Disentangling Rotational Dynamics and Ordering Transitions in a System of Self-Organizing Protein Nanorods <i>via</i> Rotationally Invariant Latent Representations

Kalinin, Sergei V.; Zhang, Shuai; Valleti, Mani; Pyles, Harley; Baker, David; Yoreo, James J. De; Ziatdinov, Maxim

doi:10.1021/acsnano.0c08914

Cited by 26 publications

(15 citation statements)

References 69 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this regard, there is a growing body of work to embed physics in machine learning models, which serve as the ultimate regularizers. For instance, rotational (Kalinin et al, 2020 ; Oxley et al, 2020 ) and Euclidean equivariance (Smidt, 2020 ; Smidt et al, 2021 ) has been built into the model architectures, and methods to learn sparse representations of underlying governing equations have been developed (Champion et al, 2019 ; de Silva et al, 2020 ; Kaheman et al, 2020 ).…”

Section: Exemplars Of Domain Applicationsmentioning

confidence: 99%

Applications and Techniques for Fast Machine Learning in Science

Deiana¹,

Tran²,

Agar³

et al. 2022

Front. Big Data

View full text Add to dashboard Cite

In this community review report, we discuss applications and techniques for fast machine learning (ML) in science—the concept of integrating powerful ML methods into the real-time experimental data processing loop to accelerate scientific discovery. The material for the report builds on two workshops held by the Fast ML for Science community and covers three main areas: applications for fast ML across a number of scientific domains; techniques for training and implementing performant and resource-efficient ML algorithms; and computing architectures, platforms, and technologies for deploying these algorithms. We also present overlapping challenges across the multiple scientific domains where common solutions can be found. This community report is intended to give plenty of examples and inspiration for scientific discovery through integrated and accelerated ML solutions. This is followed by a high-level overview and organization of technical advances, including an abundance of pointers to source material, which can enable these breakthroughs.

show abstract

Section: Exemplars Of Domain Applicationsmentioning

confidence: 99%

Applications and Techniques for Fast Machine Learning in Science

Deiana¹,

Tran²,

Agar³

et al. 2022

Front. Big Data

View full text Add to dashboard Cite

show abstract

“…An alternative approach is developed based on rotationally invariant variational autoencoders (rVAE), a class of unsupervised machine learning methods projecting discrete large‐dimensional spaces on a continuous latent space. Previously, we applied the rVAE approach to explore the evolution of atomic‐scale structures in graphene under electron beam irradiation, [ 43 ] analyze the self‐assembly of protein nanorods, [ 44 ] investigate the domain wall dynamics in piezoresponse force microscopy, [ 45 ] and create a bottom‐up symmetry analysis workflow for atom‐resolved data. [ 46 ] Here, we demonstrate that this approach can be extended to explore domain evolution mechanisms via detailed analysis of the latent spaces of rVAE.…”

Section: Resultsmentioning

confidence: 99%

Latent Mechanisms of Polarization Switching from In Situ Electron Microscopy Observations

Ignatāns

Ziatdinov

Vasudevan

et al. 2022

Adv Funct Materials

Self Cite

View full text Add to dashboard Cite

In situ scanning transmission electron microscopy enables observation of the domain dynamics in ferroelectric materials as a function of externally applied bias and temperature. The resultant data sets contain a wealth of information on polarization switching and phase transition mechanisms. However, identification of these mechanisms from observational data sets has remained a problem due to a large variety of possible configurations, many of which are degenerate. Here, an approach based on a combination of deep learning‐based semantic segmentation, rotationally invariant variational autoencoder (VAE), and non‐negative matrix factorization to enable learning of a latent space representation of the data with multiple real‐space rotationally equivalent variants mapped to the same latent space descriptors is introduced. By varying the size of training sub‐images in the VAE, the degree of complexity in the structural descriptors is tuned from simple domain wall detection to the identification of switching pathways. This yields a powerful tool for the exploration of the dynamic data in mesoscopic electron, scanning probe, optical, and chemical imaging. Moreover, this work adds to the growing body of knowledge of incorporating physical constraints into the machine and deep‐learning methods to improve learned descriptors of physical phenomena.

show abstract

“…We used the rVAE implementation in Kalinin et al [20] and AtomAI [21]. This rVAE encodes the images into unstructured latent variables, of which we used only two, L1 and L2, and the latent variables encoding the rotational angle, L θ , and the translation in x and y, L∆x and L∆y.…”

Section: Resultsmentioning

confidence: 99%

Investigating Carboxysome Morphology Dynamics with a Rotationally Invariant Variational Autoencoder

Fuentes‐Cabrera

Sakkos

Ducat

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Carboxysomes are a class of bacterial microcompartments that form proteinaceous organelles within the cytoplasm of cyanobacteria and play a central role in photosynthetic metabolism by defining a cellular microenvironment permissive to CO2 fixation. Critical aspects of the assembly of the carboxysomes remain relatively unknown, especially with regard to the dynamics of this microcompartment. We have recently expressed an exogenous protease as a way of gaining control over endogenous protein levels, including carboxysomal components, in the model cyanobacterium Synechococcous elongatus PCC 7942. By utilizing this system, proteins that compose the carboxysome can be tuned in real-time as a method to examine carboxysome dynamics. Yet, analysis of subtle changes in carboxysome morphology with microscopy remains a low-throughput and subjective process. Here we use deep learning techniques, specifically a Rotationally Invariant Variational Autoencoder (rVAE), to analyze the fluorescence microscopy images and quantitatively evaluate how carboxysome shell remodelling impacts trends in the morphology of the microcompartment over time. We find that rVAEs are able to assist in the quantitative evaluation of changes in carboxysome location, shape, and size over time. We propose that rVAEs may be a useful tool to accelerate the analysis of carboxysome assembly and dynamics in response to genetic or environmental perturbation, and may be more generally useful to probe regulatory processes involving a broader array of bacterial microcompartments.

show abstract

Disentangling Rotational Dynamics and Ordering Transitions in a System of Self-Organizing Protein Nanorods via Rotationally Invariant Latent Representations

Cited by 26 publications

References 69 publications

Applications and Techniques for Fast Machine Learning in Science

Applications and Techniques for Fast Machine Learning in Science

Latent Mechanisms of Polarization Switching from In Situ Electron Microscopy Observations

Investigating Carboxysome Morphology Dynamics with a Rotationally Invariant Variational Autoencoder

Contact Info

Product

Resources

About