Supervised Learning of Protein Melting Temperature: Cross‐Species vs. Species‐Specific Prediction
Proteins: Structure, Function, and Bioinformatics · 2025
DOI: 10.1002/prot.70019 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proteins: Structure, Function, and Bioinformatics, 2025. Verfasst von Sebastián García López und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science-DIKU, University of Copenhagen, Copenhagen, Denmark. Hauptthemen laut MEDLINE: Proteins, Supervised Machine Learning. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 33 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Danmarks Grundforskningsfond, H2020 Marie Skłodowska-Curie Actions, Novo Nordisk Fonden.
Abstract (Originalsprache)
Protein melting temperatures are important proxies for stability, and frequently probed in protein engineering campaigns, for instance for enzyme discovery and protein optimization. With the emergence of large datasets of melting temperatures for diverse natural proteins, it has become possible to train models to predict this quantity, and the literature has reported impressive performance values in terms of Spearman rho. The high correlation scores suggest that it should be possible to accurately predict melting temperature changes in engineered variants, and to reliably identify naturally thermostable proteins. However, in practice, results in these settings are often disappointing. In this paper, we explore this apparent discrepancy. We show that Spearman rho over cross‐species data gives an overly optimistic impression of prediction performance, and that this metric reflects the ability to distinguish global differences in amino acid composition between species, rather than the specific effects of genetic variation. We proceed by investigating whether cross‐species training on melting temperature is beneficial at all, compared to training specific models for each species. We address this question using four different transfer‐learning approaches and a fine‐tuning procedure. Surprisingly, we consistently find no benefit of cross‐species training. We conclude that (1) current models for supervised prediction of melting temperature perform substantially worse than the literature suggests, and (2) that reliable transfer across species is still a challenging problem. An implementation of this work is available at https://github.com/deltadedirac/thermocontrast_tm .
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Department of Computer Science-DIKU, University of Copenhagen, Copenhagen, Denmark.
- Enzyme Research Division, Novonesis, Kongens Lyngby, Denmark.
ORCID-Profile: Wouter Boomsma
Förderung
- Danmarks Grundforskningsfond
- H2020 Marie Skłodowska-Curie Actions
- Novo Nordisk Fonden
Zitieren
APA
López, S. G., Salomon, J., & Boomsma, W. (2025). Supervised Learning of Protein Melting Temperature: Cross‐Species vs. Species‐Specific Prediction. Proteins: Structure, Function, and Bioinformatics. https://doi.org/10.1002/prot.70019
Vancouver
López SG, Salomon J, Boomsma W. Supervised Learning of Protein Melting Temperature: Cross‐Species vs. Species‐Specific Prediction. Proteins: Structure, Function, and Bioinformatics. 2025. doi:10.1002/prot.70019
BibTeX
@article{Lpez2025,
author = {López, Sebastián García and Salomon, Jesper and Boomsma, Wouter},
title = {Supervised Learning of Protein Melting Temperature: Cross‐Species vs. Species‐Specific Prediction},
journal = {Proteins: Structure, Function, and Bioinformatics},
year = {2025},
doi = {10.1002/prot.70019}
}
EUVIMED