BibTeX

@article{2504.11249v3,
Author        = {Luke Evans and Octavian-Vlad Murad and Lars Dingeldein and Pilar Cossio and Roberto Covino and Marina Meila},
Title         = {Cryo-em images are intrinsically low dimensional},
Eprint        = {2504.11249v3},
DOI           = {10.1103/txrb-fw3z},
ArchivePrefix = {arXiv},
PrimaryClass  = {q-bio.QM},
Abstract      = {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.},
Year          = {2025},
Month         = {Apr},
Url           = {http://arxiv.org/abs/2504.11249v3},
File          = {2504.11249v3.pdf}
}