Credit: ESM Metagenomic Atlas
“These are the structures we know the least about. These are incredibly mysterious proteins. I think they offer the potential for great insight into biology,” says Alexander Rives, the research lead for Meta AI’s protein team.— using a ‘large language model’, a type of AI that are the basis for tools that can predict text from just a few letters or words.
As a test case, they decided to wield their model on a database of bulk-sequenced ‘metagenomic’ DNA from environmental sources including soil, seawater, the human gut, skin and other microbial habitats. The vast majority of the DNA entries — which encode potential proteins — come from organisms that have never been cultured and are unknown to science.
Interesting
We must be careful that this is not an achievement like HUGO: Interesting, but then irrelevant for decades, oversold. Better add inverse protein folding and create antibodies per mRNA. Passive immunization in an instant, theoretically. Worth exploring, huge potential.
Poll: MetaBust?
Who is in charge of checking all of these predictions?
If the human body “only” uses 12,000 what are the other 599,988,000 proteins from? Extraterrestrial genomes
'...ESMFold, isn’t quite as accurate as AlphaFold, Rives’ team reported earlier this summer, but it is about 60 times faster at predicting structures' I don't think this is an application where speed is more important than accuracy, when 1 amino acid swap can ruin the structure
Pretty sure that Zuckerberg will install fb rules and regulations on the predicted structures. Once you submit a sequence 400 residues, your browser will be locked for 24 hours. 😄
GeneInvesting Skeptical
been saying that Meta AI & FAIR are the most slept on thing. rly amazing stuff and cool open source things as well
Technology Technology Latest News, Technology Technology Headlines
Similar News:You can also read news stories similar to this one that we have collected from other news sources.
Source: IntEngineering - 🏆 287. / 63 Read more »