通过本地配对改进抗体语言模型
Sarah M Burbach1,2,3, Bryan Briney1,2,3,4,5
1Department of Immunology and Microbiology, The Scripps Research Institute, La Jolla, CA 92037, USA.
Patterns (New York, N.Y.)
|May 27, 2024
概括
用本地配对的序列训练抗体语言模型可以提高性能,并揭示免疫特征. 这种方法提高了病原体特异性分类,而不是在未配对或随机配对数据上训练的模型.
科学领域:
- 计算生物学是一种计算生物学.
- 免疫信息学是指免疫信息学.
- 机器学习在免疫学中的应用
背景情况:
- 目前的抗体语言模型通常使用未配对的序列数据,限制它们捕获关键链际关系的能力.
- 大量的原生配对的人类抗体序列数据集为推进抗体建模提供了新的资源.
研究的目的:
- 为了评估训练抗体语言模型与原生配对序列相比不配对或随机配对序列的影响.
- 评估本地配对是否使模型能够学习跨链免疫特征,并提高下游任务的性能.
主要方法:
- 训练了三个基线抗体语言模型 (BALM),使用原生配对,随机配对和未配对的序列.
- 精心调整了进化规模建模 (ESM) -2 模型与原生配对的抗体序列.
- 在各种指标上评估模型性能,包括根据病原体特异性对抗体的分类.
主要成果:
- 用原生配对序列训练的模型学习了跨越轻重链的免疫学相关特征.
- 与随机或未配对训练相比,本地配对显著改善了模型性能.
- 观察到基于病原体特异性的抗体分类能力提高.
结论:
- 使用原生配对序列训练抗体语言模型优于使用未配对或随机配对数据.
- 原生配对促进了关键链间抗体特征的学习,从而提高了预测能力.
- 这种方法促进了更准确,更有效的抗体预测模型的开发.
更多相关视频
03:14Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
Published on: December 6, 2024
544
10:00Methods of Pairing and Pair Maintenance of New Zealand White Rabbits Oryctolagus Cuniculus Via Behavioral Ethogram, Monitoring, and Interventions
Published on: March 16, 2018
14.0K
相关概念视频
01:41Affinity and Avidity
36.0K
Overview
36.0K
01:31Hybridoma Technology
14.7K
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,...
Hybridoma Selection
Commonly used fusion techniques — electroporation,...
14.7K
01:10Antibody Structure
60.1K
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...
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...
60.1K
02:07Improving Translational Accuracy
10.1K
Base complementarity between the three base pairs of mRNA codon and the tRNA anticodon is not a failsafe mechanism. Inaccuracies can range from a single mismatch to no correct base pairing at all. The free energy difference between the correct and nearly correct base pairs can be as small as 3 kcal/ mol. With complementarity being the only proofreading step, the estimated error frequency would be one wrong amino acid in every 100 amino acids incorporated. However, error frequencies observed in...
10.1K