- Preprint Article
1
- 10.21203/rs.3.rs-3367941/v1
Uni-pKa: An Accurate and Physically Consistent pKa Prediction through Protonation Ensemble Modeling
- Oct 19, 2023
- Research Square
- Hang Zheng + 7 more +7
Abstract Predicting pKa values of small molecules has key applications in drug discovery and molecular simulation. However, current methods face challenges in rigorously interpreting experimental data and ensuring thermodynamic consistency between successive pKa values. To address these limitations, we present Uni-pKa, an accurate and reliable pKa prediction framework. Uni-pKa is based on comprehensive free energy modeling of possible molecules in protonation equilibrium. Within this framework, a structural enumerator recovers underlying structures in pKa datapoints, and a neural network serves as a free energy predictor, learning from data rigorously while inherently preserving thermodynamic consistency. Through a pretraining-finetuning strategy utilizing predicted and experimental pKa data, Uni-pKa achieves state-of-the-art accuracy among chemoinformatic methods. Uni-pKa provides a good example of combining chemical principles and machine learning to solve scientific problems.
Read more