MOLECULE: Molecular-dynamics and Optimized deep Learning for Entropy-regularized Classification and Uncertainty-aware Ligand Evaluation
Journal of Chemical Theory and Computation · 2025
DOI: 10.1021/acs.jctc.5c01140 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Chemical Theory and Computation, 2025. Verfasst von Ivan Cucchi und 6 weiteren Autor:innen. Beteiligte Einrichtung: Dipartimento di Matematica "F. Casorati", Università di Pavia, Via Ferrata 5, Pavia 27100, Italy. Hauptthemen laut MEDLINE: Deep Learning, Molecular Dynamics Simulation, Protein Kinase Inhibitors. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 56 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Associazione Italiana per la Ricerca sul Cancro, Eni, Congressionally Directed Medical Research Programs.
Abstract (Originalsprache)
Machine learning (ML) and deep learning (DL) methodologies have significantly advanced drug discovery and design in several aspects. Additionally, the integration of structure-based data has proven to successfully support and improve the models' predictions. Indeed, we previously demonstrated that combining molecular dynamics (MD)-derived descriptors with ML models allows to effectively classify kinase ligands as allosteric or orthosteric. Extending this approach, we curated a wide and diverse kinase data set (comprising 280 experimentally resolved structures) to train and evaluate a new dual-modal deep neural network classifier, which is tailored to process separately and efficiently the dynamical and structural data to predict the mode of action of a compound. The developed model demonstrated robust classification performance, effective uncertainty handling, and underscored the critical importance of incorporating protein dynamics data. Remarkably, our method maintained high performance even with imputed dynamics data, enabling rapid compound screening and prioritization, without the need for extensive MD simulations.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Substanzen
Autor:innen und Institutionen
- Dipartimento di Matematica "F. Casorati", Università di Pavia, Via Ferrata 5, Pavia 27100, Italy.
- Dipartimento di Chimica, Università di Pavia, Via Taramelli 12, Pavia 27100, Italy.
- Department of Physical Chemistry, R&D Eni SpA, via Maritano 27, San Donato Milanese (Mi) 20097, Italy.
- Upstream & Technical Services - TECS/STES - Eni Spa, via Emilia 1, San Donato Milanese (Mi) 20097, Italy.
ORCID-Profile: Ivan Cucchi, Elena Frasnetti, Giorgio Colombo
Förderung
- Associazione Italiana per la Ricerca sul Cancro
- Eni
- Congressionally Directed Medical Research Programs
- Ministero dell'Universit? e della Ricerca
Zitieren
APA
Cucchi, I., Frasnetti, E., Frigerio, F., Cinquini, F., Pavoni, S., Pavarino, L. F., & Colombo, G. (2025). MOLECULE: Molecular-dynamics and Optimized deep Learning for Entropy-regularized Classification and Uncertainty-aware Ligand Evaluation. Journal of Chemical Theory and Computation. https://doi.org/10.1021/acs.jctc.5c01140
Vancouver
Cucchi I, Frasnetti E, Frigerio F, Cinquini F, Pavoni S, Pavarino LF, et al. MOLECULE: Molecular-dynamics and Optimized deep Learning for Entropy-regularized Classification and Uncertainty-aware Ligand Evaluation. Journal of Chemical Theory and Computation. 2025. doi:10.1021/acs.jctc.5c01140
BibTeX
@article{Cucchi2025,
author = {Cucchi, Ivan and Frasnetti, Elena and Frigerio, Francesco and Cinquini, Fabrizio and Pavoni, Silvia and Pavarino, Luca F and Colombo, Giorgio},
title = {MOLECULE: Molecular-dynamics and Optimized deep Learning for Entropy-regularized Classification and Uncertainty-aware Ligand Evaluation},
journal = {Journal of Chemical Theory and Computation},
year = {2025},
doi = {10.1021/acs.jctc.5c01140}
}
EUVIMED