CryoPoseNet: End-to-End Simultaneous Learning of Single-Particle Orientation and 3D Map Reconstruction From Cryo-Electron Microscopy Data

Youssef S. G. Nashed, Frédéric Poitevin, Harshit Gupta, Geoffrey Woollard, Michael Kagan, Chun Hong Yoon, Daniel Ratner; Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops, 2021, pp. 4066-4076

Abstract

Cryogenic electron microscopy (cryo-EM) provides im-ages from different copies of the same biomolecule in ar-bitrary orientations. Here, we present an end-to-end unsu-pervised approach that learns individual particle orienta-tions directly from cryo-EM data while reconstructing the3D map of the biomolecule following random initialization.The approach relies on an auto-encoder architecture wherethe latent space is explicitly interpreted as orientations usedby the decoder to form an image according to the physi-cal projection model. We evaluate our method on simulateddata and show that it is able to reconstruct 3D particle mapsfrom noisy- and CTF-corrupted 2D projection images of un-known particle orientations

Related Material

[pdf]
[bibtex]
@InProceedings{Nashed_2021_ICCV, author = {Nashed, Youssef S. G. and Poitevin, Fr\'ed\'eric and Gupta, Harshit and Woollard, Geoffrey and Kagan, Michael and Yoon, Chun Hong and Ratner, Daniel}, title = {CryoPoseNet: End-to-End Simultaneous Learning of Single-Particle Orientation and 3D Map Reconstruction From Cryo-Electron Microscopy Data}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops}, month = {October}, year = {2021}, pages = {4066-4076} }