End-to-End Simultaneous Learning of Single-particle Orientation and 3D Map Reconstruction from Cryo-electron Microscopy Data
arXiv:2107.02958
Abstract
Cryogenic electron microscopy (cryo-EM) provides images from different copies of the same biomolecule in arbitrary orientations. Here, we present an end-to-end unsupervised approach that learns individual particle orientations from cryo-EM data while reconstructing the average 3D map of the biomolecule, starting from a random initialization. The approach relies on an auto-encoder architecture where the latent space is explicitly interpreted as orientations used by the decoder to form an image according to the linear projection model. We evaluate our method on simulated data and show that it is able to reconstruct 3D particle maps from noisy- and CTF-corrupted 2D projection images of unknown particle orientations.
arXiv comment13 pages, 4 figures
References in corpus (6)
- A Survey on Deep Learning in Medical Image Analysis
- Explorations in Homeomorphic Variational Auto-Encoding
- Inferring a Continuous Distribution of Atom Coordinates from Cryo-EM Images using VAEs
- Common lines modeling for reference free ab-initio reconstruction in cryo-EM
- A common lines approach for ab-initio modeling of cyclically-symmetric molecules
- Differentiable probabilistic models of scientific imaging with the Fourier slice theorem