{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T17:28:49Z","timestamp":1781803729697,"version":"3.54.5"},"reference-count":56,"publisher":"Oxford University Press (OUP)","issue":"8","license":[{"start":{"date-parts":[[2022,2,16]],"date-time":"2022-02-16T00:00:00Z","timestamp":1644969600000},"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":["61873089"],"award-info":[{"award-number":["61873089"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Key Program of National Natural Science Foundation of China","award":["62032007"],"award-info":[{"award-number":["62032007"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,4,12]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:sec><jats:title>Motivation<\/jats:title><jats:p>Graphs or networks are widely utilized to model the interactions between different entities (e.g. proteins, drugs, etc.) for biomedical applications. Predicting potential interactions\/links in biomedical networks is important for understanding the pathological mechanisms of various complex human diseases, as well as screening compound targets for drug discovery. Graph neural networks (GNNs) have been utilized for link prediction in various biomedical networks, which rely on the node features extracted from different data sources, e.g. sequence, structure and network data. However, it is challenging to effectively integrate these data sources and automatically extract features for different link prediction tasks.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>In this article, we propose a novel Pre-Training Graph Neural Networks-based framework named PT-GNN to integrate different data sources for link prediction in biomedical networks. First, we design expressive deep learning methods [e.g. convolutional neural network and graph convolutional network (GCN)] to learn features for individual nodes from sequence and structure data. Second, we further propose a GCN-based encoder to effectively refine the node features by modelling the dependencies among nodes in the network. Third, the node features are pre-trained based on graph reconstruction tasks. The pre-trained features can be used for model initialization in downstream tasks. Extensive experiments have been conducted on two critical link prediction tasks, i.e. synthetic lethality (SL) prediction and drug\u2013target interaction (DTI) prediction. Experimental results demonstrate PT-GNN outperforms the state-of-the-art methods for SL prediction and DTI prediction. In addition, the pre-trained features benefit improving the performance and reduce the training time of existing models.<\/jats:p><\/jats:sec><jats:sec><jats:title>Availability and implementation<\/jats:title><jats:p>Python codes and dataset are available at: https:\/\/github.com\/longyahui\/PT-GNN.<\/jats:p><\/jats:sec><jats:sec><jats:title>Supplementary information<\/jats:title><jats:p>Supplementary data are available at Bioinformatics online.<\/jats:p><\/jats:sec>","DOI":"10.1093\/bioinformatics\/btac100","type":"journal-article","created":{"date-parts":[[2022,2,14]],"date-time":"2022-02-14T20:27:34Z","timestamp":1644870454000},"page":"2254-2262","source":"Crossref","is-referenced-by-count":85,"title":["Pre-training graph neural networks for link prediction in biomedical networks"],"prefix":"10.1093","volume":"38","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2765-3007","authenticated-orcid":false,"given":"Yahui","family":"Long","sequence":"first","affiliation":[{"name":"Singapore Immunology Network (SIgN), Agency for Science, Technology and Research , Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0977-3600","authenticated-orcid":false,"given":"Min","family":"Wu","sequence":"additional","affiliation":[{"name":"Institute for Infocomm Research, Agency for Science, Technology and Research , Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yong","family":"Liu","sequence":"additional","affiliation":[{"name":"Joint NTU-UBC Research Centre of Excellence in Active Living for the Elderly , Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuan","family":"Fang","sequence":"additional","affiliation":[{"name":"School of Information Systems, Singapore Management University , 178902 Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chee Keong","family":"Kwoh","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanyang Technological University , Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7547-6423","authenticated-orcid":false,"given":"Jinmiao","family":"Chen","sequence":"additional","affiliation":[{"name":"Singapore Immunology Network (SIgN), Agency for Science, Technology and Research , Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiawei","family":"Luo","sequence":"additional","affiliation":[{"name":"College of Computer Science and Electronic Engineering, Hunan University , Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoli","family":"Li","sequence":"additional","affiliation":[{"name":"Institute for Infocomm Research, Agency for Science, Technology and Research , Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2022,2,16]]},"reference":[{"key":"2023020109030076900_btac100-B1","doi-asserted-by":"crossref","first-page":"4458","DOI":"10.1093\/bioinformatics\/btaa211","article-title":"Dual-dropout graph convolutional network for predicting synthetic lethality in human cancers","volume":"36","author":"Cai","year":"2020","journal-title":"Bioinformatics"},{"key":"2023020109030076900_btac100-B2","first-page":"3438","article-title":"Measuring and relieving the over-smoothing problem for graph neural networks from the topological view","volume":"34","author":"Chen","year":"2020","journal-title":"Proc. AAAI Conf. Artif. Intell"},{"key":"2023020109030076900_btac100-B3","first-page":"558","article-title":"Long non-coding rnas and complex diseases: from experimental results to computational models","volume":"18","author":"Chen","year":"2017","journal-title":"Brief. Bioinf"},{"key":"2023020109030076900_btac100-B4","doi-asserted-by":"crossref","first-page":"733","DOI":"10.1093\/bioinformatics\/btw715","article-title":"A novel approach based on katz measure to predict associations of human microbiota with non-infectious diseases","volume":"33","author":"Chen","year":"2017","journal-title":"Bioinformatics"},{"key":"2023020109030076900_btac100-B5","doi-asserted-by":"crossref","first-page":"3178","DOI":"10.1093\/bioinformatics\/bty333","article-title":"Bnpmda: bipartite network projection for mirna\u2013disease association prediction","volume":"34","author":"Chen","year":"2018","journal-title":"Bioinformatics"},{"key":"2023020109030076900_btac100-B6","doi-asserted-by":"crossref","first-page":"4256","DOI":"10.1093\/bioinformatics\/bty503","article-title":"Predicting mirna\u2013disease association based on inductive matrix completion","volume":"34","author":"Chen","year":"2018","journal-title":"Bioinformatics"},{"key":"2023020109030076900_btac100-B7","doi-asserted-by":"crossref","first-page":"515","DOI":"10.1093\/bib\/bbx130","article-title":"Micrornas and complex diseases: from experimental results to computational models","volume":"20","author":"Chen","year":"2019","journal-title":"Brief. Bioinf"},{"key":"2023020109030076900_btac100-B8","doi-asserted-by":"crossref","first-page":"2617","DOI":"10.1093\/bioinformatics\/btab143","article-title":"Bipartite graph-based approach for clustering of cell lines by gene expression-drug response associations","volume":"37","author":"Chi","year":"2021","journal-title":"Bioinformatics"},{"key":"2023020109030076900_btac100-B9","doi-asserted-by":"crossref","first-page":"813","DOI":"10.1098\/rsif.2008.0014","article-title":"Random walk models in biology","volume":"5","author":"Codling","year":"2008","journal-title":"J. R. Soc. Interface"},{"key":"2023020109030076900_btac100-B10","first-page":"4171","article-title":"Bert: pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2019"},{"key":"2023020109030076900_btac100-B11","first-page":"865","author":"Dhingra","year":"2021"},{"key":"2023020109030076900_btac100-B12","doi-asserted-by":"crossref","first-page":"426","DOI":"10.1093\/bioinformatics\/btab651","article-title":"Mvgcn: data integration through multi-view graph convolutional network for predicting links in biomedical bipartite networks","volume":"38","author":"Fu","year":"2022","journal-title":"Bioinformatics"},{"key":"2023020109030076900_btac100-B13","doi-asserted-by":"crossref","first-page":"D1011","DOI":"10.1093\/nar\/gkv1108","article-title":"Synlethdb: synthetic lethality database toward discovery of selective and sensitive anticancer drug targets","volume":"44","author":"Guo","year":"2016","journal-title":"Nucleic Acids Res"},{"key":"2023020109030076900_btac100-B14","doi-asserted-by":"crossref","first-page":"4041","DOI":"10.1109\/JBHI.2021.3079302","article-title":"Prediction of synthetic lethal interactions in human cancers using multi-view graph auto-encoder","volume":"25","author":"Hao","year":"2021","journal-title":"IEEE J. Biomed. Health Inf"},{"key":"2023020109030076900_btac100-B15","doi-asserted-by":"crossref","first-page":"1037","DOI":"10.1093\/bioinformatics\/btz694","article-title":"Identifying enhancer\u2013promoter interactions with neural network based on pre-trained dna vectors and attention mechanism","volume":"36","author":"Hong","year":"2020","journal-title":"Bioinformatics"},{"key":"2023020109030076900_btac100-B16","author":"Hu","year":"2020"},{"key":"2023020109030076900_btac100-B17","first-page":"1857","author":"Hu","year":"2020"},{"key":"2023020109030076900_btac100-B18","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s12859-019-3197-3","article-title":"Predicting synthetic lethal interactions in human cancers using graph regularized self-representative matrix factorization","volume":"20","author":"Huang","year":"2019","journal-title":"BMC Bioinformatics"},{"key":"2023020109030076900_btac100-B19","doi-asserted-by":"crossref","first-page":"830","DOI":"10.1093\/bioinformatics\/btaa880","article-title":"Moltrans: molecular interaction transformer for drug\u2013target interaction prediction","volume":"37","author":"Huang","year":"2021","journal-title":"Bioinformatics"},{"key":"2023020109030076900_btac100-B20","author":"Kingma","year":"2015"},{"key":"2023020109030076900_btac100-B21","author":"Kipf","year":"2017"},{"key":"2023020109030076900_btac100-B22","doi-asserted-by":"crossref","first-page":"e1007129","DOI":"10.1371\/journal.pcbi.1007129","article-title":"Deepconv-dti: prediction of drug\u2013target interactions via deep learning with convolution on protein sequences","volume":"15","author":"Lee","year":"2019","journal-title":"PLoS Comput. Biol"},{"key":"2023020109030076900_btac100-B23","first-page":"121","author":"Li","year":"2020"},{"key":"2023020109030076900_btac100-B24","doi-asserted-by":"crossref","first-page":"e1004760","DOI":"10.1371\/journal.pcbi.1004760","article-title":"Neighborhood regularized logistic matrix factorization for drug\u2013target interaction prediction","volume":"12","author":"Liu","year":"2016","journal-title":"PLoS Comput. Biol"},{"key":"2023020109030076900_btac100-B25","doi-asserted-by":"crossref","first-page":"748","DOI":"10.1109\/TCBB.2019.2909908","article-title":"Sl 2 mf: predicting synthetic lethality in human cancers via logistic matrix factorization","volume":"17","author":"Liu","year":"2019","journal-title":"IEEE\/ACM Trans. Comput. Biol. Bioinf"},{"key":"2023020109030076900_btac100-B26","first-page":"64","author":"Liu","year":"2020"},{"key":"2023020109030076900_btac100-B27","doi-asserted-by":"crossref","first-page":"3328","DOI":"10.1093\/bioinformatics\/btab224","article-title":"Hpofiller: identifying missing protein\u2013phenotype associations by graph convolutional network","volume":"37","author":"Liu","year":"2021","journal-title":"Bioinformatics"},{"key":"2023020109030076900_btac100-B28","doi-asserted-by":"crossref","first-page":"bbab457","DOI":"10.1093\/bib\/bbab457","article-title":"Graphcdr: a graph neural network method with contrastive learning for cancer drug response prediction","volume":"23","author":"Liu","year":"2021","journal-title":"Brief. Bioinf"},{"key":"2023020109030076900_btac100-B29","first-page":"1","author":"Liu","year":"2021"},{"key":"2023020109030076900_btac100-B30","doi-asserted-by":"crossref","first-page":"i779","DOI":"10.1093\/bioinformatics\/btaa891","article-title":"Ensembling graph attention networks for human microbe\u2013drug association prediction","volume":"36","author":"Long","year":"2020","journal-title":"Bioinformatics"},{"key":"2023020109030076900_btac100-B31","doi-asserted-by":"crossref","first-page":"4918","DOI":"10.1093\/bioinformatics\/btaa598","article-title":"Predicting human microbe-drug associations via graph convolutional network with conditional random field","volume":"36","author":"Long","year":"2020","journal-title":"Bioinformatics"},{"key":"2023020109030076900_btac100-B32","doi-asserted-by":"crossref","first-page":"2432","DOI":"10.1093\/bioinformatics\/btab110","article-title":"Graph contextualized attention network for predicting synthetic lethality in human cancers","volume":"37","author":"Long","year":"2021","journal-title":"Bioinformatics"},{"key":"2023020109030076900_btac100-B33","first-page":"4276","article-title":"Learning to pre-train graph neural networks","volume":"35","author":"Lu","year":"2021","journal-title":"Proceed. AAAI Conf. Artif. Intell"},{"key":"2023020109030076900_btac100-B34","doi-asserted-by":"crossref","first-page":"1341","DOI":"10.1109\/TCBB.2018.2883041","article-title":"Ntshmda: prediction of human microbe-disease association based on random walk by integrating network topological similarity","volume":"17","author":"Luo","year":"2020","journal-title":"IEEE\/ACM Trans. Comput. Biol. Bioinf"},{"key":"2023020109030076900_btac100-B35","doi-asserted-by":"crossref","first-page":"435","DOI":"10.1093\/bioinformatics\/btab652","article-title":"Hypergraph-based logistic matrix factorization for metabolite\u2013disease interaction prediction","volume":"38","author":"Ma","year":"2022","journal-title":"Bioinformatics"},{"key":"2023020109030076900_btac100-B36","first-page":"13886","author":"Mi","year":"2020"},{"key":"2023020109030076900_btac100-B37","author":"Navarin","year":"2017"},{"key":"2023020109030076900_btac100-B38","doi-asserted-by":"crossref","first-page":"1140","DOI":"10.1093\/bioinformatics\/btaa921","article-title":"Graphdta: predicting drug\u2013target binding affinity with graph neural networks","volume":"37","author":"Nguyen","year":"2021","journal-title":"Bioinformatics"},{"key":"2023020109030076900_btac100-B39","doi-asserted-by":"crossref","first-page":"D529","DOI":"10.1093\/nar\/gky1079","article-title":"The biogrid interaction database: 2019 update","volume":"47","author":"Oughtred","year":"2019","journal-title":"Nucleic Acids Res"},{"key":"2023020109030076900_btac100-B40","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":"2023020109030076900_btac100-B41","doi-asserted-by":"crossref","first-page":"553","DOI":"10.1186\/s12864-016-2828-6","article-title":"Intego2: a web tool for measuring and visualizing gene semantic similarities using gene ontology","volume":"17","author":"Peng","year":"2016","journal-title":"BMC Genomics"},{"key":"2023020109030076900_btac100-B42","first-page":"7458","author":"Qian","year":"2021"},{"key":"2023020109030076900_btac100-B43","doi-asserted-by":"crossref","first-page":"2401","DOI":"10.1093\/bioinformatics\/btaa003","article-title":"Udsmprot: universal deep sequence models for protein classification","volume":"36","author":"Strodthoff","year":"2020","journal-title":"Bioinformatics"},{"key":"2023020109030076900_btac100-B44","doi-asserted-by":"crossref","first-page":"182","DOI":"10.1093\/bib\/bby117","article-title":"Network embedding in biomedical data science","volume":"21","author":"Su","year":"2020","journal-title":"Brief. Bioinf"},{"key":"2023020109030076900_btac100-B45","doi-asserted-by":"crossref","first-page":"D506","DOI":"10.1093\/nar\/gky1049","article-title":"UniProt: a worldwide hub of protein knowledge","volume":"47","year":"2019","journal-title":"Nucleic Acids Res"},{"key":"2023020109030076900_btac100-B46","author":"Veli\u010dkovi\u0107","year":"2018"},{"key":"2023020109030076900_btac100-B47","doi-asserted-by":"crossref","first-page":"104","DOI":"10.1093\/bioinformatics\/bty543","article-title":"Neodti: neural integration of neighbor information from a heterogeneous network for discovering new drug\u2013target interactions","volume":"35","author":"Wan","year":"2019","journal-title":"Bioinformatics"},{"key":"2023020109030076900_btac100-B48","doi-asserted-by":"crossref","first-page":"bbab286","DOI":"10.1093\/bib\/bbab286","article-title":"Circular rnas and complex diseases: from experimental results to computational models","volume":"22","author":"Wang","year":"2021","journal-title":"Brief. Bioinf"},{"key":"2023020109030076900_btac100-B49","doi-asserted-by":"crossref","first-page":"D1074","DOI":"10.1093\/nar\/gkx1037","article-title":"Drugbank 5.0: a major update to the drugbank database for 2018","volume":"46","author":"Wishart","year":"2018","journal-title":"Nucleic Acids Res"},{"key":"2023020109030076900_btac100-B50","first-page":"7370","article-title":"Graph convolutional networks for text classification","volume":"33","author":"Yao","year":"2019","journal-title":"Proc. AAAI Conf. Artif. Intell"},{"key":"2023020109030076900_btac100-B51","doi-asserted-by":"crossref","first-page":"1241","DOI":"10.1093\/bioinformatics\/btz718","article-title":"Graph embedding on biomedical networks: methods, applications and evaluations","volume":"36","author":"Yue","year":"2020","journal-title":"Bioinformatics"},{"key":"2023020109030076900_btac100-B52","doi-asserted-by":"crossref","first-page":"i121","DOI":"10.1093\/bioinformatics\/btw255","article-title":"Convolutional neural network architectures for predicting dna\u2013protein binding","volume":"32","author":"Zeng","year":"2016","journal-title":"Bioinformatics"},{"key":"2023020109030076900_btac100-B53","doi-asserted-by":"crossref","first-page":"3474","DOI":"10.1093\/bioinformatics\/btaa157","article-title":"A graph regularized generalized matrix factorization model for predicting links in biomedical bipartite networks","volume":"36","author":"Zhang","year":"2020","journal-title":"Bioinformatics"},{"key":"2023020109030076900_btac100-B54","first-page":"1025","author":"Zheng","year":"2013"},{"key":"2023020109030076900_btac100-B55","doi-asserted-by":"crossref","first-page":"461","DOI":"10.1093\/bioinformatics\/btab650","article-title":"Tgsa: protein-protein association-based twin graph neural networks for drug response prediction with similarity augmentation","volume":"38","author":"Zhu","year":"2022","journal-title":"Bioinformatics"},{"key":"2023020109030076900_btac100-B56","doi-asserted-by":"crossref","first-page":"2337","DOI":"10.1093\/bioinformatics\/btx160","article-title":"Deep mining heterogeneous networks of biomedical linked data to predict novel drug\u2013target associations","volume":"33","author":"Zong","year":"2017","journal-title":"Bioinformatics"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btac100\/42674506\/btac100.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/38\/8\/2254\/49009728\/btac100.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/38\/8\/2254\/49009728\/btac100.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,18]],"date-time":"2024-09-18T14:46:54Z","timestamp":1726670814000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/38\/8\/2254\/6529539"}},"subtitle":[],"editor":[{"given":"Inanc","family":"Birol","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2022,2,16]]},"references-count":56,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2022,4,12]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btac100","relation":{},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"value":"1367-4803","type":"print"},{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2022,4,15]]},"published":{"date-parts":[[2022,2,16]]}}}