Back to Search Start Over

Prediction of Placental Barrier Permeability: A Model Based on Partial Least Squares Variable Selection Procedure

Authors :
Yong-Hong Zhang
Zhi-Ning Xia
Li Yan
Shu-Shen Liu
Source :
Molecules, Vol 20, Iss 5, Pp 8270-8286 (2015)
Publication Year :
2015
Publisher :
MDPI AG, 2015.

Abstract

Assessing the human placental barrier permeability of drugs is very important to guarantee drug safety during pregnancy. Quantitative structure–activity relationship (QSAR) method was used as an effective assessing tool for the placental transfer study of drugs, while in vitro human placental perfusion is the most widely used method. In this study, the partial least squares (PLS) variable selection and modeling procedure was used to pick out optimal descriptors from a pool of 620 descriptors of 65 compounds and to simultaneously develop a QSAR model between the descriptors and the placental barrier permeability expressed by the clearance indices (CI). The model was subjected to internal validation by cross-validation and y-randomization and to external validation by predicting CI values of 19 compounds. It was shown that the model developed is robust and has a good predictive potential (r2 = 0.9064, RMSE = 0.09, q2 = 0.7323, rp2 = 0.7656, RMSP = 0.14). The mechanistic interpretation of the final model was given by the high variable importance in projection values of descriptors. Using PLS procedure, we can rapidly and effectively select optimal descriptors and thus construct a model with good stability and predictability. This analysis can provide an effective tool for the high-throughput screening of the placental barrier permeability of drugs.

Details

Language :
English
ISSN :
14203049
Volume :
20
Issue :
5
Database :
Directory of Open Access Journals
Journal :
Molecules
Publication Type :
Academic Journal
Accession number :
edsdoj.b424ed68685d4732b8ac97b261e4bc45
Document Type :
article
Full Text :
https://doi.org/10.3390/molecules20058270