Prediction of Placental Barrier Permeability: A Model Based on Partial Least Squares Variable Selection Procedure
Open Access
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.Keywords
Funding Information
- National Natural Science Foundation of China (21177097)
This publication has 52 references indexed in Scilit:
- Drug Interactions at the Human Placenta: What is the Evidence?Frontiers in Pharmacology, 2012
- Medication use during pregnancy, with particular focus on prescription drugs: 1976-2008American Journal of Obstetrics and Gynecology, 2011
- Some remarks on protein attribute prediction and pseudo amino acid compositionJournal of Theoretical Biology, 2011
- Quantitative Structure‐Activity Relationships for PPAR‐γ Binding and Gene Transactivation of Tyrosine‐Based Agonists Using Multivariate StatisticsChemical Biology & Drug Design, 2008
- Use of computer-assisted prediction of toxic effects of chemical substancesToxicology, 2006
- In silico prediction of harmful effects triggered by drugs and chemicalsToxicology and Applied Pharmacology, 2005
- Performance of some variable selection methods when multicollinearity is presentChemometrics and Intelligent Laboratory Systems, 2005
- Prescription drug use in pregnancyAmerican Journal of Obstetrics and Gynecology, 2004
- Prediction of Protein Structural ClassesCritical Reviews in Biochemistry and Molecular Biology, 1995
- Clearance of Compounds of Different Molecular Size in the Human Placenta in vitroNeonatology, 1985