Proteins are made up of chains of amino acids that fold into complex three-dimensional shapes that determine their function. Mapping protein structures is important for understanding what they do and how they work, and how things can go wrong. However, it is still difficult to calculate the exact structure of a protein based on the amino acids that make it up. This usually requires a large amount of computing power and operating hours.

That was until Alphabet used its powerful DeepMind artificial intelligence to solve this problem. Initially trained on 100,000 known protein structures, the system has evolved the ability to predict the structures of millions of other proteins, each of which takes minutes or seconds instead of months or years to determine.

DeepMind recently released a massive new database update containing around 214 million structures from one million species. This encompasses almost every protein known to science, which is a huge help for research into disease treatments, vaccines, antibiotic resistance, and even plastic pollution.

The entire protein structure database of more than 25 terabytes of data can be downloaded from Google Cloud Public Datasets.

Source: Ferra

Previous articleSony just released an iPhone game controller and it’s as cool as it sounds
Next articleZephyr drone has been flying above ground for 43 days

LEAVE A REPLY

Please enter your comment!
Please enter your name here