小柯机器人

瑞士洛桑联邦理工学院Bruno E. Correia等研究人员合作利用学习的表面指纹从头设计蛋白质的相互作用。该研究于2023年4月26日在线发表于国际一流学术期刊《自然》。

研究人员使用了一个在蛋白质表面操作的几何深度学习框架，该框架生成指纹来描述对驱动蛋白质-蛋白质相互作用至关重要的几何和化学特征。研究人员假设这些指纹捕捉到了分子识别的关键方面，并且代表了新型蛋白质相互作用的计算设计的新模式。作为一个原则性的证明，研究人员通过计算设计了几个新的蛋白质结合物，以接触四个蛋白质目标： SARS-CoV-2刺凸、PD-1、PD-L1和CTLA-4。一些设计经过了实验优化，而其他设计则是纯粹在计算中产生的，达到了纳摩尔的亲和力，其结构和突变特征显示了高度准确的预测。总的来说，研究人员以表面为中心的方法抓住了分子识别的物理和化学决定因素，使其能够从头设计蛋白质的相互作用，以及更广泛地设计具有功能的人工蛋白质。

据介绍，蛋白质之间的物理相互作用对管理生命的大多数生物过程是必不可少的。然而，即使在基因组学、蛋白质组学和结构数据增加的情况下，这种相互作用的分子决定因素一直是难以理解的。这一知识差距一直是全面了解细胞蛋白质-蛋白质相互作用网络和重新设计蛋白质结合物的主要障碍，这对合成生物学和转化应用至关重要。

附：英文原文

Title: De novo design of protein interactions with learned surface fingerprints

Author: Gainza, Pablo, Wehrle, Sarah, Van Hall-Beauvais, Alexandra, Marchand, Anthony, Scheck, Andreas, Harteveld, Zander, Buckley, Stephen, Ni, Dongchun, Tan, Shuguang, Sverrisson, Freyr, Goverde, Casper, Turelli, Priscilla, Raclot, Charlne, Teslenko, Alexandra, Pacesa, Martin, Rosset, Stphane, Georgeon, Sandrine, Marsden, Jane, Petruzzella, Aaron, Liu, Kefang, Xu, Zepeng, Chai, Yan, Han, Pu, Gao, George F., Oricchio, Elisa, Fierz, Beat, Trono, Didier, Stahlberg, Henning, Bronstein, Michael, Correia, Bruno E.

Issue&Volume: 2023-04-26

Abstract: Physical interactions between proteins are essential for most biological processes governing life1. However, the molecular determinants of such interactions have been challenging to understand, even as genomic, proteomic and structural data increase. This knowledge gap has been a major obstacle for the comprehensive understanding of cellular protein–protein interaction networks and for the de novo design of protein binders that are crucial for synthetic biology and translational applications2,3,4,5,6,7,8,9. Here we use a geometric deep-learning framework operating on protein surfaces that generates fingerprints to describe geometric and chemical features that are critical to drive protein–protein interactions10. We hypothesized that these fingerprints capture the key aspects of molecular recognition that represent a new paradigm in the computational design of novel protein interactions. As a proof of principle, we computationally designed several de novo protein binders to engage four protein targets: SARS-CoV-2 spike, PD-1, PD-L1 and CTLA-4. Several designs were experimentally optimized, whereas others were generated purely in silico, reaching nanomolar affinity with structural and mutational characterization showing highly accurate predictions. Overall, our surface-centric approach captures the physical and chemical determinants of molecular recognition, enabling an approach for the de novo design of protein interactions and, more broadly, of artificial proteins with function.

DOI: 10.1038/s41586-023-05993-x

Source: https://www.nature.com/articles/s41586-023-05993-x

Nature：《自然》，创刊于1869年。隶属于施普林格·自然出版集团，最新IF：69.504
官方网址：http://www.nature.com/
投稿链接：http://www.nature.com/authors/submit_manuscript.html