C3Net: interatomic potential neural network for prediction of physicochemical properties in heterogenous systems
This work addresses the challenge of accurately modeling solute-environment interactions in chemistry and biology, offering a generalized method for predicting key physicochemical properties, though it appears incremental as it builds on existing neural network and physical law frameworks.
The authors tackled the problem of predicting physicochemical properties in heterogeneous systems by developing C3Net, a deep neural network architecture for atom type embeddings and interatomic potentials that adheres to physical laws. The result showed that C3Net outperformed state-of-the-art quantum mechanics and neural network approaches in solvation free energy prediction, with a single set of network weights generalizing well to tasks like solvation, 1-octanol-water partitioning, and PAMPA.
Understanding the interactions of a solute with its environment is of fundamental importance in chemistry and biology. In this work, we propose a deep neural network architecture for atom type embeddings in its molecular context and interatomic potential that follows fundamental physical laws. The architecture is applied to predict physicochemical properties in heterogeneous systems including solvation in diverse solvents, 1-octanol-water partitioning, and PAMPA with a single set of network weights. We show that our architecture is generalized well to the physicochemical properties and outperforms state-of-the-art approaches based on quantum mechanics and neural networks in the task of solvation free energy prediction. The interatomic potentials at each atom in a solute obtained from the model allow quantitative analysis of the physicochemical properties at atomic resolution consistent with chemical and physical reasoning. The software is available at https://github.com/SehanLee/C3Net.