和高粘度可能会限制治疗疗效和给药途径.
需要预测模型来指导蛋白质工程的努力,以改善配方特性.

研究的目的:

开发一种基于氨基酸序列的机器学习模型,用于预测基于氨基酸序列的抗体粘度.
应用基于结构的合理设计策略,结合in silico选来降低抗体粘度.
为了高效地设计一种高粘度的抗IL-13单克隆抗体候选者.

主要方法:

机器学习算法被用来识别抗体氨基酸序列及其物理特征之间的相关性.
基于结构的理性设计方法被用于生成具有预测较低粘度的抗体变体.
在实验验证之前使用in silico粘度预测工具来选和优先考虑工程变体.

主要成果:

成功开发了一种针对抗体内部粘度的预测模型.
产生了一个由16种高度粘性抗IL-13单克隆抗体的变异组.
综合策略有效地降低了抗IL-13抗体候选者的粘度,从34cP降至13cP在150mg/ml的剂量下.

结论:

将基于机器学习的粘度预测与理性设计相结合,加速了低粘度抗体疗法的工程.
这种方法可以有效地优化用于高度配方的抗体候选物.
开发的方法提供了一个强大的工具,可以提高治疗抗体的开发能力.