Generative Modeling of Entangled Polymers with a Distance-Based Variational Autoencoder

TL;DR

This paper introduces a variational autoencoder framework that learns and generates structured polymer configurations from distance matrices, capturing key physical properties with high fidelity.

Contribution

It develops a novel distance-based VAE combining convolution and attention layers to encode polymer structures into an invariant latent space, enabling realistic generation of polymer configurations.

Findings

Reproduces energy, size, and entanglement observables accurately

Uses coarse-grained MD data for training

Generates physically meaningful polymer configurations

Abstract

We present a variational autoencoder framework for learning and generating configurations of structured polymer globules from distance matrices. We used coarse-grained molecular dynamics to sample polyethylene structures, which we used as the training set for our deep learning model. By combining convolution and attention layers, the model encodes the structural patterns of distance matrices into an organized and roto-translationally invariant latent space of lower dimensionality. The generative capability of the variational autoencoder, coupled with a post-processing pipeline based on multidimensional scaling and short molecular dynamics, enables the recovery of physically meaningful configurations. The reconstructed and generated samples reproduce key observables, including energy, size, and entanglement, despite minor discrepancies in the raw decoder output.