Using beta binomials to estimate classification uncertainty for ensemble models

Authors: Clark RD, Liang W, Lee AC, Lawless M, Fraczkiewicz R, Waldman M
Publication: J Cheminform
Keywords: ANNE, artificial neural network ensemble, classification, confidence, error estimation, predictive value, quantitative structure–activity relationship (QSAR)
Software: ADMET Predictor®
Division: Simulations Plus

Background

Quantitative structure-activity (QSAR) models have enormous potential for reducing drug discovery and development costs as well as the need for animal testing. Great strides have been made in estimating their overall reliability, but to fully realize that potential, researchers and regulators need to know how confident they can be in individual predictions.

By Robert D Clark, Michael S Lawless, Robert Fraczkiewicz, Marvin Waldman