Applications of AlphaFold beyond Protein Structure Prediction

Abstract Predicting structures accurately for natural protein sequences by DeepMind’s AlphaFold is certainly one of the greatest breakthroughs in biology in the twenty-first century. For designed or engineered sequences, which can be unstable, predicting the stabilities together with their structures is essential since unstable structures will not function properly. We found that experimentally measured stability changes of point mutations correlate poorly with the confidence scores produced by AlphaFold. However, the stability changes can be accurately predicted using features extracted from the representations learned by AlphaFold, indicating greater generalizability of AlphaFold to designed or engineered sequences than previously thought. We then used AlphaFold to validate our previously developed protein design method, ProDCoNN, that designs sequences to fold to target protein structures given only the backbone structure information of the target proteins. We showed that ProDCoNN was able to design sequences that fold to structures very close to target structures. By combining a modified ProDCoNN, AlphaFold, and sequential Monte Carlo, we designed a novel framework to estimate the designability of protein structures. The designability of a protein structure is defined as the number of sequences, which encode the protein structure, and is an indicator of the functional robustness of proteins. For the first time, we estimated the designability of a real protein structure, chain A of FLT3 ligand (PDB ID: 1ETE) with 134 residues, as 3.12±2.14E85.