Geometric learning of the conformational dynamics of molecules using dynamic graph neural networks
This work addresses the challenge of simulating molecular conformational dynamics for computational chemistry, offering an incremental improvement in efficiency through transfer learning.
The paper tackles the problem of predicting time-dependent changes in molecular structure by applying a dynamic graph neural network to predict atom-to-atom distances with a mean absolute error of 0.017 Å, achieving chemical accuracy, and demonstrates transferability to new systems with finetuning using less than 10% of trajectory data.
We apply a temporal edge prediction model for weighted dynamic graphs to predict time-dependent changes in molecular structure. Each molecule is represented as a complete graph in which each atom is a vertex and all vertex pairs are connected by an edge weighted by the Euclidean distance between atom pairs. We ingest a sequence of complete molecular graphs into a dynamic graph neural network (GNN) to predict the graph at the next time step. Our dynamic GNN predicts atom-to-atom distances with a mean absolute error of 0.017 Å, which is considered ``chemically accurate'' for molecular simulations. We also explored the transferability of a trained network to new molecular systems and found that finetuning with less than 10% of the total trajectory provides a mean absolute error of the same order of magnitude as that when training from scratch on the full molecular trajectory.