EUVIMEDEUVIMED entdecken
Crossref

Multitask Deep Learning Models of Combined Industrial Absorption, Distribution, Metabolism, and Excretion Datasets to Improve Generalization

Joseph A Napoli iD, Michael Reutlinger, Patricia Brandl, Wenyi Wang, Jérôme Hert, Prashant Desai iD

Molecular Pharmaceutics · 07.04.2025 · 22 (4) · 1892-1900

DOI: 10.1021/acs.molpharmaceut.4c01086 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Molecular Pharmaceutics, online erschienen am 07.03.2025. Verfasst von Joseph A Napoli und 5 weiteren Autor:innen. Beteiligte Einrichtung: Drug Metabolism & Pharmacokinetics (DMPK), Genentech, Inc., 1 DNA Way, South San Francisco, California 94080, United States. Hauptthemen laut MEDLINE: Deep Learning, Drug Discovery. Die Arbeit wurde bisher 15-mal zitiert (Crossref) und nennt 57 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The optimization of absorption, distribution, metabolism, and excretion (ADME) profiles of compounds is critical to the drug discovery process. As such, machine learning (ML) models for ADME are widely used for prioritizing the design and synthesis of compounds. The effectiveness of ML models for ADME depends on the availability of high-quality experimental data for a diverse set of compounds that is relevant to the emerging chemical space being explored by the drug discovery teams. To that end, ADME data sets from Genentech and Roche were combined to evaluate the impact of expanding the chemical space on the performance of ML models, a first experiment of its kind for large-scale, historical ADME data sets. The combined ADME data set consisted of over 1 million individual measurements distributed across 11 assay end points. We utilized a multitask (MT) neural network architecture that enables the modeling of multiple end points simultaneously and thereby exploits information transfer between interconnected ADME end points. Both single- and cross-site MT models were trained and compared against single-site, single-task baseline models. Given the differences in assay protocols across the two sites, the data for corresponding end points across sites were modeled as separate tasks. Models were evaluated against test sets representing varying degrees of extrapolation difficulty, including cluster-based, temporal, and external test sets. We found that cross-site MT models appeared to provide a greater generalization capacity compared to single-site models. The performance improvement of the cross-site MT models was more pronounced for the relatively "distant" external and temporal test sets, suggesting an expanded applicability domain. The data exchange exercise described here demonstrates the value of expanding the learning from ADME data from multiple sources without the need to aggregate such data when the experimental methods are disparate.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningDrug DiscoveryHumansNeural Networks, ComputerPharmaceutical Preparations

Stichwörter der Autor:innen

ADME modelsdata sharing for machine learningmachine learningmodel generalizationmultitask neural network modelstemporal test sets

Substanzen

Pharmaceutical Preparations

Autor:innen und Institutionen

  • Drug Metabolism & Pharmacokinetics (DMPK), Genentech, Inc., 1 DNA Way, South San Francisco, California 94080, United States.
  • F. Hoffmann-La Roche Ltd., Pharma Research & Early Development (pRED), Roche Innovation Center Basel, Grenzacherstrasse 124, 4070 Basel, Switzerland.

ORCID-Profile: Joseph A Napoli, Prashant Desai

Zitieren

APA

Napoli, J. A., Reutlinger, M., Brandl, P., Wang, W., Hert, J., & Desai, P. (2025). Multitask Deep Learning Models of Combined Industrial Absorption, Distribution, Metabolism, and Excretion Datasets to Improve Generalization. Molecular Pharmaceutics, 22(4), 1892-1900. https://doi.org/10.1021/acs.molpharmaceut.4c01086

Vancouver

Napoli JA, Reutlinger M, Brandl P, Wang W, Hert J, Desai P. Multitask Deep Learning Models of Combined Industrial Absorption, Distribution, Metabolism, and Excretion Datasets to Improve Generalization. Molecular Pharmaceutics. 2025;22(4):1892-1900. doi:10.1021/acs.molpharmaceut.4c01086

BibTeX
@article{Napoli2025,
  author = {Napoli, Joseph A and Reutlinger, Michael and Brandl, Patricia and Wang, Wenyi and Hert, Jérôme and Desai, Prashant},
  title = {Multitask Deep Learning Models of Combined Industrial Absorption, Distribution, Metabolism, and Excretion Datasets to Improve Generalization},
  journal = {Molecular Pharmaceutics},
  year = {2025},
  volume = {22},
  number = {4},
  pages = {1892--1900},
  doi = {10.1021/acs.molpharmaceut.4c01086}
}
Kostenlos starten →