EUVIMEDEUVIMED entdecken
VergleichsstudieOpen Access · CC BY-NC-ND 4.0

Predicting First-in-Human Pharmacokinetics: Comparative Evaluation of Standard PBPK, High-Throughput PBPK, and Machine Learning

Silvan Käser iD, Davide Bassani iD, Neil John Parrott iD, Kenichi Umehara, Marie-Laure Delporte iD, Pascale David-Pierson iD

Molecular Pharmaceutics · 2026

DOI: 10.1021/acs.molpharmaceut.6c00429 ↗

Kurz gefasst

Vergleichsstudie in der Zeitschrift Molecular Pharmaceutics, 2026. Verfasst von Silvan Käser und 5 weiteren Autor:innen. Beteiligte Einrichtung: Roche Pharma Research and Early Development, F. Hoffmann-La Roche AG, Grenzacherstrasse 124, 4070Basel, Switzerland. Hauptthemen laut MEDLINE: Machine Learning, Pharmacokinetics, Models, Biological. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 44 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: Roche, F. Hoffmann-La Roche.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate prediction of human pharmacokinetics is essential for selecting safe starting doses in first-in-human (FiH) trials. This study compares the predictive accuracy of three methodologies including standard physiologically based pharmacokinetic (PBPK) modeling incorporating animal verification, high-throughput (HT) PBPK based on in vitro inputs, and machine learning (ML). We evaluated their performance on 40 diverse small molecules that entered clinical development at Roche between 2003 and 2024. Standard PBPK predictions were assessed prospectively from original reports, while HT-PBPK and ML predictions were obtained retrospectively. Predicted area under the curve (AUCinf) and maximum plasma concentration (Cmax) for oral administration were compared to observed clinical data. While all three approaches demonstrated a useful level of accuracy with at least 49% of predicted AUCinf and Cmax values within 2-fold, standard PBPK was the most precise method with 65 and 63% of AUCinf and Cmax within that margin, respectively. This higher precision likely results from the integration of expert judgment and animal in vivo data for model refinement, whereas HT-PBPK and ML provide valuable animal-free, high-throughput alternatives. Ensemble models leveraging two or three models were explored, which generally improved accuracy in comparison to single models. This highlights the complementary nature of mechanistic and ML-based models. Currently, standard PBPK is still the preferred method for FiH dose selection for which highest accuracy and mechanistic insight is sought. However, although less accurate, we believe that HT-PBPK and ML are viable animal-free alternatives with value for early human dose prediction, reducing costs and cycle times.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Machine LearningPharmacokineticsModels, BiologicalHumansArea Under CurveAnimalsAdministration, OralPredictive Learning ModelsPrediction Algorithms

Stichwörter der Autor:innen

Drug DiscoveryFirst-in-Human PredictionsHuman PharmacokineticsMachine LearningPhysiologically based Pharmacokinetic Modeling

Autor:innen und Institutionen

  • Roche Pharma Research and Early Development, F. Hoffmann-La Roche AG, Grenzacherstrasse 124, 4070Basel, Switzerland.

ORCID-Profile: Silvan Käser, Davide Bassani, Neil John Parrott, Marie-Laure Delporte, Pascale David-Pierson

Förderung

  • Roche
  • F. Hoffmann-La Roche

Zitieren

APA

Käser, S., Bassani, D., Parrott, N. J., Umehara, K., Delporte, M. L., & David-Pierson, P. (2026). Predicting First-in-Human Pharmacokinetics: Comparative Evaluation of Standard PBPK, High-Throughput PBPK, and Machine Learning. Molecular Pharmaceutics. https://doi.org/10.1021/acs.molpharmaceut.6c00429

Vancouver

Käser S, Bassani D, Parrott NJ, Umehara K, Delporte ML, David-Pierson P. Predicting First-in-Human Pharmacokinetics: Comparative Evaluation of Standard PBPK, High-Throughput PBPK, and Machine Learning. Molecular Pharmaceutics. 2026. doi:10.1021/acs.molpharmaceut.6c00429

BibTeX
@article{Kser2026,
  author = {Käser, Silvan and Bassani, Davide and Parrott, Neil John and Umehara, Kenichi and Delporte, Marie-Laure and David-Pierson, Pascale},
  title = {Predicting First-in-Human Pharmacokinetics: Comparative Evaluation of Standard PBPK, High-Throughput PBPK, and Machine Learning},
  journal = {Molecular Pharmaceutics},
  year = {2026},
  doi = {10.1021/acs.molpharmaceut.6c00429}
}
Kostenlos starten →