Co-optimization of therapeutic antibody affinity and specificity using machine learning models that generalize to novel mutational space.
Co-optimization of therapeutic antibody affinity and specificity using machine learning models that generalize to novel mutational space.
复制标题
使用机器学习模型对治疗性抗体亲和力和特异性进行共优化，该模型推广到新的突变空间。
DOI：
10.1038/s41467-022-31457-3
复制
发表时间：
2022-07-01
影响因子：
16.6
通讯作者：
中科院分区：
文献类型：
--
作者：
治疗性抗体的开发需要选择和工程分子具有高亲和力和其他类似药物的生物物理性质。多种抗体特性的协同优化仍然是一个困难和耗时的过程，阻碍了药物的开发。在这里，我们评估了机器学习的使用，以简化临床阶段抗体（emibetuzumab）的抗体协同优化，该抗体显示出高水平的靶上（抗原）和靶外（非特异性）结合。我们对抗体互补决定区域的位点进行突变，对抗体文库进行高亲和力和低亲和力和非特异性结合的排序，并对富集的文库进行深度测序。有趣的是，在带有二元标签的数据集上训练的机器学习模型能够预测与抗体亲和力和非特异性结合密切相关的连续指标。这些模型说明了这两种特性之间的强烈权衡，因为沿共同最优（帕累托）边界的亲和力增加需要特异性的逐步降低。值得注意的是，使用深度学习特征训练的模型能够预测新的抗体突变，这些突变可以共同优化原始抗体库的亲和力和特异性。这些发现证明了机器学习模型的强大功能，可以极大地扩展对新型抗体序列空间的探索，并加速开发高效的药物样抗体。优化抗体特性，如亲和力，可能对其他关键特性有害。在这里，作者使用机器学习来简化具有共同最佳亲和力和特异性水平的抗体的鉴定，以用于显示高水平的靶向和脱靶结合的临床阶段抗体。
Therapeutic antibody development requires selection and engineering of molecules with high affinity and other drug-like biophysical properties. Co-optimization of multiple antibody properties remains a difficult and time-consuming process that impedes drug development. Here we evaluate the use of machine learning to simplify antibody co-optimization for a clinical-stage antibody (emibetuzumab) that displays high levels of both on-target (antigen) and off-target (non-specific) binding. We mutate sites in the antibody complementarity-determining regions, sort the antibody libraries for high and low levels of affinity and non-specific binding, and deep sequence the enriched libraries. Interestingly, machine learning models trained on datasets with binary labels enable predictions of continuous metrics that are strongly correlated with antibody affinity and non-specific binding. These models illustrate strong tradeoffs between these two properties, as increases in affinity along the co-optimal (Pareto) frontier require progressive reductions in specificity. Notably, models trained with deep learning features enable prediction of novel antibody mutations that co-optimize affinity and specificity beyond what is possible for the original antibody library. These findings demonstrate the power of machine learning models to greatly expand the exploration of novel antibody sequence space and accelerate the development of highly potent, drug-like antibodies. Optimising antibody properties such as affinity can be detrimental to other key properties. Here the authors use machine learning to simplify the identification of antibodies with co-optimal levels of affinity and specificity for a clinical-stage antibody that displays high levels of on- and off-target binding.
登录
查看更多内容
DOI：
10.1073/pnas.89.22.10915
发表时间：
1992-11-15
影响因子：
11.1
作者：
HENIKOFF, S;HENIKOFF, JG
通讯作者：
HENIKOFF, JG
影响因子：
5.3
作者：
Bailly, Marc;Mieczkowski, Carl;Fayadat-Dilman, Laurence
通讯作者：
Fayadat-Dilman, Laurence
DOI：
10.1073/pnas.0901522106
发表时间：
2009-06-16
影响因子：
11.1
作者：
Bloom, Jesse D.;Arnold, Frances H.
通讯作者：
Arnold, Frances H.
影响因子：
48
作者：
Alley, Ethan C.;Khimulya, Grigory;Church, George M.
通讯作者：
Church, George M.
DOI：
10.1093/protein/gzv029
发表时间：
2015-09
期刊：
Protein engineering, design & selection : PEDS
影响因子：
--
作者：
Houlihan G;Gatti-Lafranconi P;Lowe D;Hollfelder F
通讯作者：
Hollfelder F