RGN: Residue-Based Graph Attention and Convolutional Network for Protein–Protein Interaction Site Prediction

Abstract

The prediction of a protein−protein interaction site (PPI site) plays a very important role in the biochemical process, and lots of computational methods have been proposed in the past. However, the majority of the past methods are time consuming and lack accuracy. Hence, coming up with an effective computational method is necessary. In this article, we present a novel computational model called RGN (residue-based graph attention and convolutional network) to predict PPI sites. In our paper, the protein is treated as a graph. The amino acid can be seen as the node in the graph structure. The position-specific scoring matrix, hidden Markov model, hydrogen bond estimation algorithm, and ProtBert are applied as node features. The edges are decided by the spatial distance between the amino acids. Then, we utilize a residue-based graph convolutional network and graph attention network to further extract the deeper feature. Finally, the processed node feature is fed into the prediction layer. We show the superiority of our model by comparing it with the other four protein structure-based methods and five protein sequence-based methods. Our model obtains the best performance on all the evaluation metrics (accuracy, precision, recall, F 1 score, Matthews correlation coefficient, area under the receiver operating characteristic curve, and area under the precision recall curve). We also conduct a case study to demonstrate that extracting the protein information from the protein structure perspective is effective and points out the difficult aspect of PPI site prediction.

Seq-InSite: sequence supersedes structure for protein interaction site prediction

“…More details are given in the Supplementary Material . The methods considered include sequence-based models: CRFPPI ( Wei et al 2015 ), DELPHI ( Li et al 2021 ), DLPred ( Zhang et al 2019 ), D-PPIsite ( Hu et al 2023 ), ISPRED-SEQ ( Manfredi et al 2023 ), LORIS ( Dhole et al 2014 ), PIPENN ( Stringer et al 2022 ), PITHIA ( Hosseini and Ilie 2022 ), PSIVER ( Murakami and Mizuguchi 2010 ), SCRIBER ( Zhang and Kurgan 2019 ), SPPIDER ( Porollo and Meller 2007 ), SPRINGS ( Singh et al 2014 ), SPRINT ( Taherzadeh et al 2016 ) and SSWRF ( Wei et al 2016 ); and structure-based models: AttentionCNN ( Lu et al 2021 ), DeepPPISP ( Zeng et al 2020 ), EGRET ( Mahbub and Bayzid 2022 ), GraphPPIS ( Yuan et al 2022 ), HN-PPISP ( Kang et al 2023 ), MaSIF ( Gainza et al 2020 ), ProB-site ( Khan et al 2022 ) and RGN ( Wang et al 2022 ).…”

“…Computational models can be classified into two large categories, according to the type of information used as input: sequence or structure. Structured-based methods use the 3D structures of proteins to predict interaction sites ( Zeng et al 2020 , Wang et al 2022 , Yuan et al 2022 ). The main drawback of these methods is the limited availability of protein structures.…”

Exploring the conformational ensembles of protein-protein complex with transformer-based generative model

“…In the future, we can combine the rich conformational information of protein-protein complexes, the prediction of protein-protein interactions/binding affinity [56], PPI binding site prediction [57], the prediction of PPI-modulator interaction [58], and the generative design of PPI modulators for accelerating the study of PPI targets and the design/screening of modulators [59,60].…”

Adaptive Workflows of Machine Learning Illuminate the Sequential Operation Mechanism of the TAK1′s Allosteric Network

“…However, by integrating a mutual information (MI) rescoring step on the pool of features prioritized by various MLP architectures of differing depths, the information gain was maximized, significantly boosting the efficiency of discriminant identification significantly. Several studies use hybrid model techniques, combining the advantages of multiple ML algorithms to make improved biochemical predictions on data. − But the novelty of this hybrid framework (Workflow2) lies in its ability to detect fluid patterns that consolidate diverse, well-correlated features through an end-to-end combination of a general, nonspecific RF-based prescreening, MLP-based feature identification (principal technique), and MI rescoring (Figures and ).…”