{"ok":true,"nota":{"id":"60db77afcb3f261f","slug":"una-inteligencia-artificial-diseno-peptidos-que-frenan-una-enzima-liga-60db77","titulo":"Una inteligencia artificial diseñó péptidos que frenan una enzima ligada a la inflamación del tejido","resumen":"Investigadores usaron CAMOLE-1, una plataforma de aprendizaje automático, para diseñar péptidos inhibidores de metaloproteinasas de matriz, enzimas que degradan tejido. Combinaron el diseño por computadora con filtros físicos y pruebas bioquímicas.","fuente":"biorxiv","fuenteNombre":"bioRxiv · preprints","color":"#be2628","autor":"Calico Life Sciences LLC,, Lin, J., Bratkowski, M. A.","url":"https://www.biorxiv.org/content/10.64898/2026.10.21.755545v1?rss=1","imagen":"/hoy/portada/60db77afcb3f261f","tema":"salud","subtemas":["inteligencia-artificial","farmacos","peptidos","enzimas","desarrollo-de-medicamentos"],"entidades":["Calico","CAMOLE-1","bioRxiv"],"formato":"dato","entretenimiento":false,"pubTs":"2026-10-26T00:00:00.000Z","indexTs":"2026-10-27T00:12:40.142Z","hash":"10f7efa9df1d7d12d62e85167fa682fc631cbe6e50877f72dc9b0427b56e0bb2","tsa":{"time":"Oct 27 00:13:42 2026 GMT","provider":"freetsa.org","sobre":"sello"},"stats":{"views":0,"likes":0,"clicks":0,"dwell":0},"tipo":"normal","registro":"hallazgo","porQueImporta":"Diseñar fármacos tarda años y cuesta fortunas, y este trabajo muestra que una IA puede proponer candidatos con potencia y selectividad en menos tiempo. Eso puede acelerar tratamientos futuros para enfermedades donde estas enzimas están involucradas. Pero que haya un candidato prometedor en laboratorio no significa que funcione en personas: esa etapa todavía falta, y muchas moléculas prometedoras fracasan ahí.","quienFirma":"Calico (preprint de bioRxiv; institución principal inferida del nombre de la plataforma)","confianza":"preprint","consulta":null},"sello":{"hash":"10f7efa9df1d7d12d62e85167fa682fc631cbe6e50877f72dc9b0427b56e0bb2","sello":"310dcfcce4caad1a20e0f5a1cd31508c7df657c9db249912a99fb241c8f741d9","beacon":{"drand":{"cadena":"8990e7a9aaed2ffed73dbd7092123d6f289930540d7651336225dc172e51b2ce","ronda":6587632,"aleatorio":"e5f4501cec646e43fc02e0fe1fe4a007971ca7f76b2ee59bcfa3c5f64bf15567","tiempo":"2026-10-27T00:13:00.000Z"},"nist":{"cadena":2,"pulso":2001009,"salida":"D40E14007D6713315067C4542F3D7D0FF922C8FB815DB05FEACE37847166032AAD7591924E5D2623E17D17CD6D56FA07A2A5696B5751C1B97915B1C932BE8E75","tiempo":"2026-10-27T00:12:00.000Z"},"noAntes":"2026-10-27T00:13:00.000Z"},"verificacion":{"drand":true,"nist":true},"tsa":{"time":"Oct 27 00:13:42 2026 GMT","provider":"freetsa.org","sobre":"sello"},"original":{"titulo":"Accelerated discovery and optimization of a potent andselective MMP12 inhibitor with the machine learningplatform CAMOLE-1","descripcion":"Machine learning techniques are being readily utilized to accelerate drug discovery pipelines. Peptide therapeutics are an emerging modality that offer the advantage of increased potency with reduced toxicity that are amenable to machine learning discovery and optimization. This work describes the Calico All-Atom Molecule Engine (CAMOLE-1), a machine learning platform for de novo peptide inhibitor design. CAMOLE-1 incorporates an all-atom diffusion model that enables rapid non-canonical peptide discovery and optimization, and integrates physics based computational filtering, and biochemical testing. We applied CAMOLE-1 towards the discovery of peptide inhibitors of matrix metalloproteinases ","pubDate":"2026-10-26","url":"https://www.biorxiv.org/content/10.64898/2026.10.21.755545v1?rss=1"},"indexado":"2026-10-27T00:12:40.142Z"}}