{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T12:01:53Z","timestamp":1788868913440,"version":"build-2803163510"},"reference-count":42,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2024,5,6]],"date-time":"2024-05-06T00:00:00Z","timestamp":1714953600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2024,5,6]],"date-time":"2024-05-06T00:00:00Z","timestamp":1714953600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["npj Syst Biol Appl"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Drug-drug interaction (DDI) may result in clinical toxicity or treatment failure of antiretroviral therapy (ARV) or comedications. Despite the high number of possible drug combinations, only a limited number of clinical DDI studies are conducted. Computational prediction of DDIs could provide key evidence for the rational management of complex therapies. Our study aimed to assess the potential of deep learning approaches to predict DDIs of clinical relevance between ARVs and comedications. DDI severity grading between 30,142 drug pairs was extracted from the Liverpool HIV Drug Interaction database. Two feature construction techniques were employed: 1) drug similarity profiles by comparing Morgan fingerprints, and 2) embeddings from SMILES of each drug via ChemBERTa, a transformer-based model. We developed DeepARV-Sim and DeepARV-ChemBERTa to predict four categories of DDI: i) Red: drugs should not be co-administered, ii) Amber: interaction of potential clinical relevance manageable by monitoring\/dose adjustment, iii) Yellow: interaction of weak relevance and iv) Green: no expected interaction. The imbalance in the distribution of DDI severity grades was addressed by undersampling and applying ensemble learning. DeepARV-Sim and DeepARV-ChemBERTa predicted clinically relevant DDI between ARVs and comedications with a weighted mean balanced accuracy of 0.729\u2009\u00b1\u20090.012 and 0.776\u2009\u00b1\u20090.011, respectively. DeepARV-Sim and DeepARV-ChemBERTa have the potential to leverage molecular structures associated with DDI risks and reduce DDI class imbalance, effectively increasing the predictive ability on clinically relevant DDIs. This approach could be developed for identifying high-risk pairing of drugs, enhancing the screening process, and targeting DDIs to study in clinical drug development.<\/jats:p>","DOI":"10.1038\/s41540-024-00374-0","type":"journal-article","created":{"date-parts":[[2024,5,6]],"date-time":"2024-05-06T03:02:54Z","timestamp":1714964574000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":25,"title":["DeepARV: ensemble deep learning to predict drug-drug interaction of clinical relevance with antiretroviral therapy"],"prefix":"10.1038","volume":"10","author":[{"given":"Thao","family":"Pham","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mohamed","family":"Ghafoor","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sandra","family":"Gra\u00f1ana-Castillo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Catia","family":"Marzolini","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sara","family":"Gibbons","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2769-0967","authenticated-orcid":false,"given":"Saye","family":"Khoo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Justin","family":"Chiong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0068-1005","authenticated-orcid":false,"given":"Dennis","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marco","family":"Siccardi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,5,6]]},"reference":[{"key":"374_CR1","doi-asserted-by":"publisher","DOI":"10.1002\/jia2.25449","volume":"23","author":"D Back","year":"2020","unstructured":"Back, D. & Marzolini, C. The challenge of HIV treatment in an era of polypharmacy. J. Int. AIDS Soc. 23, e25449 (2020).","journal-title":"J. Int. AIDS Soc."},{"key":"374_CR2","doi-asserted-by":"publisher","first-page":"1362","DOI":"10.1002\/cpt.1393","volume":"105","author":"AS Devanathan","year":"2019","unstructured":"Devanathan, A. S. et al. Contemporary drug\u2013drug interactions in HIV treatment. Clin. Pharmacol. Therapeutics. 105, 1362\u20131377 (2019).","journal-title":"Clin. Pharmacol. Therapeutics."},{"key":"374_CR3","doi-asserted-by":"publisher","first-page":"36","DOI":"10.1503\/cmaj.131626","volume":"187","author":"CA Hughes","year":"2015","unstructured":"Hughes, C. A., Tseng, A. & Cooper, R. Managing drug interactions in HIV-infected adults with comorbid illness. Cmaj 187, 36\u201343 (2015).","journal-title":"Cmaj"},{"key":"374_CR4","doi-asserted-by":"publisher","first-page":"1345","DOI":"10.1002\/cpt.1435","volume":"105","author":"A Tornio","year":"2019","unstructured":"Tornio, A., Filppula, A. M., Niemi, M. & Backman, J. T. Clinical studies on drug\u2013drug interactions involving metabolism and transport: methodology, pitfalls, and interpretation. Clin. Pharmacol. Therapeutics. 105, 1345\u20131361 (2019).","journal-title":"Clin. Pharmacol. Therapeutics."},{"key":"374_CR5","doi-asserted-by":"publisher","first-page":"1356","DOI":"10.1007\/s12272-017-0976-0","volume":"40","author":"JS Min","year":"2017","unstructured":"Min, J. S. & Bae, S. K. Prediction of drug\u2013drug interaction potential using physiologically based pharmacokinetic modelling. Arch. Pharmacal. Res. 40, 1356\u20131379 (2017).","journal-title":"Arch. Pharmacal. Res."},{"key":"374_CR6","doi-asserted-by":"publisher","first-page":"268","DOI":"10.1111\/jcpt.12786","volume":"44","author":"D Song","year":"2019","unstructured":"Song, D. et al. Similarity\u2010based machine learning support vector machine predictor of drug\u2010drug interactions with improved accuracies. J. Clin. Pharm. Therap. 44, 268\u2013275 (2019).","journal-title":"J. Clin. Pharm. Therap."},{"key":"374_CR7","doi-asserted-by":"crossref","unstructured":"Yi, Z. et al. Drug-drug interaction extraction via recurrent neural network with multiple attention layers. International Conference on Advanced Data Mining and Applications 2017. 554\u2013566 (Springer, Cham, 2017).","DOI":"10.1007\/978-3-319-69179-4_39"},{"key":"374_CR8","doi-asserted-by":"publisher","unstructured":"Liu, S., Tang, B., Chen, Q. & Wang, X. Drug-drug interaction extraction via convolutional neural networks. Comput. Math. Methods Med. 2016, https:\/\/doi.org\/10.1155\/2016\/6918381 (2016).","DOI":"10.1155\/2016\/6918381"},{"key":"374_CR9","doi-asserted-by":"publisher","first-page":"e278","DOI":"10.1136\/amiajnl-2013-002512","volume":"21","author":"F Cheng","year":"2014","unstructured":"Cheng, F. & Zhao, Z. Machine learning-based prediction of drug\u2013drug interactions by integrating drug phenotypic, therapeutic, chemical, and genomic properties. J. Am. Med. Inform. Assoc. 21, e278\u2013e286 (2014).","journal-title":"J. Am. Med. Inform. Assoc."},{"key":"374_CR10","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","volume":"521","author":"Y LeCun","year":"2015","unstructured":"LeCun, Y., Bengio, Y. & Hinton, G. Deep learning. Nature 521, 436\u2013444 (2015).","journal-title":"Nature"},{"key":"374_CR11","doi-asserted-by":"crossref","unstructured":"Gillioz, A. et al. Overview of the Transformer-based Models for NLP Tasks. In 2020 15th Conference on Computer Science and Information Systems (FedCSIS). 179\u2013183 (IEEE, 2020).","DOI":"10.15439\/2020F20"},{"key":"374_CR12","unstructured":"Devlin, J. et al. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)."},{"key":"374_CR13","unstructured":"Chithrananda, S., Grand, G. and Ramsundar, B. ChemBERTa: large-scale self-supervised pretraining for molecular property prediction. arXiv preprint arXiv:2010.09885 (2020)."},{"key":"374_CR14","doi-asserted-by":"publisher","first-page":"1912","DOI":"10.1021\/ci049782w","volume":"44","author":"RP Sheridan","year":"2004","unstructured":"Sheridan, R. P., Feuston, B. P., Maiorov, V. N. & Kearsley, S. K. Similarity to molecules in the training set is a good discriminator for prediction accuracy in QSAR. J. Chem. Inf. Computer Sci. 44, 1912\u20131928 (2004).","journal-title":"J. Chem. Inf. Computer Sci."},{"key":"374_CR15","doi-asserted-by":"publisher","first-page":"503","DOI":"10.1016\/j.jmgm.2005.03.003","volume":"23","author":"L He","year":"2005","unstructured":"He, L. & Jurs, P. C. Assessing the reliability of a QSAR model\u2019s predictions. J. Mol. Graph. Model. 23, 503\u2013523 (2005).","journal-title":"J. Mol. Graph. Model."},{"key":"374_CR16","doi-asserted-by":"publisher","first-page":"6716","DOI":"10.1021\/jm060167o","volume":"49","author":"J Bostr\u00f6m","year":"2006","unstructured":"Bostr\u00f6m, J., Hogner, A. & Schmitt, S. Do structurally similar ligands bind in a similar fashion? J. Medi. Chem. 49, 6716\u20136725 (2006).","journal-title":"J. Medi. Chem."},{"key":"374_CR17","doi-asserted-by":"publisher","first-page":"805","DOI":"10.1038\/nbt1228","volume":"24","author":"GV Paolini","year":"2006","unstructured":"Paolini, G. V., Shapland, R. H., van Hoorn, W. P., Mason, J. S. & Hopkins, A. L. Global mapping of pharmacological space. Nat. Biotechnol. 24, 805\u2013815 (2006).","journal-title":"Nat. Biotechnol."},{"key":"374_CR18","doi-asserted-by":"publisher","first-page":"175","DOI":"10.1038\/nature08506","volume":"462","author":"MJ Keiser","year":"2009","unstructured":"Keiser, M. J. et al. Predicting new molecular targets for known drugs. Nature 462, 175\u2013181 (2009).","journal-title":"Nature"},{"key":"374_CR19","doi-asserted-by":"publisher","first-page":"1066","DOI":"10.1136\/amiajnl-2012-000935","volume":"19","author":"S Vilar","year":"2012","unstructured":"Vilar, S. et al. Drug-drug interaction through molecular structure similarity analysis. J. Am. Med. Inform. Assoc. 19, 1066\u20131074 (2012).","journal-title":"J. Am. Med. Inform. Assoc."},{"key":"374_CR20","doi-asserted-by":"publisher","first-page":"490","DOI":"10.2174\/138920021505141126102223","volume":"15","author":"S Vilar","year":"2014","unstructured":"Vilar, S. et al. State of the art and development of a drug-drug interaction large scale predictor based on 3D pharmacophoric similarity. Curr. Drug Metab. 15, 490\u2013501 (2014).","journal-title":"Curr. Drug Metab."},{"key":"374_CR21","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41598-019-50121-3","volume":"9","author":"N Rohani","year":"2019","unstructured":"Rohani, N. & Eslahchi, C. Drug-drug interaction predicting by neural network using integrated similarity. Sci. Rep. 9, 1\u201311 (2019).","journal-title":"Sci. Rep."},{"key":"374_CR22","first-page":"2739","volume":"380","author":"X Lin","year":"2020","unstructured":"Lin, X., Quan, Z., Wang, Z. J., Ma, T. & Zeng, X. KGNN: Knowledge Graph Neural Network for Drug-Drug Interaction Prediction. IJCAI 380, 2739\u20132745 (2020).","journal-title":"IJCAI"},{"key":"374_CR23","doi-asserted-by":"publisher","first-page":"4304","DOI":"10.1073\/pnas.1803294115","volume":"115","author":"JY Ryu","year":"2018","unstructured":"Ryu, J. Y., Kim, H. U. & Lee, S. Y. Deep learning improves prediction of drug\u2013drug and drug\u2013food interactions. Proc. Natl. Acad. Sci. 115, 4304\u20134311 (2018).","journal-title":"Proc. Natl. Acad. Sci."},{"key":"374_CR24","doi-asserted-by":"publisher","first-page":"457","DOI":"10.1093\/bioinformatics\/bty294","volume":"34","author":"M Zitnik","year":"2018","unstructured":"Zitnik, M., Agrawal, M. & Leskovec, J. Modeling polypharmacy side effects with graph convolutional networks. Bioinformatics 34, 457\u2013466 (2018).","journal-title":"Bioinformatics"},{"key":"374_CR25","doi-asserted-by":"publisher","unstructured":"Seden, K. et al. Development of an evidence evaluation and synthesis system for drug-drug interactions, and its application to a systematic review of HIV and malaria co-infection. PLoS One. 12, https:\/\/doi.org\/10.1371\/journal.pone.0173509 (2017).","DOI":"10.1371\/journal.pone.0173509"},{"key":"374_CR26","doi-asserted-by":"publisher","first-page":"403","DOI":"10.1002\/minf.201400024","volume":"33","author":"P Willett","year":"2014","unstructured":"Willett, P. The calculation of molecular structural similarity: principles and practice. Mol. Inform. 33, 403\u2013413 (2014).","journal-title":"Mol. Inform."},{"key":"374_CR27","doi-asserted-by":"publisher","first-page":"742","DOI":"10.1021\/ci100050t","volume":"50","author":"D Rogers","year":"2010","unstructured":"Rogers, D. & Hahn, M. Extended-connectivity fingerprints. J. Chem. Inf. Model. 50, 742\u2013754 (2010).","journal-title":"J. Chem. Inf. Model."},{"key":"374_CR28","unstructured":"Landrum, G. Rdkit documentation. http:\/\/www.rdkit.org\/RDKit_Docs.2011_12_1.pdf (2012)."},{"key":"374_CR29","first-page":"618","volume":"41","author":"C Bastida","year":"2017","unstructured":"Bastida, C. et al. Polypharmacy and potential drug-drug interactions in an HIV-infected elderly population. Farmacia Hospitalaria. 41, 618\u2013624 (2017).","journal-title":"Farmacia Hospitalaria."},{"key":"374_CR30","first-page":"1","volume":"52","author":"H Kaur","year":"2019","unstructured":"Kaur, H., Pannu, H. S. & Malhi, A. K. A systematic review on imbalanced data challenges in machine learning: Applications and solutions. ACM Comput. Surv. (CSUR). 52, 1\u201336 (2019).","journal-title":"ACM Comput. Surv. (CSUR)."},{"key":"374_CR31","doi-asserted-by":"publisher","first-page":"221","DOI":"10.1007\/s13748-016-0094-0","volume":"5","author":"B Krawczyk","year":"2016","unstructured":"Krawczyk, B. Learning from imbalanced data: open challenges and future directions. Prog. Artif. Intell. 5, 221\u2013232 (2016).","journal-title":"Prog. Artif. Intell."},{"key":"374_CR32","first-page":"332","volume":"1","author":"SM Abd Elrahman","year":"2013","unstructured":"Abd Elrahman, S. M. & Abraham, A. A review of class imbalance problem. J. Netw. Innovative Comput. 1, 332\u2013340 (2013).","journal-title":"J. Netw. Innovative Comput."},{"key":"374_CR33","doi-asserted-by":"publisher","first-page":"168","DOI":"10.1016\/j.aci.2018.08.003","volume":"17","author":"A Tharwat","year":"2020","unstructured":"Tharwat, A. Classification assessment methods. Appl. Comput. Inform. 17, 168\u2013192 (2020).","journal-title":"Appl. Comput. Inform."},{"key":"374_CR34","doi-asserted-by":"publisher","unstructured":"Garc\u00eda, V., Mollineda, R. A. & S\u00e1nchez, J. S. Index of Balanced Accuracy: A Performance Measure for Skewed Class Distributions. In: Araujo, H., Mendon\u00e7a, A. M., Pinho, A. J., Torres, M. I. (eds) Pattern Recognition and Image Analysis. IbPRIA 2009. Lecture Notes in Computer Science, vol 5524. Springer, Berlin, Heidelberg. https:\/\/doi.org\/10.1007\/978-3-642-02172-5_57 (2009).","DOI":"10.1007\/978-3-642-02172-5_57"},{"key":"374_CR35","unstructured":"National Institute of Health and Care Excellence. Lopinavir Interactions. https:\/\/bnf.nice.org.uk\/interactions\/lopinavir\/ (2024)."},{"key":"374_CR36","unstructured":"National Institute of Health and Care Excellence (NICE). Ritonavir Interactions. https:\/\/bnf.nice.org.uk\/interactions\/ritonavir\/ (2024)."},{"key":"374_CR37","unstructured":"European Medicines Agency (EMA). Symtuza: EPAR \u2013 Product Information. https:\/\/www.ema.europa.eu\/en\/documents\/product-information\/symtuza-epar-product-information_en.pdf (2023)."},{"key":"374_CR38","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41598-021-85586-8","volume":"11","author":"P Vivithanaporn","year":"2021","unstructured":"Vivithanaporn, P. et al. Potential drug-drug interactions of antiretrovirals and antimicrobials detected by three databases. Sci. Rep. 11, 1\u20138 (2021).","journal-title":"Sci. Rep."},{"key":"374_CR39","doi-asserted-by":"publisher","first-page":"58","DOI":"10.1016\/j.ymeth.2014.08.005","volume":"71","author":"A Cereto-Massagu\u00e9","year":"2015","unstructured":"Cereto-Massagu\u00e9, A. et al. Molecular fingerprint similarity search in virtual screening. Methods 71, 58\u201363 (2015).","journal-title":"Methods"},{"key":"374_CR40","first-page":"3","volume":"1","author":"H Zhang","year":"2004","unstructured":"Zhang, H. The optimality of naive Bayes. Aa 1, 3 (2004).","journal-title":"Aa"},{"key":"374_CR41","first-page":"130","volume":"27","author":"Y Song","year":"2015","unstructured":"Song, Y. & Ying, U. Decision tree methods: applications for classification and prediction. Shanghai Arch. Psychiatry 27, 130 (2015).","journal-title":"Shanghai Arch. Psychiatry"},{"key":"374_CR42","doi-asserted-by":"publisher","first-page":"217","DOI":"10.1080\/01431160412331269698","volume":"26","author":"M Pal","year":"2005","unstructured":"Pal, M. 2005. Random forest classifier for remote sensing classification. Int. J. Remote Sens. 26, 217\u2013222 (2005).","journal-title":"Int. J. Remote Sens."}],"container-title":["npj Systems Biology and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41540-024-00374-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41540-024-00374-0","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41540-024-00374-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,6]],"date-time":"2024-05-06T03:04:39Z","timestamp":1714964679000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41540-024-00374-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,6]]},"references-count":42,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2024,12]]}},"alternative-id":["374"],"URL":"https:\/\/doi.org\/10.1038\/s41540-024-00374-0","relation":{},"ISSN":["2056-7189"],"issn-type":[{"value":"2056-7189","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,5,6]]},"assertion":[{"value":"18 August 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 April 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 May 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"M.S. is a former employee of Labcorp and a current employee of esqLABS. All other authors declare no financial or non-financial competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"48"}}