An in silico method to assess antibody fragment polyreactivity.

An in silico method to assess antibody fragment polyreactivity.
复制标题

DOI:
10.1038/s41467-022-35276-4
复制
发表时间:
2022-12-07
影响因子:
16.6
通讯作者:
Kruse, Andrew C.
Kruse, Andrew C.
中科院分区:
综合性期刊1区
文献类型:
--
作者:
Harvey, Edward P.;Shin, Jung-Eun;Skiba, Meredith A.;Nemeth, Genevieve R.;Hurley, Joseph D.;Wellner, Alon;Shaw, Ada Y.;Miranda, Victor G.;Min, Joseph K.;Liu, Chang C.;Marks, Debora S.;Kruse, Andrew C.

文献摘要

参考文献

相似文献

抗体是必不可少的生物研究工具和重要的治疗剂,但有些抗体表现出与脱靶蛋白和其他生物分子的非特异性结合。这种多反应性抗体损害筛选管道,导致不正确和不可再现的实验结果,并且通常难以用于临床开发。在这里,我们设计了一组实验,使用不同的天然合成骆驼抗体片段(纳米抗体)库,使机器学习模型能够准确评估蛋白质序列的多反应性(AUC > 0.8)。此外,我们的模型提供了定量评分指标,预测氨基酸取代对多反应性的影响。我们在三个独立的纳米抗体支架上实验测试了我们的模型的性能,其中超过90%的预测取代成功地降低了多反应性。重要的是,这些模型使我们能够减少血管紧张素II I型受体拮抗剂纳米抗体的多反应性,而不损害其功能特性。我们提供了一个配套的网络服务器,提供了一个简单的方法来预测任何给定的纳米抗体序列的多反应性和多反应性降低突变。脱靶结合阻碍了治疗性抗体的开发和基础研究环境中的再现性。在这里,作者开发了一种方法来量化和减少基于蛋白质序列单独的抗体片段的多反应性。
Antibodies are essential biological research tools and important therapeutic agents, but some exhibit non-specific binding to off-target proteins and other biomolecules. Such polyreactive antibodies compromise screening pipelines, lead to incorrect and irreproducible experimental results, and are generally intractable for clinical development. Here, we design a set of experiments using a diverse naïve synthetic camelid antibody fragment (nanobody) library to enable machine learning models to accurately assess polyreactivity from protein sequence (AUC > 0.8). Moreover, our models provide quantitative scoring metrics that predict the effect of amino acid substitutions on polyreactivity. We experimentally test our models’ performance on three independent nanobody scaffolds, where over 90% of predicted substitutions successfully reduced polyreactivity. Importantly, the models allow us to diminish the polyreactivity of an angiotensin II type I receptor antagonist nanobody, without compromising its functional properties. We provide a companion web-server that offers a straightforward means of predicting polyreactivity and polyreactivity-reducing mutations for any given nanobody sequence. Off-target binding hinders the development of therapeutic antibodies and reproducibility in basic research settings. Here the authors develop a method to quantify and reduce the polyreactivity of antibody fragments based on protein sequence alone.
DOI: 10.1128/jb.145.1.382-390.1981
发表时间: 1981-01-01
影响因子: 3.2
作者:
GUNGE, N;TAMARU, A;SAKAGUCHI, K
通讯作者: SAKAGUCHI, K
DOI: 10.1038/nprot.2007.13
发表时间: 2007-01-01
期刊: NATURE PROTOCOLS
影响因子: 14.8
作者:
Gietz, R. Daniel;Schiestl, Robert H.
通讯作者: Schiestl, Robert H.
DOI: 10.7554/elife.61393
发表时间: 2020-11-10
期刊: eLife
影响因子: 7.7
作者:
Boughter CT;Borowska MT;Guthmiller JJ;Bendelac A;Wilson PC;Roux B;Adams EJ
通讯作者: Adams EJ
DOI: 10.1093/bioinformatics/btv552
发表时间: 2016-01-15
期刊: BIOINFORMATICS
影响因子: 5.8
作者:
Dunbar, James;Deane, Charlotte M.
通讯作者: Deane, Charlotte M.
DOI: 10.1016/j.jmb.2008.01.093
发表时间: 2008-04-11
影响因子: 5.6
作者:
Birtalan, Sara;Zhang, Yingnan;Sidhu, Sachdev S.
通讯作者: Sidhu, Sachdev S.