{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T15:11:37Z","timestamp":1783437097451,"version":"3.54.6"},"reference-count":46,"publisher":"Oxford University Press (OUP)","issue":"4","license":[{"start":{"date-parts":[[2021,11,23]],"date-time":"2021-11-23T00:00:00Z","timestamp":1637625600000},"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":["61972422"],"award-info":[{"award-number":["61972422"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62072058"],"award-info":[{"award-number":["62072058"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,1,27]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:sec><jats:title>Motivation<\/jats:title><jats:p>Accumulated clinical studies show that microbes living in humans interact closely with human hosts, and get involved in modulating drug efficacy and drug toxicity. Microbes have become novel targets for the development of antibacterial agents. Therefore, screening of microbe\u2013drug associations can benefit greatly drug research and development. With the increase of microbial genomic and pharmacological datasets, we are greatly motivated to develop an effective computational method to identify new microbe\u2013drug associations.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>In this article, we proposed a novel method, Graph2MDA, to predict microbe\u2013drug associations by using variational graph autoencoder (VGAE). We constructed multi-modal attributed graphs based on multiple features of microbes and drugs, such as molecular structures, microbe genetic sequences and function annotations. Taking as input the multi-modal attribute graphs, VGAE was trained to learn the informative and interpretable latent representations of each node and the whole graph, and then a deep neural network classifier was used to predict microbe\u2013drug associations. The hyperparameter analysis and model ablation studies showed the sensitivity and robustness of our model. We evaluated our method on three independent datasets and the experimental results showed that our proposed method outperformed six existing state-of-the-art methods. We also explored the meaning of the learned latent representations of drugs and found that the drugs show obvious clustering patterns that are significantly consistent with drug ATC classification. Moreover, we conducted case studies on two microbes and two drugs and found 75\u201395% predicted associations have been reported in PubMed literature. Our extensive performance evaluations validated the effectiveness of our proposed method.<\/jats:p><\/jats:sec><jats:sec><jats:title>Availability and implementation<\/jats:title><jats:p>Source codes and preprocessed data are available at https:\/\/github.com\/moen-hyb\/Graph2MDA.<\/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\/btab792","type":"journal-article","created":{"date-parts":[[2021,11,17]],"date-time":"2021-11-17T12:20:04Z","timestamp":1637151604000},"page":"1118-1125","source":"Crossref","is-referenced-by-count":76,"title":["Graph2MDA: a multi-modal variational graph embedding model for predicting microbe\u2013drug associations"],"prefix":"10.1093","volume":"38","author":[{"given":"Lei","family":"Deng","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Central South University , Changsha 410083, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yibiao","family":"Huang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Central South University , Changsha 410083, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuejun","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Nanjing Tech University , Nanjing 211816, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7158-913X","authenticated-orcid":false,"given":"Hui","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Nanjing Tech University , Nanjing 211816, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2021,11,23]]},"reference":[{"key":"2023020108523707100_btab792-B1","doi-asserted-by":"crossref","first-page":"268","DOI":"10.1016\/j.ijid.2020.02.018","article-title":"Discovery and development of safe-in-man broad-spectrum antiviral agents","volume":"93","author":"Andersen","year":"2020","journal-title":"Int. J. Infect. Dis"},{"key":"2023020108523707100_btab792-B2","first-page":"1","volume-title":"Cloxacillin.sciencedirect. xPharm: The Comprehensive Pharmacology Reference","author":"Castle","year":"2007"},{"key":"2023020108523707100_btab792-B3","doi-asserted-by":"crossref","first-page":"1440","DOI":"10.1093\/bioinformatics\/btx773","article-title":"A novel approach based on KATZ measure to predict associations of human microbiota with non-infectious diseases","volume":"34","author":"Chen","year":"2018","journal-title":"Bioinformatics"},{"key":"2023020108523707100_btab792-B4","doi-asserted-by":"crossref","first-page":"e01724-17","DOI":"10.1128\/AAC.01724-17","article-title":"Susceptibility of Mycobacterium tuberculosis to Amikacin, Kanamycin, and Capreomycin","volume":"62","author":"Dijkstra","year":"2018","journal-title":"Antimicrob. Agents Chemother"},{"key":"2023020108523707100_btab792-B5","doi-asserted-by":"crossref","first-page":"25","DOI":"10.1016\/j.ymeth.2020.08.004","article-title":"Variational graph auto-encoders for miRNA\u2013disease association prediction","volume":"192","author":"Ding","year":"2021","journal-title":"Methods"},{"key":"2023020108523707100_btab792-B6","doi-asserted-by":"crossref","first-page":"15","DOI":"10.2334\/josnusd.54.15","article-title":"Inhibitory activity of Aloe vera gel on some clinically isolated cariogenic and periodontopathic bacteria","volume":"54","author":"Fani","year":"2012","journal-title":"J. Oral Sci"},{"key":"2023020108523707100_btab792-B7","doi-asserted-by":"crossref","first-page":"193","DOI":"10.4103\/0974-8520.105237","article-title":"Pharmacological attribute of Aloe vera: revalidation through experimental and clinical studies","volume":"33","author":"Gupta","year":"2012","journal-title":"Ayu"},{"key":"2023020108523707100_btab792-B8","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":"2023020108523707100_btab792-B9","doi-asserted-by":"crossref","first-page":"W652","DOI":"10.1093\/nar\/gkq367","article-title":"SIMCOMP\/SUBCOMP: chemical structure search servers for network analyses","volume":"38","author":"Hattori","year":"2010","journal-title":"Nucleic Acids Res"},{"key":"2023020108523707100_btab792-B10","author":"He","year":"2016"},{"key":"2023020108523707100_btab792-B11","author":"Hinton","year":"2017"},{"key":"2023020108523707100_btab792-B12","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":"2023020108523707100_btab792-B13","doi-asserted-by":"crossref","first-page":"92","DOI":"10.1016\/j.patrec.2018.02.004","article-title":"Random walk-based feature learning for micro-expression recognition","volume":"115","author":"Jain","year":"2018","journal-title":"Pattern Recogn. Lett"},{"key":"2023020108523707100_btab792-B14","doi-asserted-by":"crossref","first-page":"135","DOI":"10.3109\/01480545.2013.834350","article-title":"Evaluation of in vitro and in vivo antioxidant potential of polysaccharides from Aloe vera (Aloe barbadensis Miller) gel","volume":"37","author":"Kaithwas","year":"2014","journal-title":"Drug Chem. Toxicol"},{"key":"2023020108523707100_btab792-B15","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":"2023020108523707100_btab792-B16","doi-asserted-by":"crossref","first-page":"1855","DOI":"10.1016\/j.mayocp.2017.10.004","article-title":"Microbiome at the frontier of personalized medicine","volume":"92","author":"Kashyap","year":"2017","journal-title":"Mayo Clin. Proc"},{"key":"2023020108523707100_btab792-B17","author":"Kingma","year":"2014"},{"key":"2023020108523707100_btab792-B18","author":"Kipf","year":"2016"},{"key":"2023020108523707100_btab792-B19","author":"Kipf","year":"2016"},{"key":"2023020108523707100_btab792-B20","doi-asserted-by":"crossref","first-page":"938","DOI":"10.1126\/science.aai9383","article-title":"Vaginal bacteria modify HIV tenofovir microbicide efficacy in African women","volume":"356","author":"Klatt","year":"2017","journal-title":"Science"},{"key":"2023020108523707100_btab792-B21","doi-asserted-by":"crossref","first-page":"12509","DOI":"10.1073\/pnas.0805504105","article-title":"Erythromycin derivatives inhibit HIV-1 replication in macrophages through modulation of MAPK activity to induce small isoforms of C\/EBPbeta","volume":"105","author":"Komuro","year":"2008","journal-title":"Proc. Natl. Acad. Sci. USA"},{"key":"2023020108523707100_btab792-B22","doi-asserted-by":"crossref","first-page":"266","DOI":"10.1109\/JBHI.2020.2998906","article-title":"Association mining to identify microbe drug interactions based on heterogeneous network embedding representation","volume":"25","author":"Long","year":"2021","journal-title":"IEEE J. Biomed. Health Inform"},{"key":"2023020108523707100_btab792-B23","doi-asserted-by":"crossref","first-page":"4918","DOI":"10.1093\/bioinformatics\/btaa598","article-title":"Predicting human microbe\u2013drug associations via graph convolutional network with conditional random field","volume":"36","author":"Long","year":"2020","journal-title":"Bioinformatics"},{"key":"2023020108523707100_btab792-B24","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":"2023020108523707100_btab792-B25","doi-asserted-by":"crossref","first-page":"1341","DOI":"10.1109\/TCBB.2018.2883041","article-title":"NTSHMDA: prediction of human microbe\u2013disease association based on random walk by integrating network topological similarity","volume":"17","author":"Luo","year":"2020","journal-title":"IEEE\/ACM Trans. Comput. Biol. Bioinform"},{"key":"2023020108523707100_btab792-B26","doi-asserted-by":"crossref","first-page":"478","DOI":"10.1038\/nri1373","article-title":"Interactions between commensal intestinal bacteria and the immune system","volume":"4","author":"Macpherson","year":"2004","journal-title":"Nat. Rev. Immunol"},{"key":"2023020108523707100_btab792-B27","doi-asserted-by":"crossref","first-page":"2868","DOI":"10.3389\/fimmu.2018.02868","article-title":"Exploring the human microbiome: the potential future role of next-generation sequencing in disease diagnosis and treatment","volume":"9","author":"Malla","year":"2018","journal-title":"Front. Immunol"},{"key":"2023020108523707100_btab792-B28","doi-asserted-by":"crossref","first-page":"107135","DOI":"10.1016\/j.asoc.2021.107135","article-title":"Drug repositioning based on similarity constrained probabilistic matrix factorization: COVID-19 as a case study","volume":"103","author":"Meng","year":"2021","journal-title":"Appl. Soft Comput"},{"key":"2023020108523707100_btab792-B29","doi-asserted-by":"crossref","first-page":"6938","DOI":"10.1128\/AAC.03239-14","article-title":"In vivo efficacy of apramycin in murine infection models","volume":"58","author":"Meyer","year":"2014","journal-title":"Antimicrob. Agents Chemother"},{"key":"2023020108523707100_btab792-B30","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-211-89836-9_64","volume-title":"Anatomical Therapeutic Chemical Classification System (ATC)","author":"Nahler","year":"2009"},{"key":"2023020108523707100_btab792-B31","doi-asserted-by":"crossref","first-page":"D894","DOI":"10.1093\/nar\/gkx1157","article-title":"aBiofilm: a resource of anti-biofilm agents and their potential implications in targeting antibiotic drug resistance","volume":"46","author":"Rajput","year":"2018","journal-title":"Nucleic Acids Res"},{"key":"2023020108523707100_btab792-B32","doi-asserted-by":"crossref","first-page":"823178","DOI":"10.1155\/2015\/823178","article-title":"Antibacterial and antiproliferative activities of plumericin, an iridoid isolated from Momordica charantia Vine","volume":"2015","author":"Saengsai","year":"2015","journal-title":"Evid. Based Complement Alternat. Med"},{"key":"2023020108523707100_btab792-B33","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":"2023020108523707100_btab792-B34","doi-asserted-by":"crossref","first-page":"136","DOI":"10.1186\/s12859-021-04073-z","article-title":"A representation learning model based on variational inference and graph autoencoder for predicting lncRNA\u2013disease associations","volume":"22","author":"Shi","year":"2021","journal-title":"BMC Bioinformatics"},{"key":"2023020108523707100_btab792-B35","doi-asserted-by":"crossref","first-page":"227","DOI":"10.1038\/nrmicro2974","article-title":"The gut microbiota\u2013masters of host development and physiology","volume":"11","author":"Sommer","year":"2013","journal-title":"Nat. Rev. Microbiol"},{"key":"2023020108523707100_btab792-B36","first-page":"487","article-title":"HIV-1 infection: pathogenesis of immune suppression","volume":"138","author":"Stingl","year":"1988","journal-title":"Wien Med. Wochenschr"},{"key":"2023020108523707100_btab792-B37","doi-asserted-by":"crossref","first-page":"424","DOI":"10.3389\/fcimb.2018.00424","article-title":"MDAD: a special resource for microbe\u2013drug associations","volume":"8","author":"Sun","year":"2018","journal-title":"Front. Cell Infect. Microbiol"},{"key":"2023020108523707100_btab792-B38","doi-asserted-by":"crossref","first-page":"e0036021","DOI":"10.1128\/mSystems.00360-21","article-title":"Computational model to quantify the growth of antibiotic-resistant bacteria in wastewater","volume":"6","author":"Sutradhar","year":"2021","journal-title":"mSystems"},{"key":"2023020108523707100_btab792-B39","doi-asserted-by":"crossref","first-page":"D605","DOI":"10.1093\/nar\/gkaa1074","article-title":"The STRING database in 2021: customizable protein-protein networks, and functional characterization of user-uploaded gene\/measurement sets","volume":"49","author":"Szklarczyk","year":"2021","journal-title":"Nucleic Acids Res"},{"key":"2023020108523707100_btab792-B40","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":"2023020108523707100_btab792-B41","doi-asserted-by":"crossref","first-page":"138","DOI":"10.1186\/s12933-016-0455-9","article-title":"Associations between explorative dietary patterns and serum lipid levels and their interactions with ApoA5 and ApoE haplotype in patients with recently diagnosed type 2 diabetes","volume":"15","author":"Weber","year":"2016","journal-title":"Cardiovasc Diabetol"},{"key":"2023020108523707100_btab792-B42","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":"2023020108523707100_btab792-B43","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":"2023020108523707100_btab792-B44","doi-asserted-by":"crossref","first-page":"bbaa243","DOI":"10.1093\/bib\/bbaa243","article-title":"Predicting drug\u2013disease associations through layer attention graph convolutional network","volume":"22","author":"Yu","year":"2021","journal-title":"Brief. Bioinform"},{"key":"2023020108523707100_btab792-B45","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":"2023020108523707100_btab792-B46","doi-asserted-by":"crossref","first-page":"e10116","DOI":"10.15252\/msb.202010116","article-title":"Towards a mechanistic understanding of reciprocal drug\u2013microbiome interactions","volume":"17","author":"Zimmermann","year":"2021","journal-title":"Mol. Syst. Biol"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btab792\/41478458\/btab792.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/38\/4\/1118\/49008424\/btab792.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/38\/4\/1118\/49008424\/btab792.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,12]],"date-time":"2024-09-12T11:32:11Z","timestamp":1726140731000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/38\/4\/1118\/6433669"}},"subtitle":[],"editor":[{"given":"Zhiyong","family":"Lu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2021,11,23]]},"references-count":46,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2022,1,27]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btab792","relation":{},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"value":"1367-4803","type":"print"},{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2022,2,15]]},"published":{"date-parts":[[2021,11,23]]}}}