{"title":"Improving protein-protein interaction site prediction using Graph Neural Network and structure profiles.","authors":"Qing Zhang, You-Hang Hu, Yu Zhou, Jun Hu, Xiao-Gen Zhou, Biao Zhang","doi":"10.1016/j.ab.2025.115929","DOIUrl":null,"url":null,"abstract":"<p><p>Protein-protein interactions (PPIs) play a pivotal role in numerous biological processes. Accurate identification of the amino acid residues involved in these interactions is essential for understanding the functional mechanisms of proteins. To effectively integrate both structure and sequence information, we propose a new interaction site predictor, TargetPPI, which leverages bidirectional long short-term memory networks (Bi-LSTM), convolutional neural networks (CNN), and Edge Aggregation through Graph Attention layers with Node Similarity (EGR-NS) neural networks. In TargetPPI, CNN and Bi-LSTM are first employed to extract the global and local feature information, respectively. The combination of global and local features is then used as node embeddings in the graph derived from the protein structure. We have also extracted six discriminative structural features as edge features in the graph. Additionally, a mean ensemble strategy is used to integrate multiple prediction models with diverse model parameters into the final model, resulting in more accurate PPIs prediction performance. Benchmarked results on seven independent testing datasets demonstrate that, compared to most of the state-of-the-art methods, TargetPPI achieves higher accuracy, precision, and Matthews Correlation Coefficient (MCC) values on average, specifically, 84.3%, 57.6%, and 0.383, respectively. The source code of TargetPPI is freely available at https://github.com/bukkeshuo/TargetPPI.</p>","PeriodicalId":7830,"journal":{"name":"Analytical biochemistry","volume":" ","pages":"115929"},"PeriodicalIF":2.6000,"publicationDate":"2025-06-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Analytical biochemistry","FirstCategoryId":"99","ListUrlMain":"https://doi.org/10.1016/j.ab.2025.115929","RegionNum":4,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"BIOCHEMICAL RESEARCH METHODS","Score":null,"Total":0}
引用次数: 0
Abstract
Protein-protein interactions (PPIs) play a pivotal role in numerous biological processes. Accurate identification of the amino acid residues involved in these interactions is essential for understanding the functional mechanisms of proteins. To effectively integrate both structure and sequence information, we propose a new interaction site predictor, TargetPPI, which leverages bidirectional long short-term memory networks (Bi-LSTM), convolutional neural networks (CNN), and Edge Aggregation through Graph Attention layers with Node Similarity (EGR-NS) neural networks. In TargetPPI, CNN and Bi-LSTM are first employed to extract the global and local feature information, respectively. The combination of global and local features is then used as node embeddings in the graph derived from the protein structure. We have also extracted six discriminative structural features as edge features in the graph. Additionally, a mean ensemble strategy is used to integrate multiple prediction models with diverse model parameters into the final model, resulting in more accurate PPIs prediction performance. Benchmarked results on seven independent testing datasets demonstrate that, compared to most of the state-of-the-art methods, TargetPPI achieves higher accuracy, precision, and Matthews Correlation Coefficient (MCC) values on average, specifically, 84.3%, 57.6%, and 0.383, respectively. The source code of TargetPPI is freely available at https://github.com/bukkeshuo/TargetPPI.
期刊介绍:
The journal''s title Analytical Biochemistry: Methods in the Biological Sciences declares its broad scope: methods for the basic biological sciences that include biochemistry, molecular genetics, cell biology, proteomics, immunology, bioinformatics and wherever the frontiers of research take the field.
The emphasis is on methods from the strictly analytical to the more preparative that would include novel approaches to protein purification as well as improvements in cell and organ culture. The actual techniques are equally inclusive ranging from aptamers to zymology.
The journal has been particularly active in:
-Analytical techniques for biological molecules-
Aptamer selection and utilization-
Biosensors-
Chromatography-
Cloning, sequencing and mutagenesis-
Electrochemical methods-
Electrophoresis-
Enzyme characterization methods-
Immunological approaches-
Mass spectrometry of proteins and nucleic acids-
Metabolomics-
Nano level techniques-
Optical spectroscopy in all its forms.
The journal is reluctant to include most drug and strictly clinical studies as there are more suitable publication platforms for these types of papers.