{"ok":true,"nota":{"id":"269aeed81b1cbdc2","slug":"disenan-anticuerpos-completos-por-computadora-para-enfermedades-difici-269aee","titulo":"Diseñan anticuerpos completos por computadora para enfermedades difíciles de tratar","resumen":"Investigadores usaron un modelo de inteligencia artificial que trabaja con secuencia y estructura atómica para diseñar anticuerpos terapéuticos completos, sin depender solo de pruebas de laboratorio largas. Los diseños lograron actuar sobre blancos biológicos considerados complicados.","fuente":"biorxiv","fuenteNombre":"bioRxiv · preprints","color":"#be2628","autor":"Pythia Labs Team,, Aglietti, R. A., Ansari, R., Bowers, P. M., Buelles, T.-H., Chauvin, H., Duplay, T. M., El Hibouri, M","url":"https://www.biorxiv.org/content/10.64898/2026.10.21.760573v1?rss=1","imagen":"/hoy/portada/269aeed81b1cbdc2","tema":"ciencia","subtemas":["anticuerpos","inteligencia artificial","diseño de medicamentos","biotecnología","terapias"],"entidades":["Pythia-1","bioRxiv"],"formato":"dato","entretenimiento":false,"pubTs":"2026-10-26T00:00:00.000Z","indexTs":"2026-10-26T23:22:05.517Z","hash":"4fc5ca6a69e6face695cfa4a31e0ac1b0167780b6d1eab2e42c1d208440de811","tsa":{"time":"Oct 26 23:22:43 2026 GMT","provider":"freetsa.org","sobre":"sello"},"stats":{"views":0,"likes":0,"clicks":0,"dwell":0},"tipo":"motor","registro":"hallazgo","porQueImporta":"Hoy encontrar un anticuerpo que sirva como medicamento puede llevar años de prueba y error, y muchas enfermedades quedan afuera porque no hay forma práctica de atacarlas. Si el diseño por computadora se confirma, esas búsquedas podrían acortarse y llegar a pacientes que hoy no tienen opciones. El estudio todavía no está revisado por pares y los resultados vienen de modelos, así que falta comprobarlos en personas. Medicina más rápida no es lo mismo que medicina lista para usar.","quienFirma":"Preprint en bioRxiv (autoría institucional no especificada en el resumen)","confianza":"preprint","consulta":{"pregunta":"¿Le confiarías un tratamiento diseñado por computadora?"}},"sello":{"hash":"4fc5ca6a69e6face695cfa4a31e0ac1b0167780b6d1eab2e42c1d208440de811","sello":"6bb7e2364b705ca109b6c3483d4613fc3105d51ae68c9d825cbd9e969e4482b1","beacon":{"drand":{"cadena":"8990e7a9aaed2ffed73dbd7092123d6f289930540d7651336225dc172e51b2ce","ronda":6587531,"aleatorio":"fe6a0d1e32f33530ee3865ce898a933a679d836c030556cafcf9f7f9e03e9c1f","tiempo":"2026-10-26T23:22:30.000Z"},"nist":{"cadena":2,"pulso":2000959,"salida":"38EFC3652F96D1340187DD7D5B32A840F878CD33000D34F2E88A92400DF1FC86B990B57549F5A1FBF1EAABF05D417E628C2ED1C646A08A636235AA53F1954B2D","tiempo":"2026-10-26T23:22:00.000Z"},"noAntes":"2026-10-26T23:22:30.000Z"},"verificacion":{"drand":true,"nist":true},"tsa":{"time":"Oct 26 23:22:43 2026 GMT","provider":"freetsa.org","sobre":"sello"},"original":{"titulo":"Design of full-length agonist and antagonist antibodies for hard targets","descripcion":"Therapeutic antibodies have transformed modern medicine, yet conventional discovery relies on lengthy experimental workflows, offers limited control over how antibodies engage their targets, and struggles to deliver candidates across many important target classes. Despite recent advances in computational protein design, generating full-length antibodies with desired functional activity and favorable developability profiles remains challenging. Here we present an end-to-end computational design pipeline built around Pythia-1, an all-atom generative model that reasons jointly over amino acid sequence and three-dimensional atomic structure under explicit design constraints. We generated candida","pubDate":"2026-10-26","url":"https://www.biorxiv.org/content/10.64898/2026.10.21.760573v1?rss=1"},"indexado":"2026-10-26T23:22:05.517Z"}}