Chemometric modeling for blood–brain-barrier permeability prediction of protein kinase inhibitors

3rd International Conference on Chemo and BioInformatics, Kragujevac, September 25-26. 2025. (pp. 664-667) 

 

АУТОР(И) / AUTHOR(S): Alen Čebzan, Milan Jovanović, Milica Radan, Marija Čarapić, Nenad Filipović, Katarina Nikolić, Milkica Crevar

 

Download Full Pdf   

DOI:  10.46793/ICCBIKG25.664C

САЖЕТАК / ABSTRACT:

Limited passage through the blood-brain barrier (BBB) poses a major challenge in developing therapeutics for the central nervous system (CNS), especially for protein kinase inhibitors, which have high potential for treating different neurological disorders and malignancies. This study investigates the passive permeability of 34 diverse compounds, comprising both approved protein kinase inhibitors and experimental compounds, using the parallel artificial membrane permeability assay (PAMPA-BBB). Quantitative structure-property relationship (QSPR) models were developed utilizing Multiple Linear Regression (MLR), Support Vector Machine Regression (SVM), and Artificial Neural Networks (ANN). These models employed molecular descriptors of the compounds to create predictive models for assessing the permeability of other compounds. The study found that among the molecular descriptors, CATS2D_04_AA had the strongest positive correlation with logPe, indicating enhanced BBB permeability, while CATS2D_09_DA negatively impacted permeability. Both linear (MLR) and nonlinear (ANN and SVM) models confirmed these relationships, with the SVM model showing better performance due to capturing nonlinear dependencies, particularly for descriptors like CATS2D_04_AA and F07[C-N]. Optimizing structural features, including reducing hydrogen bond donors, was proposed to improve BBB permeability, thus offering guidance for the design of kinase inhibitors with improved CNS delivery potential. The integration of PAMPA-BBB assays with robust QSAR modeling provides a reliable framework for optimizing CNS-targeted drug candidates.

КЉУЧНЕ РЕЧИ / KEYWORDS:

PAMPA-BBB, kinase inhibitors, QSPR, SVM

ПРОЈЕКАТ / ACKNOWLEDGEMENT:

This research is funded by the Ministry of Education and Ministry of Science, Technological Development and Innovation, Republic of Serbia, Grants: No. 451-03- 136/2025-03/ 200161, 451-03-137/2025-03/ 200161, 451-03-136/2025-03/200017, 451-03-136/2025-03/200003 and 451-03-66/2024-03/200003.

ЛИТЕРАТУРА / REFERENCES:

  • L. Di, E.H. Kerns, K. Fan, O.J. McConnell, G.T. Carter, High throughput artificial membrane permeability assay for blood-brain barrier, Eur. J. Med. Chem. 38 (2003) 223–232.
  • P. K. Ojha, K. Roy, Comparative QSARs for antimalarial endochins: Importance of descriptor- thinning and noise reduction prior to feature selection, Chemom. Intell. Lab. Syst. 109 (2011) 146–161.
  • R. Todeschini, V. Consonni, Molecular Descriptors for Chemoinformatics, Mol. Descriptors Chemoinformatics. 2 (2010) 1–252.