AlphaFold at CASP13

Abstract

Computational prediction of protein structure from sequence is broadly viewed as a foundational problem of biochemistry and one of the most difficult challenges in bioinformatics. Once every two years the Critical Assessment of protein Structure Prediction (CASP) experiments are held to assess the state of the art in the field in a blind fashion, by presenting predictor groups with protein sequences whose structures have been solved but have not yet been made publicly available. The first CASP was organized in 1994, and the latest, CASP13, took place last December, when for the first time the industrial laboratory DeepMind entered the competition. DeepMind's entry, AlphaFold, placed first in the Free Modeling (FM) category, which assesses methods on their ability to predict novel protein folds (the Zhang group placed first in the Template-Based Modeling (TBM) category, which assess methods on predicting proteins whose folds are related to ones already in the Protein Data Bank.) DeepMind's success generated significant public interest. Their approach builds on two ideas developed in the academic community during the preceding decade: (i) the use of co-evolutionary analysis to map residue co-variation in protein sequence to physical contact in protein structure, and (ii) the application of deep neural networks to robustly identify patterns in protein sequence and co-evolutionary couplings and convert them into contact maps. In this Letter, we contextualize the significance of DeepMind's entry within the broader history of CASP, relate AlphaFold's methodological advances to prior work, and speculate on the future of this important problem.

Fig. 1.

Historical CASP performance in prediction of gross protein topology. Curves show the best and second best predictors at each CASP, while the dashed line shows the expected improvement at CASP13 given the average rate of improvement from CASP10 to 12. Ranking is based on CASP assessor’s formula, and does not always coincide with highest mean GDT_TS (e.g. CASP10). Error bars correspond to 95% confidence intervals

Fig. 2.

Historical CASP performance in prediction of fine-grained protein topology. Curves show the best and second best predictors at each CASP, while the dashed line shows the expected improvement at CASP13 given the average rate of improvement from CASP10 to 12. Ranking is based on CASP assessor’s formula, and does not always coincide with highest mean GDT_HA (e.g. CASP10). Error bars correspond to 95% confidence intervals