Prediction of Protein pKa with Representation Learning

Abstract

The behavior of proteins is closely related to the protonation states of the residues. Therefore, prediction and measurement of pKa are essential to understand the basic functions of proteins. In this work, we develop a new empirical scheme for protein pKa prediction that is based on deep representation learning. It combines machine learning with atomic environment vector (AEV) and learned quantum mechanical representation from ANI-2x neural network potential (J. Chem. Theory Comput. 2020, 16, 4192). The scheme requires only the coordinate information of a protein as the input and separately estimates the pKa for all five titratable amino acid types. The accuracy of the approach was analyzed with both cross-validation and an external test set of proteins. Obtained results were compared with the widely used empirical approach PROPKA. The new empirical model provides accuracy with MAEs below 0.5 for all amino acid types. It surpasses the accuracy of PROPKA and performs significantly better than the null model. Our model is also sensitive to the local conformational changes and molecular interactions.

Protein pKa Prediction by Tree-Based Machine Learning

“…The RMSE values are summarized in Table 4, which also shows RMSE values for five other pK a predictors: DelPhiPKa, a popular continuum electrostatic pK a prediction method; 122 PypKa, a python module calculating pK a values by continuum electrostatic method; 57 DeepKa, a deep-learning-based pK a predictor trained on pK a values derived from continuous constant-pH simulations; 27 pKAI, a deep learning model trained on pK a values calculated by PypKa; 104 and a pK a predictor based on deep representation learning and trained on experimental pK a values, which we will refer to as DRL. 28 Because DelPhiPKa and DeepKa only predict the pK a values of Asp, Glu, His and Lys (DEHK) residues, and PypKa and DRL only predict for Asp, Glu, His, Lys, and Tyr (DEHK + Y) residues, we also show DEHK and "DEHK + Y" RMSE values in Table 4. The DEHK RMSE of the XGB-WMa model is 0.63.…”

“…104 Another protein pK a prediction paper from Gokcan and Isayev introduced a new empirical scheme based on deep representation learning that was trained on experimental pK a data. 28 We chose to use the prevalent treebased ML models in this work because of their robustness and well-known good performance on various tasks. We noticed that support vector machine and cascade deep forest could perform well on small datasets.…”