There’s an age-old adage in biology: structure determines function. In order to understand the function of the myriad proteins that perform vital jobs in a healthy body—or malfunction in a diseased one—scientists have to first determine these proteins’ molecular structure.
We pretty much started the project roughly the day after we came back from the AlphaGo match in Seoul, where we beat Lee Sedol, the world [Go] champion. I was talking to Dave Silver, the project lead on AlphaGo, and we were discussing “What’s the next big project that DeepMind should do?” I was feeling like it was time to tackle something really hard in science because we had just solved more or less the pinnacle of games AI. I wanted to finally apply the AI to real-world domains.
One of the things we built in was this understanding of chemical bond angles and also evolutionary history using a process called multisequence alignment. These bring in some constraints, which help to narrow the search space of possible protein structures. The search space is too huge to do by brute force. But obviously, real-world physics solves this somehow because proteins fold up in nanoseconds or milliseconds.
But there’s also lots of really cool fundamental research being done with it. There was a whole special issue in Science on the nuclear pore complex. They solved the structure of one of the biggest proteins in the body. And I think three groups solved it at the same time from the cryo-EM [cryogenic electron microscopy] data—but they all needed AlphaFold predictions to augment the cryo-EM lower-resolution data in some places.
Short question: When has the intervention in nature, in biology, actually worked? I don't talk about medicin, who tries to heal our diseases... I look forward to a meaningful answer!
After reading this, I was surprised to see that foldingathome still exists. All folding problems are not solved?
🎅🏼
Predicted…
Google is evil.
You mean it wasn’t solved by a committee of trans midgets, but by a single person. Science can be estrange to Woke editors!
Now they can construct new proteins 🤔
Another nonsense statement by Scientific American. How the hell can anything 'predict' something that is already known?
It predicted a structure (some with extremely low confidence) of all human protein. Some might be the structures of those proteins. Many may not be.
Demis, is this the key to some psysiology fighting covid and cancer?
DrAhmedKalebi Take that with a pinch of salt. We have to confirm it in the wet lab especially OCT4. Otherwise we'll be out of our jobs
The human body is too complex for accurate analysis which is why doctors 'practice '
Huge claim based on false assumptions. Science by dictate.
BretWeinstein HeatherEHeying this seems cool.
Remarkable! Just remarkable:)
What an achievement demishassabis 👏🏿