{"ok":true,"nota":{"id":"aaa80591f0b8328e","slug":"un-nuevo-modelo-de-ia-estima-la-edad-biologica-con-menos-parametros-aaa805","titulo":"Un nuevo modelo de IA estima la edad biológica con menos parámetros","resumen":"Un equipo desarrolló EG-BINN, un conjunto de redes neuronales que estima la edad biológica a partir de marcas epigenéticas del ADN. Lo entrenaron con 93 conjuntos de datos de distintos tejidos y superó a modelos lineales y no lineales de referencia en validación cruzada.","fuente":"biorxiv","fuenteNombre":"bioRxiv · preprints","color":"#be2628","autor":"Edwards, T. A., Long, Q., Shen, L.","url":"https://www.biorxiv.org/content/10.64898/2026.10.17.759869v1?rss=1","imagen":"/hoy/portada/aaa80591f0b8328e","tema":"ciencia","subtemas":["envejecimiento","epigenetica","inteligencia artificial","metilacion del adn","relojes biologicos"],"entidades":["bioRxiv","EG-BINN"],"formato":"dato","entretenimiento":false,"pubTs":"2026-10-22T00:00:00.000Z","indexTs":"2026-10-23T06:48:38.804Z","hash":"a25616fc11ad85978803c4de38907834f5f308ecd19301e8ba7e3c160d0fa988","tsa":{"time":"Oct 23 06:48:59 2026 GMT","provider":"freetsa.org","sobre":"sello"},"stats":{"views":0,"likes":0,"clicks":0,"dwell":0},"tipo":"motor","registro":"hallazgo","porQueImporta":"Los relojes epigenéticos se usan para medir qué tan rápido envejece una persona y el riesgo de ciertas enfermedades. Este modelo logra mejores estimaciones con una estructura más liviana y más fácil de interpretar que las redes profundas comunes. Para alguien de acá, esto podría traducirse en pruebas de envejecimiento más precisas algún día, aunque todavía no hay uso clínico. Antes de confiar en un resultado así hay que ver si funciona en poblaciones diferentes a las del estudio.","quienFirma":"Preprint en bioRxiv (institución principal no identificada en el resumen)","confianza":"preprint","consulta":{"pregunta":"¿Te gustaría saber tu edad biológica?"}},"sello":{"hash":"a25616fc11ad85978803c4de38907834f5f308ecd19301e8ba7e3c160d0fa988","sello":"5fd876e85757adcb9b7c9e4ea28c69eec2c77755f24b1f055364b86e5536b36d","beacon":{"drand":{"cadena":"8990e7a9aaed2ffed73dbd7092123d6f289930540d7651336225dc172e51b2ce","ronda":6576903,"aleatorio":"8e583525a288ba13cde66d0d6539d282d867cec58f75a0217a855687a27f9649","tiempo":"2026-10-23T06:48:30.000Z"},"nist":{"cadena":2,"pulso":1995651,"salida":"AA82134D649B7B25F10D77FD67053808011261EF94B49E048C931DF7D357E824C95C66604E50CE6E37F934A39EE493177DEA66983586EA3E4667145C3C8919D6","tiempo":"2026-10-23T06:48:00.000Z"},"noAntes":"2026-10-23T06:48:30.000Z"},"verificacion":{"drand":true,"nist":true},"tsa":{"time":"Oct 23 06:48:59 2026 GMT","provider":"freetsa.org","sobre":"sello"},"original":{"titulo":"EG-BINN: Parameter-Efficient Ensembling of Gated Biologically Informed Neural Networks for Epigenetic Age Estimation","descripcion":"Epigenetic aging clocks are widely used to evaluate biological aging, disease risk, and clinical interventions. However, most existing clocks rely on linear models that overlook nonlinear relationships between age and methylation patterns, or on deep learning architectures that are parameter-intensive and difficult to interpret. We developed EG-BINN, a parameter-efficient ensemble of biologically informed neural networks that uses sample-specific gating to modulate representations across biologically annotated nodes. Trained on 93 multi-tissue datasets, EG-BINN achieved the lowest mean and median absolute errors among matched linear and nonlinear baselines in five-fold cross-validation, as w","pubDate":"2026-10-22","url":"https://www.biorxiv.org/content/10.64898/2026.10.17.759869v1?rss=1"},"indexado":"2026-10-23T06:48:38.804Z"}}