EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Efficient Adaptation of Chemical Language Models for Molecular Property Prediction

Kavya Agrawal, Harsha Harod, Ines Simeone, Michele Ceccarelli, Halima Bensmail, Sukrit Gupta, Raghvendra Mall

Translational Insights · 2026

DOI: 10.53941/ti.2026.100013 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Translational Insights, 2026. Verfasst von Kavya Agrawal und 6 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Chemical language models (CLMs) like ChemBERTa and Molformer enable compound property prediction, but their computational demands limit adoption in resource-constrained settings. We integrate Low-Rank Adapters (LoRA) with CLMs to significantly reduce trainable parameters required for finetuning. Results: We observe 3–5% area under the receiver operating curve (AUC) improvement across classification tasks for molecule toxicity, blood-brain barrier permeability, and flavor prediction over Molformer-XL. Our approach achieves Matthews correlation coefficient (MCC) scores of 0.80–0.90 across three tasks while reducing model parameters by 75–95%. By comparing embeddings from zero-shot and finetuned CLMs combined with molecular physicochemical properties, we attain optimal performance across four datasets. This lightweight adaptation retains performance efficiency while reducing over-parameterization.

Zitieren

APA

Agrawal, K., Harod, H., Simeone, I., Ceccarelli, M., Bensmail, H., Gupta, S., & Mall, R. (2026). Efficient Adaptation of Chemical Language Models for Molecular Property Prediction. Translational Insights. https://doi.org/10.53941/ti.2026.100013

Vancouver

Agrawal K, Harod H, Simeone I, Ceccarelli M, Bensmail H, Gupta S, et al. Efficient Adaptation of Chemical Language Models for Molecular Property Prediction. Translational Insights. 2026. doi:10.53941/ti.2026.100013

BibTeX
@article{Agrawal2026,
  author = {Agrawal, Kavya and Harod, Harsha and Simeone, Ines and Ceccarelli, Michele and Bensmail, Halima and Gupta, Sukrit and Mall, Raghvendra},
  title = {Efficient Adaptation of Chemical Language Models for Molecular Property Prediction},
  journal = {Translational Insights},
  year = {2026},
  doi = {10.53941/ti.2026.100013}
}
Kostenlos starten →