EUVIMEDEUVIMED entdecken
Crossref

Deep Learning Foundation Models for Low-Data Regimes from Classical Molecular Descriptors

Jackson W Burns iD, Akshat Shirish Zalte iD, Charlles R A Abreu, Jochen Sieg, Christian Feldmann iD, Miriam Mathea iD, William H Green iD

Journal of Chemical Information and Modeling · 14.09.2026 · 66 (17) · 10692-10701

DOI: 10.1021/acs.jcim.6c01546 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Chemical Information and Modeling, online erschienen am 07.08.2026. Verfasst von Jackson W Burns und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Chemical Engineering, Massachusetts Institute of Technology, 77 Massachusetts Avenue, Cambridge, Massachusetts02139, United States. Hauptthemen laut MEDLINE: Deep Learning, Drug Discovery. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 58 Literaturangaben. Gefördert von: Advanced Scientific Computing Research, MathWorks, Machine Learning for Pharmaceutical Discovery and Synthesis Consortium.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Fast and accurate data-driven prediction of molecular properties is pivotal to scientific advancements across myriad chemical domains. Deep learning methods have recently garnered much attention, despite their inability to outperform classical machine learning methods when tested on practical, real-world benchmarks with limited training data. This study seeks to bridge this gap by introducing a new avenue for foundation model pretraining. We propose pretraining on low-noise, calculable molecular descriptors via supervised learning to obtain rich, highly transferable molecular representations. We demonstrate this strategy with CheMeleon, a O(10M) parameter foundation model that enables directed message-passing neural networks to finally exceed the performance of classical methods in the low-data regime. We evaluate on 58 benchmark data sets spanning a range of properties relevant to small-molecule drug discovery, sourced from the industry-led Polaris benchmarking initiative. Rigorous statistical comparisons show that CheMeleon outperforms classical baselines like Random Forest on molecular fingerprints and descriptors, as well as existing foundation models. We open-source the CheMeleon model and the pretraining framework to encourage adoption and extension of this pretraining strategy across chemical sciences.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningDrug DiscoveryNeural Networks, ComputerCheminformatics

Autor:innen und Institutionen

  • Department of Chemical Engineering, Massachusetts Institute of Technology, 77 Massachusetts Avenue, Cambridge, Massachusetts02139, United States.
  • BASF SE , Ludwigshafen67056, Germany.

ORCID-Profile: Jackson W Burns, Akshat Shirish Zalte, Christian Feldmann, Miriam Mathea, William H Green

Förderung

  • Advanced Scientific Computing Research
  • MathWorks
  • Machine Learning for Pharmaceutical Discovery and Synthesis Consortium

Zitieren

APA

Burns, J. W., Zalte, A. S., Abreu, C. R. A., Sieg, J., Feldmann, C., Mathea, M., & Green, W. H. (2026). Deep Learning Foundation Models for Low-Data Regimes from Classical Molecular Descriptors. Journal of Chemical Information and Modeling, 66(17), 10692-10701. https://doi.org/10.1021/acs.jcim.6c01546

Vancouver

Burns JW, Zalte AS, Abreu CRA, Sieg J, Feldmann C, Mathea M, et al. Deep Learning Foundation Models for Low-Data Regimes from Classical Molecular Descriptors. Journal of Chemical Information and Modeling. 2026;66(17):10692-10701. doi:10.1021/acs.jcim.6c01546

BibTeX
@article{Burns2026,
  author = {Burns, Jackson W and Zalte, Akshat Shirish and Abreu, Charlles R A and Sieg, Jochen and Feldmann, Christian and Mathea, Miriam and Green, William H},
  title = {Deep Learning Foundation Models for Low-Data Regimes from Classical Molecular Descriptors},
  journal = {Journal of Chemical Information and Modeling},
  year = {2026},
  volume = {66},
  number = {17},
  pages = {10692--10701},
  doi = {10.1021/acs.jcim.6c01546}
}
Kostenlos starten →