Achieving well-informed decision-making in drug discovery: a comprehensive calibration study using neural network-based structure-activity models
Journal article, 2025
Hamiltonian monte carlo sampling
Uncertainty estimation
Drug discovery
Probability calibration
Deep learning
Bayesian neural network
QSAR
Author
Hannah Rosa Friesacher
KU Leuven
AstraZeneca AB
Ola Engkvist
Chalmers, Computer Science and Engineering (Chalmers), Data Science and AI
AstraZeneca AB
Lewis H. Mervin
AstraZeneca AB
Yves Moreau
KU Leuven
Ádám Arany
KU Leuven
Journal of Cheminformatics
1758-2946 (ISSN) 17582946 (eISSN)
Vol. 17 1 29Subject Categories (SSIF 2025)
Probability Theory and Statistics
Computer graphics and computer vision
Control Engineering
DOI
10.1186/s13321-025-00964-y