In Silico Human and Rat V ss Quantitative Structure−Activity Relationship Models

• Published in: Journal of medicinal chemistry Vol. 49; no. 6; pp. 1953 - 1963
• Main Authors: Gleeson, M. Paul, Waters, Nigel J, Paine, Stuart W, Davis, Andrew M
• Format: Journal Article
• Language: English
• Published: American Chemical Society 23.03.2006
• ISSN: 0022-2623; 1520-4804
• DOI: 10.1021/jm0510070

We present herein a QSAR tool enabling an entirely in silico prediction of human and rat steady-state volume of distribution (V ss), to be made prior to chemical synthesis, preceding detailed allometric or mechanistic assessment of V ss. Three different statistical methodologies, Bayesian neural networks (BNN), classification and regression trees (CART), and partial least squares (PLS) were employed to model human (N = 199) and rat (N = 2086) data sets. The results in prediction of an independent test set show the human model has an r 2 of 0.60 and an rms error in prediction of 0.48. The corresponding rat model has an r 2 of 0.53 and an rms error in prediction of 0.37, indicating both models could be very useful in the early stages of the drug discovery process. This is the first reported entirely in silico approach to the prediction of rat and human steady-state volume of distribution.