{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T04:35:03Z","timestamp":1784608503224,"version":"3.55.0"},"reference-count":57,"publisher":"Oxford University Press (OUP)","issue":"7","license":[{"start":{"date-parts":[[2022,1,19]],"date-time":"2022-01-19T00:00:00Z","timestamp":1642550400000},"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":["61832019"],"award-info":[{"award-number":["61832019"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Hunan Provincial Science and Technology Program","award":["2019CB1007"],"award-info":[{"award-number":["2019CB1007"]}]},{"name":"Hunan Provincial Science and Technology Program","award":["2021RC0048"],"award-info":[{"award-number":["2021RC0048"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,3,28]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:sec><jats:title>Motivation<\/jats:title><jats:p>The identification of compound\u2013protein interactions (CPIs) is an essential step in the process of drug discovery. The experimental determination of CPIs is known for a large amount of funds and time it consumes. Computational model has therefore become a promising and efficient alternative for predicting novel interactions between compounds and proteins on a large scale. Most supervised machine learning prediction models are approached as a binary classification problem, which aim to predict whether there is an interaction between the compound and the protein or not. However, CPI is not a simple binary on\u2013off relationship, but a continuous value reflects how tightly the compound binds to a particular target protein, also called binding affinity.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>In this study, we propose an end-to-end neural network model, called BACPI, to predict CPI and binding affinity. We employ graph attention network and convolutional neural network (CNN) to learn the representations of compounds and proteins and develop a bi-directional attention neural network model to integrate the representations. To evaluate the performance of BACPI, we use three CPI datasets and four binding affinity datasets in our experiments. The results show that, when predicting CPIs, BACPI significantly outperforms other available machine learning methods on both balanced and unbalanced datasets. This suggests that the end-to-end neural network model that predicts CPIs directly from low-level representations is more robust than traditional machine learning-based methods. And when predicting binding affinities, BACPI achieves higher performance on large datasets compared to other state-of-the-art deep learning methods. This comparison result suggests that the proposed method with bi-directional attention neural network can capture the important regions of compounds and proteins for binding affinity prediction.<\/jats:p><\/jats:sec><jats:sec><jats:title>Availability and implementation<\/jats:title><jats:p>Data and source codes are available at https:\/\/github.com\/CSUBioGroup\/BACPI<\/jats:p><\/jats:sec>","DOI":"10.1093\/bioinformatics\/btac035","type":"journal-article","created":{"date-parts":[[2022,1,14]],"date-time":"2022-01-14T12:08:53Z","timestamp":1642162133000},"page":"1995-2002","source":"Crossref","is-referenced-by-count":108,"title":["BACPI: a bi-directional attention neural network for compound\u2013protein interaction and binding affinity prediction"],"prefix":"10.1093","volume":"38","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0188-1394","authenticated-orcid":false,"given":"Min","family":"Li","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Central South University , Changsha, Hunan, 410083, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhangli","family":"Lu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Central South University , Changsha, Hunan, 410083, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yifan","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Central South University , Changsha, Hunan, 410083, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"YaoHang","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Old Dominion University , Norfolk, VA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2022,1,19]]},"reference":[{"key":"2023020109003040700_btac035-B1","doi-asserted-by":"crossref","first-page":"451","DOI":"10.1093\/bioinformatics\/btp002","article-title":"Properties and identification of human protein drug targets","volume":"25","author":"Bakheet","year":"2009","journal-title":"Bioinformatics"},{"key":"2023020109003040700_btac035-B2","doi-asserted-by":"crossref","first-page":"235","DOI":"10.1093\/nar\/28.1.235","article-title":"The protein data bank","volume":"28","author":"Berman","year":"2000","journal-title":"Nucleic Acids Res"},{"key":"2023020109003040700_btac035-B3","doi-asserted-by":"crossref","first-page":"2397","DOI":"10.1093\/bioinformatics\/btp433","article-title":"Supervised prediction of drug\u2013target interactions using bipartite local models","volume":"25","author":"Bleakley","year":"2009","journal-title":"Bioinformatics"},{"key":"2023020109003040700_btac035-B4","first-page":"14","article-title":"High-throughput screening for drug discovery","volume":"384","author":"Broach","year":"1996","journal-title":"Nature"},{"key":"2023020109003040700_btac035-B5","doi-asserted-by":"crossref","first-page":"ofaa241","DOI":"10.1093\/ofid\/ofaa241","article-title":"Antiviral activity and safety of darunavir\/cobicistat for the treatment of COVID-19","volume":"7","author":"Chen","year":"2020","journal-title":"Open Forum Infect. Dis"},{"key":"2023020109003040700_btac035-B6","doi-asserted-by":"crossref","first-page":"2373","DOI":"10.1039\/c2mb25110h","article-title":"Prediction of chemical\u2013protein interactions: multitarget-QSAR versus computational chemogenomic methods","volume":"8","author":"Cheng","year":"2012","journal-title":"Mol. BioSyst"},{"key":"2023020109003040700_btac035-B7","doi-asserted-by":"crossref","first-page":"56","DOI":"10.1186\/1752-0509-2-56","article-title":"Construction of a cancer-perturbed protein-protein interaction network for discovery of apoptosis drug targets","volume":"2","author":"Chu","year":"2008","journal-title":"BMC Syst. Biol"},{"key":"2023020109003040700_btac035-B8","doi-asserted-by":"crossref","first-page":"4536","DOI":"10.2174\/0929867327666200416131117","article-title":"SARS-CoV-2: recent reports on antiviral therapies based on lopinavir\/ritonavir, darunavir\/umifenovir, hydroxychloroquine, remdesivir, favipiravir and other drugs for the treatment of the new coronavirus","volume":"27","author":"Costanzo","year":"2020","journal-title":"Curr. Med. Chem."},{"key":"2023020109003040700_btac035-B9","first-page":"233","author":"Davis","year":"2006"},{"key":"2023020109003040700_btac035-B10","author":"Dayer","year":"2020"},{"key":"2023020109003040700_btac035-B11","doi-asserted-by":"crossref","first-page":"734","DOI":"10.1093\/bib\/bbt056","article-title":"Similarity-based machine learning methods for predicting drug\u2013target interactions: a brief review","volume":"15","author":"Ding","year":"2014","journal-title":"Brief. Bioinformatics"},{"key":"2023020109003040700_btac035-B12","doi-asserted-by":"crossref","first-page":"2807","DOI":"10.1021\/ci500406k","article-title":"Beware of machine learning-based scoring functions on the danger of developing black boxes","volume":"54","author":"Gabel","year":"2014","journal-title":"J. Chem. Inform. Model"},{"key":"2023020109003040700_btac035-B13","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1146\/annurev.biophys.36.040306.132550","article-title":"Calculation of protein-ligand binding affinities","volume":"36","author":"Gilson","year":"2007","journal-title":"Annu. Rev. Biophys. Biomol. Struct"},{"key":"2023020109003040700_btac035-B14","doi-asserted-by":"crossref","first-page":"D919","DOI":"10.1093\/nar\/gkm862","article-title":"Supertarget and matador: resources for exploring drug-target relationships","volume":"36","author":"G\u00fcnther","year":"2008","journal-title":"Nucleic Acids Res"},{"key":"2023020109003040700_btac035-B15","doi-asserted-by":"crossref","first-page":"40376","DOI":"10.1038\/srep40376","article-title":"Predicting drug-target interactions by dual-network integrated logistic matrix factorization","volume":"7","author":"Hao","year":"2017","journal-title":"Sci. Rep"},{"key":"2023020109003040700_btac035-B16","doi-asserted-by":"crossref","first-page":"5545","DOI":"10.1093\/bioinformatics\/btaa1005","article-title":"DeepPurpose: a deep learning library for drug\u2013target interaction prediction","volume":"36","author":"Huang","year":"2021","journal-title":"Bioinformatics"},{"key":"2023020109003040700_btac035-B17","first-page":"223","article-title":"Nouvelles recherches sur la distribution florale","volume":"44","author":"Jaccard","year":"1908","journal-title":"Bull. Soc. Vaud. Sci. Nat"},{"key":"2023020109003040700_btac035-B18","doi-asserted-by":"crossref","first-page":"3329","DOI":"10.1093\/bioinformatics\/btz111","article-title":"DeepAffinity: interpretable deep learning of compound\u2013protein affinity through unified recurrent and convolutional neural networks","volume":"35","author":"Karimi","year":"2019","journal-title":"Bioinformatics"},{"key":"2023020109003040700_btac035-B19","doi-asserted-by":"crossref","first-page":"D1202","DOI":"10.1093\/nar\/gkv951","article-title":"PubChem substance and compound databases","volume":"44","author":"Kim","year":"2016","journal-title":"Nucleic Acids Res"},{"key":"2023020109003040700_btac035-B20","author":"Kingma","year":"2014"},{"key":"2023020109003040700_btac035-B21","doi-asserted-by":"crossref","first-page":"711","DOI":"10.1038\/nrd1470","article-title":"Can the pharmaceutical industry reduce attrition rates?","volume":"3","author":"Kola","year":"2004","journal-title":"Nat. Rev. Drug Discov"},{"key":"2023020109003040700_btac035-B22","doi-asserted-by":"crossref","first-page":"2554","DOI":"10.1016\/j.jprot.2011.05.011","article-title":"From in silico target prediction to multi-target drug design: current databases, methods and applications","volume":"74","author":"Koutsoukas","year":"2011","journal-title":"J. Proteomics"},{"key":"2023020109003040700_btac035-B23","doi-asserted-by":"crossref","first-page":"D401","DOI":"10.1093\/nar\/gkt1207","article-title":"STITCH 4: integration of protein\u2013chemical interactions with user data","volume":"42","author":"Kuhn","year":"2014","journal-title":"Nucleic Acids Res"},{"key":"2023020109003040700_btac035-B24","doi-asserted-by":"crossref","first-page":"10947","DOI":"10.3390\/molecules200610947","article-title":"Low-quality structural and interaction data improves binding affinity prediction via random forest","volume":"20","author":"Li","year":"2015","journal-title":"Molecules"},{"key":"2023020109003040700_btac035-B25","first-page":"575","author":"Li","year":"2019"},{"key":"2023020109003040700_btac035-B26","doi-asserted-by":"crossref","first-page":"308","DOI":"10.1016\/j.cels.2020.03.002","article-title":"MONN: a multi-objective neural network for predicting compound-protein interactions and affinities","volume":"10","author":"Li","year":"2020","journal-title":"Cell Systems"},{"key":"2023020109003040700_btac035-B27","first-page":"3367","author":"Liang","year":"2015"},{"key":"2023020109003040700_btac035-B28","doi-asserted-by":"crossref","first-page":"i221","DOI":"10.1093\/bioinformatics\/btv256","article-title":"Improving compound\u2013protein interaction prediction by building up highly credible negative samples","volume":"31","author":"Liu","year":"2015","journal-title":"Bioinformatics"},{"key":"2023020109003040700_btac035-B29","doi-asserted-by":"crossref","first-page":"D198","DOI":"10.1093\/nar\/gkl999","article-title":"BindingDB: a web-accessible database of experimentally determined protein\u2013ligand binding affinities","volume":"35","author":"Liu","year":"2007","journal-title":"Nucleic Acids Res"},{"key":"2023020109003040700_btac035-B30","doi-asserted-by":"crossref","first-page":"e1004760","DOI":"10.1371\/journal.pcbi.1004760","article-title":"Neighborhood regularized logistic matrix factorization for drug-target interaction prediction","volume":"12","author":"Liu","year":"2016","journal-title":"PLoS Comput. Biol"},{"key":"2023020109003040700_btac035-B31","doi-asserted-by":"crossref","first-page":"792","DOI":"10.1021\/acscentsci.0c01186","article-title":"Simeprevir potently suppresses SARS-CoV-2 replication and synergizes with remdesivir","volume":"7","author":"Lo","year":"2021","journal-title":"ACS Central Sci"},{"key":"2023020109003040700_btac035-B32","doi-asserted-by":"crossref","first-page":"1426","DOI":"10.1001\/jama.2021.3071","article-title":"Effect of ivermectin on time to resolution of symptoms among adults with mild COVID-19: a randomized clinical trial","volume":"325","author":"L\u00f3pez-Medina","year":"2021","journal-title":"JAMA"},{"key":"2023020109003040700_btac035-B33","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41467-017-00680-8","article-title":"A network integration approach for drug-target interaction prediction and computational drug repositioning from heterogeneous information","volume":"8","author":"Luo","year":"2017","journal-title":"Nat. Commun"},{"key":"2023020109003040700_btac035-B34","doi-asserted-by":"crossref","first-page":"238","DOI":"10.1093\/bioinformatics\/bts670","article-title":"Drug\u2013target interaction prediction by learning from local information and neighbors","volume":"29","author":"Mei","year":"2013","journal-title":"Bioinformatics"},{"key":"2023020109003040700_btac035-B35","doi-asserted-by":"crossref","first-page":"6582","DOI":"10.1021\/jm300687e","article-title":"Directory of useful decoys, enhanced (DUD-E): better ligands and decoys for better benchmarking","volume":"55","author":"Mysinger","year":"2012","journal-title":"J. Med. Chem"},{"key":"2023020109003040700_btac035-B36","doi-asserted-by":"crossref","first-page":"19143","DOI":"10.1109\/ACCESS.2019.2896880","article-title":"Speech recognition using deep neural networks: a systematic review","volume":"7","author":"Nassif","year":"2019","journal-title":"IEEE Access"},{"key":"2023020109003040700_btac035-B37","doi-asserted-by":"crossref","first-page":"i821","DOI":"10.1093\/bioinformatics\/bty593","article-title":"DeepDTA: deep drug\u2013target binding affinity prediction","volume":"34","author":"\u00d6zt\u00fcrk","year":"2018","journal-title":"Bioinformatics"},{"key":"2023020109003040700_btac035-B38","doi-asserted-by":"crossref","first-page":"325","DOI":"10.1093\/bib\/bbu010","article-title":"Toward more realistic drug\u2013target interaction predictions","volume":"16","author":"Pahikkala","year":"2015","journal-title":"Brief. Bioinformatics"},{"key":"2023020109003040700_btac035-B39","doi-asserted-by":"crossref","first-page":"203","DOI":"10.1038\/nrd3078","article-title":"How to improve R&D productivity: the pharmaceutical industry\u2019s grand challenge","volume":"9","author":"Paul","year":"2010","journal-title":"Nat. Rev. Drug Discov"},{"key":"2023020109003040700_btac035-B40","doi-asserted-by":"crossref","first-page":"303","DOI":"10.1016\/j.cbpa.2006.06.024","article-title":"Genomic approaches to drug discovery","volume":"10","author":"Ricke","year":"2006","journal-title":"Curr. Opin. Chem. Biol"},{"key":"2023020109003040700_btac035-B41","doi-asserted-by":"crossref","first-page":"742","DOI":"10.1021\/ci100050t","article-title":"Extended-connectivity fingerprints","volume":"50","author":"Rogers","year":"2010","journal-title":"J. Chem. Inform. Model"},{"key":"2023020109003040700_btac035-B42","doi-asserted-by":"crossref","DOI":"10.1042\/BSR20201256","article-title":"Glecaprevir and maraviroc are high-affinity inhibitors of SARS-CoV-2 main protease: possible implication in Covid-19 therapy","volume":"40","author":"Shamsi","year":"2020","journal-title":"Biosci. Rep"},{"key":"2023020109003040700_btac035-B43","doi-asserted-by":"crossref","first-page":"1443","DOI":"10.3109\/14756366.2016.1144594","article-title":"Pred-binding: large-scale protein\u2013ligand binding affinity prediction","volume":"31","author":"Shar","year":"2016","journal-title":"J. Enzyme Inhib. Med. Chem"},{"key":"2023020109003040700_btac035-B44","doi-asserted-by":"crossref","first-page":"195","DOI":"10.1016\/0022-2836(81)90087-5","article-title":"Identification of common molecular subsequences","volume":"147","author":"Smith","year":"1981","journal-title":"J. Mol. Biol"},{"key":"2023020109003040700_btac035-B45","doi-asserted-by":"crossref","first-page":"455","DOI":"10.1002\/jcc.21334","article-title":"AutoDock Vina: improving the speed and accuracy of docking with a new scoring function, efficient optimization, and multithreading","volume":"31","author":"Trott","year":"2010","journal-title":"J. Comput. Chem"},{"key":"2023020109003040700_btac035-B46","doi-asserted-by":"crossref","first-page":"309","DOI":"10.1093\/bioinformatics\/bty535","article-title":"Compound\u2013protein interaction prediction with end-to-end learning of neural networks for graphs and sequences","volume":"35","author":"Tsubaki","year":"2019","journal-title":"Bioinformatics"},{"key":"2023020109003040700_btac035-B47","doi-asserted-by":"crossref","first-page":"e66952","DOI":"10.1371\/journal.pone.0066952","article-title":"Predicting drug-target interactions for new drug compounds using a weighted nearest neighbor profile","volume":"8","author":"Van Laarhoven","year":"2013","journal-title":"PLoS One"},{"key":"2023020109003040700_btac035-B48","article-title":"DeepDTAF: a deep learning method to predict protein\u2013ligand binding affinity","volume":"22","author":"Wang","year":"2021","journal-title":"Brief. Bioinformatics"},{"key":"2023020109003040700_btac035-B49","doi-asserted-by":"crossref","first-page":"4111","DOI":"10.1021\/jm048957q","article-title":"The PDBbind database: methodologies and updates","volume":"48","author":"Wang","year":"2005","journal-title":"J. Med. Chem"},{"key":"2023020109003040700_btac035-B50","doi-asserted-by":"crossref","first-page":"2923","DOI":"10.1093\/bioinformatics\/btu403","article-title":"Drug repositioning by integrating target information through a heterogeneous network model","volume":"30","author":"Wang","year":"2014","journal-title":"Bioinformatics"},{"key":"2023020109003040700_btac035-B51","doi-asserted-by":"crossref","first-page":"D901","DOI":"10.1093\/nar\/gkm958","article-title":"Drugbank: a knowledgebase for drugs, drug actions and drug targets","volume":"36","author":"Wishart","year":"2008","journal-title":"Nucleic Acids Res"},{"issue":"S-2","key":"2023020109003040700_btac035-B52","doi-asserted-by":"crossref","first-page":"S6","DOI":"10.1186\/1752-0509-4-S2-S6","article-title":"Semi-supervised drug-protein interaction prediction from heterogeneous biological spaces","volume":"4","author":"Xia","year":"2010","journal-title":"BMC Syst. Biol"},{"key":"2023020109003040700_btac035-B53","doi-asserted-by":"crossref","first-page":"361","DOI":"10.1146\/annurev-pharmtox-010611-134630","article-title":"Novel computational approaches to polypharmacology as a means to define responses to individual drugs","volume":"52","author":"Xie","year":"2012","journal-title":"Annu. Rev. Pharmacol. Toxicol"},{"key":"2023020109003040700_btac035-B54","doi-asserted-by":"crossref","first-page":"i232","DOI":"10.1093\/bioinformatics\/btn162","article-title":"Prediction of drug\u2013target interaction networks from the integration of chemical and genomic spaces","volume":"24","author":"Yamanishi","year":"2008","journal-title":"Bioinformatics"},{"key":"2023020109003040700_btac035-B55","first-page":"2208","author":"Zhang","year":"2020"},{"key":"2023020109003040700_btac035-B56","first-page":"1025","author":"Zheng","year":"2013"},{"key":"2023020109003040700_btac035-B57","first-page":"1059","author":"Zhou","year":"2018"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btac035\/42377810\/btac035.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/38\/7\/1995\/49010037\/btac035.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/38\/7\/1995\/49010037\/btac035.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,15]],"date-time":"2023-11-15T21:04:21Z","timestamp":1700082261000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/38\/7\/1995\/6511437"}},"subtitle":[],"editor":[{"given":"Zhiyong","family":"Lu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2022,1,19]]},"references-count":57,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2022,3,28]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btac035","relation":{},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"value":"1367-4803","type":"print"},{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2022,4,1]]},"published":{"date-parts":[[2022,1,19]]}}}