{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,21]],"date-time":"2026-02-21T15:04:35Z","timestamp":1771686275713,"version":"3.50.1"},"reference-count":46,"publisher":"Oxford University Press (OUP)","issue":"12","license":[{"start":{"date-parts":[[2024,11,25]],"date-time":"2024-11-25T00:00:00Z","timestamp":1732492800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,11,28]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Motivation<\/jats:title>\n                  <jats:p>Adverse reactions from drug combinations are increasingly common, making their accurate prediction a crucial challenge in modern medicine. Laboratory-based identification of these reactions is insufficient due to the combinatorial nature of the problem. While many computational approaches have been proposed, tensor factorization (TF) models have shown mixed results, necessitating a thorough investigation of their capabilities when properly optimized.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>We demonstrate that TF models can achieve state-of-the-art performance on polypharmacy side effect prediction, with our best model (SimplE) achieving median scores of 0.978 area under receiver-operating characteristic curve, 0.971 area under precision\u2013recall curve, and 1.000 AP@50 across 963 side effects. Notably, this model reaches 98.3% of its maximum performance after just two epochs of training (approximately 4\u2009min), making it substantially faster than existing approaches while maintaining comparable accuracy. We also find that incorporating monopharmacy data as self-looping edges in the graph performs marginally better than using it to initialize embeddings.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Availability and implementation<\/jats:title>\n                  <jats:p>All code used in the experiments is available in our GitHub repository (https:\/\/doi.org\/10.5281\/zenodo.10684402). The implementation was carried out using Python 3.8.12 with PyTorch 1.7.1, accelerated with CUDA 11.4 on NVIDIA GeForce RTX 2080 Ti GPUs.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btae706","type":"journal-article","created":{"date-parts":[[2024,11,25]],"date-time":"2024-11-25T07:15:32Z","timestamp":1732518932000},"source":"Crossref","is-referenced-by-count":1,"title":["Fast polypharmacy side effect prediction using tensor factorization"],"prefix":"10.1093","volume":"40","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6436-9446","authenticated-orcid":false,"given":"Oliver","family":"Lloyd","sequence":"first","affiliation":[{"name":"MRC Integrative Epidemiology Unit, Bristol Medical School, University of Bristol , Bristol, BS8 2BN,","place":["United Kingdom"]}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2051-440X","authenticated-orcid":false,"given":"Yi","family":"Liu","sequence":"additional","affiliation":[{"name":"MRC Integrative Epidemiology Unit, Bristol Medical School, University of Bristol , Bristol, BS8 2BN,","place":["United Kingdom"]}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0924-3247","authenticated-orcid":false,"given":"Tom R","family":"Gaunt","sequence":"additional","affiliation":[{"name":"MRC Integrative Epidemiology Unit, Bristol Medical School, University of Bristol , Bristol, BS8 2BN,","place":["United Kingdom"]}]}],"member":"286","published-online":{"date-parts":[[2024,11,25]]},"reference":[{"key":"2024121419112264500_btae706-B1","doi-asserted-by":"publisher","first-page":"e112133","DOI":"10.1371\/journal.pone.0112133","article-title":"Effects of polypharmacy on adverse drug reactions among geriatric outpatients at a tertiary care hospital in Karachi: a prospective cohort study","volume":"9","author":"Ahmed","year":"2014","journal-title":"PLoS One"},{"key":"2024121419112264500_btae706-B2","doi-asserted-by":"publisher","first-page":"8825","DOI":"10.1109\/TPAMI.2021.3124805","article-title":"Bringing light into the dark: a large-scale evaluation of knowledge graph embedding models under a unified framework","volume":"44","author":"Ali","year":"2022","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"2024121419112264500_btae706-B3","first-page":"165","author":"Broscheit","year":"2020"},{"key":"2024121419112264500_btae706-B4","first-page":"992","author":"Burkhardt","year":"2019"},{"key":"2024121419112264500_btae706-B5","doi-asserted-by":"publisher","first-page":"119","DOI":"10.1007\/978-3-030-73973-7_12","author":"Carletti","year":"2021"},{"key":"2024121419112264500_btae706-B6","doi-asserted-by":"publisher","first-page":"4773","DOI":"10.1111\/bcp.15395","article-title":"Skeletal muscle relaxant drug\u2013drug\u2013drug interactions and unintentional traumatic injury: screening to detect three-way drug interaction signals","volume":"88","author":"Chen","year":"2022","journal-title":"Br J Clin Pharmacol"},{"key":"2024121419112264500_btae706-B7","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1093\/bib\/bbaa256","article-title":"Drug\u2013drug interaction prediction with wasserstein adversarial autoencoder-based knowledge graph embeddings","volume":"22","author":"Dai","year":"2021","journal-title":"Brief Bioinform"},{"key":"2024121419112264500_btae706-B8","doi-asserted-by":"publisher","first-page":"429","DOI":"10.3390\/ph14050429","article-title":"Cold-start problems in data-driven prediction of drug\u2013drug interaction effects","volume":"14","author":"Dewulf","year":"2021","journal-title":"Pharmaceuticals"},{"key":"2024121419112264500_btae706-B9","author":"Glorot","year":"2010"},{"key":"2024121419112264500_btae706-B10","doi-asserted-by":"publisher","first-page":"312","DOI":"10.1016\/j.icte.2020.04.010","article-title":"The effect of batch size on the generalizability of the convolutional neural networks on a histopathology dataset","volume":"6","author":"Kandel","year":"2020","journal-title":"ICT Express"},{"key":"2024121419112264500_btae706-B11","first-page":"4284","author":"Kazemi","year":"2018"},{"key":"2024121419112264500_btae706-B12","doi-asserted-by":"publisher","first-page":"2842","DOI":"10.3390\/app13052842","article-title":"A knowledge graph embedding approach for polypharmacy side effects prediction","volume":"13","author":"Kim","year":"2023","journal-title":"Appl Sci"},{"key":"2024121419112264500_btae706-B13","author":"Kingma","year":"2015"},{"key":"2024121419112264500_btae706-B14","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/bbac597","article-title":"DSN-DDI: an accurate and generalized framework for drug\u2013drug interaction prediction by dual-view representation learning","volume":"24","author":"Li","year":"2023","journal-title":"Brief Bioinform"},{"key":"2024121419112264500_btae706-B15","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/bbac576","article-title":"R2-DDI: relation-aware feature refinement for drug\u2013drug interaction prediction","volume":"24","author":"Lin","year":"2023","journal-title":"Brief Bioinform"},{"key":"2024121419112264500_btae706-B16","doi-asserted-by":"publisher","first-page":"bbab421","DOI":"10.1093\/bib\/bbab421","article-title":"MDF-SA-DDI: predicting drug\u2013drug interaction events based on multi-source drug fusion, multi-source feature fusion and transformer self-attention mechanism","volume":"23","author":"Lin","year":"2021","journal-title":"Brief Bioinform"},{"key":"2024121419112264500_btae706-B17","doi-asserted-by":"publisher","first-page":"49","DOI":"10.1186\/s13321-022-00632-5","article-title":"Simvec: predicting polypharmacy side effects for new drugs","volume":"14","author":"Lukashina","year":"2022","journal-title":"J Cheminform"},{"key":"2024121419112264500_btae706-B18","doi-asserted-by":"publisher","first-page":"144","DOI":"10.1007\/978-3-030-06016-9_14","author":"Malone","year":"2019"},{"key":"2024121419112264500_btae706-B19","first-page":"430","volume-title":"Ageing Res Rev","author":"Marengoni","year":"2011"},{"key":"2024121419112264500_btae706-B20","doi-asserted-by":"publisher","first-page":"vbad110","DOI":"10.1093\/bioadv\/vbad110","article-title":"DPSP: a multimodal deep learning framework for polypharmacy side effects prediction","volume":"3","author":"Masumshah","year":"2023","journal-title":"Bioinform Adv"},{"key":"2024121419112264500_btae706-B21","doi-asserted-by":"publisher","first-page":"385","DOI":"10.1186\/s12859-021-04298-y","article-title":"A neural network-based method for polypharmacy side effects prediction","volume":"22","author":"Masumshah","year":"2021","journal-title":"BMC Bioinformatics"},{"key":"2024121419112264500_btae706-B22","first-page":"449","article-title":"Predicting polypharmacy side-effects using knowledge graph embeddings","volume":"2020","author":"Nov\u00e1\u010dek","year":"2020","journal-title":"AMIA Jt Summits Transl Sci Proc"},{"key":"2024121419112264500_btae706-B23","author":"Ruffinelli","year":"2020"},{"key":"2024121419112264500_btae706-B24","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1186\/s13321-015-0055-9","article-title":"Systems biology approaches for advancing the discovery of effective drug combinations rajarshi guha","volume":"7","author":"Ryall","year":"2015","journal-title":"J Cheminform"},{"key":"2024121419112264500_btae706-B25","first-page":"1503","author":"Saifuddin"},{"key":"2024121419112264500_btae706-B26","doi-asserted-by":"publisher","first-page":"54","DOI":"10.1145\/3381831","article-title":"Green AI","volume":"63","author":"Schwartz","year":"2020","journal-title":"Commun ACM"},{"key":"2024121419112264500_btae706-B27","doi-asserted-by":"publisher","first-page":"174","DOI":"10.1038\/S41587-022-01630-6","article-title":"Fresh from the biotech pipeline: fewer approvals, but biologics gain share","volume":"41","author":"Senior","year":"2023","journal-title":"Nat Biotechnol"},{"key":"2024121419112264500_btae706-B28","first-page":"384","author":"Sserwadda","year":"2022"},{"key":"2024121419112264500_btae706-B29","first-page":"1003","author":"Tallarida"},{"key":"2024121419112264500_btae706-B30","first-page":"2071","author":"Trouillon","year":"2016"},{"key":"2024121419112264500_btae706-B31","author":"UK Government"},{"key":"2024121419112264500_btae706-B32","author":"United Nations","year":", :        , 2022."},{"key":"2024121419112264500_btae706-B33","first-page":"1860","author":"Vaida","year":"2019"},{"key":"2024121419112264500_btae706-B34","first-page":"1093","author":"Wang","year":"2022"},{"key":"2024121419112264500_btae706-B35","author":"Wiffen","year":"2002"},{"key":"2024121419112264500_btae706-B36","author":"World Health Organisation","year":", :   , 2022."},{"key":"2024121419112264500_btae706-B37","doi-asserted-by":"crossref","first-page":"4","DOI":"10.1109\/TNNLS.2020.2978386","article-title":"A comprehensive survey on graph neural networks","volume":"32","author":"Wu","year":"2019","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"2024121419112264500_btae706-B38","doi-asserted-by":"publisher","author":"Yang","DOI":"10.48550\/arXiv.1411.4072"},{"key":"2024121419112264500_btae706-B39","doi-asserted-by":"crossref","first-page":"260","DOI":"10.15302\/J-QB-022-0320","article-title":"Deepdrug: a general graph-based deep learning framework for drug-drug interactions and drug-target interactions prediction","volume":"11","author":"Yin","journal-title":"Quant Biol"},{"key":"2024121419112264500_btae706-B40","doi-asserted-by":"crossref","first-page":"1023","DOI":"10.1038\/s43588-023-00558-4","article-title":"Emerging drug interaction prediction enabled by a flow-based graph neural network with biomedical network","volume":"3","author":"Zhang","year":"2023","journal-title":"Nat Comput Sci"},{"key":"2024121419112264500_btae706-B41","doi-asserted-by":"publisher","first-page":"106434","DOI":"10.1016\/j.knosys.2020.106434","article-title":"Trusttf: a tensor factorization model using user trust and implicit feedback for context-aware recommender systems","volume":"209","author":"Zhao","year":"2020","journal-title":"Knowledge-Based Systems"},{"key":"2024121419112264500_btae706-B42","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1186\/s12859-024-05654-4","article-title":"SSF-DDI: a deep learning method utilizing drug sequence and substructure features for drug\u2013drug interaction prediction","volume":"25","author":"Zhu","year":"2024","journal-title":"BMC Bioinformatics"},{"key":"2024121419112264500_btae706-B43","first-page":"277","author":"Zhuang","year":"2021"},{"key":"2024121419112264500_btae706-B44","doi-asserted-by":"publisher","first-page":"11795","DOI":"10.1007\/s00500-022-06951-x","article-title":"MS-ADR: predicting drug\u2013drug adverse reactions base on multi-source heterogeneous convolutional signed network","volume":"26","author":"Zhuang","year":"2022","journal-title":"Soft Comput"},{"key":"2024121419112264500_btae706-B45","doi-asserted-by":"publisher","first-page":"17411","DOI":"10.1007\/s10489-022-04372-9","article-title":"Predicting drug-drug adverse reactions via multi-view graph contrastive representation model","volume":"53","author":"Zhuang","year":"2023","journal-title":"Appl Intell"},{"key":"2024121419112264500_btae706-B46","doi-asserted-by":"publisher","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\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btae706\/60805527\/btae706.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/40\/12\/btae706\/61165117\/btae706.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/40\/12\/btae706\/61165117\/btae706.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,14]],"date-time":"2024-12-14T19:12:23Z","timestamp":1734203543000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/doi\/10.1093\/bioinformatics\/btae706\/7907967"}},"subtitle":[],"editor":[{"given":"Macha","family":"Nikolski","sequence":"additional","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2024,11,25]]},"references-count":46,"journal-issue":{"issue":"12","published-print":{"date-parts":[[2024,11,28]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btae706","relation":{},"ISSN":["1367-4811"],"issn-type":[{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2024,12]]},"published":{"date-parts":[[2024,11,25]]},"article-number":"btae706"}}