Progress in protein structure prediction: AlphaFold2 and beyond

Abstract

AlphaFold2, a protein structure prediction method developed by Google DeepMind, surprised the world with its high prediction accuracy of protein structures. And it quickly became widely used by researchers around the world. 2020 may be remembered as the year that the long-standing problem of protein structure prediction was solved. Before AlphaFold2 emerged, there are the accumulation of research on protein structures, advances in genome research with the next-generation sequencers, improvements in computing power, and the development of artificial intelligence (AI). In this article, we will explain AlphaFold2 while mentioning these factors. Finally, we would like to look to the future by introducing AlphaFold3, which was just announced this May.