Pharmaceutical Research

, Volume 30, Issue 7, pp 1790–1798

The Use of Pseudo-Equilibrium Constant Affords Improved QSAR Models of Human Plasma Protein Binding

Authors

  • Xiang-Wei Zhu
    • Key Laboratory of Yangtze River Water Environment, Ministry of Education, College of Environmental Science & EngineeringTongji University
    • Division of Chemical Biology and Medicinal Chemistry Eshelman School of PharmacyUniversity of North Carolina at Chapel Hill
  • Alexander Sedykh
    • Division of Chemical Biology and Medicinal Chemistry Eshelman School of PharmacyUniversity of North Carolina at Chapel Hill
  • Hao Zhu
    • Division of Chemical Biology and Medicinal Chemistry Eshelman School of PharmacyUniversity of North Carolina at Chapel Hill
    • Department of ChemistryRutgers University
    • The Rutgers Center for Computational and Integrative BiologyRutgers University
    • Key Laboratory of Yangtze River Water Environment, Ministry of Education, College of Environmental Science & EngineeringTongji University
    • Division of Chemical Biology and Medicinal Chemistry Eshelman School of PharmacyUniversity of North Carolina at Chapel Hill
    • 100K Beard HallUniversity of North Carolina at Chapel Hill
Research Paper

DOI: 10.1007/s11095-013-1023-6

Cite this article as:
Zhu, X., Sedykh, A., Zhu, H. et al. Pharm Res (2013) 30: 1790. doi:10.1007/s11095-013-1023-6

Abstract

Purpose

To develop accurate in silico predictors of Plasma Protein Binding (PPB).

Methods

Experimental PPB data were compiled for over 1,200 compounds. Two endpoints have been considered: (1) fraction bound (%PPB); and (2) the logarithm of a pseudo binding constant (lnKa) derived from %PPB. The latter metric was employed because it reflects the PPB thermodynamics and the distribution of the transformed data is closer to normal. Quantitative Structure-Activity Relationship (QSAR) models were built with Dragon descriptors and three statistical methods.

Results

Five-fold external validation procedure resulted in models with the prediction accuracy (R2) of 0.67 ± 0.04 and 0.66 ± 0.04, respectively, and the mean absolute error (MAE) of 15.3 ± 0.2% and 13.6 ± 0.2%, respectively. Models were validated with two external datasets: 173 compounds from DrugBank, and 236 chemicals from the US EPA ToxCast project. Models built with lnKa were significantly more accurate (MAE of 6.2–10.7 %) than those built with %PPB (MAE of 11.9–17.6 %) for highly bound compounds both for the training and the external sets.

Conclusions

The pseudo binding constant (lnKa) is more appropriate for characterizing PPB binding than conventional %PPB. Validated QSAR models developed herein can be applied as reliable tools in early drug development and in chemical risk assessment.

KEY WORDS

%PPBADMETdrug fraction boundmachine learningpharmacokinetics

ABBREVIATIONS

%PPB

Percent plasma protein binding

5FCV

5-fold external cross-validation

AD

Applicability domain

ADMET

Absorption, distribution, metabolism, excretion, and toxicity

CCR

Correct classification rate (balanced classification accuracy)

HSA

Human serum albumin

kNN

k nearest neighbors

lnKa

Natural logarithm of the pseudo binding constant imputed from %PPB

LogP

Octanol-water partition coefficient

LOO-CV

Leave-one-out cross validation

MAE

Mean absolute error

QSAR

Qualitative structure-activity relationship

R2

Coefficient of determination

RED

Rapid equilibrium dialysis

RF

Random forest

RMSE

Root mean square error

SVM

Support vector machine

Tc

Tanimoto similarity coefficient

Supplementary material

11095_2013_1023_MOESM1_ESM.docx (179 kb)
ESM 1(DOCX 179kb)
11095_2013_1023_MOESM2_ESM.xlsx (289 kb)
ESM 2(XLSX 288kb)
11095_2013_1023_MOESM3_ESM.xlsx (66 kb)
ESM 3(XLSX 65kb)
11095_2013_1023_MOESM4_ESM.xlsx (66 kb)
ESM 4(XLSX 65kb)
11095_2013_1023_MOESM5_ESM.xlsx (23 kb)
ESM 5(XLSX 22kb)

Copyright information

© Springer Science+Business Media New York 2013