Cryo-em images are intrinsically low dimensional

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Evans, Luke, Murad, Octavian-Vlad, Dingeldein, Lars, Cossio, Pilar, Covino, Roberto, Meila, Marina
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866915477996961792
author Evans, Luke
Murad, Octavian-Vlad
Dingeldein, Lars
Cossio, Pilar
Covino, Roberto
Meila, Marina
author_facet Evans, Luke
Murad, Octavian-Vlad
Dingeldein, Lars
Cossio, Pilar
Covino, Roberto
Meila, Marina
contents Simulation-based inference provides a powerful framework for cryo-electron microscopy, employing neural networks in methods like CryoSBI to infer biomolecular conformations via learned latent representations. This latent space represents a rich opportunity, encoding valuable information about the physical system and the inference process. Harnessing this potential hinges on understanding the underlying geometric structure of these representations. We investigate this structure by applying manifold learning techniques to CryoSBI representations of hemagglutinin (simulated and experimental). We reveal that these high-dimensional data inherently populate low-dimensional, smooth manifolds, with simulated data effectively covering the experimental counterpart. By characterizing the manifold's geometry using Diffusion Maps and identifying its principal axes of variation via coordinate interpretation methods, we establish a direct link between the latent structure and key physical parameters. Discovering this intrinsic low-dimensionality and interpretable geometric organization not only validates the CryoSBI approach but enables us to learn more from the data structure and provides opportunities for improving future inference strategies by exploiting this revealed manifold geometry.
format Preprint
id arxiv_https___arxiv_org_abs_2504_11249
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Cryo-em images are intrinsically low dimensional
Evans, Luke
Murad, Octavian-Vlad
Dingeldein, Lars
Cossio, Pilar
Covino, Roberto
Meila, Marina
Quantitative Methods
Computer Vision and Pattern Recognition
Machine Learning
Biomolecules
Simulation-based inference provides a powerful framework for cryo-electron microscopy, employing neural networks in methods like CryoSBI to infer biomolecular conformations via learned latent representations. This latent space represents a rich opportunity, encoding valuable information about the physical system and the inference process. Harnessing this potential hinges on understanding the underlying geometric structure of these representations. We investigate this structure by applying manifold learning techniques to CryoSBI representations of hemagglutinin (simulated and experimental). We reveal that these high-dimensional data inherently populate low-dimensional, smooth manifolds, with simulated data effectively covering the experimental counterpart. By characterizing the manifold's geometry using Diffusion Maps and identifying its principal axes of variation via coordinate interpretation methods, we establish a direct link between the latent structure and key physical parameters. Discovering this intrinsic low-dimensionality and interpretable geometric organization not only validates the CryoSBI approach but enables us to learn more from the data structure and provides opportunities for improving future inference strategies by exploiting this revealed manifold geometry.
title Cryo-em images are intrinsically low dimensional
topic Quantitative Methods
Computer Vision and Pattern Recognition
Machine Learning
Biomolecules
url https://arxiv.org/abs/2504.11249