The latest AlphaFold AI model developed by Google DeepMind and Isomorphic Labs has the ability to predict the 3D structures of almost all known molecules, including DNA, RNA, ligands, and proteins. Researchers believe this AI update has the potential to unlock and accelerate medical research, drug development, synthetic biology, and other scientific fields.
Google DeepMind announced in an Oct. 31 blog post that the latest AlphaFold model can accurately predict the structure of almost every molecule in the Protein Data Bank. The post said this breakthrough could revolutionize the scientific community’s understanding of biology and lead to new biomedical breakthroughs, such as new drug targets and therapies.
AlphaFold has undergone continuous development since its release in 2020, expanding its capabilities from single-chain proteins to multi-chain complexes and improving its prediction accuracy. In a major step towards open science, AlphaFold's predictions for nearly all known proteins were made freely accessible through the AlphaFold Protein Structure Database, fostering global collaboration and accelerating research in various fields.
More than 1.4 million people from more than 190 countries have accessed the database for diverse applications, including malaria vaccine development, cancer drug discovery, and plastic-degrading enzyme design to address climate change.
Google DeepMind said in the post that AlphaFold “has already catalyzed major scientific advances around the world,” and its new generation could “help advance scientific exploration at digital speed.
