Related Experiment Video
Updated: Mar 2, 2026
13:43
A Robust Single-Particle Cryo-Electron Microscopy cryo-EM Processing Workflow with cryoSPARC, RELION, and Scipion
Published on: January 31, 2022
15.5K
ProPicker: Promptable segmentation for particle picking in cryogenic electron tomography.
Simon Wiedemann1, Zalan Fabian2, Mahdi Soltanolkotabi2
1Technical University of Munich, Arcisstraße 21, 80333 Munich, Germany.
Journal of Structural Biology
|February 28, 2026
Summary
ProPicker, a new AI tool, simplifies particle picking in 3D cryo-electron tomography (cryo-ET) images. This pretrained model efficiently detects cellular structures, improving data analysis speed and accuracy.
Area of Science:
- Structural Biology
- Biophysics
- Computational Biology
Background:
- Cryo-electron tomography (cryo-ET) generates high-resolution 3D cellular images.
- Particle picking, identifying specific structures in cryo-ET data, is crucial but challenging due to noise and complex cellular environments.
Purpose of the Study:
- To introduce ProPicker, a novel pretrained, promptable 3D segmentation model for particle picking in cryo-ET.
- To develop a flexible and data-efficient workflow for identifying diverse cellular particles.
Main Methods:
- ProPicker utilizes a promptable 3D segmentation approach.
- The model can be used directly with a prompt or fine-tuned for particle-specific accuracy.
Main Results:
- ProPicker achieves performance comparable to state-of-the-art methods, up to 10x faster, using a single prompt.
- The model demonstrates the ability to detect particles not encountered during training.
- Fine-tuning ProPicker surpasses existing methods when limited training data is available.
Conclusions:
- ProPicker offers a versatile and efficient solution for particle picking in cryo-ET data analysis.
- The promptable nature of ProPicker enhances its applicability across various particle types and datasets.
