EUVIMEDEUVIMED entdecken
Crossref

Multitask Learning for Membrane Permeability Prediction across Assays with Prediction Reliability Assessment

Yuki Doi iD, Tsuyoshi Esaki iD

Journal of Chemical Information and Modeling · 2026

DOI: 10.1021/acs.jcim.6c00597 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Chemical Information and Modeling, 2026. Verfasst von Yuki Doi und 1 weiteren Autor:innen. Beteiligte Einrichtung: DMPK Research Laboratories, Tanabe Pharma Corporation, 2-26-1 Muraoka-Higashi, Fujisawa, Kanagawa251-8555, Japan. Hauptthemen laut MEDLINE: Cell Membrane Permeability, Machine Learning. Die Arbeit nennt 42 Literaturangaben. Gefördert von: Japan Society for the Promotion of Science.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Membrane permeability is a critical determinant of drug exposure and distribution; however, experimental permeability data are unevenly available across assay systems, thereby restricting the robustness and predictive utility of the in silico models. In this study, we curated five apparent permeability (Papp) data sets (Caco-2, MDCK, Ralph Russ canine kidney (RRCK), LLC-PK1, and parallel artificial membrane permeability assay (PAMPA)) and developed a multitask graph convolutional neural network (MT-GCN) to predict Papp jointly across assays, benchmarking it against a fingerprint-based random forest (RF), single-task graph convolutional network (GCN) (ST-GCN), and transfer-learning GCN (TL-GCN). In 10-fold cross-validation, MT-GCN achieved the best overall performance for Caco-2 and MDCK (R2 values of 0.503 and 0.500, respectively). It also delivered the clearest gains in data-limited assays, where the ST-GCN did not exceed the RF baseline. MT-GCN achieved R2 = 0.558 for LLC-PK1 and R2 = 0.449 for RRCK, whereas PAMPA remained an exception in which RF performed comparably or better (RF R2 = 0.532). A Caco-2 subsampling study showed that MT-GCN improves data efficiency, outperforming RF and ST-GCN, even with a relatively small number of training samples. Furthermore, we introduced an applicability domain framework to quantify the prediction confidence at the compound level. We trained assay-specific error models using ensemble dispersion, learned-space similarity, and local-consistency metrics and defined a reliability score as the probability that a prediction falls within a 2-fold error. These scores were consistent with the observed errors and enabled practical accuracy coverage control by filtering out predictions with low-reliability scores. The findings of this study indicate that integrating multitask learning with applicability domain assessment facilitates precise and practical permeability prediction across assays, enhancing performance and decision confidence for data-limited end points.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Cell Membrane PermeabilityMachine LearningAnimalsHumansDogsCaco-2 CellsReproducibility of ResultsGraph Neural NetworksMadin Darby Canine Kidney CellsPrediction Algorithms

Autor:innen und Institutionen

  • DMPK Research Laboratories, Tanabe Pharma Corporation, 2-26-1 Muraoka-Higashi, Fujisawa, Kanagawa251-8555, Japan.
  • Faculty of Data Science, Shiga University, 1-1-1 Banba, Hikone, Shiga522-8522, Japan.

ORCID-Profile: Yuki Doi, Tsuyoshi Esaki

Förderung

  • Japan Society for the Promotion of Science

Zitieren

APA

Doi, Y., & Esaki, T. (2026). Multitask Learning for Membrane Permeability Prediction across Assays with Prediction Reliability Assessment. Journal of Chemical Information and Modeling. https://doi.org/10.1021/acs.jcim.6c00597

Vancouver

Doi Y, Esaki T. Multitask Learning for Membrane Permeability Prediction across Assays with Prediction Reliability Assessment. Journal of Chemical Information and Modeling. 2026. doi:10.1021/acs.jcim.6c00597

BibTeX
@article{Doi2026,
  author = {Doi, Yuki and Esaki, Tsuyoshi},
  title = {Multitask Learning for Membrane Permeability Prediction across Assays with Prediction Reliability Assessment},
  journal = {Journal of Chemical Information and Modeling},
  year = {2026},
  doi = {10.1021/acs.jcim.6c00597}
}
Kostenlos starten →