当前位置:科学网首页 > 小柯机器人 >详情
科学家开发出用于蛋白质结合位点预测的几何深度学习模型
作者:小柯机器人 发布时间:2022/5/31 13:12:37

以色列特拉维夫大学Haim J. Wolfson等研究人员合作开发出用于蛋白质结合位点预测的几何深度学习模型。2022年5月30日,国际知名学术期刊《自然—方法学》在线发表了这一成果。

研究人员介绍了ScanNet,一个端到端的、可解释的几何深度学习模型,它直接从三维结构中学习特征。ScanNet根据原子和氨基酸相邻的空间化学排列建立了原子和氨基酸的表征。研究人员训练了ScanNet来检测蛋白质-蛋白质和蛋白质-抗体结合点,证明了其准确性,包括对未见过的蛋白质褶皱,并解释了学到的过滤器。最后,研究人员预测了SARS-CoV-2突刺蛋白的表位,验证了已知的抗原区域,并预测了以前未被描述的抗原区域。总的来说,ScanNet是一个通用的、强大的、可解释的模型,适合于功能位点预测任务。ScanNet的网络服务器可从http://bioinfo3d.cs.tau.ac.il/ScanNet/获取。

据悉,从一个蛋白质的结构中预测其功能位点,如小分子、其他蛋白质或抗体的结合位点,可以了解其在体内的功能。目前,有两类方法占主导地位:建立在手工制作的特征之上的机器学习模型和比较模型。它们分别受限于手工制作的特征的表现力和类似蛋白质的可用性。

附:英文原文

Title: ScanNet: an interpretable geometric deep learning model for structure-based protein binding site prediction

Author: Tubiana, Jrme, Schneidman-Duhovny, Dina, Wolfson, Haim J.

Issue&Volume: 2022-05-30

Abstract: Predicting the functional sites of a protein from its structure, such as the binding sites of small molecules, other proteins or antibodies, sheds light on its function in vivo. Currently, two classes of methods prevail: machine learning models built on top of handcrafted features and comparative modeling. They are, respectively, limited by the expressivity of the handcrafted features and the availability of similar proteins. Here, we introduce ScanNet, an end-to-end, interpretable geometric deep learning model that learns features directly from 3D structures. ScanNet builds representations of atoms and amino acids based on the spatio-chemical arrangement of their neighbors. We train ScanNet for detecting protein–protein and protein–antibody binding sites, demonstrate its accuracy—including for unseen protein folds—and interpret the filters learned. Finally, we predict epitopes of the SARS-CoV-2 spike protein, validating known antigenic regions and predicting previously uncharacterized ones. Overall, ScanNet is a versatile, powerful and interpretable model suitable for functional site prediction tasks. A webserver for ScanNet is available from http://bioinfo3d.cs.tau.ac.il/ScanNet/.

DOI: 10.1038/s41592-022-01490-7

Source: https://www.nature.com/articles/s41592-022-01490-7

期刊信息

Nature Methods:《自然—方法学》,创刊于2004年。隶属于施普林格·自然出版集团,最新IF:28.467
官方网址:https://www.nature.com/nmeth/
投稿链接:https://mts-nmeth.nature.com/cgi-bin/main.plex