Co-evolutionary distance predictions contain flexibility information

Abstract

Motivation Co-evolution analysis can be used to accurately predict residue-residue contacts from multiple sequence alignments. The introduction of machine-learning techniques has enabled substantial improvements in precision and a shift from predicting binary contacts to predicting distances between pairs of residues. These developments have significantly improved the accuracy of de novo prediction of static protein structures. With AlphaFold2 lifting the accuracy of some predicted protein models close to experimental levels, structure prediction research will move on to other challenges. One of those areas is the prediction of more than one conformation of a protein. Here we examine the potential of residue-residue distance predictions to be informative of protein flexibility rather than simply static structure. Results We used DMPfold to predict distance distributions for every residue pair in a set of proteins that showed both rigid and flexible behaviour. Residue pairs that were in contact in at least one reference structure were classified as rigid, flexible or neither. The predicted distance distribution of each residue pair was analysed for local maxima of probability indicating the most likely distance or distances between a pair of residues. We found that rigid residue pairs tended to have only a single local maximum in their predicted distance distributions while flexible residue pairs more often had multiple local maxima. These results suggest that the shape of predicted distance distributions contains information on the rigidity or flexibility of a protein and its constituent residues. Supplementary information Supplementary data are available at Bioinformatics online.

Current structure predictors are not learning the physics of protein folding

“…Related work has studied the search trajectories of fragment replacement methods ( Kandathil et al , 2016 ), or attempted to introduce biological constraints into folding ( de Oliveira et al , 2018 ). Furthermore, recent work has shown that some deep learning predictors can pinpoint flexible residues ( Schwarz et al , 2020 ) or conformational changes ( Del Alamo et al , 2021 ), suggesting that these methods may capture dynamic phenomena reflected in the multiple sequence alignment. In this work, we examine whether protein structure prediction methods are able to reveal anything about a protein’s folding pathway.…”

Antibody structure prediction using interpretable deep learning

“… 51 DMPfold 52 , a similar method for general proteins, has been shown to contain flexibility information within inter-residue distance distributions. 53 In principle, DeepAb might provide similar insights into CDR loop flexibility, but further investigation is necessary.…”

Modeling Alternate Conformations with Alphafold2 via Modification of the Multiple Sequence Alignment

“…This is in agreement with a study that found that residues that had differential contacts in conformationally heterogenous proteins had multiple distance peaks in the distance matrix derived from MSAs. 32 Therefore, these regions of uncertainty are targets for conformational switching as well as for direct contact points to consider for alternate conformations.…”