Many of us are familiar with protein. It’s the thing we get when we consume certain foods, and it is also the building blocks of life where it helps with the formation of bones, muscles, skin, blood, and so on. While scientists have familiarized themselves with it, one of the mysteries is how it forms.
Protein starts off as a series of amino acids that can twist and fold onto themselves before it forms its final shape, but what has puzzled scientists for decades is trying to find a way to predict a protein’s final shape. However, this seems to be a problem that Alphabet’s DeepMind AI has solved, or at least come pretty close.
Dubbed the AlphaFold 2 AI, it appears that the DeepMind AI is capable of predicting with a high degree of accuracy how a protein is able to fold and form its shape, where the results are said to be “competitive” when put up against actual, experimental data.
According to Professor John Moult, CASP chair and co-founder, “We have been stuck on this one problem – how do proteins fold up – for nearly 50 years. To see DeepMind produce a solution for this, having worked personally on this problem for so long and after so many stops and starts, wondering if we’d ever get there, is a very special moment.”