In silico prediction of pKa values using explainable deep learning methods
10.1016/j.jpha.2024.101174
- Author:
Chen YANG
1
;
Changda GONG
1
;
Zhixing ZHANG
1
;
Jiaojiao FANG
1
;
Weihua LI
1
;
Guixia LIU
1
;
Yun TANG
1
Author Information
1. Shanghai Frontiers Science Center of Optogenetic Techniques for Cell Metabolism,Shanghai Key Laboratory of New Drug Design,School of Pharmacy,East China University of Science and Technology,Shanghai,200237,China
- Publication Type:Journal Article
- Keywords:
pKa;
Deep learning;
Graph neural networks;
AttentiveFP;
Integrated gradients;
In silico prediction
- From:
Journal of Pharmaceutical Analysis
2025;15(6):1264-1276
- CountryChina
- Language:English
-
Abstract:
Negative logarithm of the acid dissociation constant(pKa)significantly influences the absorption,dis-tribution,metabolism,excretion,and toxicity(ADMET)properties of molecules and is a crucial indicator in drug research.Given the rapid and accurate characteristics of computational methods,their role in predicting drug properties is increasingly important.Although many pKa prediction models currently exist,they often focus on enhancing model precision while neglecting interpretability.In this study,we present GraFpKa,a pKa prediction model using graph neural networks(GNNs)and molecular finger-prints.The results show that our acidic and basic models achieved mean absolute errors(MAEs)of 0.621 and 0.402,respectively,on the test set,demonstrating good predictive performance.Notably,to improve interpretability,GraFpKa also incorporates Integrated Gradients(IGs),providing a clearer visual description of the atoms significantly affecting the pKa values.The high reliability and interpretability of GraFpKa ensure accurate pKa predictions while also facilitating a deeper understanding of the relation-ship between molecular structure and pKa values,making it a valuable tool in the field of pKa prediction.
