Highly accurate protein structure prediction for the human proteome

Protein structures can provide invaluable information, both for reasoning about biological processes and for enabling interventions such as structure-based drug development or targeted mutagenesis. After decades of effort, 17% of the total residues in human protein sequences are covered by an experimentally determined structure(1). Here we markedly expand the structural coverage of the proteome by applying the state-of-the-art machine learning method, AlphaFold(2), at a scale that covers almost the entire human proteome (98.5% of human proteins). The resulting dataset covers 58% of residues with a confident prediction, of which a subset (36% of all residues) have very high confidence. We introduce several metrics developed by building on the AlphaFold model and use them to interpret the dataset, identifying strong multi-domain predictions as well as regions that are likely to be disordered. Finally, we provide some case studies to illustrate how high-quality predictions could be used to generate biological hypotheses. We are making our predictions freely available to the community and anticipate that routine large-scale and high-accuracy structure prediction will become an important tool that will allow new questions to be addressed from a structural perspective.

Automated summary

Using the AlphaFold method, the structural coverage of the proteome has been significantly expanded, covering 98.5% of human proteins with 58% of residues having confident predictions and 36% having very high confidence. Introducing new metrics to interpret the dataset and identify disordered regions, this study aims to provide high-quality predictions for generating biological hypotheses.