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

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.

arXiv commentUploading the accepted version

References in corpus (24)

• Adam: A Method for Stochastic Optimization
• Auto-Encoding Variational Bayes
• Crystal Graph Convolutional Neural Networks for an Accurate and Interpretable Prediction of Material Properties
• An Introduction to Variational Autoencoders
• Tutorial on Variational Autoencoders
• Deep Learning Microscopy
• Deep Learning of Atomically Resolved Scanning Transmission Electron Microscopy Images: Chemical Identification and Tracking Local Transformations
• Time-lagged autoencoders: Deep learning of slow collective variables for molecular kinetics
• Scalar ${\varphi }^4$ field theory for active-particle phase separation
• Towards a Definition of Disentangled Representations
• Assembly and Phase Transitions within Colloidal Crystals
• Convolutional neural networks automate detection for tracking of submicron scale particles in 2D and 3D
• AxonDeepSeg: automatic axon and myelin segmentation from microscopy data using convolutional neural networks
• Deep Learning Analysis of Defect and Phase Evolution During Electron Beam Induced Transformations in WS2
• Nonequilibrium steady states in a vibrated-rod monolayer: tetratic, nematic and smectic correlations
• Mean-field theory of random close packings of axisymmetric particles
• Graph Dynamical Networks for Unsupervised Learning of Atomic Scale Dynamics in Materials
• A deep convolutional neural network approach to single-particle recognition in cryo-electron microscopy
• Novel Features Arising in the Maximally Random Jammed Packings of Superballs
• Unsupervised learning for local structure detection in colloidal systems
• Control of pathways and yields of protein crystallization through the interplay of nonspecific and specific attractions
• Multi-scale Convolutional Neural Networks for Inverse Problems
• Explicitly disentangling image content from translation and rotation with spatial-VAE
• Quantifying the dynamics of protein self-organization using deep learning analysis of atomic force microscopy data

Cited by in corpus (5)

• AtomAI: A Deep Learning Framework for Analysis of Image and Spectroscopy Data in (Scanning) Transmission Electron Microscopy and Beyond
• Applications and Techniques for Fast Machine Learning in Science
• Benchmark tests of atom segmentation deep learning models with a consistent dataset
• Unsupervised learning of ferroic variants from atomically resolved STEM images
• Physical discovery in representation learning via conditioning on prior knowledge: applications for ferroelectric domain dynamics