Tópicos populares
#
Bonk Eco continues to show strength amid $USELESS rally
#
Pump.fun to raise $1B token sale, traders speculating on airdrop
#
Boop.Fun leading the way with a new launchpad on Solana.
A IA REENGENHARIA PROTEÍNAS VENCEDORAS DO NOBEL PARA REVERSÃO DO ENVELHECIMENTO CELULAR
A OpenAI, em colaboração com a startup de longevidade Retro Bio, desenvolveu um modelo especializado chamado GPT-4b Micro que redesenhou os fatores de Yamanaka, vencedores do Prêmio Nobel, com uma eficiência impressionante.
Ao contrário da descoberta de 2012, que reprogramou menos de 0,1% das células ao longo de semanas, as proteínas projetadas pela IA converteram mais de 30% das células e mostraram um poderoso reparo de danos no DNA.
Vários laboratórios confirmaram os resultados em diferentes tipos de células e métodos de entrega.
A descoberta sinaliza um salto para a medicina regenerativa, comprimindo décadas de pesquisa sobre envelhecimento em meras semanas.
Fonte: rowancheung
31/01/2025
🚨 AI DID IN SECONDS WHAT NATURE NEEDED 500 MILLION YEARS FOR
Nature spent half a billion years crafting proteins—AI just did it in months. Meet ESM3, the super-powered AI that designs brand-new proteins from scratch, no evolution required.
This could change medicine, biotech, and maybe even life itself.
Trained on 2.78 billion proteins, ESM3 has 98 billion parameters, making it one of the most advanced AI models ever.
Instead of just remixing nature’s greatest hits, it creates entirely new proteins, like a biological DJ with infinite samples.
Its biggest flex?
esmGFP, a glowing protein 58% different from anything found in nature. Evolution would need millions of years to make this—ESM3 whipped it up in no time.
This isn’t just a cool science trick. It could revolutionize drug discovery, speed up new medicine development, and push biotech into sci-fi territory with stronger materials, cleaner energy, and futuristic food production.
It might even help us predict how life itself will evolve, which sounds like something we should keep an eye on.
AI-powered protein design isn’t just coming—it’s here. And it’s about to shake things up.
Source: bioRxiv
223,4K
Top
Classificação
Favoritos