{"ok":true,"nota":{"id":"9a59d44d3e7365eb","slug":"un-nuevo-modelo-digital-predice-mejor-donde-se-pegan-las-proteinas-ent-9a59d4","titulo":"Un nuevo modelo digital predice mejor dónde se pegan las proteínas entre sí","resumen":"Investigadores crearon un sistema computacional que analiza la forma de las proteínas para identificar los puntos donde se unen con otras moléculas. Lo probaron con distintos tipos de interacciones y lo presentan como un método unificado.","fuente":"biorxiv","fuenteNombre":"bioRxiv · preprints","color":"#be2628","autor":"Nguyen, V. T. D., Johnstone, J. K., Hy, T.-S.","url":"https://www.biorxiv.org/content/10.64898/2026.10.18.759950v1?rss=1","imagen":"/hoy/portada/9a59d44d3e7365eb","tema":"ciencia","subtemas":["biologia molecular","proteinas","descubrimiento de farmacos","inteligencia artificial","bioinformatica"],"entidades":["PRIME-ISP"],"formato":"dato","entretenimiento":false,"pubTs":"2026-10-22T00:00:00.000Z","indexTs":"2026-10-23T06:48:38.804Z","hash":"16d406c0f39006c09cc35a7d69bf9244ef26720bbc14fa8d69c079e7635f6fe5","tsa":{"time":"Oct 23 06:48:58 2026 GMT","provider":"freetsa.org","sobre":"sello"},"stats":{"views":0,"likes":0,"clicks":0,"dwell":0},"tipo":"normal","registro":"hallazgo","porQueImporta":"Saber en qué zona exacta una proteína se engancha con otra es clave para entender cómo funcionan las células y para diseñar medicamentos. Hasta ahora cada herramienta servía para un solo tipo de unión, y esto apunta a reemplazarlas por una sola. Para un laboratorio argentino que busque nuevos fármacos, eso podría ahorrar tiempo y recursos. Todavía es un preprint sin revisión por pares, así que conviene esperar la validación independiente antes de confiar en sus resultados.","quienFirma":"bioRxiv (preprint, institución de los autores no especificada en el resumen)","confianza":"preprint","consulta":null},"sello":{"hash":"16d406c0f39006c09cc35a7d69bf9244ef26720bbc14fa8d69c079e7635f6fe5","sello":"f10a5221f3ee1b3e248b8515a2a7a9573e935cc8276cd4dc7cec2b45a4f287d5","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 06:48:58 2026 GMT","provider":"freetsa.org","sobre":"sello"},"original":{"titulo":"Towards a Unified Framework for Protein Interaction Site Prediction Using Hierarchical Protein Representations","descripcion":"Proteins interact with a wide range of biomolecular partners, yet identifying the interaction sites that mediate these events remains a major challenge for understanding cellular function and guiding drug discovery. Existing computational methods are typically designed for specific interaction classes and often rely on task-specific features. Here, we introduce PRIME-ISP, a structure-based framework for predicting interaction sites across diverse biomolecular interaction types using a unified architecture. PRIME-ISP represents proteins at five organizational levels, including solvent-excluded surfaces, atoms, residues, secondary-structure elements, and whole proteins, and integrates informat","pubDate":"2026-10-22","url":"https://www.biorxiv.org/content/10.64898/2026.10.18.759950v1?rss=1"},"indexado":"2026-10-23T06:48:38.804Z"}}