Portal de Periódicos da CAPES

Computing linkage disequilibrium aware genome embeddings using autoencoders

2024; Oxford University Press; Volume: 40; Issue: 6 Linguagem: Inglês

10.1093/bioinformatics/btae326

1367-4811

Gizem Taş, Timo Westerdijk, Eric Postma, Wouter van Rheenen, Mark K. Bakker, Kristel R. van Eijk, Maarten Kooyman, Ahmad Al Khleifat, Alfredo Iacoangeli, Nicola Ticozzi, Johnathan Cooper‐Knock, Marta Gromicho, Siddharthan Chandran, Karen Morrison, Pamela J. Shaw, John Hardy, Michael Sendtner, Thomas Meyer, Nazlı Başak, Isabella Fogh, Adriano Chiò, Andrea Calvo, Elisabetta Pupillo, Giancarlo Logroscino, Marc Gotkine, Patrick Vourc’h, Philippe Corcia, Philippe Couratier, Stéphanie Millecamps, François Salachas, Jesús S. Mora Pardina, Ricardo Rojas‐García, Patrick A. Dion, Jay P. Ross, Albert C. Ludolph, Jochen H. Weishaupt, Axel Freischmidt, Gilbert Bensimon, Lukas Tittmann, Wolfgang Lieb, Andre Franke, Stephan Ripke, David C. Whiteman, Catherine M. Olsen, André G. Uitterlinden, Albert Hofman, Philippe Amouyel, Bryan J. Traynor, A. Singleton, Miguel Mitne Neto, Ruben J. Cauchi, Roel A. Ophoff, Vivianna M. Van Deerlin, Julian Großkreutz, Caroline Graff, Lev Brylev, Boris Rogelj, Blaž Koritnik, Janez Zidar, Zorica Stević, Vivian E. Drory, Mónica Povedano, Ian P Blair, Matthew C. Kiernan, Garth A. Nicholson, Anjali K. Henders, Mamede de Carvalho, Susana Pinto, Susanne Petri, Markus Weber, Guy A. Rouleau, Vincenzo Silani, Jonathan D. Glass, Robert H. Brown, John E. Landers, Christopher E. Shaw, Peter M. Andersen, Fleur C. Garton, Allan F. McRae, Russell L. McLaughlin, Orla Hardiman, Kevin P. Kenna, Naomi R. Wray, Ammar Al‐Chalabi, Philip Van Damme, Leonard H. van den Berg, Jan H. Veldink, Jan H. Veldink, Alexander Schönhuth, Marleen Balvert,

Genetic and phenotypic traits in livestock

The completion of the genome has paved the way for genome-wide association studies (GWAS), which explained certain proportions of heritability. GWAS are not optimally suited to detect non-linear effects in disease risk, possibly hidden in non-additive interactions (epistasis). Alternative methods for epistasis detection using, e.g. deep neural networks (DNNs) are currently under active development. However, DNNs are constrained by finite computational resources, which can be rapidly depleted due to increasing complexity with the sheer size of the genome. Besides, the curse of dimensionality complicates the task of capturing meaningful genetic patterns for DNNs; therefore necessitates dimensionality reduction.