Highly accurate protein structure prediction for the human proteome

ABSTRACT

The sequence of the human genome has been available for two decades, but the structures of the proteins it encodes have largely remained unknown, limiting our understanding of human health and disease. Here we use AlphaFold to predict the structure of almost the entire human proteome (98.5% of all human proteins). We find that 58% of the residues are predicted with high confidence, more than doubling the structural coverage provided by decades of experimental efforts. We also provide structural predictions for the proteomes of 20 other biologically significant organisms. All predictions are made freely available in the AlphaFold Protein Structure Database, dramatically expanding our knowledge of protein space.