EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Multi-Task Learning of Blood–Brain Barrier Permeability and hERG Cardiotoxicity: A Random- and Scaffold-Split Evaluation on Experimental Data

Surya Veerendra Prabhakar Vattikuti, Saurabh Tiwari, Priya Sharma

Pharmaceutics · 09.11.2026 · 18 (11) · 1449

DOI: 10.3390/pharmaceutics18111449 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Pharmaceutics, online erschienen am 09.11.2026. Verfasst von Surya Veerendra Prabhakar Vattikuti und 2 weiteren Autor:innen. Die Arbeit nennt 22 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background/Objectives: Blood–brain barrier (BBB) permeability and cardiac hERG liability share physicochemical determinants, motivating the hypothesis that multi-task learning could improve BBB prediction.

Methods

We tested this hypothesis using B3DB logBB regression (n = 1058) and a curated hERG dataset (n = 8960). A shared-encoder multi-task neural network was compared with a matched single-task network and Bayesian-optimized gradient boosting under ten random splits, 30 Murcko scaffold splits, and held-out classification sets.

Results

Multi-task learning did not improve random-split R2 (0.485 ± 0.016 vs. 0.482 ± 0.015). Under scaffold splitting, its mean R2 was higher (−0.054 vs. −0.817) only because its failures were less severe (the same number of partitions had negative R2); medians were nearly identical (0.394 vs. 0.398). Neither loss weighting, network tuning, nor removal of 39.6% of test compounds sharing a parent structure with hERG training data changed this. Gradient boosting was more robust (scaffold R2 = 0.388 ± 0.188; better in 28–29 of 30 partitions), although not significantly so under a dependence-corrected test.

Conclusions

Network failures occurred only when a scaffold group containing 18 atypical compounds (e.g., xenon) entered the test set; after removing 20 such compounds, multi-task R2 (0.409) matched gradient boosting (0.420). On 3031 held-out parent structures, AUCs were similar (0.764–0.772).

Zitieren

APA

Vattikuti, S. V. P., Tiwari, S., & Sharma, P. (2026). Multi-Task Learning of Blood–Brain Barrier Permeability and hERG Cardiotoxicity: A Random- and Scaffold-Split Evaluation on Experimental Data. Pharmaceutics, 18(11), 1449. https://doi.org/10.3390/pharmaceutics18111449

Vancouver

Vattikuti SVP, Tiwari S, Sharma P. Multi-Task Learning of Blood–Brain Barrier Permeability and hERG Cardiotoxicity: A Random- and Scaffold-Split Evaluation on Experimental Data. Pharmaceutics. 2026;18(11):1449. doi:10.3390/pharmaceutics18111449

BibTeX
@article{Vattikuti2026,
  author = {Vattikuti, Surya Veerendra Prabhakar and Tiwari, Saurabh and Sharma, Priya},
  title = {Multi-Task Learning of Blood–Brain Barrier Permeability and hERG Cardiotoxicity: A Random- and Scaffold-Split Evaluation on Experimental Data},
  journal = {Pharmaceutics},
  year = {2026},
  volume = {18},
  number = {11},
  pages = {1449},
  doi = {10.3390/pharmaceutics18111449}
}
Kostenlos starten →