Deep generative modeling of temperature-dependent structural ensembles of proteins.

ABSTRACT: Deep learning has revolutionized protein structure prediction, but capturing conformational ensembles remains a challenge. Molecular dynamics (MD) simulations can describe biomolecular dynamics, but they are computationally expensive. Alternatively, deep learning models trained on MD can generate structural ensembles at reduced cost. We present aSAM (atomistic structural autoencoder model), a latent diffusion model trained on MD to generate heavy atom protein ensembles. aSAM models atoms in a latent space to accurate sample side chain and backbone torsion angle distributions. Additionally, the aSAMt version generates ensembles conditioned on temperature. Trained on mdCATH, aSAMt captures temperature-dependent ensemble properties and demonstrates generalization beyond training temperatures.

SUBMITTER: Janson G 

PROVIDER: S-EPMC12627665 | biostudies-literature | 2025 Nov

REPOSITORIES: biostudies-literature