Google DeepMind has taken the wraps off a new version of AlphaFold, their transformative machine learning model that predicts the shape and behavior of proteins. AlphaFold 3 is not only more accurate, but predicts interactions with other biomolecules, making it a far more versatile research tool — and the company is putting a limited version of the model free to use online.
From the debut of the first AlphaFold back in 2018, the model has remained the leading method of predicting protein structure from the sequence of amino acids that make them up.
Though this sounds like rather a narrow task, it’s foundational to nearly all biology to understand proteins — which perform a nearly endless variety of tasks in our bodies — at the molecular level. In recent years, computational modeling techniques like AlphaFold and RoseTTaFold have taken over from expensive, lab-based…
