A password will be e-mailed to you.

DeepMind’s AI solved a 50-year-old protein-related challenge



DeepMind is a research company owned by Google that specialises in using Artificial Intelligence for positive impacts in the world. According to recent reports, DeepMind is successfully continuing to do its job in finding answers to impossible questions and to solve challenges with Artificial Intelligence.

DeepMind has recently solved a 50-year-old protein-related challenge that has notched up the level of biology for scientists. AI can help us understand the world and DeepMind has proof. Today, DeepMind in association with CASP or Critical Assessment of protein Structure Prediction competition announced an Artificial Intelligence that should have a huge impact on biology and the human efforts to understand life. We are talking about DeepMind’s AlphaFold, the latest iteration, a deep-learning system that can accurately predict the structure of proteins within the size of an atom. This is a major development in biology as this has been a challenge since the 1970s, almost 50 years old challenge has today been solved by an Artificial Intelligence system.

John Moult leader of CASP at the University of Maryland says that it is the first-ever use of an Artificial Intelligence system to solve a serious problem.

Now, a protein’s shape is closely associated with its functions and the ability to predict its structure can unlock a greater understanding of what the protein actually does and how it works. There are countless diseases in the world that are all linked with the shape of the virus’ protein. Having DeepMind’s AlphaFold AI understand and predict the shape of the protein will give us answers to a lot of solutions, finding enzymes that break industrial issues.

This has been a challenge for almost 50 years and a focus of intrinsic scientific research for many years. Scientists have used a variety of different techniques and experiments to determine protein structures but none of them is as feasible as DeepMind’s solution.

Not just this, AlphaFold is accurate too. The main metric to measure the accuracy of predictions is the Global Distance Test. CASP says that their new technique would open up the potential of biologists to use computational methods to understand protein structures as a core tool of scientific research. The advanced protein-folding problem will especially prove helpful in predicting structures of important classes of protein such as membrane proteins that are very difficult to crystallise.

However, this process will take days to computationally provide the prediction results as opposed to months or even years with the older processes. AlphaFold has done a fabulous job and biologists and scientists from all across the globe are praising this new discovery.


Click here to see what DeepMind has to say.




Send this to a friend