{"ok":true,"nota":{"id":"8c1f269fb8556a84","slug":"una-ia-de-proposito-general-encontro-pistas-biologicas-pero-varias-no--8c1f26","titulo":"Una IA de propósito general encontró pistas biológicas, pero varias no se confirmaron en el laboratorio","resumen":"Investigadores usaron inteligencia artificial para analizar datos moleculares públicos y generar hipótesis. Algunas pistas se repitieron entre corridas, pero un candidato no mostró efecto en los experimentos posteriores.","fuente":"biorxiv","fuenteNombre":"bioRxiv · preprints","color":"#be2628","autor":"Jin, G., Bao, X.","url":"https://www.biorxiv.org/content/10.64898/2026.10.16.759709v1?rss=1","imagen":"/hoy/portada/8c1f269fb8556a84","tema":"tecnologia","subtemas":["inteligencia artificial","biologia computacional","datos publicos","celulas madre","mieloma multiple"],"entidades":["bioRxiv"],"formato":"dato","entretenimiento":false,"pubTs":"2026-10-22T00:00:00.000Z","indexTs":"2026-10-22T22:54:28.111Z","hash":"037073679429b6b20b289d2a7cae0a75163dd81bc1e4f98ba14e672452211997","tsa":{"time":"Oct 22 22:55:02 2026 GMT","provider":"freetsa.org","sobre":"sello"},"stats":{"views":0,"likes":0,"clicks":0,"dwell":0},"tipo":"motor","registro":"hallazgo","porQueImporta":"Cada vez más investigaciones dependen de herramientas de IA para revisar bases de datos enormes que ya existen. Este trabajo muestra que la IA puede proponer caminos prometedores, como antígenos para terapias con células inmunes, pero también que muchas hipótesis no sobreviven al experimento real. Para quien sigue las noticias de avances médicos, conviene desconfiar de los titulares que anuncian descubrimientos hechos solo por algoritmos. La distancia entre una predicción de computadora y una cura sigue siendo enorme.","quienFirma":"bioRxiv (preprint sin revisión por pares; institución de los autores no identificada en el resumen)","confianza":"preprint","consulta":{"pregunta":"¿Confiarías en un descubrimiento médico hecho por una IA?"}},"sello":{"hash":"037073679429b6b20b289d2a7cae0a75163dd81bc1e4f98ba14e672452211997","sello":"313fd5c0062b740062236dacc4c5e620fa7d6135be793778843f43dd46c8f12e","beacon":{"drand":{"cadena":"8990e7a9aaed2ffed73dbd7092123d6f289930540d7651336225dc172e51b2ce","ronda":6575956,"aleatorio":"2a57a8658c1d539864cc4ae3efbab33cd3270e814e75bf7846346721462f12e7","tiempo":"2026-10-22T22:55:00.000Z"},"nist":{"cadena":2,"pulso":1995177,"salida":"44471E1C8A000FA428D45A5C480CB1AAB6429BD43B19D16210510F8146BBA7769584FA09251B999E8D0B2F0EEC2EEEC53219499677294EE43E94C8610586BE7D","tiempo":"2026-10-22T22:54:00.000Z"},"noAntes":"2026-10-22T22:55:00.000Z"},"verificacion":{"drand":true,"nist":true},"tsa":{"time":"Oct 22 22:55:02 2026 GMT","provider":"freetsa.org","sobre":"sello"},"original":{"titulo":"General Purpose AI for Public Data Analysis and Experimental Hypothesis Generation","descripcion":"Public molecular datasets can support biological questions beyond those addressed in the original studies. We examined how general-purpose AI could help generate and investigate such questions through four complementary investigations. Interactive single-cell analysis identified Apelin signaling as a candidate for promoting mesendoderm differentiation of human pluripotent stem cells, although subsequent experiments did not establish an effect under the tested conditions. Autonomous analyses then searched public single-cell data for tumor antigens that could be targeted by engineered immune cells. Three multiple-myeloma runs shared 50 candidates and repeatedly recovered BCMA and CD38, whereas","pubDate":"2026-10-22","url":"https://www.biorxiv.org/content/10.64898/2026.10.16.759709v1?rss=1"},"indexado":"2026-10-22T22:54:28.111Z"}}