EUVIMEDOpdag EUVIMED
Open access · CC BY 4.0

Mass balance approximation of unfolding boosts potential‐based protein stability predictions

Ivan Rossi iD, Guido Barducci iD, Tiziana Sanavia iD, Paola Turina iD, Emidio Capriotti iD, Piero Fariselli iD

Protein Science · 2025-05 · 34 (5)

DOI: 10.1002/pro.70134 ↗

At a glance

Journal article in Protein Science, published online on 2025-04-25. Written by Ivan Rossi and 5 co-authors. Institution: Department of Medical Sciences, University of Torino, Torino, Italy. Major MEDLINE topics: Protein Unfolding, Proteins. Cited 3 times so far (Crossref); 38 references. The full text is freely available (open access, CC BY 4.0). Funded by: Italian Ministry for Education, University and Research, European Union's Horizon 2020.

AbstractSubjectsBibliografiske oplysningerCiteRelated studies

Abstract (original language)

Predicting protein stability changes upon single‐point mutations is crucial in computational biology, with applications in drug design, enzyme engineering, and understanding disease mechanisms. While deep‐learning approaches have emerged, many remain inaccessible for routine use. In contrast, potential‐like methods, including deep‐learning‐based ones, are faster, user‐friendly, and effective in estimating stability changes. However, most of them approximate Gibbs free‐energy differences without accounting for the free‐energy changes of the unfolded state, violating mass balance and potentially reducing accuracy. Here, we show that incorporating mass balance as a first approximation of the unfolded state significantly improves potential‐like methods. While many machine‐learning models implicitly or explicitly use mass balance, our findings suggest that a more accurate unfolded‐state representation could further enhance stability change predictions.

Subjects

MeSH terms (MEDLINE)

Protein UnfoldingProteinsProtein StabilityThermodynamicsMachine LearningComputational BiologyDeep Learning

Author keywords

Gibbs free energydeep learning modelsmass‐balance correctionpotential‐like methodsprotein stability predictionsingle‐point mutations

Substances

Proteins

Authors and institutions

  • Department of Medical Sciences, University of Torino, Torino, Italy.
  • Department of Pharmacy and Biotechnology (FaBiT), University of Bologna, Bologna, Italy.
  • Computational Genomics Platform, IRCCS University Hospital of Bologna, Bologna, Italy.

ORCID profiles: Ivan Rossi, Guido Barducci, Tiziana Sanavia, Paola Turina, Emidio Capriotti, Piero Fariselli

Funding

  • Italian Ministry for Education, University and Research
  • European Union's Horizon 2020

Cite

APA

Rossi, I., Barducci, G., Sanavia, T., Turina, P., Capriotti, E., & Fariselli, P. (2025). Mass balance approximation of unfolding boosts potential‐based protein stability predictions. Protein Science, 34(5). https://doi.org/10.1002/pro.70134

Vancouver

Rossi I, Barducci G, Sanavia T, Turina P, Capriotti E, Fariselli P. Mass balance approximation of unfolding boosts potential‐based protein stability predictions. Protein Science. 2025;34(5). doi:10.1002/pro.70134

BibTeX
@article{Rossi2025,
  author = {Rossi, Ivan and Barducci, Guido and Sanavia, Tiziana and Turina, Paola and Capriotti, Emidio and Fariselli, Piero},
  title = {Mass balance approximation of unfolding boosts potential‐based protein stability predictions},
  journal = {Protein Science},
  year = {2025},
  volume = {34},
  number = {5},
  doi = {10.1002/pro.70134}
}
Start for free →