Prediction of the brain-blood distribution of a large set of drugs from structurally derived descriptors using partial least-squares (PLS) modeling

In this study, the multivariate partial least-squares projections to latent structures (PLS) technique was used for modeling the brain-blood concentra tion ratio (BB) of 61 structurally diverse compounds. The PLS model was bas ed on molecular descriptors that can be calculated for any compound simply from a knowledge of its molecular structure, and the model included several topological and constitutional descriptors. The PLS analysis resulted in a significant three-component model with the following statistics: r = 0.922 , Q = 0.867, s = 0.318, n = 58, and F = 102. The predictive ability of the model was assessed by means of crossvalidation and also by using BE partiti oning data, BBB permeability data, and 1 set of qualitative brain penetrati on data, resulting in BE distribution data for 97 compounds. The results in dicate that the PLS model developed is statistically sound and is sufficien tly robust for predictive use. Taking into account the great ease of comput ation and interpretation of the derived model, it may be of general utility in predicting BE ratios for a very wide range of new drags.