Cellular Electron Cryotomography (CryoET) offers the ability to look insidecells and observe macromolecules frozen in action. A primary challenge for thistechnique is identifying and extracting the molecular components within thecrowded cellular environment. We introduce a method using neural networks todramatically reduce the time and human effort required for subcellularannotation and feature extraction. Subsequent subtomogram classification andaveraging yields in-situ structures of molecular components of interest.
展开▼
