{"ok":true,"nota":{"id":"fce4d643f5c96da4","slug":"un-nuevo-metodo-con-inteligencia-artificial-ayuda-a-identificar-tipos--fce4d6","titulo":"Un nuevo método con inteligencia artificial ayuda a identificar tipos de células en tejidos con mayor precisió","resumen":"Investigadores crearon BiNVaST, una herramienta que combina aprendizaje automático y simulaciones estadísticas para clasificar células en mapas de expresión génica espacial. Según el trabajo, funciona de forma consistente en distintas plataformas, incluso en tumores.","fuente":"biorxiv","fuenteNombre":"bioRxiv · preprints","color":"#be2628","autor":"Zhang, J., Li, L., Liu, L., Fridley, B. L., Cheng, C., Plummer, J. T., Wu, G., Chiang, J. C.-H., Li, Q.","url":"https://www.biorxiv.org/content/10.64898/2026.10.15.759369v1?rss=1","imagen":"/hoy/portada/fce4d643f5c96da4","tema":"ciencia","subtemas":["transcriptomica espacial","inteligencia artificial","oncologia","biologia celular","analisis de datos"],"entidades":["BiNVaST"],"formato":"dato","entretenimiento":false,"pubTs":"2026-10-21T00:00:00.000Z","indexTs":"2026-10-21T16:39:55.345Z","hash":"ab4735b657103e11a3db9e56cc298b7edddf83e495f5bb0d0d055f2acce98e9d","tsa":{"time":"Oct 21 16:40:53 2026 GMT","provider":"freetsa.org","sobre":"sello"},"stats":{"views":0,"likes":0,"clicks":0,"dwell":0},"tipo":"normal","registro":"hallazgo","porQueImporta":"Hoy los médicos y biólogos que estudian un tumor tienen dificultades para saber qué células hay en cada zona, sobre todo las raras. Una herramienta que lo haga con más consistencia puede acortar el camino entre un mapa de tejido y una decisión de investigación. El límite es que todavía es un preprint, sin revisión por pares, y evaluado con datos de laboratorio.","quienFirma":"bioRxiv · preprints","confianza":"preprint","consulta":null},"sello":{"hash":"ab4735b657103e11a3db9e56cc298b7edddf83e495f5bb0d0d055f2acce98e9d","sello":"c55a2b4a570f12183081dab8eb5af19cef73fd6fc8c7701dd79a7314f852920b","beacon":{"drand":{"cadena":"8990e7a9aaed2ffed73dbd7092123d6f289930540d7651336225dc172e51b2ce","ronda":6572327,"aleatorio":"d83e967e4c34cdf1b7eff62e6ba3c2a80c045b63fe1850f9291b003cd2f10aa6","tiempo":"2026-10-21T16:40:30.000Z"},"nist":{"cadena":2,"pulso":1993369,"salida":"46902ECFB36399313FFB65B445E71293DBF949380A38ED8B222CF72E430037F81238506B220BC468F19AAF1083C6EF424CA492E1A3404D8F36DA9E790C7B253D","tiempo":"2026-10-21T16:40:00.000Z"},"noAntes":"2026-10-21T16:40:30.000Z"},"verificacion":{"drand":true,"nist":true},"tsa":{"time":"Oct 21 16:40:53 2026 GMT","provider":"freetsa.org","sobre":"sello"},"original":{"titulo":"BiNVaST: niche boundary-preserving and synthetic data-guided variational autoencoders for concordant inference across high-resolution spatial transcriptomic platforms","descripcion":"High-resolution spatial transcriptomics (ST) enables subcellular spatially resolved transcript profiling but remains difficult to annotate in complex tissues because of gene coverage and super sparseness in expression. These challenges are amplified in cancer research, where neoplastic cell states and rare immune cells in tumor microenvironment are often poorly captured by generic references and/or cell typing tools exclusively built on molecular profile. Here, we present BiNVaST, a niche boundary-preserving and dual-branch variational autoencoder fused with statistical simulator for reliable cell typing across multiple spatial platforms. It generates platform-adjusted in silico training dat","pubDate":"2026-10-21","url":"https://www.biorxiv.org/content/10.64898/2026.10.15.759369v1?rss=1"},"indexado":"2026-10-21T16:39:55.345Z"}}