Bracher-Smith M, Melograna F, Ulm B, Bellenguez C, Grenier-Boley B, Duroux D, Nevado AJ, Holmans P, Tijms BM, Hulsman M, de Rojas I, Campos-Martin R, der Lee Sv, Castillo A, Küçükali F, Peters O, Schneider A, Dichgans M, Rujescu D, Scherbaum N, Deckert J, Riedel-Heller S, Hausner L, Molina-Porcel L, Düzel E, Grimmer T, Wiltfang J, Heilmann-Heimbach S, Moebus S, Tegos T, Scarmeas N, Dols-Icardo O, Moreno F, Pérez-Tur J, Bullido MJ, Pastor P, Sánchez-Valle R, Álvarez V, Boada M, Puerta R, Mir P, Real LM, Piñol-Ripoll G, Rodriguez-Rodriguez E, Soininen H, Heikkinen S, de Mendonça A, Mehrabian S, Traykov L, Hort J, Vyhnalek M, Sandau N, Thomassen JQ, Pijnenburg YA, Holstege H, van Swieten J, Ramakers I, Verhey F, Scheltens P, Graff C, Papenberg G, Giedraitis V, Williams J, Amouyel P, Boland A, Deleuze JF, Nicolas G, Dufouil C, Pasquier F, Hanon O, Debette S, Grünblatt E, Popp J, Ghidoni R, Galimberti D, Arosio B, Mecocci P, Solfrizzi V, Parnetti L, Squassina A, Tremolizzo L, Borroni B, Nacmias B, Spallazzi M, Seripa D, Rainero I, Daniele A, Piras F, Masullo C, Rossi G, Jessen F, Kehoe P, Magda T, Sánchez-Juan P, Sleegers K, Ingelsson M, Hiltunen M, Sims R, van der Flier W, Andreassen OA, Ruiz A, Ramirez A, Ikram MA, Mather K, Sachdev P, Ghanbari M, Zulaica M, Yannakoulia M, Woods B, Windle G, Weinhold L, Wallon D, Wagner M, Vogelgsang J, Vita MG, Vidal JS, Vandenberghe R, van Rooij J, Van Dongen J, Van Broeckhoven C, Valero S, Ulstein I, Ullgren A, Uitterlinden A, Tybjærg-Hansen A, Thomas T, Thalamuthu A, Tesí N, Tárraga L, Miguel A, Stordal E, Spottke A, Sotolongo-Grau O, Sorbi S, Solomon A, Skrobot O, Shadrin AA, Selbæk G, Schott JM, Schmid M, Scherer M, Scarpini E, Scamosci M, Sando SB, Sanchez-Garcia F, Sánchez-Arjona MB, García-Gutierrez F, Saltvedt I, Sakka P, Sáez ME, Rubino E, Royo JL, Rosende-Roca M, Allende IR, Rongve A, Olivé C, Riederer P, Reinders MJ, Rábano A, Quintela I, Quenez O, Puerta R, Priller J, Posthuma D, Polak T, Pisanu C, Pineda JA, Pericard P, Martinez-Lucas M, Paolo C, Padovani A, Capdevila M, Orsini M, Orellana A, Olaso R, Nordestgaard BG, Ngandu T, Nöthen MM, Morgan K, Montrreal L, Mol M, Menéndez-González M, Mendoza S, Meggy A, Medina M, Mead S, Rodríguez CM, Montes AM, Marshall R, Marquié M, Marco S, Mangialasche F, Maier W, MacLeod CA, Macías J, Luckcuck L, Löwemark M, Love S, de Munain AL, Lleó A, Lerch O, Lehtisalo J, Lauria A, Laukka EJ, Lage C, Kosmidis MH, Kornhuber J, Koivisto A, Kivipelto M, Ståhlbom AK, Kilander L, Johansson C, Jan Biessels G, Vilas RH, Holmes C, Hoffmann P, Herrmann MJ, Hernández I, Heneka MT, Helisalmi S, Harwood J, Leonenko G, Hartmann AM, Hardy J, Hampel H, Hadjigeorgiou G, Haapasalo A, Guetta-Baranes T, Green E, Grande G, González-Pérez A, Goldhardt O, Giorgio G, Giegling I, Garcia-Ribas G, Garcia-Madrona S, García-González P, García-Alberca JM, Froelich L, Frank-García A, Franco-Macías E, Fox NC, Fostinelli S, Foroud TM, Fortea J, Fließbach K, Fladby T, Fischer P, Fin B, Ferri E, Ferreira CB, Fernández-Fuertes M, Fenoglio C, Farotti L, Nielsen SF, Fabrizio T, Ewers M, Blázquez J, Engelborghs S, Duron E, Djurovic S, Rossi PD, Diez-Fairen M, Diehl-Schmid J, Denning N, del Ser T, de Deyn PP, Dartigues JF, Dardiotis E, Daian D, Custodero C, Giuffrè GM, Corma-Gómez A, Conti E, Clark C, Clarimon J, Claassen JA, Ciccone S, Chillotti C, Charbonnier C, Cervera-Carles L, Cecchetti R, Carracedo Á, Chene G, Calero M, Burholt V, Bûrger K, Buiza-Rueda D, Brookes KJ, Brodaty H, Bresner C, Bråthen G, Bossù P, Boschi S, Boada M, Blesa R, Bizarro A, Bellini S, Binetti G, Bessi V, Besse C, Berr C, Pastor AB, Baquero M, Banaj N, Bailly H, Athanasiu L, Pastor AA, Archetti S, Arcaro M, Appollonio I, Anthoula T, Armstrong NJ, Alvarez I, Alegret M, Alcolea D, Alarcón-Martín E, Abdelnour C, Cano A, Aarsland D, Ahmad S, Kleineidam L, Dalmasso MC, Fernández V, Andrade V, van der Lee S, Jansen I, Frikke-Schmidt R, Amin N, Roshchupkin G, Lambert JC, Van Steen K, van Duijn C, Escott-Price V (2025)
Publication Type: Journal article
Publication year: 2025
Book Volume: 16
Article Number: 6726
Journal Issue: 1
DOI: 10.1038/s41467-025-61650-z
Traditional statistical approaches have advanced our understanding of the genetics of complex diseases, yet are limited to linear additive models. Here we applied machine learning (ML) to genome-wide data from 41,686 individuals in the largest European consortium on Alzheimer’s disease (AD) to investigate the effectiveness of various ML algorithms in replicating known findings, discovering novel loci, and predicting individuals at risk. We utilised Gradient Boosting Machines (GBMs), biological pathway-informed Neural Networks (NNs), and Model-based Multifactor Dimensionality Reduction (MB-MDR) models. ML approaches successfully captured all genome-wide significant genetic variants identified in the training set and 22% of associations from larger meta-analyses. They highlight 6 novel loci which replicate in an external dataset, including variants which map to ARHGAP25, LY6H, COG7, SOD1 and ZNF597. They further identify novel association in AP4E1, refining the genetic landscape of the known SPPL2A locus. Our results demonstrate that machine learning methods can achieve predictive performance comparable to classical approaches in genetic epidemiology and have the potential to uncover novel loci that remain undetected by traditional GWAS. These insights provide a complementary avenue for advancing the understanding of AD genetics.
APA:
Bracher-Smith, M., Melograna, F., Ulm, B., Bellenguez, C., Grenier-Boley, B., Duroux, D.,... Escott-Price, V. (2025). Machine learning in Alzheimer’s disease genetics. Nature Communications, 16(1). https://doi.org/10.1038/s41467-025-61650-z
MLA:
Bracher-Smith, Matthew, et al. "Machine learning in Alzheimer’s disease genetics." Nature Communications 16.1 (2025).
BibTeX: Download