MolGpka: A Web Server for Small Molecule pK_aPrediction Using a Graph-Convolutional Neural Network

pK_ais an important property in the lead optimization process since the charge state of a molecule in physiologic pH plays a critical role in its biological activity, solubility, membrane permeability, metabolism, and toxicity. Accurate and fast estimation of small molecule pK_ais vital during the drug discovery process. We present MolGpKa, a web server for pK_aprediction using a graph-convolutional neural network model. The model works by learning pK_arelated chemical patterns automatically and building reliable predictors with learned features. ACD/pK_adata for 1.6 million compounds from the ChEMBL database was used for model training. We found that the performance of the model is better than machine learning models built with human-engineered fingerprints. Detailed analysis shows that the substitution effect on pK_ais well learned by the model. MolGpKa is a handy tool for the rapid estimation of pK_aduring the ligand design process. The MolGpKa server is freely available to researchers and can be accessed athttps://xundrug.cn/molgpka.