Discover more from @JamieBykovBrett
Meta AI Unlocks Hundreds of Millions of Proteins to Aid Drug Discovery 🧬
🧬 Meta Platforms has developed a new AI-based computer program known as ESMFold that predicts protein structures promising to deepen scientists' understanding of biology and speed up the discovery of new drugs.
💻 Rather than using microscopes, the ESMFold model uses the same technology as ChatGPT - a large language model that predicts text responses. Meta scientists gave the ESMFold program a series of letters representing the amino acids that form a protein's genetic code, and ESMFold then learned how to fill in the missing sections in the sequence.
🔬 Determining protein structure has been traditionally difficult and expensive. However, ESMFold is expected to boost the effectiveness of existing drugs while helping in the discovery of molecules that could treat diseases that have remained elusive.
👨🔬 "Often proteins which share similar structures have similar biological functions", explains co-author of a study published in the journal 'Science', Alexander Rives, "And if you can have a really high-resolution structure, then you can begin to think about what is the actual biochemical function of these proteins."
⚙️ With ESMFold, researchers can search through large genetic databases to find possible applications in medicine, health, food and the environment.
#Metaplatforms #ESMFold #AI #Insights #proteins
💡 Would you like to learn more? Join our Web3, Metaverse & AI learning community: http://distributedrepublic.xyz/