{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,16]],"date-time":"2026-01-16T07:56:42Z","timestamp":1768550202966,"version":"3.49.0"},"reference-count":55,"publisher":"Oxford University Press (OUP)","issue":"Supplement_2","license":[{"start":{"date-parts":[[2020,12,1]],"date-time":"2020-12-01T00:00:00Z","timestamp":1606780800000},"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"}]},{"DOI":"10.13039\/501100004543","name":"Chinese Scholarship Council","doi-asserted-by":"crossref","award":["201906130027"],"award-info":[{"award-number":["201906130027"]}],"id":[{"id":"10.13039\/501100004543","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020,12,30]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:sec><jats:title>Motivation<\/jats:title><jats:p>Human microbes get closely involved in an extensive variety of complex human diseases and become new drug targets. In silico methods for identifying potential microbe\u2013drug associations provide an effective complement to conventional experimental methods, which can not only benefit screening candidate compounds for drug development but also facilitate novel knowledge discovery for understanding microbe\u2013drug interaction mechanisms. On the other hand, the recent increased availability of accumulated biomedical data for microbes and drugs provides a great opportunity for a machine learning approach to predict microbe\u2013drug associations. We are thus highly motivated to integrate these data sources to improve prediction accuracy. In addition, it is extremely challenging to predict interactions for new drugs or new microbes, which have no existing microbe\u2013drug associations.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>In this work, we leverage various sources of biomedical information and construct multiple networks (graphs) for microbes and drugs. Then, we develop a novel ensemble framework of graph attention networks with a hierarchical attention mechanism for microbe\u2013drug association prediction from the constructed multiple microbe\u2013drug graphs, denoted as EGATMDA. In particular, for each input graph, we design a graph convolutional network with node-level attention to learn embeddings for nodes (i.e. microbes and drugs). To effectively aggregate node embeddings from multiple input graphs, we implement graph-level attention to learn the importance of different input graphs. Experimental results under different cross-validation settings (e.g. the setting for predicting associations for new drugs) showed that our proposed method outperformed seven state-of-the-art methods. Case studies on predicted microbe\u2013drug associations further demonstrated the effectiveness of our proposed EGATMDA method.<\/jats:p><\/jats:sec><jats:sec><jats:title>Availability<\/jats:title><jats:p>Source codes and supplementary materials are available at: https:\/\/github.com\/longyahui\/EGATMDA\/<\/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\/btaa891","type":"journal-article","created":{"date-parts":[[2020,10,8]],"date-time":"2020-10-08T19:23:26Z","timestamp":1602185006000},"page":"i779-i786","source":"Crossref","is-referenced-by-count":77,"title":["Ensembling graph attention networks for human microbe\u2013drug association prediction"],"prefix":"10.1093","volume":"36","author":[{"given":"Yahui","family":"Long","sequence":"first","affiliation":[{"name":"College of Computer Science and Electronic Engineering, Hunan University , Changsha, 410000, China"},{"name":"School of Computer Science and Engineering, Nanyang Technological University , Singapore, 639798, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0977-3600","authenticated-orcid":false,"given":"Min","family":"Wu","sequence":"additional","affiliation":[{"name":"Machine Intellection Department, Institute for Infocomm Research, Agency for Science, Technology and Research (A*STAR) , 138632, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yong","family":"Liu","sequence":"additional","affiliation":[{"name":"Joint NTU-UBC Research Centre of Excellence in Active Living for the Elderly (LILY), Nanyang Technological University , Singapore, 639798, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chee Keong","family":"Kwoh","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanyang Technological University , Singapore, 639798, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiawei","family":"Luo","sequence":"additional","affiliation":[{"name":"College of Computer Science and Electronic Engineering, Hunan University , Changsha, 410000, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoli","family":"Li","sequence":"additional","affiliation":[{"name":"Machine Intellection Department, Institute for Infocomm Research, Agency for Science, Technology and Research (A*STAR) , 138632, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2020,12,29]]},"reference":[{"key":"2023062409330671900_btaa891-B1","doi-asserted-by":"crossref","first-page":"1557","DOI":"10.1016\/j.sjbs.2018.11.016","article-title":"Prevalence of Escherichia coli strains resistance to antibiotics in wound infections and raw milk","volume":"26","author":"Alharbi","year":"2019","journal-title":"Saudi J. Biol. Sci"},{"key":"2023062409330671900_btaa891-B2","doi-asserted-by":"crossref","first-page":"115","DOI":"10.2165\/00003495-200059010-00010","article-title":"Moxifloxacin","volume":"59","author":"Balfour","year":"2000","journal-title":"Drugs"},{"key":"2023062409330671900_btaa891-B3","doi-asserted-by":"crossref","first-page":"363","DOI":"10.2165\/00003495-199957030-00007","article-title":"Moxifloxacin","volume":"57","author":"Balfour","year":"1999","journal-title":"Drugs"},{"key":"2023062409330671900_btaa891-B4","doi-asserted-by":"crossref","DOI":"10.1093\/bioinformatics\/btaa211","article-title":"Dual-dropout graph convolutional network for predicting synthetic lethality in human cancers","author":"Cai","year":"2020","journal-title":"Bioinformatics"},{"key":"2023062409330671900_btaa891-B5","first-page":"61","author":"Chen","year":"2002"},{"key":"2023062409330671900_btaa891-B6","doi-asserted-by":"crossref","first-page":"4256","DOI":"10.1093\/bioinformatics\/bty503","article-title":"Predicting miRNA-disease association based on inductive matrix completion","volume":"34","author":"Chen","year":"2018","journal-title":"Bioinformatics"},{"key":"2023062409330671900_btaa891-B7","first-page":"151","author":"Colmer-Hamood","year":"2016"},{"key":"2023062409330671900_btaa891-B8","doi-asserted-by":"crossref","first-page":"D948","DOI":"10.1093\/nar\/gky868","article-title":"The comparative toxicogenomics database: update 2019","volume":"47","author":"Davis","year":"2019","journal-title":"Nucleic Acids Res"},{"key":"2023062409330671900_btaa891-B9","doi-asserted-by":"crossref","first-page":"1019","DOI":"10.2165\/00003495-199651060-00010","article-title":"Ciprofloxacin","volume":"51","author":"Davis","year":"1996","journal-title":"Drugs"},{"key":"2023062409330671900_btaa891-B10","doi-asserted-by":"crossref","first-page":"371","DOI":"10.1016\/j.ijantimicag.2018.11.010","article-title":"Antibiotic discovery: history, methods and perspectives","volume":"53","author":"Durand","year":"2019","journal-title":"Int. J. Antimicrob. Agents"},{"key":"2023062409330671900_btaa891-B11","doi-asserted-by":"crossref","first-page":"499","DOI":"10.1089\/aid.1998.14.499","article-title":"Ciprofloxacin inhibits activation of latent human immunodeficiency virus type 1 in chronically infected promonocytic u1 cells","volume":"14","author":"Gollapudi","year":"1998","journal-title":"AIDS Res. Hum. Retroviruses"},{"key":"2023062409330671900_btaa891-B12","doi-asserted-by":"crossref","first-page":"1729","DOI":"10.2147\/DDDT.S138888","article-title":"Efficacy of antibiotic treatment of implant-associated Staphylococcus aureus infections with moxifloxacin, flucloxacillin, rifampin, and combination therapy: an animal study","volume":"11","author":"Greimel","year":"2017","journal-title":"Drug Des. Dev. Therapy"},{"key":"2023062409330671900_btaa891-B13","doi-asserted-by":"crossref","first-page":"e0156690","DOI":"10.1371\/journal.pone.0156690","article-title":"Comparative activity of ciprofloxacin, levofloxacin and moxifloxacin against Klebsiella pneumoniae, Pseudomonas aeruginosa and Stenotrophomonas maltophilia assessed by minimum inhibitory concentrations and time-kill studies","volume":"11","author":"Grillon","year":"2016","journal-title":"PLoS One"},{"key":"2023062409330671900_btaa891-B14","doi-asserted-by":"crossref","first-page":"27","DOI":"10.1038\/s41522-017-0034-1","article-title":"Human microbiome signatures of differential colorectal cancer drug metabolism","volume":"3","author":"Guthrie","year":"2017","journal-title":"NPJ Biofilms Microbiomes"},{"key":"2023062409330671900_btaa891-B15","doi-asserted-by":"crossref","first-page":"114863","DOI":"10.1016\/j.diagmicrobio.2019.06.014","article-title":"Effects of ceragenins and conventional antimicrobials on Candida albicans and Staphylococcus aureus mono and multispecies biofilms","volume":"95","author":"Hacioglu","year":"2019","journal-title":"Diagn. Microbiol. Infect. Dis"},{"key":"2023062409330671900_btaa891-B16","doi-asserted-by":"crossref","first-page":"295","DOI":"10.1126\/science.1235872","article-title":"Predicting and manipulating cardiac drug inactivation by the human gut bacterium Eggerthella lenta","volume":"341","author":"Haiser","year":"2013","journal-title":"Science"},{"key":"2023062409330671900_btaa891-B17","first-page":"705","author":"Han","year":"2019"},{"key":"2023062409330671900_btaa891-B18","doi-asserted-by":"crossref","first-page":"851","DOI":"10.1093\/bioinformatics\/btz621","article-title":"Graph convolution for predicting associations between miRNA and drug resistance","volume":"36","author":"Huang","year":"2019","journal-title":"Bioinformatics"},{"key":"2023062409330671900_btaa891-B19","doi-asserted-by":"crossref","first-page":"207","DOI":"10.1038\/nature11234","article-title":"Structure, function and diversity of the healthy human microbiome","volume":"486","author":"Huttenhower","year":"2012","journal-title":"Nature"},{"key":"2023062409330671900_btaa891-B20","author":"Jain","year":"2013"},{"key":"2023062409330671900_btaa891-B21","doi-asserted-by":"crossref","first-page":"e1005366","DOI":"10.1371\/journal.pcbi.1005366","article-title":"Genome composition and phylogeny of microbes predict their co-occurrence in the environment","volume":"13","author":"Kamneva","year":"2017","journal-title":"PLoS Comput. Biol"},{"key":"2023062409330671900_btaa891-B22","first-page":"1855","author":"Kashyap","year":"2017"},{"key":"2023062409330671900_btaa891-B23","doi-asserted-by":"crossref","first-page":"327","DOI":"10.1038\/nature10213","article-title":"Human nutrition, the gut microbiome and the immune system","volume":"474","author":"Kau","year":"2011","journal-title":"Nature"},{"key":"2023062409330671900_btaa891-B24","doi-asserted-by":"crossref","first-page":"2858","DOI":"10.1002\/jsfa.8115","article-title":"Characterization of antimicrobial resistance and quinolone resistance factors in high-level ciprofloxacin-resistant Enterococcus faecalis and Enterococcus faecium isolates obtained from fresh produce and fecal samples of patients","volume":"97","author":"Kim","year":"2017","journal-title":"J. Sci. Food Agric"},{"key":"2023062409330671900_btaa891-B25","author":"Kingma","year":"2019"},{"key":"2023062409330671900_btaa891-B26","author":"Kipf","year":"2017"},{"key":"2023062409330671900_btaa891-B27","doi-asserted-by":"crossref","first-page":"343","DOI":"10.1038\/msb.2009.98","article-title":"A side effect resource to capture phenotypic effects of drugs","volume":"6","author":"Kuhn","year":"2010","journal-title":"Mol. Syst. Biol"},{"key":"2023062409330671900_btaa891-B28","first-page":"4823","author":"Linmei","year":"2019"},{"key":"2023062409330671900_btaa891-B29","first-page":"64","author":"Liu","year":"2020"},{"key":"2023062409330671900_btaa891-B30","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":"2018","journal-title":"IEEE\/ACM Trans. Comput. Biol. Bioinformatics"},{"key":"2023062409330671900_btaa891-B31","doi-asserted-by":"crossref","first-page":"85","DOI":"10.1093\/bib\/bbw005","article-title":"An analysis of human microbe\u2013disease associations","volume":"18","author":"Ma","year":"2017","journal-title":"Briefings in Bioinformatics"},{"key":"2023062409330671900_btaa891-B32","doi-asserted-by":"crossref","first-page":"238","DOI":"10.1093\/bioinformatics\/bts670","article-title":"Drug-target interaction prediction by learning from local information and neighbors","volume":"29","author":"Mei","year":"2013","journal-title":"Bioinformatics"},{"key":"2023062409330671900_btaa891-B33","doi-asserted-by":"crossref","first-page":"20","DOI":"10.1016\/j.jpeds.2009.06.063","article-title":"Intestinal microbial ecology in premature infants assessed with non-culture-based techniques","volume":"156","author":"Mshvildadze","year":"2010","journal-title":"J. Pediat"},{"key":"2023062409330671900_btaa891-B34","doi-asserted-by":"crossref","first-page":"142","DOI":"10.1128\/CMR.11.1.142","article-title":"Diarrheagenic Escherichia coli","volume":"11","author":"Nataro","year":"1998","journal-title":"Clin. Microbiol. Rev"},{"key":"2023062409330671900_btaa891-B35","first-page":"2110","author":"Qiu","year":"2018"},{"key":"2023062409330671900_btaa891-B36","first-page":"121","author":"Ravindra","year":"2020"},{"key":"2023062409330671900_btaa891-B37","doi-asserted-by":"crossref","first-page":"800","DOI":"10.1038\/nrc3610","article-title":"The microbiome and cancer","volume":"13","author":"Schwabe","year":"2013","journal-title":"Nat. Rev. Cancer"},{"key":"2023062409330671900_btaa891-B38","doi-asserted-by":"crossref","first-page":"227","DOI":"10.1038\/nrmicro2974","article-title":"The gut microbiota-masters of host development and physiology","volume":"11","author":"Sommer","year":"2013","journal-title":"Nat. Rev. Microbiol"},{"key":"2023062409330671900_btaa891-B39","doi-asserted-by":"crossref","DOI":"10.3389\/fcimb.2018.00424","article-title":"Mdad: a special resource for microbe-drug associations","author":"Sun","year":"2018","journal-title":"Front. Cell. Infect. Microbiol"},{"key":"2023062409330671900_btaa891-B40","doi-asserted-by":"crossref","first-page":"207","DOI":"10.1038\/nrmicro2298","article-title":"The population genetics of commensal Escherichia coli","volume":"8","author":"Tenaillon","year":"2010","journal-title":"Nat. Rev. Microbiol"},{"key":"2023062409330671900_btaa891-B41","doi-asserted-by":"crossref","first-page":"71","DOI":"10.2165\/11634300-000000000-00000","article-title":"Moxifloxacin safety","volume":"12","author":"Tulkens","year":"2012","journal-title":"Drugs R&D"},{"key":"2023062409330671900_btaa891-B42","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":"2023062409330671900_btaa891-B43","author":"Veli\u010dkovi\u0107","year":"2018"},{"key":"2023062409330671900_btaa891-B44","doi-asserted-by":"crossref","first-page":"61","DOI":"10.1038\/nrmicro2047","article-title":"Genome-scale analyses of health-promoting bacteria: probiogenomics","volume":"7","author":"Ventura","year":"2009","journal-title":"Nat. Rev. Microbiol"},{"key":"2023062409330671900_btaa891-B45","first-page":"2022","author":"Wang","year":"2019"},{"key":"2023062409330671900_btaa891-B46","doi-asserted-by":"crossref","first-page":"1109","DOI":"10.1038\/nature07336","article-title":"Innate immunity and intestinal microbiota in the development of type 1 diabetes","volume":"455","author":"Wen","year":"2008","journal-title":"Nature"},{"key":"2023062409330671900_btaa891-B47","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":"2023062409330671900_btaa891-B48","first-page":"2091","author":"Wu","year":"2019"},{"key":"2023062409330671900_btaa891-B49","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":"2023062409330671900_btaa891-B50","first-page":"7370","author":"Yao","year":"2019"},{"key":"2023062409330671900_btaa891-B51","doi-asserted-by":"crossref","first-page":"2365","DOI":"10.1073\/pnas.0812600106","article-title":"Human gut microbiota in obesity and after gastric bypass","volume":"106","author":"Zhang","year":"2009","journal-title":"Proc. Natl. Acad. Sci. USA"},{"key":"2023062409330671900_btaa891-B52","first-page":"2347","author":"Zhao","year":"2019"},{"key":"2023062409330671900_btaa891-B53","first-page":"183","author":"Zhu","year":"2019"},{"key":"2023062409330671900_btaa891-B54","doi-asserted-by":"crossref","first-page":"462","DOI":"10.1038\/s41586-019-1291-3","article-title":"Mapping human microbiome drug metabolism by gut bacteria and their genes","volume":"570","author":"Zimmermann","year":"2019","journal-title":"Nature"},{"key":"2023062409330671900_btaa891-B55","doi-asserted-by":"crossref","first-page":"i457","DOI":"10.1093\/bioinformatics\/bty294","article-title":"Modeling polypharmacy side effects with graph convolutional networks","volume":"34","author":"Zitnik","year":"2018","journal-title":"Bioinformatics"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/36\/Supplement_2\/i779\/50693574\/btaa891.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/36\/Supplement_2\/i779\/50693574\/btaa891.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,15]],"date-time":"2024-08-15T18:37:12Z","timestamp":1723747032000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/36\/Supplement_2\/i779\/6055932"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,12]]},"references-count":55,"journal-issue":{"issue":"Supplement_2","published-print":{"date-parts":[[2020,12,30]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btaa891","relation":{},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"value":"1367-4803","type":"print"},{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2020,12]]},"published":{"date-parts":[[2020,12]]}}}