Exploring particle dynamics during self-organization processes via rotationally invariant latent representations

TL;DR

This paper introduces a machine learning approach combining deep learning and rotationally invariant autoencoders to analyze particle orientation and shape evolution during self-organization, revealing local transitions and system dynamics.

Contribution

It presents a novel method for disentangling particle orientation from other degrees of freedom using rotationally invariant latent representations, applicable to various microscopy imaging data.

Findings

Disentangled particle orientation from shape and position.

Visualization of local transitions via continuous latent variables.

Insights into the potential ordering transition in the system.

Abstract

The dynamic of complex ordering systems with active rotational degrees of freedom exemplified by protein self-assembly is explored using a machine learning workflow that combines deep learning-based semantic segmentation and rotationally invariant variational autoencoder-based analysis of orientation and shape evolution. The latter allows for disentanglement of the particle orientation from other degrees of freedom and compensates for shifts. The disentangled representations in the latent space encode the rich spectrum of local transitions that can now be visualized and explored via continuous variables. The time dependence of ensemble averages allows insight into the time dynamics of the system, and in particular, illustrates the presence of the potential ordering transition. Finally, analysis of the latent variables along the single-particle trajectory allows tracing these parameters on a single particle level. The proposed approach is expected to be universally applicable for the description of the imaging data in optical, scanning probe, and electron microscopy seeking to understand the dynamics of complex systems where rotations are a significant part of the process.