{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,20]],"date-time":"2026-02-20T17:23:37Z","timestamp":1771608217077,"version":"3.50.1"},"reference-count":43,"publisher":"Oxford University Press (OUP)","issue":"1","license":[{"start":{"date-parts":[[2022,11,19]],"date-time":"2022-11-19T00:00:00Z","timestamp":1668816000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/journals\/pages\/open_access\/funder_policies\/chorus\/standard_publication_model"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61762092"],"award-info":[{"award-number":["61762092"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,1,19]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:sec><jats:title>Motivation<\/jats:title><jats:p>Biological experimental approaches to protein\u2013protein interaction (PPI) site prediction are critical for understanding the mechanisms of biochemical processes but are time-consuming and laborious. With the development of Deep Learning (DL) techniques, the most popular Convolutional Neural Networks (CNN)-based methods have been proposed to address these problems. Although significant progress has been made, these methods still have limitations in encoding the characteristics of each amino acid in protein sequences. Current methods cannot efficiently explore the nature of Position Specific Scoring Matrix (PSSM), secondary structure and raw protein sequences by processing them all together. For PPI site prediction, how to effectively model the PPI context with attention to prediction remains an open problem. In addition, the long-distance dependencies of PPI features are important, which is very challenging for many CNN-based methods because the innate ability of CNN is difficult to outperform auto-regressive models like Transformers.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>To effectively mine the properties of PPI features, a novel hybrid neural network named HN-PPISP is proposed, which integrates a Multi-layer Perceptron Mixer (MLP-Mixer) module for local feature extraction and a two-stage multi-branch module for global feature capture. The model merits Transformer, TextCNN and Bi-LSTM as a powerful alternative for PPI site prediction. On the one hand, this is the first application of an advanced Transformer (i.e. MLP-Mixer) with a hybrid network for sequence-based PPI prediction. On the other hand, unlike existing methods that treat global features altogether, the proposed two-stage multi-branch hybrid module firstly assigns different attention scores to the input features and then encodes the feature through different branch modules. In the first stage, different improved attention modules are hybridized to extract features from the raw protein sequences, secondary structure and PSSM, respectively. In the second stage, a multi-branch network is designed to aggregate information from both branches in parallel. The two branches encode the features and extract dependencies through several operations such as TextCNN, Bi-LSTM and different activation functions. Experimental results on real-world public datasets show that our model consistently achieves state-of-the-art performance over seven remarkable baselines.<\/jats:p><\/jats:sec><jats:sec><jats:title>Availability<\/jats:title><jats:p>The source code of HN-PPISP model is available at https:\/\/github.com\/ylxu05\/HN-PPISP.<\/jats:p><\/jats:sec>","DOI":"10.1093\/bib\/bbac480","type":"journal-article","created":{"date-parts":[[2022,11,20]],"date-time":"2022-11-20T06:52:15Z","timestamp":1668927135000},"source":"Crossref","is-referenced-by-count":43,"title":["HN-PPISP: a hybrid network based on MLP-Mixer for protein\u2013protein interaction site prediction"],"prefix":"10.1093","volume":"24","author":[{"given":"Yan","family":"Kang","sequence":"first","affiliation":[{"name":"National Pilot School of Software, Yunnan University , Kunming, 650091, P.R . China"}]},{"given":"Yulong","family":"Xu","sequence":"additional","affiliation":[{"name":"National Pilot School of Software, Yunnan University , Kunming, 650091, P.R . China"}]},{"given":"Xinchao","family":"Wang","sequence":"additional","affiliation":[{"name":"National Pilot School of Software, Yunnan University , Kunming, 650091, P.R . China"}]},{"given":"Bin","family":"Pu","sequence":"additional","affiliation":[{"name":"College of Computer Science and Electronic Engineeringg, Hunan University , Changsha, 410082, P.R . China"}]},{"given":"Xuekun","family":"Yang","sequence":"additional","affiliation":[{"name":"National Pilot School of Software, Yunnan University , Kunming, 650091, P.R . China"}]},{"given":"Yulong","family":"Rao","sequence":"additional","affiliation":[{"name":"National Pilot School of Software, Yunnan University , Kunming, 650091, P.R . China"}]},{"given":"Jianguo","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Software Engineering, Sun Yat-Sen University , Zhuhai, 519082, P.R . China"}]}],"member":"286","published-online":{"date-parts":[[2022,11,19]]},"reference":[{"issue":"6995","key":"2023011917115175700_ref1","doi-asserted-by":"crossref","first-page":"88","DOI":"10.1038\/nature02555","article-title":"Evidence for dynamically organized modularity in the yeast protein-protein interaction network.[J]","volume":"430","author":"Han","year":"2004","journal-title":"Nature"},{"issue":"7025","key":"2023011917115175700_ref2","doi-asserted-by":"crossref","first-page":"531","DOI":"10.1038\/nature03239","article-title":"Interaction network containing conserved and essential protein complexes in Escherichia coli[J]","volume":"433","author":"Butland","year":"2005","journal-title":"Nature"},{"issue":"7062","key":"2023011917115175700_ref3","doi-asserted-by":"crossref","first-page":"1173","DOI":"10.1038\/nature04209","article-title":"Towards a proteome-scale map of the human protein-protein interaction network.[J]","volume":"437","author":"Rual","year":"2005","journal-title":"Nature"},{"issue":"1","key":"2023011917115175700_ref4","doi-asserted-by":"crossref","first-page":"1761","DOI":"10.1038\/s41598-020-80900-2","article-title":"Classification and prediction of protein-protein interaction interface using machine learning algorithm[J]","volume":"11","author":"Das","year":"2021","journal-title":"Sci Rep"},{"issue":"7","key":"2023011917115175700_ref5","doi-asserted-by":"crossref","first-page":"896","DOI":"10.1093\/bioinformatics\/btaa750","article-title":"DELPHI: accurate deep ensemble model for protein interaction sites prediction[J]","volume":"37","author":"Li","year":"2021","journal-title":"Bioinformatics"},{"issue":"3","key":"2023011917115175700_ref6","doi-asserted-by":"crossref","first-page":"233","DOI":"10.1093\/bib\/bbp021","article-title":"Progress and challenges in predicting protein-protein interaction sites[J]","volume":"10","author":"Ezkurdia","year":"2009","journal-title":"Brief Bioinform"},{"issue":"3","key":"2023011917115175700_ref7","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pcbi.0030042","article-title":"Deciphering Protein-Protein Interactions. Part I. Experimental Techniques and Databases[J]","volume":"3","author":"Shoemaker","year":"2013","journal-title":"PLoS Comput Biol"},{"issue":"10","key":"2023011917115175700_ref8","doi-asserted-by":"crossref","first-page":"1521","DOI":"10.1093\/bioinformatics\/btu857","article-title":"More challenges for machine-learning protein interactions[J]","volume":"31","author":"Hamp","year":"2015","journal-title":"Bioinformatics"},{"issue":"10","key":"2023011917115175700_ref9","doi-asserted-by":"crossref","first-page":"1479","DOI":"10.1093\/bioinformatics\/btx005","article-title":"Seeing the trees through the forest: sequence-based homo-and heteromeric protein-protein interaction sites prediction using random forest[J]","volume":"33","author":"Hou","year":"2017","journal-title":"Bioinformatics"},{"issue":"1","key":"2023011917115175700_ref16","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/1471-2105-7-365","article-title":"PIPE: a protein-protein interaction prediction engine based on the re-occurring short polypeptide sequences between known interacting protein pairs[J]","volume":"7","author":"Pitre","year":"2006","journal-title":"BMC bioinformatics"},{"issue":"1","key":"2023011917115175700_ref17","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0030938","article-title":"SPPS: a sequence-based method for predicting probability of protein-protein interaction partners[J]","volume":"7","author":"Liu","year":"2012","journal-title":"PloS one"},{"issue":"1","key":"2023011917115175700_ref23","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/1471-2105-10-426","article-title":"Prediction of protein-protein interaction sites using an ensemble method[J]","volume":"10","author":"Deng","year":"2009","journal-title":"BMC bioinformatics"},{"issue":"4","key":"2023011917115175700_ref25","doi-asserted-by":"crossref","first-page":"1155","DOI":"10.1109\/TCBB.2012.58","article-title":"Detection of outlier residues for improving interface prediction in protein heterocomplexes[J]","volume":"9","author":"Chen","year":"2012","journal-title":"IEEE\/ACM Trans Comput Biol Bioinform"},{"issue":"14","key":"2023011917115175700_ref19","doi-asserted-by":"crossref","first-page":"2395","DOI":"10.1093\/bioinformatics\/bty995","article-title":"Protein-protein interaction sites prediction by ensemble random forests with synthetic minority oversampling technique[J]","volume":"35","author":"Wang","year":"2019","journal-title":"Bioinformatics"},{"issue":"5","key":"2023011917115175700_ref22","doi-asserted-by":"crossref","first-page":"585","DOI":"10.1093\/bioinformatics\/btp039","article-title":"Sequence-based prediction of protein interaction sites with an integrative method[J]","volume":"25","author":"Chen","year":"2009","journal-title":"Bioinformatics"},{"issue":"15","key":"2023011917115175700_ref13","doi-asserted-by":"crossref","first-page":"1841","DOI":"10.1093\/bioinformatics\/btq302","article-title":"Applying the Na\u00efve Bayes classifier with kernel density estimation to the prediction of protein-protein interaction sites[J]","volume":"26","author":"Murakami","year":"2010","journal-title":"Bioinformatics"},{"key":"2023011917115175700_ref20","doi-asserted-by":"crossref","first-page":"231","DOI":"10.1016\/j.jtbi.2013.07.001","article-title":"A novel method based on new adaptive LVQ neural network for predicting protein-protein interactions from protein sequences[J]","volume":"336","author":"Yousef","year":"2013","journal-title":"J Theor Biol"},{"issue":"Supplement_2","key":"2023011917115175700_ref27","doi-asserted-by":"crossref","first-page":"i735","DOI":"10.1093\/bioinformatics\/btaa806","article-title":"PROBselect: accurate prediction of protein-binding residues from proteins sequences via dynamic predictor selection[J]","volume":"36","author":"Zhang","year":"2020","journal-title":"Bioinformatics"},{"issue":"14","key":"2023011917115175700_ref28","doi-asserted-by":"crossref","first-page":"2395","DOI":"10.1093\/bioinformatics\/bty995","article-title":"Protein-protein interaction sites prediction by ensemble random forests with synthetic minority oversampling technique[J]","volume":"35","author":"Wang","year":"2019","journal-title":"Bioinformatics"},{"issue":"6","key":"2023011917115175700_ref21","doi-asserted-by":"crossref","first-page":"496","DOI":"10.1016\/j.ygeno.2014.10.006","article-title":"LocFuse: human protein-protein interaction prediction via classifier fusion using protein localization information[J]","volume":"104","author":"Zahiri","year":"2014","journal-title":"Genomics"},{"issue":"3","key":"2023011917115175700_ref10","doi-asserted-by":"crossref","first-page":"336","DOI":"10.1002\/prot.1099","article-title":"Prediction of protein interaction sites from sequence profile and residue neighbor list[J]","volume":"44","author":"Zhou","year":"2001","journal-title":"Proteins: Structure, Function, and Bioinformatics"},{"issue":"2","key":"2023011917115175700_ref11","doi-asserted-by":"crossref","first-page":"e13","DOI":"10.1093\/bioinformatics\/btl303","article-title":"ISIS: interaction sites identified from sequence[J]","volume":"23","author":"Ofran","year":"2007","journal-title":"Bioinformatics"},{"key":"2023011917115175700_ref14","first-page":"1","article-title":"SPRINGS: Prediction of Protein-Protein Interaction Sites Using Artificial Neural Networks[J]","author":"Dhole","year":"2014","journal-title":"Peerj"},{"key":"2023011917115175700_ref15","doi-asserted-by":"crossref","first-page":"47","DOI":"10.1016\/j.jtbi.2014.01.028","article-title":"Sequence-based prediction of protein-protein interaction sites with L1-logreg classifier[J]","volume":"348","author":"Dhole","year":"2014","journal-title":"J Theor Biol"},{"issue":"3","key":"2023011917115175700_ref12","doi-asserted-by":"crossref","first-page":"630","DOI":"10.1002\/prot.21248","article-title":"Prediction-based fingerprints of protein-protein interactions.[J]","volume":"66","author":"Porollo","year":"2010","journal-title":"Proteins-structure Function & Bioinformatics"},{"issue":"9","key":"2023011917115175700_ref24","doi-asserted-by":"crossref","first-page":"1111","DOI":"10.2174\/092986610791760397","article-title":"Radial basis function neural network ensemble for predicting protein-protein interaction sites in heterocomplexes[J]","volume":"17","author":"Wang","year":"2010","journal-title":"Protein Pept Lett"},{"key":"2023011917115175700_ref41","article-title":"Learning Bounded Context-Free-Grammar via LSTM and the Transformer: Difference and Explanations[J]","author":"Shi","year":"2021"},{"issue":"6","key":"2023011917115175700_ref40","doi-asserted-by":"crossref","first-page":"bbab228","DOI":"10.1093\/bib\/bbab228","article-title":"LSTM-PHV: prediction of human-virus protein-protein interactions by LSTM with word2vec[J]","volume":"22","author":"Tsukiyama","year":"2021","journal-title":"Brief Bioinform"},{"key":"2023011917115175700_ref26","doi-asserted-by":"crossref","first-page":"86","DOI":"10.1016\/j.neucom.2019.05.013","article-title":"Sequence-based prediction of protein-protein interaction sites by simplified long short-term memory network[J]","volume":"357","author":"Zhang","year":"2019","journal-title":"Neurocomputing"},{"key":"2023011917115175700_ref34","first-page":"225","volume-title":"Chinese Text Emotional Analysis Based on Bi-LSTM Model Fusing Emotional Features[M]\/\/Advances in Intelligent Data Analysis and Applications","author":"Li","year":"2022"},{"issue":"2","key":"2023011917115175700_ref35","doi-asserted-by":"crossref","first-page":"3091","DOI":"10.32604\/cmc.2022.022609","article-title":"Attention-Based Bi-LSTM Model for Arabic Depression Classification[J]","volume":"71","author":"Almars","year":"2022","journal-title":"CMC-COMPUTERS MATERIALS & CONTINUA"},{"issue":"4","key":"2023011917115175700_ref29","doi-asserted-by":"crossref","first-page":"1114","DOI":"10.1093\/bioinformatics\/btz699","article-title":"Protein-protein interaction site prediction through combining local and global features with deep neural networks[J]","volume":"36","author":"Zeng","year":"2020","journal-title":"Bioinformatics"},{"key":"2023011917115175700_ref30","first-page":"141","article-title":"Attention-based convolutional neural networks for protein-protein interaction site prediction[C]\/\/2021 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","author":"Lu","year":"2021","journal-title":"IEEE"},{"key":"2023011917115175700_ref33","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale[J]","author":"Dosovitskiy","year":"2020"},{"key":"2023011917115175700_ref36","first-page":"34","article-title":"Mlp-mixer: An all-mlp architecture for vision[J]","author":"Tolstikhin","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2023011917115175700_ref32","first-page":"7132","article-title":"Squeeze-and-excitation networks[C]","author":"Hu","year":"2018","journal-title":"Proceedings of the IEEE conference on computer vision and pattern recognition"},{"key":"2023011917115175700_ref37","article-title":"RaftMLP: Do MLP-based Models Dream of Winning Over Computer Vision?[J]","author":"Tatsunami","year":"2021"},{"key":"2023011917115175700_ref38","article-title":"Lawin Transformer: Improving Semantic Segmentation Transformer with Multi-Scale Representations via Large Window Attention[J]","author":"Yan","year":"2022"},{"issue":"4","key":"2023011917115175700_ref18","doi-asserted-by":"crossref","first-page":"237","DOI":"10.1016\/j.ygeno.2013.05.006","article-title":"PPIevo: Protein-protein interaction prediction from PSSM based evolutionary information[J]","volume":"102","author":"Zahiri","year":"2013","journal-title":"Genomics"},{"issue":"1","key":"2023011917115175700_ref31","doi-asserted-by":"crossref","first-page":"235","DOI":"10.1093\/nar\/28.1.235","article-title":"The protein data bank[J]","volume":"28","author":"Berman","year":"2000","journal-title":"Nucleic Acids Res"},{"issue":"14","key":"2023011917115175700_ref43","doi-asserted-by":"crossref","first-page":"i343","DOI":"10.1093\/bioinformatics\/btz324","article-title":"SCRIBER: accurate and partner type-specific prediction of protein-binding residues from proteins sequences[J]","volume":"35","author":"Zhang","year":"2019","journal-title":"Bioinformatics"},{"key":"2023011917115175700_ref42","article-title":"Attention is all you need[J]","volume":"30","author":"Vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"2023011917115175700_ref39","doi-asserted-by":"crossref","first-page":"233","DOI":"10.1145\/1143844.1143874","article-title":"The relationship between Precision-Recall and ROC curves[C]","author":"Davis","year":"2006","journal-title":"Proceedings of the 23rd international conference on Machine learning"}],"container-title":["Briefings in Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/24\/1\/bbac480\/48782521\/bbac480.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/24\/1\/bbac480\/48782521\/bbac480.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,3,10]],"date-time":"2023-03-10T14:52:52Z","timestamp":1678459972000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bib\/article\/doi\/10.1093\/bib\/bbac480\/6833645"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,11,19]]},"references-count":43,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2023,1,19]]}},"URL":"https:\/\/doi.org\/10.1093\/bib\/bbac480","relation":{},"ISSN":["1467-5463","1477-4054"],"issn-type":[{"value":"1467-5463","type":"print"},{"value":"1477-4054","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2023,1]]},"published":{"date-parts":[[2022,11,19]]},"article-number":"bbac480"}}