J Chem Theory Comput. 2025 Mar 25. doi: 10.1021/acs.jctc.4c01747. Online ahead of print.
ABSTRACT
Physics-informed neural networks (PINN) is a machine learning (ML)-based method to solve partial differential equations that has gained great popularity due to the fast development of ML libraries in the past few years. The Poisson-Boltzmann equation (PBE) is widely used to model mean-field electrostatics in molecular systems, and in this work we present a detailed investigation of the use of PINN to solve the linear PBE. Starting from a multidomain PINN for the linear PBE with an interface, we assess the importance of incorporating different features into the neural network architecture. Our findings indicate that the most accurate architecture utilizes input and output scaling layers, a random Fourier features layer, trainable activation functions, and a loss balancing algorithm. The accuracy of our implementation is on the order of 10-2-10-3, which is similar to previous work using PINN to solve other differential equations. We also explore the possibility of incorporating experimental information into the model, and discuss challenges and future work, especially regarding the nonlinear PBE. We are providing an open-source implementation to easily perform computations from a PDB file. We hope this work will motivate application scientists into using PINN to study molecular electrostatics, as ML technology continues to evolve at a high pace.
PMID:40131176 | DOI:10.1021/acs.jctc.4c01747
