Alphabet's DeepMind AI has solved "the protein folding problem" that could aid medicine...

Pete Flint

Posts: 37   +7
TL;DR: DeepMind Technologies, a research lab in the UK owned by Alphabet, has developed an AI that can determine the folded shape of a protein in a matter of hours, which would typically require months or years of lab research. Depending on how Alphabet distributes this technology to the science community, this development has the potential to affect a huge array of medical and biological research.

Computer scientists at DeepMind, a lab owned by Alphabet, Google’s parent company, have developed an AI that has made a monumental leap in solving “the protein folding problem.” This conundrum has plagued biologists for decades, and solving it can accelerate countless other studies in medicine, agriculture, and conservation, to name a few.

Proteins are crucial "macromolecules" built from strings of molecules called amino acids. These strings of molecules are built inside of each cell by reading an organism’s DNA and blocking together long chains of amino acids. Of the 20 amino acids that make up proteins, each one chosen depends on the DNA sequence being read, and each amino acid has special properties that cause the long chain of molecules to fold over itself into a very specific, highly complicated shape, which gives the protein its function.

Understanding the shape and how it relates to the function of proteins is so important because they are responsible for most biological functions in the body, including immune response, digestion, energy production, muscle contraction, blood clotting, and countless more.

The interest of many research groups revolves around synthetic proteins used in medicines. Knowing the order of amino acids in a protein is easy enough for researchers if they know the DNA sequence that is used as its template, but knowing its shape can dramatically expedite the process of determining how it will function in people, bacteria or viruses. Among other mysteries this can unravel, think of vaccine research, a topic on everyone’s mind presently.

DeepMind’s neural network can quickly and reliably determine a protein’s shape, given the string of amino acids that comprise the protein.

Scientists have been working hard to crack this nut for over 50 years. A competition called the Critical Assessment of Structure Prediction (CASP) was formed 25 years ago to bring together this research, compare results and spur on investigation.

No one has really come close to solving this problem until DeepMind came onto the scene. Tested on a variety of proteins, DeepMind’s neural network was able to accurately assume the folded structure of a protein with the precision of lab-based experiments that typically take months or years to solve.

It should be noted that experts say solving the protein folding problem speeds up just the initial stage of the long process of safely developing a medication.

This has also apparently emerged too late to affect vaccine research into the coronavirus but could be used down the line to stem future pandemics, determine whether existing medications can be used on novel infections, and research genetic diseases such as Alzheimer’s.

John Moult, a University of Maryland professor that co-created CASP back in 1994, said about this new development, “I always hoped I would live to see this day.”

Permalink to story.


Uncle Al

Posts: 7,797   +6,450
This is extraordinary news, solving a puzzle of over 50 years and unless I'm mistaken, this is the first MAJOR solution to come out of AI .....
  • Like
Reactions: terzaerian


Posts: 1,735   +988
If it’s good enough to do this it’s good enough to choose it’s own damn photos of buses and traffic lights 😉
It's good enough to do this because you have been choosing the buses and traffic lights: you're helping to train Google's AI algorithms with each CAPTCHA you go through. Just think, every troll on 4chan is really just helping to cure cancer and AIDs.


Posts: 833   +318
It's good enough to do this because you have been choosing the buses and traffic lights: you're helping to train Google's AI algorithms with each CAPTCHA you go through. Just think, every troll on 4chan is really just helping to cure cancer and AIDs.
Interesting comment. I find most of those "select all the pictures with a/an X" very difficult. So, I generally have to do it multiple times. It suggests that I'm retarded and don't know what a bike, boat or airplane is. So, if the AI is counting on me to help it get smarter it needs to provide pictures that are easier to identify the target objects. And not have me second guessing everything.



Posts: 1,735   +988
So is this a huge RIP to the whole Folding@Home project?
Depends on what Google does with this algorithm. If it can be distributed across different network agents, and Alphabet implements this, then get ready for a whole lot of gasoline to get dumped on the folding@home project.


Posts: 319   +243
BRILLIANT! I've been working on this problem for over a decade by contributing to the Rosetta@home project. As it currently stands, complex problems are broken into pieces which are sent out to the client PC's for analysis. It takes thousands of computing hours to complete a project. This is a SIGNIFICANT break through.


Posts: 875   +349
But still haven't find a way to send a chemical signal to gingiva so that people can regrow their teeth (like all adults already did twice in their lifetime). Instead we have to visit those torture-loving-greedy-leeches called dentists, who are selling us crap solutions at the price of alien technology.

I'm still waiting to see the ACTUAL, tangible medical results of using top technology. So far, pharmaceuticals can't even find solutions for simple problems, after having access to the most advanced computer tech for more than 20 years. So, either they don't want good solutions, or they are complete morons.

Or maybe it's a combination, since their combined GQ (greed coefficient) is several orders of magnitude higher than their combined IQ.