Adversarial reverse mapping of condensed-phase molecular structures: Chemical transferability

TL;DR

This paper extends a neural network approach for reverse-mapping molecular structures to different chemical systems, demonstrating transferability from small molecules to polymers with physics-based regularization.

Contribution

It introduces a method to enhance chemical transferability of deepBackmap by training on small molecules and applying to polymers, incorporating physics-based priors for improved accuracy.

Findings

Successful transfer from small molecules to polymer melts

Physics-based priors improve reconstruction quality

Local environment representation aids transferability

Abstract

Switching between different levels of resolution is essential for multiscale modeling, but restoring details at higher resolution remains challenging. In our previous study we have introduced deepBackmap: a deep neural-network-based approach to reverse-map equilibrated molecular structures for condensed-phase systems. Our method combines data-driven and physics-based aspects, leading to high-quality reconstructed structures. In this work, we expand the scope of our model and examine its chemical transferability. To this end, we train deepBackmap solely on homogeneous molecular liquids of small molecules, and apply it to a more challenging polymer melt. We augment the generator's objective with different force-field-based terms as prior to regularize the results. The best performing physical prior depends on whether we train for a specific chemistry, or transfer our model. Our local environment representation combined with the sequential reconstruction of fine-grained structures help reach transferability of the learned correlations.