EUVIMEDEUVIMED entdecken
Crossref

Actionable Predictions of Human Pharmacokinetics at the Drug Design Stage

Leonid Komissarov iD, Nenad Manevski iD, Katrin Groebke Zbinden, Torsten Schindler, Marinka Zitnik, Lisa Sach-Peltason

Molecular Pharmaceutics · 02.09.2024 · 21 (9) · 4356-4371

DOI: 10.1021/acs.molpharmaceut.4c00311 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Molecular Pharmaceutics, online erschienen am 12.08.2024. Verfasst von Leonid Komissarov und 5 weiteren Autor:innen. Beteiligte Einrichtung: Roche Pharmaceutical Research and Early Development, Roche Innovation Center Basel, Basel 4070, Switzerland. Hauptthemen laut MEDLINE: Machine Learning, Drug Design. Die Arbeit wurde bisher 18-mal zitiert (Crossref) und nennt 65 Literaturangaben. Gefördert von: Roche.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

We present a novel computational approach for predicting human pharmacokinetics (PK) that addresses the challenges of early stage drug design. Our study introduces and describes a large-scale data set of 11 clinical PK end points, encompassing over 2700 unique chemical structures to train machine learning models. To that end multiple advanced training strategies are compared, including the integration of in vitro data and a novel self-supervised pretraining task. In addition to the predictions, our final model provides meaningful epistemic uncertainties for every data point. This allows us to successfully identify regions of exceptional predictive performance, with an absolute average fold error (AAFE/geometric mean fold error) of less than 2.5 across multiple end points. Together, these advancements represent a significant leap toward actionable PK predictions, which can be utilized early on in the drug design process to expedite development and reduce reliance on nonclinical studies.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Machine LearningDrug DesignHumansPharmacokineticsPharmaceutical Preparations

Stichwörter der Autor:innen

PKclinicaldatasetgraph neural networkshumanmachine learningpharmacokineticspredictionstransfer learninguncertainty quantification

Substanzen

Pharmaceutical Preparations

Autor:innen und Institutionen

  • Roche Pharmaceutical Research and Early Development, Roche Innovation Center Basel, Basel 4070, Switzerland.
  • Harvard Medical School, Department of Biomedical Informatics, Boston, Massachusetts 02115, United States.

ORCID-Profile: Leonid Komissarov, Nenad Manevski

Förderung

  • Roche

Zitieren

APA

Komissarov, L., Manevski, N., Groebke Zbinden, K., Schindler, T., Zitnik, M., & Sach-Peltason, L. (2024). Actionable Predictions of Human Pharmacokinetics at the Drug Design Stage. Molecular Pharmaceutics, 21(9), 4356-4371. https://doi.org/10.1021/acs.molpharmaceut.4c00311

Vancouver

Komissarov L, Manevski N, Groebke Zbinden K, Schindler T, Zitnik M, Sach-Peltason L. Actionable Predictions of Human Pharmacokinetics at the Drug Design Stage. Molecular Pharmaceutics. 2024;21(9):4356-4371. doi:10.1021/acs.molpharmaceut.4c00311

BibTeX
@article{Komissarov2024,
  author = {Komissarov, Leonid and Manevski, Nenad and Groebke Zbinden, Katrin and Schindler, Torsten and Zitnik, Marinka and Sach-Peltason, Lisa},
  title = {Actionable Predictions of Human Pharmacokinetics at the Drug Design Stage},
  journal = {Molecular Pharmaceutics},
  year = {2024},
  volume = {21},
  number = {9},
  pages = {4356--4371},
  doi = {10.1021/acs.molpharmaceut.4c00311}
}
Kostenlos starten →