Biologics Engineering, R&D, AstraZeneca, Gaithersburg, MD, USA.
Program in Molecular Biophysics, The Johns Hopkins University, Baltimore, MD, USA.
MAbs. 2024 Jan-Dec;16(1):2362775. doi: 10.1080/19420862.2024.2362775. Epub 2024 Jun 20.
Over the past two decades, therapeutic antibodies have emerged as a rapidly expanding domain within the field of biologics. tools that can streamline the process of antibody discovery and optimization are critical to support a pipeline that is growing more numerous and complex every year. High-quality structural information remains critical for the antibody optimization process, but antibody-antigen complex structures are often unavailable and antibody docking methods are still unreliable. In this study, DeepAb, a deep learning model for predicting antibody Fv structure directly from sequence, was used in conjunction with single-point experimental deep mutational scanning (DMS) enrichment data to design 200 potentially optimized variants of an anti-hen egg lysozyme (HEL) antibody. We sought to determine whether DeepAb-designed variants containing combinations of beneficial mutations from the DMS exhibit enhanced thermostability and whether this optimization affected their developability profile. The 200 variants were produced through a robust high-throughput method and tested for thermal and colloidal stability (T, T, T), affinity (K) relative to the parental antibody, and for developability parameters (nonspecific binding, aggregation propensity, self-association). Of the designed clones, 91% and 94% exhibited increased thermal and colloidal stability and affinity, respectively. Of these, 10% showed a significantly increased affinity for HEL (5- to 21-fold increase) and thermostability (>2.5C increase in T), with most clones retaining the favorable developability profile of the parental antibody. Additional tests suggest that these methods would enrich for binding affinity even without first collecting experimental DMS measurements. These data open the possibility of antibody optimization without the need to predict the antibody-antigen interface, which is notoriously difficult in the absence of crystal structures.
在过去的二十年中，治疗性抗体已成为生物制品领域中迅速发展的领域。能够简化抗体发现和优化过程的工具对于支持每年数量和复杂性不断增加的管道至关重要。高质量的结构信息仍然是抗体优化过程的关键，但抗体-抗原复合物结构通常不可用，抗体对接方法仍然不可靠。在这项研究中，DeepAb 是一种直接从序列预测抗体 Fv 结构的深度学习模型，与单点实验深度突变扫描 (DMS) 富集数据结合使用，用于设计 200 种潜在优化的抗鸡卵溶菌酶 (HEL) 抗体变体。我们试图确定是否包含 DMS 中有益突变组合的 DeepAb 设计变体表现出增强的热稳定性，以及这种优化是否会影响其可开发性。通过稳健的高通量方法生产了这 200 个变体，并对其进行了热和胶体稳定性 (T、T、T)、与亲本抗体的亲和力 (K) 以及可开发性参数 (非特异性结合、聚集倾向、自缔合) 的测试。在设计的克隆中，91%和 94%分别表现出热稳定性和胶体稳定性的增加，分别提高了 91%和 94%。其中，10%表现出对 HEL 的亲和力显著增加（5-21 倍增加）和热稳定性（T 增加>2.5°C），大多数克隆保留了亲本抗体的有利可开发性。进一步的测试表明，即使没有首先收集实验 DMS 测量值，这些方法也会富集结合亲和力。这些数据为无需预测抗体-抗原界面即可进行抗体优化打开了可能性，而在没有晶体结构的情况下，预测抗体-抗原界面是非常困难的。
