Reconstruction-Aware Cryo-EM Particle Picking
Computer Vision and Pattern Recognition
Summary
The authors explain that figuring out the 3D shape of proteins using cryo-electron microscopy depends on picking out good images of these proteins from noisy pictures. Normally, scientists do this in three separate steps: finding particles, removing junk, and choosing the best 2D images, but these steps are done separately and not optimized together. The authors combined all three into one process that focuses on improving the final 3D picture. They show that their combined method results in sharper 3D images than any step done alone, and they found that the best scores for 2D images don’t always mean the best 3D result.
Authors
Riku Itsuji, Yuanhao Wang, Xingjian Li, Seonghui Min, Hideo Saito, Min Xu
Abstract
Cryo-electron microscopy (cryo-EM) determines the structures of proteins and macromolecular assemblies at near-atomic resolution, and the final 3D reconstruction depends on extracting a clean particle stack from noisy micrographs. This extraction decomposes into three sub-tasks, namely particle picking, contamination removal, and 2D class selection. Each of them, however, is trained and evaluated in isolation, and none is optimized for the reconstruction. We instead integrate the three sub-tasks into a single pipeline posed against downstream reconstruction quality. We instantiate the pipeline with a state-of-the-art component for each sub-task, CryoTransformer picking permissively, MicrographCleaner masking contamination, and CryoSift selecting 2D classes by a continuous quality score, and close the loop with a fine-tuning step that returns the surviving particles to the picker. The pipeline achieves a better 3D resolution than every picker we compare. We also show that the best 2D F1 is not the best resolution, so particle selection is better treated as one reconstruction-aware pipeline judged by the map it delivers.