{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T16:28:34Z","timestamp":1784392114905,"version":"3.55.0"},"reference-count":50,"publisher":"Oxford University Press (OUP)","issue":"2","license":[{"start":{"date-parts":[[2023,2,20]],"date-time":"2023-02-20T00:00:00Z","timestamp":1676851200000},"content-version":"vor","delay-in-days":19,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"United States Government"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,2,3]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:sec><jats:title>Motivation<\/jats:title><jats:p>Predicting molecule\u2013disease indications and side effects is important for drug development and pharmacovigilance. Comprehensively mining molecule\u2013molecule, molecule\u2013disease and disease\u2013disease semantic dependencies can potentially improve prediction performance.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>We introduce a Multi-Modal REpresentation Mapping Approach to Predicting molecular-disease relations (M2REMAP) by incorporating clinical semantics learned from electronic health records (EHR) of 12.6 million patients. Specifically, M2REMAP first learns a multimodal molecule representation that synthesizes chemical property and clinical semantic information by mapping molecule chemicals via a deep neural network onto the clinical semantic embedding space shared by drugs, diseases and other common clinical concepts. To infer molecule\u2013disease relations, M2REMAP combines multimodal molecule representation and disease semantic embedding to jointly infer indications and side effects.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>We extensively evaluate M2REMAP on molecule indications, side effects and interactions. Results show that incorporating EHR embeddings improves performance significantly, for example, attaining an improvement over the baseline models by 23.6% in PRC-AUC on indications and 23.9% on side effects. Further, M2REMAP overcomes the limitation of existing methods and effectively predicts drugs for novel diseases and emerging pathogens.<\/jats:p><\/jats:sec><jats:sec><jats:title>Availability and implementation<\/jats:title><jats:p>The code is available at https:\/\/github.com\/celehs\/M2REMAP, and prediction results are provided at https:\/\/shiny.parse-health.org\/drugs-diseases-dev\/.<\/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\/btad085","type":"journal-article","created":{"date-parts":[[2023,2,20]],"date-time":"2023-02-20T14:18:23Z","timestamp":1676902703000},"source":"Crossref","is-referenced-by-count":24,"title":["Multimodal representation learning for predicting molecule\u2013disease relations"],"prefix":"10.1093","volume":"39","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5067-2647","authenticated-orcid":false,"given":"Jun","family":"Wen","sequence":"first","affiliation":[{"name":"Department of Biomedical Informatics, Harvard Medical School , Boston, MA 02115, USA"},{"name":"VA Boston Healthcare System , Boston, MA 02130, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiang","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Biomedical Informatics, Harvard Medical School , Boston, MA 02115, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Everett","family":"Rush","sequence":"additional","affiliation":[{"name":"Department of Energy, Oak Ridge National Laboratory , Oak Ridge, TN 37831, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vidul A","family":"Panickan","sequence":"additional","affiliation":[{"name":"Department of Biomedical Informatics, Harvard Medical School , Boston, MA 02115, USA"},{"name":"VA Boston Healthcare System , Boston, MA 02130, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xingyu","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Biomedical Informatics, Harvard Medical School , Boston, MA 02115, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianrun","family":"Cai","sequence":"additional","affiliation":[{"name":"VA Boston Healthcare System , Boston, MA 02130, USA"},{"name":"Mass General Brigham , Boston, MA 02130, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Doudou","family":"Zhou","sequence":"additional","affiliation":[{"name":"Department of Statistics, University of California , Davis, CA 95616, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuk-Lam","family":"Ho","sequence":"additional","affiliation":[{"name":"VA Boston Healthcare System , Boston, MA 02130, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lauren","family":"Costa","sequence":"additional","affiliation":[{"name":"VA Boston Healthcare System , Boston, MA 02130, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Edmon","family":"Begoli","sequence":"additional","affiliation":[{"name":"Department of Energy, Oak Ridge National Laboratory , Oak Ridge, TN 37831, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chuan","family":"Hong","sequence":"additional","affiliation":[{"name":"VA Boston Healthcare System , Boston, MA 02130, USA"},{"name":"Department of Biostatistics and Bioinformatics, Duke University , Durham, NC 27708, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"J Michael","family":"Gaziano","sequence":"additional","affiliation":[{"name":"Department of Biomedical Informatics, Harvard Medical School , Boston, MA 02115, USA"},{"name":"VA Boston Healthcare System , Boston, MA 02130, USA"},{"name":"Brigham and Women\u2019s Hospital , Boston, MA 02115, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1727-7076","authenticated-orcid":false,"given":"Kelly","family":"Cho","sequence":"additional","affiliation":[{"name":"Department of Biomedical Informatics, Harvard Medical School , Boston, MA 02115, USA"},{"name":"VA Boston Healthcare System , Boston, MA 02130, USA"},{"name":"Brigham and Women\u2019s Hospital , Boston, MA 02115, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junwei","family":"Lu","sequence":"additional","affiliation":[{"name":"VA Boston Healthcare System , Boston, MA 02130, USA"},{"name":"Department of Biostatistics, Harvard T.H. Chan School of Public Health , Boston, MA 02115, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Katherine P","family":"Liao","sequence":"additional","affiliation":[{"name":"Department of Biomedical Informatics, Harvard Medical School , Boston, MA 02115, USA"},{"name":"VA Boston Healthcare System , Boston, MA 02130, USA"},{"name":"Department of Biostatistics, Harvard T.H. Chan School of Public Health , Boston, MA 02115, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8530-7228","authenticated-orcid":false,"given":"Marinka","family":"Zitnik","sequence":"additional","affiliation":[{"name":"Department of Biomedical Informatics, Harvard Medical School , Boston, MA 02115, USA"},{"name":"Broad Institute of MIT and Harvard , Cambridge, MA 02142, USA"},{"name":"Harvard Data Science Initiative , Cambridge, MA 02138, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5379-2502","authenticated-orcid":false,"given":"Tianxi","family":"Cai","sequence":"additional","affiliation":[{"name":"Department of Biomedical Informatics, Harvard Medical School , Boston, MA 02115, USA"},{"name":"VA Boston Healthcare System , Boston, MA 02130, USA"},{"name":"Mass General Brigham , Boston, MA 02130, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2023,2,10]]},"reference":[{"key":"2023022013441454100_","doi-asserted-by":"crossref","first-page":"156","DOI":"10.1038\/s41418-021-00844-6","article-title":"Repurposing the estrogen receptor modulator raloxifene to treat SARS-COV-2 infection","volume":"29","author":"Allegretti","year":"2022","journal-title":"Cell Death Differ"},{"key":"2023022013441454100_","doi-asserted-by":"crossref","first-page":"2000113","DOI":"10.1002\/minf.202000113","article-title":"QSAR modeling of SARS-CoV Mpro inhibitors identifies sufugolix, cenicriviroc, proglumetacin, and other drugs as candidates for repurposing against SARS-CoV-2","volume":"40","author":"Alves","year":"2021","journal-title":"Mol. Inf"},{"key":"2023022013441454100_","first-page":"295","author":"Beam","year":"2019"},{"key":"2023022013441454100_","doi-asserted-by":"crossref","first-page":"2040206620983780","DOI":"10.1177\/2040206620983780","article-title":"Gallium maltolate has in vitro antiviral activity against SARS-CoV-2 and is a potential treatment for COVID-19","volume":"28","author":"Bernstein","year":"2020","journal-title":"Antivir. Chem. Chemother"},{"key":"2023022013441454100_","author":"Chandak","year":"2022"},{"key":"2023022013441454100_","doi-asserted-by":"crossref","first-page":"625","DOI":"10.3390\/antiox8120625","article-title":"Dietary antioxidant trans-cinnamaldehyde reduced visfatin-induced breast cancer progression: in vivo and in vitro study","volume":"8","author":"Chiang","year":"2019","journal-title":"Antioxidants"},{"key":"2023022013441454100_","doi-asserted-by":"crossref","first-page":"64","DOI":"10.3390\/cancers11010064","article-title":"Paroxetine induces apoptosis of human breast cancer MCF-7 cells through Ca2+-and p38 MAP kinase-dependent ROS generation","volume":"11","author":"Cho","year":"2019","journal-title":"Cancers"},{"key":"2023022013441454100_","doi-asserted-by":"crossref","first-page":"20","DOI":"10.1016\/j.jhealeco.2016.01.012","article-title":"Innovation in the pharmaceutical industry: new estimates of R&D costs","volume":"47","author":"DiMasi","year":"2016","journal-title":"J. Health Econ"},{"key":"2023022013441454100_","doi-asserted-by":"crossref","first-page":"427","DOI":"10.1016\/S0885-3924(99)00093-7","article-title":"Reporting of adverse effects in clinical trials should be improved: lessons from acute postoperative pain","volume":"18","author":"Edwards","year":"1999","journal-title":"J. Pain Symptom Manage"},{"key":"2023022013441454100_","doi-asserted-by":"crossref","first-page":"e005090","DOI":"10.1136\/bmjopen-2014-005090","article-title":"A systematic review and meta-analysis assessing adverse event profile and tolerability of nicergoline","volume":"4","author":"Fioravanti","year":"2014","journal-title":"BMJ Open"},{"key":"2023022013441454100_","first-page":"1263","author":"Gilmer","year":"2017"},{"key":"2023022013441454100_","doi-asserted-by":"crossref","first-page":"e1001026","DOI":"10.1371\/journal.pmed.1001026","article-title":"Meta-analyses of adverse effects data derived from randomised controlled trials as compared to observational studies: methodological overview","volume":"8","author":"Golder","year":"2011","journal-title":"PLoS Med"},{"key":"2023022013441454100_","doi-asserted-by":"crossref","first-page":"268","DOI":"10.1021\/acscentsci.7b00572","article-title":"Automatic chemical design using a data-driven continuous representation of molecules","volume":"4","author":"G\u00f3mez-Bombarelli","year":"2018","journal-title":"ACS Cent. Sci"},{"key":"2023022013441454100_","first-page":"855","author":"Grover","year":"2016"},{"key":"2023022013441454100_","doi-asserted-by":"crossref","DOI":"10.1038\/s41746-021-00519-z","article-title":"Clinical knowledge extraction via sparse embedding regression (KESER) with multi-center large scale electronic health record data","author":"Hong","year":"2021","journal-title":"NPJ Digit. Med"},{"key":"2023022013441454100_","doi-asserted-by":"crossref","first-page":"124","DOI":"10.1007\/s12275-021-0617-7","article-title":"Raloxifene as a treatment option for viral infections","volume":"59","author":"Hong","year":"2021","journal-title":"J. Microbiol"},{"key":"2023022013441454100_","doi-asserted-by":"crossref","first-page":"3332","DOI":"10.3390\/cancers12113332","article-title":"The potential of lonidamine in combination with chemotherapy and physical therapy in cancer treatment","volume":"12","author":"Huang","year":"2020","journal-title":"Cancers"},{"key":"2023022013441454100_","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41598-017-00908-z","article-title":"Predicting neurological adverse drug reactions based on biological, chemical and phenotypic properties of drugs using machine learning models","volume":"7","author":"Jamal","year":"2017","journal-title":"Sci. Rep"},{"key":"2023022013441454100_","doi-asserted-by":"crossref","first-page":"1106","DOI":"10.1111\/jcmm.14011","article-title":"Anticancer activity of paroxetine in human colon cancer cells: involvement of MET and ERBB3","volume":"23","author":"Jang","year":"2019","journal-title":"J. Cell. Mol. Med"},{"key":"2023022013441454100_","doi-asserted-by":"crossref","first-page":"D1075","DOI":"10.1093\/nar\/gkv1075","article-title":"The sider database of drugs and side effects","volume":"44","author":"Kuhn","year":"2016","journal-title":"Nucleic Acids Res"},{"key":"2023022013441454100_","doi-asserted-by":"crossref","first-page":"1884","DOI":"10.1093\/bib\/bbaa040","article-title":"Prediction of drug adverse events using deep learning in pharmaceutical discovery","volume":"22","author":"Lee","year":"2021","journal-title":"Brief. Bioinform"},{"key":"2023022013441454100_","author":"Levy","year":"2014"},{"key":"2023022013441454100_","doi-asserted-by":"crossref","first-page":"e28","DOI":"10.1136\/amiajnl-2011-000699","article-title":"Large-scale prediction of adverse drug reactions using chemical, biological, and phenotypic properties of drugs","volume":"19","author":"Liu","year":"2012","journal-title":"J. Am. Med. Inform. Assoc"},{"key":"2023022013441454100_","doi-asserted-by":"crossref","first-page":"1751","DOI":"10.3389\/fphar.2020.582719","article-title":"Targets and mechanism used by cinnamaldehyde, the main active ingredient in cinnamon, in the treatment of breast cancer","volume":"11","author":"Liu","year":"2020","journal-title":"Front. Pharmacol"},{"key":"2023022013441454100_","doi-asserted-by":"crossref","first-page":"651","DOI":"10.1016\/j.trci.2017.10.005","article-title":"Drug discovery and development: role of basic biological research","volume":"3","author":"Mohs","year":"2017","journal-title":"Alzheimers Dement (NY)"},{"key":"2023022013441454100_","doi-asserted-by":"crossref","first-page":"190","DOI":"10.1093\/bib\/bbx099","article-title":"Facilitating prediction of adverse drug reactions by using knowledge graphs and multi-label learning models","volume":"20","author":"Mu\u00f1oz","year":"2019","journal-title":"Brief. Bioinform"},{"key":"2023022013441454100_","doi-asserted-by":"crossref","first-page":"16584","DOI":"10.1021\/acsomega.1c01797","article-title":"Inhibition of the 3cl protease and sars-cov-2 replication by dalcetrapib","volume":"6","author":"Niesor","year":"2021","journal-title":"ACS Omega"},{"key":"2023022013441454100_","doi-asserted-by":"crossref","first-page":"477","DOI":"10.3390\/biom10030477","article-title":"The role of nicotinamide in cancer chemoprevention and therapy","volume":"10","author":"Nikas","year":"2020","journal-title":"Biomolecules"},{"key":"2023022013441454100_","doi-asserted-by":"crossref","first-page":"926","DOI":"10.1007\/s43440-021-00228-0","article-title":"Rifampicin and letermovir as potential repurposed drug candidate for covid-19 treatment: insights from an in-silico study","volume":"73","author":"Pathak","year":"2021","journal-title":"Pharmacol. Rep"},{"key":"2023022013441454100_","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. Inf. Model"},{"key":"2023022013441454100_","doi-asserted-by":"crossref","first-page":"422","DOI":"10.1111\/1440-1681.13452","article-title":"The nicotinamide phosphoribosyltransferase antagonist fk866 inhibits growth of prostate tumour spheroids and increases doxorubicin retention without changes in drug transporter and cancer stem cell protein expression","volume":"48","author":"Sauer","year":"2021","journal-title":"Clin. Exp. Pharmacol. Physiol"},{"key":"2023022013441454100_","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s13046-020-01719-3","article-title":"Nicotinamide inhibits melanoma in vitro and in vivo","volume":"39","author":"Scatozza","year":"2020","journal-title":"J. Exp. Clin. Cancer Res"},{"key":"2023022013441454100_","doi-asserted-by":"crossref","first-page":"497","DOI":"10.1038\/nm.4493","article-title":"H3b-8800, an orally available small-molecule splicing modulator, induces lethality in spliceosome-mutant cancers","volume":"24","author":"Seiler","year":"2018","journal-title":"Nat. Med"},{"issue":"11","key":"2023022013441454100_","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"Van der Maaten","year":"2008","journal-title":"J. Mach. Learn. Res"},{"key":"2023022013441454100_","author":"Vaswani","year":"2017"},{"key":"2023022013441454100_","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41421-020-00217-2","article-title":"Sunitinib reduces the infection of SARS-CoV, MERS-CoV and SARS-CoV-2 partially by inhibiting AP2M1 phosphorylation","volume":"6","author":"Wang","year":"2020","journal-title":"Cell Discov"},{"key":"2023022013441454100_","first-page":"1","article-title":"The essential role of PRAK in tumor metastasis and its therapeutic potential","volume":"12","author":"Wang","year":"2021","journal-title":"Nat. Commun"},{"key":"2023022013441454100_","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":"2023022013441454100_","doi-asserted-by":"crossref","first-page":"3284","DOI":"10.1021\/ci2005548","article-title":"Drug side-effect prediction based on the integration of chemical and biological spaces","volume":"52","author":"Yamanishi","year":"2012","journal-title":"J. Chem. Inf. Model"},{"key":"2023022013441454100_","author":"Yu","year":"2013"},{"key":"2023022013441454100_","doi-asserted-by":"crossref","first-page":"2988","DOI":"10.1093\/bioinformatics\/btab207","article-title":"SumGNN: multi-typed drug interaction prediction via efficient knowledge graph summarization","volume":"37","author":"Yu","year":"2021","journal-title":"Bioinformatics"},{"key":"2023022013441454100_","doi-asserted-by":"crossref","first-page":"bbab291","DOI":"10.1093\/bib\/bbab291","article-title":"Comparative analysis of molecular fingerprints in prediction of drug combination effects","volume":"22","author":"Zagidullin","year":"2021","journal-title":"Brief. Bioinformatics"},{"key":"2023022013441454100_","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s12859-015-0774-y","article-title":"Predicting drug side effects by multi-label learning and ensemble learning","volume":"16","author":"Zhang","year":"2015","journal-title":"BMC Bioinformatics"},{"key":"2023022013441454100_","first-page":"427","author":"Zhang","year":"2016"},{"key":"2023022013441454100_","doi-asserted-by":"crossref","first-page":"666","DOI":"10.1038\/s43588-021-00138-4","article-title":"Population-scale identification of differential adverse events before and during a pandemic","volume":"1","author":"Zhang","year":"2021","journal-title":"Nat. Comput. Sci"},{"key":"2023022013441454100_","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s12935-021-02028-1","article-title":"Synergism between the phosphatidylinositol 3-kinase p110\u03b2 isoform inhibitor AZD6482 and the mixed lineage kinase 3 inhibitor URMC-099 on the blockade of glioblastoma cell motility and focal adhesion formation","volume":"21","author":"Zhao","year":"2021","journal-title":"Cancer Cell Int"},{"key":"2023022013441454100_","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1186\/s12859-018-2563-x","article-title":"Inverse similarity and reliable negative samples for drug side-effect prediction","volume":"19","author":"Zheng","year":"2019","journal-title":"BMC Bioinformatics"},{"key":"2023022013441454100_","doi-asserted-by":"crossref","first-page":"1558","DOI":"10.1021\/acs.molpharmaceut.9b01248","article-title":"MEDICASCY: a machine learning approach for predicting small-molecule drug side effects, indications, efficacy, and modes of action","volume":"17","author":"Zhou","year":"2020","journal-title":"Mol. Pharm"},{"key":"2023022013441454100_","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s10020-021-00269-4","article-title":"Discovery of vanoxerine dihydrochloride as a CDK2\/4\/6 triple-inhibitor for the treatment of human hepatocellular carcinoma","volume":"27","author":"Zhu","year":"2021","journal-title":"Mol. Med"},{"key":"2023022013441454100_","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\/39\/2\/btad085\/49278341\/btad085.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/39\/2\/btad085\/49278341\/btad085.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,3,24]],"date-time":"2023-03-24T18:57:11Z","timestamp":1679684231000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/doi\/10.1093\/bioinformatics\/btad085\/7034101"}},"subtitle":[],"editor":[{"given":"Zhiyong","family":"Lu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2023,2,1]]},"references-count":50,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2023,2,3]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btad085","relation":{},"ISSN":["1367-4811"],"issn-type":[{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2023,2,1]]},"published":{"date-parts":[[2023,2,1]]},"article-number":"btad085"}}