预先训练的抗体语言模型的监督微调可以改善抗原特异性预测
Meng Wang1, Jonathan Patsenker2, Henry Li2
1Program in Computational Biology and Bioinformatics, Yale University, New Haven, Connecticut, United States of America.
bioRxiv : the preprint server for biology
|May 27, 2024
概括
监督微调增强了用于预测抗体-抗原特异性的抗体语言模型. 这种方法提高了对疫苗和病原体的免疫反应识别的准确性.
科学领域:
- 免疫学 免疫学 免疫学
- 生物信息学是一种生物信息学.
- 计算生物学 计算生物学
背景情况:
- 抗体是适应性免疫的关键,调解B细胞特异性和病原体向.
- 从测序数据中预测抗体-抗原特异性有助于理解免疫力,疫苗设计和治疗方法.
研究的目的:
- 为抗体语言模型提供监督微调方法,以改善抗原特异性预测.
- 与以前的方法相比,评估微调模型的增强预测准确度.
主要方法:
- 对四个预先训练的抗体语言模型进行了监督微调.
- 模型被训练来预测SARS-CoV-2尖端蛋白和流感血素的特异性.
- 分析了模型注意力激活,以了解性能驱动因素.
主要成果:
- 微调的抗体语言模型分类器显示了对抗原特异性的预测准确度的提高.
- 在微调后,观察到模型对互补性确定区域 (CDR) 的关注度增加.
- 模型成功地在接种疫苗后的BCR数据中识别了特定的免疫反应.
结论:
- 监督微调是一种有益的机制,用于增强预训练的抗体语言模型.
- 改进的模型可以准确预测抗体-抗原特异性,并识别疫苗引起的免疫反应.
- 这种方法有望促进疫苗设计和基于抗体的治疗方法的发展.
相关概念视频
02:07Improving Translational Accuracy
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...
02:07Improving Translational Accuracy
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...