Pharmaceutical Research

, Volume 30, Issue 4, pp 996–1007

Human Intestinal Transporter Database: QSAR Modeling and Virtual Profiling of Drug Uptake, Efflux and Interactions

Authors

  • Alexander Sedykh
    • Laboratory for Molecular Modeling Division of Chemical Biology and Medicinal ChemistryEshelman School of Pharmacy, University of North Carolina 100K Beard Hall,
  • Denis Fourches
    • Laboratory for Molecular Modeling Division of Chemical Biology and Medicinal ChemistryEshelman School of Pharmacy, University of North Carolina 100K Beard Hall,
  • Jianmin Duan
    • Department of Biological SciencesBoehringer Ingelheim Ltd., R&D
  • Oliver Hucke
    • Department of ChemistryBoehringer Ingelheim Ltd., R&D
  • Michel Garneau
    • Department of Biological SciencesBoehringer Ingelheim Ltd., R&D
  • Hao Zhu
    • Laboratory for Molecular Modeling Division of Chemical Biology and Medicinal ChemistryEshelman School of Pharmacy, University of North Carolina 100K Beard Hall,
  • Pierre Bonneau
    • Department of ChemistryBoehringer Ingelheim Ltd., R&D
    • Laboratory for Molecular Modeling Division of Chemical Biology and Medicinal ChemistryEshelman School of Pharmacy, University of North Carolina 100K Beard Hall,
Research Paper

DOI: 10.1007/s11095-012-0935-x

Cite this article as:
Sedykh, A., Fourches, D., Duan, J. et al. Pharm Res (2013) 30: 996. doi:10.1007/s11095-012-0935-x

Abstract

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.

KEY WORDS

ADMETdrug transporteffluxmembrane transport proteinspermeability

Abbreviations

ABC

ATP binding cassette family of transporters

ADMET

absorption distribution, metabolism, excretion, toxicity

ASBT

apical sodium-dependent bile acid transporter

AUC

area under curve

BCRP

breast cancer resistance protein

CCR

correct classification rate

kNN

k nearest neighbors

MCT1

monocarboxylate transporter 1

MDR1

multidrug resistance protein 1

MRP1-4

multidrug resistance-associated proteins 1-4

MW

molecular weight

OATP2B1

organic anion transporting polypeptide 2B1

OCT1

organic cation transporter 1

OST-αβ

organic solute transporter alpha/beta

PEPT1

peptide transporter 1

QSAR

quantitative structure-activity relationships

RF

random forest

ROC

receiver operating characteristic

SAR

structure-activity relationship

SLC transporters

solute carrier family of transporters

SVM

support vector machines

Tc

tanimoto (similarity) coefficient

VS

virtual screening

Supplementary material

11095_2012_935_MOESM1_ESM.docx (313 kb)
ESM 1(DOCX 313 kb)
11095_2012_935_MOESM2_ESM.xls (519 kb)
ESM 2(XLS 519 kb)
11095_2012_935_MOESM3_ESM.xls (2.7 mb)
ESM 3(XLS 2792 kb)

Copyright information

© Springer Science+Business Media New York 2012