DeepMind has unveiled the latest version of its AI-powered AlphaFold program, reports TechCrunch.

Its first version was presented about five years ago. Back then, it was able to predict the structure of many proteins in the human body. Later, the system was improved – in 2020, an updated and more powerful AlphaFold 2 appeared.

The current version is its successor. Its peculiarity is that it is capable of generating predictions for almost all molecules in the world’s largest database of biological molecules, the Protein Data Bank.

But that’s not all. Isomorphic Labs (a subsidiary of DeepMind) is already using the model to develop therapeutic drugs.

DeepMind emphasizes that the new AlphaFold model can accurately predict the structures of ligands (molecules that bind to “receptor” proteins and cause changes in cellular interaction), nucleic acids (molecules that contain key genetic information), and post-translational modifications (chemical changes that occur after a protein is created).

DeepMind notes that this could be a useful tool in drug development, as scientists will be able to identify and design new molecules that can form the basis of new drugs.