Uncovering distinct protein conformations using coevolutionary information and AlphaFold

Protein structure prediction has been transformed by AlphaFold, yet a key challenge remains: characterizing the multiple conformations adopted by proteins that can switch between different folds, without knowledge of their potential binding partners. Existing methods rely on sampling the multiple sequence alignment (MSA), either through random sampling or clustering, but these methods are statistically inefficient and do not explicitly utilize coevolutionary information during MSA sampling. We introduce an iterative sampling framework that systematically explores the MSA space using residue-specific frequencies and coevolutionary patterns inferred via Markov random fields. We further develop tools to identify a protein’s variable region and extract representative structures, yielding a compact, high-quality ensemble with good coverage of distinct conformations. On a benchmark set of fold-switching proteins, our method outperforms existing ones by substantially improving the diversity of the sampled structures. Overall, this work significantly advances our ability to characterize the conformational landscape of proteins.