{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T21:54:11Z","timestamp":1781646851649,"version":"3.54.5"},"reference-count":32,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,3,30]],"date-time":"2026-03-30T00:00:00Z","timestamp":1774828800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,5,11]],"date-time":"2026-05-11T00:00:00Z","timestamp":1778457600000},"content-version":"vor","delay-in-days":42,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["BioData Mining"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Alzheimer\u2019s disease (AD) remains a major therapeutic challenge, characterized by high clinical trial failure rates and limited efficacy of current treatments. Drug repurposing offers a faster, lower-risk route to new therapies; however, existing computational approaches often prioritize predictive accuracy over mechanistic novelty and interpretability, both of which are critical for clinical translation.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      We introduce a quality-diversity Automated Machine Learning (AutoML) framework that integrates biologically informed graph neural network (GNN) embeddings with a MAP-Elites-guided search to discover predictive yet mechanistically distinct therapeutic hypotheses. Drugs and genes are embedded using GraphSAGE and variational graph autoencoders trained on the Alzheimer\u2019s Knowledge Base (AlzKB), with a clustering loss used to anchor known AD entities and define dimensions of biological novelty. In an AD case study using matched ADSP GWAS-derived features, our framework successfully recovered known drug\u2013gene relationships and identified robust consensus candidates across independent validation runs. Most notably, the search consistently prioritized\n                      <jats:bold>Triclosan<\/jats:bold>\n                      \u2014a recently identified environmental risk factor for AD neuroinflammation\u2014and the\n                      <jats:bold>Ketamine\/Quazepam<\/jats:bold>\n                      pair, suggesting a model-driven preference for restoring synaptic E\/I balance. Furthermore, exploratory leads such as Exemestane and Felodipine were identified in underrepresented biological niches, supported by enrichment in oxidative stress and autophagy pathways. The framework demonstrated high stability across multiple random seeds and a\n                      <jats:bold>48% reduction in computational cost<\/jats:bold>\n                      compared to standard multi-objective evolutionary baselines.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>Beyond AD, this framework offers a generalizable strategy for integrating biomedical knowledge graphs with diversity-enhancing AutoML to accelerate the discovery of mechanistically novel drug candidates across complex polygenic diseases.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1186\/s13040-026-00550-4","type":"journal-article","created":{"date-parts":[[2026,3,30]],"date-time":"2026-03-30T10:47:04Z","timestamp":1774867624000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A biology-based quality-diversity algorithm for drug repurposing in Alzheimer\u2019s disease using automated machine learning"],"prefix":"10.1186","volume":"19","author":[{"given":"Sisi","family":"Shao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pedro Henrique","family":"Ribeiro","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alena","family":"Orlenko","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Katie M.","family":"Cardone","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Christina M.","family":"Ramirez","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Li","family":"Shen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marylyn D.","family":"Ritchie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jason H.","family":"Moore","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,3,30]]},"reference":[{"key":"550_CR1","doi-asserted-by":"crossref","unstructured":"Romano JD, Truong V, Kumar R, Venkatesan M, Graham BE, Hao Y, et al. The Alzheimer\u2019s knowledge Base: a knowledge graph for Alzheimer disease research. J Med Internet Res. 2024;26:e46777.","DOI":"10.2196\/46777"},{"issue":"1","key":"550_CR2","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1056\/NEJMoa2212948","volume":"388","author":"CH Van Dyck","year":"2023","unstructured":"Van Dyck CH, Swanson CJ, Aisen P, Bateman RJ, Chen C, Gee M, et al. Lecanemab in early Alzheimer\u2019s disease. NEJM Evid. 2023;388(1):9\u201321.","journal-title":"NEJM Evid"},{"issue":"7","key":"550_CR3","doi-asserted-by":"publisher","first-page":"1785","DOI":"10.1016\/j.drudis.2022.05.026","volume":"27","author":"P Zhan","year":"2022","unstructured":"Zhan P, Yu B, Ouyang L. Drug repurposing: an effective strategy to accelerate contemporary drug discovery. Drug Discov Today. 2022;27(7):1785.","journal-title":"Drug Discov. Today Today"},{"issue":"1","key":"550_CR4","doi-asserted-by":"publisher","first-page":"1755","DOI":"10.1038\/s41467-025-56690-4","volume":"16","author":"JL Cummings","year":"2025","unstructured":"Cummings JL, Zhou Y, Van Stone A, Cammann D, Tonegawa-Kuji R, Fonseca J, et al. Drug repurposing for Alzheimer\u2019s disease and other neurodegenerative disorders. Nat Commun. 2025;16(1):1755.","journal-title":"Nat Commun"},{"key":"550_CR5","doi-asserted-by":"crossref","unstructured":"Li VO, Han Y, Kaistha T, Zhang Q, Downey J, Gozes I, et al. DeepDrug: an expert-led domain-specific AI-Driven drug-repurposing mechanism for selecting the lead combination of. Drugs Alzheimer\u2019s Disease. medRxiv. 2024;2024\u201327.","DOI":"10.1101\/2024.07.06.24309990"},{"key":"550_CR6","doi-asserted-by":"crossref","unstructured":"Mottaqi M, Zhang P, Xie L. Integrating interpretable machine learning and multi-omics systems biology for personalized biomarker discovery and drug repurposing in Alzheimer\u2019s disease. bioRxiv. 2025;2025\u201303.","DOI":"10.1101\/2025.03.24.644676"},{"issue":"1","key":"550_CR7","doi-asserted-by":"publisher","first-page":"46","DOI":"10.1038\/s41746-024-01038-3","volume":"7","author":"C Yan","year":"2024","unstructured":"Yan C, Grabowska ME, Dickson AL, Li B, Wen Z, Roden DM, et al. Leveraging generative AI to prioritize drug repurposing candidates for Alzheimer\u2019s disease with real-world clinical validation. NPJ Digit Med. 2024;7(1):46.","journal-title":"NPJ Digit Med"},{"key":"550_CR8","doi-asserted-by":"publisher","first-page":"102172","DOI":"10.1016\/j.arr.2023.102172","volume":"93","author":"C Geng","year":"2024","unstructured":"Geng C, Wang Z, Tang Y. Machine learning in Alzheimer\u2019s disease drug discovery and target identification. Ageing Res Rev. 2024;93:102172.","journal-title":"Ageing Res Rev"},{"key":"550_CR9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-05318-5","volume-title":"Automated machine learning: methods, systems, challenges","author":"F Hutter","year":"2019","unstructured":"Hutter F, Kotthoff L, Vanschoren J. Automated machine learning: methods, systems, challenges. Springer Nature; 2019."},{"key":"550_CR10","doi-asserted-by":"crossref","unstructured":"Olson RS, Bartley N, Urbanowicz RJ, Moore JH. Evaluation of a tree-based pipeline optimization tool for automating data science. Proceedings of the genetic and evolutionary computation conference 2016. 2016. p. 485\u201392.","DOI":"10.1145\/2908812.2908918"},{"key":"550_CR11","doi-asserted-by":"crossref","unstructured":"Ribeiro P, Saini A, Moran J, Matsumoto N, Choi H, Hernandez M, et al. TPOT2: a New graph-based implementation of the tree-based pipeline optimization tool for automated machine learning. In: Genetic programming theory and practice XX. Springer; 2024. p. 1\u201317.","DOI":"10.1007\/978-981-99-8413-8_1"},{"key":"550_CR12","unstructured":"Mouret JB, Clune J. Illuminating search spaces by mapping elites. arXiv preprint arXiv:150404909. 2015."},{"issue":"1","key":"550_CR13","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1109\/TNNLS.2020.2978386","volume":"32","author":"Z Wu","year":"2020","unstructured":"Wu Z, Pan S, Chen F, Long G, Zhang C, Philip SY. A comprehensive survey on graph neural networks. IEEE Trans Neural Networks Learn Syst. 2020;32(1):4\u201324.","journal-title":"IEEE Trans Neural Networks Learn Syst"},{"key":"550_CR14","unstructured":"Hamilton W, Ying Z, Leskovec J. Inductive representation learning on large graphs. Adv Neural Inf Process Syst. 2017;30."},{"key":"550_CR15","unstructured":"Kipf TN, Welling M. Variational graph auto-encoders. arXiv preprint arXiv:161107308. 2016."},{"issue":"4","key":"550_CR16","doi-asserted-by":"publisher","first-page":"719","DOI":"10.1007\/s10994-020-05877-5","volume":"109","author":"J Bekker","year":"2020","unstructured":"Bekker J, Davis J. Learning from positive and unlabeled data: a survey. Mach Learn. 2020;109(4):719\u201360.","journal-title":"Mach Learn"},{"key":"550_CR17","doi-asserted-by":"publisher","unstructured":"Leung YY, Lee WP, Kuzma AB, Gangadharan P, Nicaretta HI, Qu L, et al. ADSP whole genome sequencing (WGS) release 4 data update from genome center for Alzheimer\u2019s disease. Alzheimer\u2019s Dementia. 2023;19:e077351. https:\/\/doi.org\/10.1002\/alz.077351.","DOI":"10.1002\/alz.077351"},{"key":"550_CR18","doi-asserted-by":"crossref","unstructured":"Orlenko A, Venkatesan M, Shen L, Ritchie MD, Wang ZP, Obafemi-Ajayi T, et al. Biologically enhanced machine learning model to uncover novel gene-drug targets for Alzheimer\u2019s disease. Biocomputing 2025: Proceedings of the Pacific Symposium. World Scientific; 2024. p. 441\u201356.","DOI":"10.1142\/9789819807024_0032"},{"issue":"9","key":"550_CR19","doi-asserted-by":"publisher","first-page":"1564","DOI":"10.1038\/nprot.2010.116","volume":"5","author":"CA Anderson","year":"2010","unstructured":"Anderson CA, et al. Data quality control in genetic case-control association studies. Nat Protoc. 2010;5(9):1564\u201373.","journal-title":"Nat Protoc"},{"key":"550_CR20","doi-asserted-by":"crossref","unstructured":"Marees AT, et al. A tutorial on conducting genome-wide association studies: quality control and imputation. Int J Methods Psychiatric Res. 2018;27(2):e1608.","DOI":"10.1002\/mpr.1608"},{"key":"550_CR21","volume-title":"Principles of population genetics","author":"DL Hartl","year":"2007","unstructured":"Hartl DL, Clark AG. Principles of population genetics. 4th. Sinauer Associates; 2007.","edition":"4th"},{"key":"550_CR22","volume-title":"Genetic data analysis II: methods for discrete population genetic data","author":"BS Weir","year":"1996","unstructured":"Weir BS. Genetic data analysis II: methods for discrete population genetic data. Sunderland, MA: Sinauer Associates; 1996."},{"issue":"6","key":"550_CR23","doi-asserted-by":"publisher","first-page":"477","DOI":"10.1038\/nrg2361","volume":"9","author":"M Slatkin","year":"2008","unstructured":"Slatkin M. Linkage disequilibrium \u2014 understanding the evolutionary past and mapping the medical future. Nat Rev Genet. 2008;9(6):477\u201385.","journal-title":"Nat Rev Genet"},{"key":"550_CR24","doi-asserted-by":"crossref","unstructured":"Kline A, Luo Y. PsmPy: a package for retrospective cohort matching in python. 2022 44th Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC). IEEE; 2022. p. 1354\u201357.","DOI":"10.1109\/EMBC48229.2022.9871333"},{"key":"550_CR25","doi-asserted-by":"crossref","unstructured":"Akiba T, Sano S, Yanase T, Ohta T, Koyama M. Optuna: a next-generation hyperparameter optimization framework. Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. 2019. p. 2623\u201331.","DOI":"10.1145\/3292500.3330701"},{"key":"550_CR26","doi-asserted-by":"publisher","first-page":"104520","DOI":"10.1016\/j.ebiom.2023.104520","volume":"90","author":"SJ Andrews","year":"2023","unstructured":"Andrews SJ, Renton AE, Fulton-Howard B, Podlesny-Drabiniok A, Marcora E, Goate AM. The complex genetic architecture of Alzheimer\u2019s disease: novel insights and future directions. EBioMedicine. 2023;90:104520. https:\/\/doi.org\/10.1016\/j.ebiom.2023.104520.","journal-title":"EBioMedicine"},{"key":"550_CR27","first-page":"2546","volume":"24","author":"J Bergstra","year":"2011","unstructured":"Bergstra J, Bardenet R, Bengio Y, K\u00e9gl B. Algorithms for hyper-parameter optimization. Adv Neural Inf Process Syst. 2011;24:2546\u201354.","journal-title":"Adv Neural Inf Process Syst"},{"key":"550_CR28","doi-asserted-by":"crossref","unstructured":"Rouillard AD, Gundersen GW, Fernandez NF, Wang Z, Monteiro CD, McDermott MG, et al. The harmonizome: a collection of processed datasets gathered to serve and mine knowledge about genes and proteins. Database. 2016;2016:baw100.","DOI":"10.1093\/database\/baw100"},{"key":"550_CR29","doi-asserted-by":"publisher","first-page":"127068","DOI":"10.1016\/j.envpol.2025.127068","volume":"385","author":"F Cheng","year":"2025","unstructured":"Cheng F, Gao H, Yan B, Chen F, Lei P. From disinfectant to neurodegeneration: integrating machine learning and mendelian randomization reveals triclosan as a novel environmental risk factor for Alzheimer\u2019s disease. Environ Pollut. 2025;385:127068.","journal-title":"Environ Pollut"},{"issue":"9","key":"550_CR30","doi-asserted-by":"publisher","first-page":"1869","DOI":"10.4103\/1673-5374.390979","volume":"19","author":"E Asimakidou","year":"2024","unstructured":"Asimakidou E, Reynolds R, Barron AM, Lo CH. Autolysosomal acidification impairment as a mediator for TNFR1 induced neuronal necroptosis in Alzheimer\u2019s disease. Neural Regener Res. 2024;19(9):1869\u201370. https:\/\/doi.org\/10.4103\/1673-5374.390979.","journal-title":"Neural Regener Res"},{"key":"550_CR31","doi-asserted-by":"publisher","first-page":"118199","DOI":"10.1016\/j.biopha.2025.118199","volume":"188","author":"M Altamura","year":"2025","unstructured":"Altamura M, Leccisotti I, Moretti MC, Bellomo A, Panza F, Cassano T, et al. Can ketamine therapy overcome treatment-resistant depression in Alzheimer\u2019s disease and older adults? Preclinical and clinical evidence. Biomed Pharmacother. 2025 Jul;188:118199. https:\/\/doi.org\/10.1016\/j.biopha.2025.118199.","journal-title":"Biomed Pharmacother"},{"key":"550_CR32","doi-asserted-by":"publisher","first-page":"149207","DOI":"10.1016\/j.brainres.2024.149207","volume":"1845","author":"J Chen","year":"2024","unstructured":"Chen J, Zhang M, Shen Z, Tang M, Zeng Y, Bai D, et al. Low-dose diazepam improves cognitive function in APP\/PS1 mouse models: involvement of AMPA receptors. Brain Res. 2024;1845:149207. https:\/\/doi.org\/10.1016\/j.brainres.2024.149207.","journal-title":"Brain Res"}],"container-title":["BioData Mining"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s13040-026-00550-4","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13040-026-00550-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13040-026-00550-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T21:10:10Z","timestamp":1781644210000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1186\/s13040-026-00550-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,30]]},"references-count":32,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["550"],"URL":"https:\/\/doi.org\/10.1186\/s13040-026-00550-4","relation":{},"ISSN":["1756-0381"],"issn-type":[{"value":"1756-0381","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,30]]},"assertion":[{"value":"26 October 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 March 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 March 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"The authors declare no competing interests.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"34"}}