Unsupervised SE(3) Disentanglement for in situ Macromolecular Morphology Identification from Cryo-Electron Tomography
This work addresses the challenge of accurately analyzing in situ macromolecular structures in noisy cryo-ET data, which is incremental as it builds on existing expectation-maximization approaches.
The paper tackled the problem of identifying macromolecular morphologies from cryo-electron tomography data by developing a disentangled deep learning framework that separates SE(3) transformations from morphological content, resulting in improved discovery of rare morphologies compared to prior methods.
Cryo-electron tomography (cryo-ET) provides direct 3D visualization of macromolecules inside the cell, enabling analysis of their in situ morphology. This morphology can be regarded as an SE(3)-invariant, denoised volumetric representation of subvolumes extracted from tomograms. Inferring morphology is therefore an inverse problem of estimating both a template morphology and its SE(3) transformation. Existing expectation-maximization based solution to this problem often misses rare but important morphologies and requires extensive manual hyperparameter tuning. Addressing this issue, we present a disentangled deep representation learning framework that separates SE(3) transformations from morphological content in the representation space. The framework includes a novel multi-choice learning module that enables this disentanglement for highly noisy cryo-ET data, and the learned morphological content is used to generate template morphologies. Experiments on simulated and real cryo-ET datasets demonstrate clear improvements over prior methods, including the discovery of previously unidentified macromolecular morphologies.