{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T04:40:58Z","timestamp":1776746458142,"version":"3.51.2"},"reference-count":55,"publisher":"Oxford University Press (OUP)","issue":"18","license":[{"start":{"date-parts":[[2021,3,26]],"date-time":"2021-03-26T00:00:00Z","timestamp":1616716800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["SCH-2014438"],"award-info":[{"award-number":["SCH-2014438"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["IIS-1418511"],"award-info":[{"award-number":["IIS-1418511"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["CCF-1533768"],"award-info":[{"award-number":["CCF-1533768"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["IIS-1838042"],"award-info":[{"award-number":["IIS-1838042"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Institute of Health"},{"DOI":"10.13039\/100000002","name":"NIH","doi-asserted-by":"publisher","award":["R01 1R01NS107291-01"],"award-info":[{"award-number":["R01 1R01NS107291-01"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"NIH","doi-asserted-by":"publisher","award":["R56HL138415"],"award-info":[{"award-number":["R56HL138415"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,9,29]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Motivation<\/jats:title>\n                  <jats:p>Thanks to the increasing availability of drug\u2013drug interactions (DDI) datasets and large biomedical knowledge graphs (KGs), accurate detection of adverse DDI using machine learning models becomes possible. However, it remains largely an open problem how to effectively utilize large and noisy biomedical KG for DDI detection. Due to its sheer size and amount of noise in KGs, it is often less beneficial to directly integrate KGs with other smaller but higher quality data (e.g. experimental data). Most of existing approaches ignore KGs altogether. Some tries to directly integrate KGs with other data via graph neural networks with limited success. Furthermore most previous works focus on binary DDI prediction whereas the multi-typed DDI pharmacological effect prediction is more meaningful but harder task.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>To fill the gaps, we propose a new method SumGNN: knowledge summarization graph neural network, which is enabled by a subgraph extraction module that can efficiently anchor on relevant subgraphs from a KG, a self-attention based subgraph summarization scheme to generate reasoning path within the subgraph, and a multi-channel knowledge and data integration module that utilizes massive external biomedical knowledge for significantly improved multi-typed DDI predictions. SumGNN outperforms the best baseline by up to 5.54%, and performance gain is particularly significant in low data relation types. In addition, SumGNN provides interpretable prediction via the generated reasoning paths for each prediction.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Availability and implementation<\/jats:title>\n                  <jats:p>The code is available in Supplementary Material.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Supplementary information<\/jats:title>\n                  <jats:p>Supplementary data are available at Bioinformatics online.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btab207","type":"journal-article","created":{"date-parts":[[2021,3,24]],"date-time":"2021-03-24T20:11:52Z","timestamp":1616616712000},"page":"2988-2995","source":"Crossref","is-referenced-by-count":154,"title":["SumGNN: multi-typed drug interaction prediction via efficient knowledge graph summarization"],"prefix":"10.1093","volume":"37","author":[{"given":"Yue","family":"Yu","sequence":"first","affiliation":[{"name":"College of Computing, Georgia Institute of Technology , Atlanta, GA 30332, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6693-8390","authenticated-orcid":false,"given":"Kexin","family":"Huang","sequence":"additional","affiliation":[{"name":"Health Data Science, Harvard T.H. Chan School of Public Health , Boston, MA 02115, USA"}]},{"given":"Chao","family":"Zhang","sequence":"additional","affiliation":[{"name":"College of Computing, Georgia Institute of Technology , Atlanta, GA 30332, USA"}]},{"given":"Lucas M","family":"Glass","sequence":"additional","affiliation":[{"name":"Analytic Center of Excellence, IQVIA , Cambridge, MA 02139, USA"},{"name":"Department of Statistics, Temple University , Philadelphia, PA 19122, USA"}]},{"given":"Jimeng","family":"Sun","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Illinois at Urbana-Champaign , Urbana, IL 61801, USA"}]},{"given":"Cao","family":"Xiao","sequence":"additional","affiliation":[{"name":"Analytic Center of Excellence, IQVIA , Cambridge, MA 02139, USA"}]}],"member":"286","published-online":{"date-parts":[[2021,3,26]]},"reference":[{"key":"2023061311064623700_btab207-B1","article-title":"Subgraph neural networks","author":"Alsentzer","year":"2020","journal-title":"NeurIPS, Virtual."},{"key":"2023061311064623700_btab207-B2","article-title":"Translating embeddings for modeling multi-relational data","author":"Bordes","year":"2013","journal-title":"NeurIPS"},{"key":"2023061311064623700_btab207-B3","first-page":"752022","article-title":"Predicting adverse drug\u2013drug interactions with neural embedding of semantic predications","author":"Burkhardt","year":"2019","journal-title":"bioRxiv"},{"key":"2023061311064623700_btab207-B4","doi-asserted-by":"crossref","first-page":"7464","DOI":"10.1609\/aaai.v34i05.6243","article-title":"Graph transformer for graph-to-sequence learning","volume":"34","author":"Cai","year":"2020","journal-title":"AAAI"},{"issue":"1","key":"2023061311064623700_btab207-B5","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s12859-019-3284-5","article-title":"Evaluation of knowledge graph embedding approaches for drug\u2013drug interaction prediction in realistic settings","volume":"20","author":"Celebi","year":"2019","journal-title":"BMC Bioinformatics"},{"key":"2023061311064623700_btab207-B6","article-title":"Cluster-gcn: an efficient algorithm for training deep and large graph convolutional networks","author":"Chiang","year":"2019","journal-title":"KDD, Anchorage, USA"},{"key":"2023061311064623700_btab207-B7","doi-asserted-by":"crossref","first-page":"37","DOI":"10.1177\/001316446002000104","article-title":"A coefficient of agreement for nominal scales","volume":"20","author":"Cohen","year":"1960","journal-title":"Educ. Psychol. Measur"},{"key":"2023061311064623700_btab207-B8","first-page":"07341","article-title":"Wasserstein adversarial autoencoders for knowledge graph embedding based drug\u2013drug interaction prediction","volume-title":"arXiv","author":"Dai","year":"2020"},{"key":"2023061311064623700_btab207-B9","first-page":"855","article-title":"node2vec: scalable feature learning for networks","author":"Grover","year":"2016","journal-title":"KDD"},{"key":"2023061311064623700_btab207-B10","first-page":"07229","article-title":"Network medicine framework for identifying drug repurposing opportunities for covid-19","author":"Gysi","year":"2020","journal-title":"arXiv"},{"key":"2023061311064623700_btab207-B11","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pcbi.1004259","article-title":"Heterogeneous network edge prediction: a data integration approach to prioritize disease-associated genes","author":"Himmelstein","year":"2015","journal-title":"PLoS Comput. Biol"},{"key":"2023061311064623700_btab207-B12","article-title":"Graph meta learning via local subgraphs","author":"Huang","year":"2020","journal-title":"NeurIPS"},{"key":"2023061311064623700_btab207-B13","doi-asserted-by":"crossref","first-page":"702","DOI":"10.1609\/aaai.v34i01.5412","article-title":"Caster: predicting drug interactions with chemical substructure representation","volume":"34","author":"Huang","year":"2020","journal-title":"AAAI"},{"key":"2023061311064623700_btab207-B14","author":"Huang","year":"2020"},{"key":"2023061311064623700_btab207-B15","author":"Ioannidis","year":"2020"},{"key":"2023061311064623700_btab207-B16","doi-asserted-by":"crossref","first-page":"1263","DOI":"10.1586\/14779072.2015.1095090","article-title":"Orthostatic hypotension: managing a difficult problem","volume":"13","author":"Jones","year":"2015","journal-title":"Exp. Rev. Cardiovasc. Ther"},{"key":"2023061311064623700_btab207-B17","first-page":"113","article-title":"Drug\u2013drug interaction prediction based on knowledge graph embeddings and convolutional-lstm network","author":"Karim","year":"2019","journal-title":"ACM-BCB"},{"key":"2023061311064623700_btab207-B18","author":"Kingma","year":"2014"},{"key":"2023061311064623700_btab207-B19","article-title":"Semi-supervised classification with graph convolutional networks","author":"Kipf","year":"2017","journal-title":"ICLR"},{"key":"2023061311064623700_btab207-B20","doi-asserted-by":"crossref","first-page":"2007","DOI":"10.1093\/bioinformatics\/btv080","article-title":"Large-scale exploration and analysis of drug combinations","volume":"31","author":"Li","year":"2015","journal-title":"Bioinformatics"},{"key":"2023061311064623700_btab207-B21","first-page":"1054","article-title":"Bond: bert-assisted open-domain named entity recognition with distant supervision","author":"Liang","year":"2020","journal-title":"KDD"},{"key":"2023061311064623700_btab207-B22","volume-title":"IJCAI","author":"Lin","year":"2020"},{"key":"2023061311064623700_btab207-B23","article-title":"Distributed representations of words and phrases and their compositionality","author":"Mikolov","year":"2013","journal-title":"NeurIPS"},{"key":"2023061311064623700_btab207-B24","doi-asserted-by":"crossref","first-page":"178","DOI":"10.1016\/j.tips.2013.01.006","article-title":"Informatics confronts drug\u2013drug interactions","volume":"34","author":"Percha","year":"2013","journal-title":"Trends Pharmacol. Sci"},{"key":"2023061311064623700_btab207-B25","article-title":"Deepwalk: online learning of social representations","author":"Perozzi","year":"2014","journal-title":"KDD"},{"key":"2023061311064623700_btab207-B26","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":"2023061311064623700_btab207-B27","doi-asserted-by":"crossref","first-page":"5994","DOI":"10.1038\/s41598-017-05778-z","article-title":"Learning a health knowledge graph from electronic medical records","volume":"7","author":"Rotmensch","year":"2017","journal-title":"Sci. Rep"},{"key":"2023061311064623700_btab207-B28","doi-asserted-by":"crossref","first-page":"E4304","DOI":"10.1073\/pnas.1803294115","article-title":"Deep learning improves prediction of drug\u2013drug and drug\u2013food interactions","volume":"115","author":"Ryu","year":"2018","journal-title":"Proc. Natl. Acad. Sci. USA"},{"key":"2023061311064623700_btab207-B29","article-title":"Modeling relational data with graph convolutional networks","author":"Schlichtkrull","year":"2018","journal-title":"ESWC"},{"key":"2023061311064623700_btab207-B30","volume-title":"IJCAI","author":"Shang","year":"2019"},{"key":"2023061311064623700_btab207-B31","volume-title":"NAACL","author":"Shaw","year":"2018"},{"key":"2023061311064623700_btab207-B32","volume-title":"ICDE","author":"Shi","year":"2020"},{"key":"2023061311064623700_btab207-B33","first-page":"08796","article-title":"Fast graph attention networks using effective resistance based graph sparsification","author":"Srinivasa","year":"2020","journal-title":"arXiv"},{"key":"2023061311064623700_btab207-B34","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":"2023061311064623700_btab207-B35","first-page":"297","article-title":"Recurrent knowledge graph embedding for effective recommendation","author":"Sun","year":"2018","journal-title":"RecSys"},{"key":"2023061311064623700_btab207-B36","doi-asserted-by":"crossref","first-page":"2688","DOI":"10.1186\/s13321-017-0200-8","article-title":"Predicting drug\u2013drug interactions through drug structural similarities and interaction networks incorporating pharmacokinetics and pharmacodynamics knowledge","volume":"9","author":"Takeda","year":"2017","journal-title":"Journal of Cheminformatics"},{"key":"2023061311064623700_btab207-B37","doi-asserted-by":"crossref","first-page":"1067","DOI":"10.1145\/2736277.2741093","article-title":"Line: large-scale information network embedding","author":"Tang","year":"2015","journal-title":"WWW"},{"key":"2023061311064623700_btab207-B38","doi-asserted-by":"crossref","first-page":"125ra31","DOI":"10.1126\/scitranslmed.3003377","article-title":"Data-driven prediction of drug effects and interactions","volume":"4","author":"Tatonetti","year":"2012","journal-title":"Sci. Transl. Med"},{"key":"2023061311064623700_btab207-B39","volume-title":"ICML","author":"Teru","year":"2020"},{"key":"2023061311064623700_btab207-B40","volume-title":"ICML","author":"Trouillon","year":"2016"},{"key":"2023061311064623700_btab207-B41","volume-title":"ICML","author":"Tzeng","year":"2019"},{"key":"2023061311064623700_btab207-B42","volume-title":"ICLR","author":"Veli\u010dkovi\u0107","year":"2018"},{"key":"2023061311064623700_btab207-B43","volume-title":"ICLR","author":"Veli\u010dkovi\u0107","year":"2019"},{"key":"2023061311064623700_btab207-B44","volume-title":"EMNLP","author":"Wang","year":"2018"},{"key":"2023061311064623700_btab207-B45","first-page":"968","article-title":"Knowledge-aware graph neural networks with label smoothness regularization for recommender systems","author":"Wang","year":"2019","journal-title":"KDD"},{"key":"2023061311064623700_btab207-B46","article-title":"KGAT: knowledge graph attention network for recommendation","author":"Wang","year":"2019","journal-title":"KDD"},{"key":"2023061311064623700_btab207-B47","first-page":"08875","article-title":"Predicting rich drug\u2013drug interactions via biomedical knowledge graphs and text jointly embedding","volume":"1712","author":"Wang","year":"2017","journal-title":"arXiv Preprint arXiv"},{"key":"2023061311064623700_btab207-B48","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":"2023061311064623700_btab207-B49","volume-title":"ICML","author":"Xu","year":"2018"},{"key":"2023061311064623700_btab207-B50","first-page":"07331","article-title":"Generalized multi-relational graph convolution network","author":"Yu","year":"2020","journal-title":"arXiv"},{"key":"2023061311064623700_btab207-B51","doi-asserted-by":"crossref","DOI":"10.1145\/3411817","article-title":"Semantic-aware spatio-temporal app usage representation via graph convolutional network","volume-title":"IMWUT","author":"Yu","year":"2020"},{"key":"2023061311064623700_btab207-B52","volume-title":"ICLR","author":"Zeng","year":"2020"},{"key":"2023061311064623700_btab207-B53","volume-title":"NeurIPS","author":"Zhang","year":"2018"},{"key":"2023061311064623700_btab207-B54","author":"Zitnik","year":"2018"},{"key":"2023061311064623700_btab207-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":"http:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btab207\/37061809\/btab207.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/37\/18\/2988\/50579378\/btab207.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/37\/18\/2988\/50579378\/btab207.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,13]],"date-time":"2023-06-13T11:07:58Z","timestamp":1686654478000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/37\/18\/2988\/6189090"}},"subtitle":[],"editor":[{"given":"Jonathan","family":"Wren","sequence":"additional","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2021,3,26]]},"references-count":55,"journal-issue":{"issue":"18","published-print":{"date-parts":[[2021,9,29]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btab207","relation":{},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"value":"1367-4803","type":"print"},{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2021,9,15]]},"published":{"date-parts":[[2021,3,26]]}}}