Building Proteins in a Day: Efficient 3D Molecular Reconstruction

TL;DR

This paper presents a scalable and efficient framework for reconstructing 3D molecular structures from Cryo-EM images, significantly reducing computation time to about a day on standard hardware.

Contribution

It introduces a novel stochastic optimization framework and a cost-reduction technique for 3D reconstruction from Cryo-EM data, enabling large-scale analysis in a practical timeframe.

Findings

Achieves 3D reconstruction in about a day on a single workstation.

Reduces evaluation cost by over five orders of magnitude.

Scales effectively to large Cryo-EM datasets.

Abstract

Discovering the 3D atomic structure of molecules such as proteins and viruses is a fundamental research problem in biology and medicine. Electron Cryomicroscopy (Cryo-EM) is a promising vision-based technique for structure estimation which attempts to reconstruct 3D structures from 2D images. This paper addresses the challenging problem of 3D reconstruction from 2D Cryo-EM images. A new framework for estimation is introduced which relies on modern stochastic optimization techniques to scale to large datasets. We also introduce a novel technique which reduces the cost of evaluating the objective function during optimization by over five orders or magnitude. The net result is an approach capable of estimating 3D molecular structure from large scale datasets in about a day on a single workstation.