AdventML: Advanced Enzyme Temperature Prediction with Transformer-Based Embeddings and Resampling Strategies
Journal of Chemical Information and Modeling · 26.10.2026 · 66 (20) · 13218-13236
DOI: 10.1021/acs.jcim.6c02109 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Chemical Information and Modeling, online erschienen am 12.10.2026. Verfasst von Jaldert François und 2 weiteren Autor:innen. Beteiligte Einrichtung: Centre of Microbial and Plant Genetics (CMPG), KU Leuven, 3001Leuven, Belgium. Hauptthemen laut MEDLINE: Temperature, Enzymes, Machine Learning. Die Arbeit nennt 80 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Agentschap Innoveren en Ondernemen, Fonds Wetenschappelijk Onderzoek.
Abstract (Originalsprache)
Accurate prediction of enzyme optimal catalytic temperature (Topt) is important for enzyme applications, particularly for identifying biocatalysts stable in extreme conditions, but experimental measurement remains costly and time-consuming. Here, we present AdventML, a machine learning framework for (Topt) prediction that expands the available models, evaluates protein representations and model architectures, and compares resampling strategies for improving performance at extremes. The base AdventML model achieved the best global held-out performance among the evaluated methods (R2 ≈ 0.64), MAE ≈7–8 °C, while tail-focused variants improved selected extreme-temperature regimes, reducing tail MAE by up to ∼1.8 °C. AdventML also showed that competitive (Topt) prediction is possible in the absence of organism growth temperature. Our Topt prediction models are made freely available as AdventML on GitHub.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Substanzen
Autor:innen und Institutionen
- Centre of Microbial and Plant Genetics (CMPG), KU Leuven, 3001Leuven, Belgium.
- Department of Electrical Engineering (ESAT), KU Leuven, 3001Leuven, Belgium.
- Institute of Biology Leiden (IBL), Leiden University, 2333 BELeiden, The Netherlands.
ORCID-Profile: Jaldert François, Vera van Noort
Förderung
- Agentschap Innoveren en Ondernemen
- Fonds Wetenschappelijk Onderzoek
Zitieren
APA
François, J., Moor, B., & van Noort, V. (2026). AdventML: Advanced Enzyme Temperature Prediction with Transformer-Based Embeddings and Resampling Strategies. Journal of Chemical Information and Modeling, 66(20), 13218-13236. https://doi.org/10.1021/acs.jcim.6c02109
Vancouver
François J, Moor B, van Noort V. AdventML: Advanced Enzyme Temperature Prediction with Transformer-Based Embeddings and Resampling Strategies. Journal of Chemical Information and Modeling. 2026;66(20):13218-13236. doi:10.1021/acs.jcim.6c02109
BibTeX
@article{Franois2026,
author = {François, Jaldert and Moor, Bart De and van Noort, Vera},
title = {AdventML: Advanced Enzyme Temperature Prediction with Transformer-Based Embeddings and Resampling Strategies},
journal = {Journal of Chemical Information and Modeling},
year = {2026},
volume = {66},
number = {20},
pages = {13218--13236},
doi = {10.1021/acs.jcim.6c02109}
}
EUVIMED