EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

LogPpred: An AI-Based Predictive Model for Accurate Estimation of Molecular LogP

Lisa Piazza iD, Lara Sortino iD, Alessio Costa iD, Clarissa Poles, Federico Fornaseri iD, Stefano Sainas iD, Marta Giorgis iD, Giulio Poli, Marco Macchia, Marco L Lolli, Tiziano Tuccinardi iD, Miriana Di Stefano iD

Molecules · 23.07.2026 · 31 (15) · 2566

DOI: 10.3390/molecules31152566 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Molecules, online erschienen am 23.07.2026. Verfasst von Lisa Piazza und 11 weiteren Autor:innen. Beteiligte Einrichtung: Department of Pharmacy, University of Pisa, 56126 Pisa, Italy. Hauptthemen laut MEDLINE: 1-Octanol, Water, Artificial Intelligence. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 39 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: University of Pisa.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Lipophilicity, commonly described by the n-octanol/water partition coefficient (LogP), is a key physicochemical property influencing the pharmacokinetic behavior of small molecules. Reliable LogP estimation during the early stages of drug discovery is essential to support molecular design and prioritize compounds with favorable ADMET properties. In this work, we report the development of LogPpred, an AI-based predictor of molecular lipophilicity. Starting from a curated dataset of 13,536 molecules with experimentally determined LogP values, multiple machine learning algorithms and molecular representations were systematically evaluated. The best-performing model, based on Gaussian Process Regression and RDKit molecular descriptors, achieved a mean absolute error (MAE) of 0.34 on the independent internal test set. External validation on a fully independent OECD-derived dataset yielded an MAE of 0.84, demonstrating good generalization capability across diverse chemical space. Furthermore, experimental LogP determination of an additional set of independently selected compounds confirmed the predictive reliability of the model, yielding an MAE of 0.66. Comparative analyses showed that LogPpred outperformed several widely used LogP prediction tools. Applicability domain analysis further supported the reliability of the model, with MAE values improving to 0.28 and 0.62 for in-domain compounds in the internal and external validation sets, respectively. Overall, LogPpred represents a robust, accurate, and transparent tool for the early assessment of molecular lipophilicity in medicinal chemistry and drug discovery.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

1-OctanolWaterArtificial IntelligencePrediction AlgorithmsPredictive Learning ModelsMachine LearningAlgorithmsDrug DiscoveryHydrophobic and Hydrophilic InteractionsReproducibility of Results

Stichwörter der Autor:innen

ADMETLogP predictionapplicability domaindrug discoverylipophilicitymachine learningmedicinal chemistry

Substanzen

1-OctanolWater

Autor:innen und Institutionen

  • Department of Pharmacy, University of Pisa, 56126 Pisa, Italy.
  • Department of Life Sciences, University of Siena, 53100 Siena, Italy.
  • Genomics and Experimental Medicine Program, Scuola Superiore Meridionale (SSM, School of Advanced Studies), Via Mezzocannone 4, 80078 Napoli, Italy.
  • Department of Drug Science and Technology, University of Turin, via Pietro Giuria 9, 10125 Turin, Italy.
  • Consorzio Interuniversitario Nazionale per la Scienza e Tecnologia dei Materiali (INSTM), 50121 Firenze, Italy.

ORCID-Profile: Lisa Piazza, Lara Sortino, Alessio Costa, Federico Fornaseri, Stefano Sainas, Marta Giorgis, Tiziano Tuccinardi, Miriana Di Stefano

Förderung

  • University of Pisa

Zitieren

APA

Piazza, L., Sortino, L., Costa, A., Poles, C., Fornaseri, F., Sainas, S., Giorgis, M., Poli, G., Macchia, M., Lolli, M. L., Tuccinardi, T., & Di Stefano, M. (2026). LogPpred: An AI-Based Predictive Model for Accurate Estimation of Molecular LogP. Molecules, 31(15), 2566. https://doi.org/10.3390/molecules31152566

Vancouver

Piazza L, Sortino L, Costa A, Poles C, Fornaseri F, Sainas S, et al. LogPpred: An AI-Based Predictive Model for Accurate Estimation of Molecular LogP. Molecules. 2026;31(15):2566. doi:10.3390/molecules31152566

BibTeX
@article{Piazza2026,
  author = {Piazza, Lisa and Sortino, Lara and Costa, Alessio and Poles, Clarissa and Fornaseri, Federico and Sainas, Stefano and Giorgis, Marta and Poli, Giulio and Macchia, Marco and Lolli, Marco L and Tuccinardi, Tiziano and Di Stefano, Miriana},
  title = {LogPpred: An AI-Based Predictive Model for Accurate Estimation of Molecular LogP},
  journal = {Molecules},
  year = {2026},
  volume = {31},
  number = {15},
  pages = {2566},
  doi = {10.3390/molecules31152566}
}
Kostenlos starten →