The validation of predictive potential via the system of self-consistent models: the simulation of blood-brain barrier permeation of organic compounds

Abstract

In order to apply quantitative relationships "structure-endpoint" approach its reliability of prediction is necessary but sometimes challenging to achieve. Here, an attempt is made to accomplish the reliability of forecasts by creating a set of random partitions of data into training and validation sets, followed by constructing random models. A system of random models for a useful approach should be self-consistent, giving a similar or at least comparable statistical quality of the predictions for models obtained using different splits of available data into training and validation sets. Developed computer experiments aimed at obtaining blood-brain barrier permeation models showed that, in principle, such an approach can be used for the above purpose taking advantage of specific algorithms to optimize the modelling steps. Results so obtained are good, and better than what reported previously. The suggested approach to validation of models is non-identic to traditionally applied manners of the checking up models. The concept of validation can be used for arbitrary models (not only for models of the blood-brain barrier).