ProInterVal: Validation of Protein-Protein Interfaces through Learned Interface Representations

被引:1
作者
Ovek, Damla [1 ,2 ]
Keskin, Ozlem [3 ]
Gursoy, Attila [2 ]
机构
[1] Koc Univ, KUIS AI Ctr, Istanbul, Turkiye
[2] Koc Univ, Comp Engn, TR-34450 Istanbul, Turkiye
[3] Koc Univ, Chem & Biol Engn, TR-34450 Istanbul, Turkiye
关键词
WEB SERVER; DOCKING; PREDICTION; BENCHMARK; CAPRI;
D O I
10.1021/acs.jcim.3c01788
中图分类号
R914 [药物化学];
学科分类号
100701 ;
摘要
Proteins are vital components of the biological world and serve a multitude of functions. They interact with other molecules through their interfaces and participate in crucial cellular processes. Disruption of these interactions can have negative effects on organisms, highlighting the importance of studying protein-protein interfaces for developing targeted therapies for diseases. Therefore, the development of a reliable method for investigating protein-protein interactions is of paramount importance. In this work, we present an approach for validating protein-protein interfaces using learned interface representations. The approach involves using a graph-based contrastive autoencoder architecture and a transformer to learn representations of protein-protein interaction interfaces from unlabeled data and then validating them through learned representations with a graph neural network. Our method achieves an accuracy of 0.91 for the test set, outperforming existing GNN-based methods. We demonstrate the effectiveness of our approach on a benchmark data set and show that it provides a promising solution for validating protein-protein interfaces.
引用
收藏
页码:2979 / 2987
页数:9
相关论文
共 32 条
[1]  
Abali Z., 2021, PROTEIN DATA BANK
[2]  
Balci A., 2019, BIOINFORMATICS, DOI [10.1101/617506, DOI 10.1101/617506]
[3]   Multifaceted protein-protein interaction prediction based on Siamese residual RCNN [J].
Chen, Muhao ;
Ju, Chelsea J. -T. ;
Zhou, Guangyu ;
Chen, Xuelu ;
Zhang, Tianran ;
Chang, Kai-Wei ;
Zaniolo, Carlo ;
Wang, Wei .
BIOINFORMATICS, 2019, 35 (14) :I305-I314
[4]   Non-Redundant Unique Interface Structures as Templates for Modeling Protein Interactions [J].
Cukuroglu, Engin ;
Gursoy, Attila ;
Nussinov, Ruth ;
Keskin, Ozlem .
PLOS ONE, 2014, 9 (01)
[5]  
Dosovitskiy A., 2020, ARXIV201011929
[6]   Predicting protein-protein interactions through sequence-based deep learning [J].
Hashemifar, Somaye ;
Neyshabur, Behnam ;
Khan, Aly A. ;
Xu, Jinbo .
BIOINFORMATICS, 2018, 34 (17) :802-810
[7]  
Hermosilla P., 2022, ARXIV2205515675
[8]   DeepTrio: a ternary prediction system for protein-protein interaction using mask multiple parallel convolutional neural networks [J].
Hu, Xiaotian ;
Feng, Cong ;
Zhou, Yincong ;
Harrison, Andrew ;
Chen, Ming .
BIOINFORMATICS, 2022, 38 (03) :694-702
[9]   Protein-protein docking benchmark version 4.0 [J].
Hwang, Howook ;
Vreven, Thom ;
Janin, Joel ;
Weng, Zhiping .
PROTEINS-STRUCTURE FUNCTION AND BIOINFORMATICS, 2010, 78 (15) :3111-3114
[10]   CAPRI: A Critical Assessment of PRedicted Interactions [J].
Janin, J ;
Henrick, K ;
Moult, J ;
Ten Eyck, L ;
Sternberg, MJE ;
Vajda, S ;
Vasker, I ;
Wodak, SJ .
PROTEINS-STRUCTURE FUNCTION AND BIOINFORMATICS, 2003, 52 (01) :2-9