Fold-switching proteins push the boundaries of conformational ensemble prediction

2026/01/05 by Myeongsang Lee, Lauren L. Porter · 1 voice
Biochemistry, Genetics and Molecular Biology · #q-bio.BM

paper · pdf · doi:10.1146/annurev-biodatasci-092524-114822

arxiv published 2026/01/05 · arxiv updated 2026/01/08

Abstract

A protein's function depends critically on its conformational ensemble, a collection of energy weighted structures whose balance depends on temperature and environment. Though recent deep learning (DL) methods have substantially advanced predictions of single protein structures, computationally modeling conformational ensembles remains a challenge. Here, we focus on modeling fold-switching proteins, which remodel their secondary and/or tertiary structures and change their functions in response to cellular stimuli. These underrepresented members of the protein universe serve as test cases for a method's generalizability. They reveal that DL models often predict conformational ensembles by association with training-set structures, limiting generalizability. These observations suggest use cases for when DL methods will likely succeed or fail. Developing computational methods that successfully identify new fold-switching proteins from large pools of candidates may advance modeling conformational ensembles more broadly.

Citations

• Physics-Grounded Evaluation to Guide Accurate Biomolecular Prediction
• AlphaFold reveals but sometimes distorts an organizational principle of protein folding
• Scalable emulation of protein equilibrium ensembles with generative deep learning
• Morpheus: A fragment-based algorithm to predict metamorphic behaviour in proteins across proteomes
• Provably Overwhelming Transformer Models with Designed Inputs
• AlphaFold 2, but not AlphaFold 3, predicts confident but unrealistic β-solenoid structures for repeat proteins
• Accurate structure prediction of biomolecular interactions with AlphaFold 3
• AlphaFold Meets Flow Matching for Generating Protein Ensembles
• Conformational sampling and interpolation using language-based protein folding neural networks
• Predicting multiple conformations via sequence clustering and AlphaFold2
• EigenFold: Generative Protein Structure Prediction with Diffusion Models
• Evolutionary-scale prediction of atomic-level protein structure with a language model
• UniProt: the Universal Protein Knowledgebase in 2023
• Highly accurate protein structure prediction with AlphaFold
• Shared Molecular Mechanisms of Membrane Transporters
• Equilibrium fluctuations of a single folded protein reveal a multitude of potential cryptic allosteric sites

Discussions

• Myeongsang Lee, Lauren L. Porter: Fold-switching proteins push the boundaries of conformational ensemble prediction https://arxiv.org/abs/2601.01740 https://arxiv.org/pdf/2601.01740 https://arxiv.org/ [bsky, 0 points, 0 comments]

Related

• Extending Conformational Ensemble Prediction to Multidomain Proteins and Protein Complex
• Neural spectroscopy of AlphaFold2 reveals encoded protein conformational landscapes
• Protein Dynamics Beyond Structure Prediction
• Fold-switching Proteins
• Inverse problems with experiment-guided AlphaFold