PURPOSE: Development of externally predictive Quantitative Structure-Activity Relationship (QSAR) models for Blood-Brain Barrier (BBB) permeability. METHODS: Combinatorial QSAR analysis was carried out for a set of 159 compounds with known BBB permeability data. All six possible combinations of three collections of descriptors derived from two-dimensional representations of molecules as chemical graphs and two QSAR methodologies have been explored. Descriptors were calculated by MolconnZ, MOE, and Dragon software. QSAR methodologies included k-Nearest Neighbors and Support Vector Machine approaches. All models have been rigorously validated using both internal and external validation methods. RESULTS: The consensus prediction for the external evaluation set afforded high predictive power (R2 = 0.80 for 10 compounds within the applicability domain after excluding one activity outlier). Classification accuracies for two additional external datasets, including 99 drugs and 267 organic compounds, classified as permeable (BBB+) or non-permeable (BBB-) were 82.5% and 59.0%, respectively. The use of a fairly conservative model applicability domain increased the prediction accuracy to 100% and 83%, respectively (while naturally reducing the dataset coverage to 60% and 43%, respectively). Important descriptors that affect BBB permeability are discussed. CONCLUSION: Models developed in these studies can be used to estimate the BBB permeability of drug candidates at early stages of drug development.
PURPOSE: Development of externally predictive Quantitative Structure-Activity Relationship (QSAR) models for Blood-Brain Barrier (BBB) permeability. METHODS: Combinatorial QSAR analysis was carried out for a set of 159 compounds with known BBB permeability data. All six possible combinations of three collections of descriptors derived from two-dimensional representations of molecules as chemical graphs and two QSAR methodologies have been explored. Descriptors were calculated by MolconnZ, MOE, and Dragon software. QSAR methodologies included k-Nearest Neighbors and Support Vector Machine approaches. All models have been rigorously validated using both internal and external validation methods. RESULTS: The consensus prediction for the external evaluation set afforded high predictive power (R2 = 0.80 for 10 compounds within the applicability domain after excluding one activity outlier). Classification accuracies for two additional external datasets, including 99 drugs and 267 organic compounds, classified as permeable (BBB+) or non-permeable (BBB-) were 82.5% and 59.0%, respectively. The use of a fairly conservative model applicability domain increased the prediction accuracy to 100% and 83%, respectively (while naturally reducing the dataset coverage to 60% and 43%, respectively). Important descriptors that affect BBB permeability are discussed. CONCLUSION: Models developed in these studies can be used to estimate the BBB permeability of drug candidates at early stages of drug development.
Authors: Min Shen; Cécile Béguin; Alexander Golbraikh; James P Stables; Harold Kohn; Alexander Tropsha Journal: J Med Chem Date: 2004-04-22 Impact factor: 7.446
Authors: Kelly M Mahar Doan; Joan E Humphreys; Lindsey O Webster; Stephen A Wring; Larry J Shampine; Cosette J Serabjit-Singh; Kimberly K Adkison; Joseph W Polli Journal: J Pharmacol Exp Ther Date: 2002-12 Impact factor: 4.030
Authors: Stephen J Capuzzi; Ian Sang-June Kim; Wai In Lam; Thomas E Thornton; Eugene N Muratov; Diane Pozefsky; Alexander Tropsha Journal: J Chem Inf Model Date: 2017-01-19 Impact factor: 4.956
Authors: Timothy S Carpenter; Daniel A Kirshner; Edmond Y Lau; Sergio E Wong; Jerome P Nilmeier; Felice C Lightstone Journal: Biophys J Date: 2014-08-05 Impact factor: 4.033
Authors: Corbin G Thompson; Alexander Sedykh; Melanie R Nicol; Eugene Muratov; Denis Fourches; Alexander Tropsha; Angela D M Kashuba Journal: AIDS Res Hum Retroviruses Date: 2014-03-13 Impact factor: 2.205
Authors: Liying Zhang; Denis Fourches; Alexander Sedykh; Hao Zhu; Alexander Golbraikh; Sean Ekins; Julie Clark; Michele C Connelly; Martina Sigal; Dena Hodges; Armand Guiguemde; R Kiplin Guy; Alexander Tropsha Journal: J Chem Inf Model Date: 2013-01-23 Impact factor: 4.956