TY - JOUR
T1 - Human intestinal transporter database
T2 - QSAR modeling and virtual profiling of drug uptake, efflux and interactions
AU - Sedykh, Alexander
AU - Fourches, Denis
AU - Duan, Jianmin
AU - Hucke, Oliver
AU - Garneau, Michel
AU - Zhu, Hao
AU - Bonneau, Pierre
AU - Tropsha, Alexander
N1 - Funding Information:
We thank Dr. Tingjun Hou (University of California at San Diego, USA) and Dr. Kazuya Maeda (The University of Tokyo, Japan) for sharing their data, Dr. Dhiren Thakker, Dr. Kim Brouwer and Kathleen Köck (all - University of North Carolina at Chapel Hill, USA), Dr. Alexander Böcker and Dr. Sanjay Srivastava (Boehringer Ingelheim (Canada) Ltd) for helpful discussions, Dr. Nancy Baker for her assistance with ChemoText, and Dr. Fabio Broccatelli (University of Perugio, Italy) for the comments on MDR1 inhibition. This work was supported, in part, by grants from NIH (GM66940 and R21GM076059), The Johns Hopkins Center for Alternatives to Animal Testing (20011–21) and Boehringer Ingelheim (Canada) Ltd.
PY - 2013/4
Y1 - 2013/4
N2 - Purpose: Membrane transporters mediate many biological effects of chemicals and play a major role in pharmacokinetics and drug resistance. The selection of viable drug candidates among biologically active compounds requires the assessment of their transporter interaction profiles. Methods: Using public sources, we have assembled and curated the largest, to our knowledge, human intestinal transporter database (>5,000 interaction entries for >3,700 molecules). This data was used to develop thoroughly validated classification Quantitative Structure-Activity Relationship (QSAR) models of transport and/or inhibition of several major transporters including MDR1, BCRP, MRP1-4, PEPT1, ASBT, OATP2B1, OCT1, and MCT1. Results: QSAR models have been developed with advanced machine learning techniques such as Support Vector Machines, Random Forest, and k Nearest Neighbors using Dragon and MOE chemical descriptors. These models afforded high external prediction accuracies of 71-100% estimated by 5-fold external validation, and showed hit retrieval rates with up to 20-fold enrichment in the virtual screening of DrugBank compounds. Conclusions: The compendium of predictive QSAR models developed in this study can be used for virtual profiling of drug candidates and/or environmental agents with the optimal transporter profiles.
AB - Purpose: Membrane transporters mediate many biological effects of chemicals and play a major role in pharmacokinetics and drug resistance. The selection of viable drug candidates among biologically active compounds requires the assessment of their transporter interaction profiles. Methods: Using public sources, we have assembled and curated the largest, to our knowledge, human intestinal transporter database (>5,000 interaction entries for >3,700 molecules). This data was used to develop thoroughly validated classification Quantitative Structure-Activity Relationship (QSAR) models of transport and/or inhibition of several major transporters including MDR1, BCRP, MRP1-4, PEPT1, ASBT, OATP2B1, OCT1, and MCT1. Results: QSAR models have been developed with advanced machine learning techniques such as Support Vector Machines, Random Forest, and k Nearest Neighbors using Dragon and MOE chemical descriptors. These models afforded high external prediction accuracies of 71-100% estimated by 5-fold external validation, and showed hit retrieval rates with up to 20-fold enrichment in the virtual screening of DrugBank compounds. Conclusions: The compendium of predictive QSAR models developed in this study can be used for virtual profiling of drug candidates and/or environmental agents with the optimal transporter profiles.
UR - http://www.scopus.com/inward/record.url?scp=84876473356&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84876473356&partnerID=8YFLogxK
U2 - 10.1007/s11095-012-0935-x
DO - 10.1007/s11095-012-0935-x
M3 - Article
C2 - 23269503
AN - SCOPUS:84876473356
SN - 0724-8741
VL - 30
SP - 996
EP - 1007
JO - Pharmaceutical Research
JF - Pharmaceutical Research
IS - 4
ER -