EUVIMEDObjevte EUVIMED
Open access

Predicting absolute protein folding stability using generative models

Matteo Cagiada, Sergey Ovchinnikov, Kresten Lindorff-Larsen iD

Protein Science · 2025-01 · 34 (1)

DOI: 10.1002/pro.5233 ↗

At a glance

Journal article in Protein Science, published online on 2024-12-14. Written by Matteo Cagiada and 2 co-authors. Institution: Linderstrøm-Lang Centre for Protein Science, Department of Biology, University of Copenhagen, Copenhagen, Denmark. Major MEDLINE topics: Protein Folding, Protein Stability, Proteins. Cited 34 times so far (Crossref); 46 references. The full text is freely available in PubMed Central. Funded by: Novo Nordisk Foundation, Carlsberg Foundation, Novo Nordisk Fonden.

AbstraktSubjectsBibliografické údajeCiteRelated studies

Abstract (original language)

While there has been substantial progress in our ability to predict changes in protein stability due to amino acid substitutions, progress has been slower in methods to predict the absolute stability of a protein. Here, we show how a generative model for protein sequence can be leveraged to predict absolute protein stability. We benchmark our predictions across a broad set of proteins and find a mean error of 1.5 kcal/mol and a correlation coefficient of 0.7 for the absolute stability across a range of natural, small‐ to medium‐sized proteins up to ca. 150 amino acid residues. We analyze current limitations and future directions including how such a model may be useful for predicting conformational free energies. Our approach is simple to use and freely available at an online implementation available via https://github.com/KULL-Centre/_2024_cagiada_stability .

Subjects

MeSH terms (MEDLINE)

Protein FoldingProtein StabilityProteinsModels, MolecularThermodynamicsProtein Conformation

Author keywords

machine learningprotein foldingprotein stabilitythermodynamics

Substances

Proteins

Authors and institutions

  • Linderstrøm-Lang Centre for Protein Science, Department of Biology, University of Copenhagen, Copenhagen, Denmark.
  • Department of Biology, Massachusetts Institute of Technology, Cambridge, Massachusetts, USA.

ORCID profiles: Kresten Lindorff-Larsen

Funding

  • Novo Nordisk Foundation
  • Carlsberg Foundation
  • Novo Nordisk Fonden
  • Carlsbergfondet

Cite

APA

Cagiada, M., Ovchinnikov, S., & Lindorff-Larsen, K. (2025). Predicting absolute protein folding stability using generative models. Protein Science, 34(1). https://doi.org/10.1002/pro.5233

Vancouver

Cagiada M, Ovchinnikov S, Lindorff-Larsen K. Predicting absolute protein folding stability using generative models. Protein Science. 2025;34(1). doi:10.1002/pro.5233

BibTeX
@article{Cagiada2025,
  author = {Cagiada, Matteo and Ovchinnikov, Sergey and Lindorff-Larsen, Kresten},
  title = {Predicting absolute protein folding stability using generative models},
  journal = {Protein Science},
  year = {2025},
  volume = {34},
  number = {1},
  doi = {10.1002/pro.5233}
}
Start for free →