A Framework for Orientation Recovery with Uncertainty Measurement in Cryo-EM Image Analysis
Cryo-forum is a framework designed to facilitate experimentation with various strategies for orientation recovery in cryo-electron microscopy (cryo-EM).
- Cryo-forum: A Framework for Orientation Recovery with Uncertainty Measurement in Cryo-EM Image Analysis
- Author: Szu-Chi Chung
- Read the Manuscript
Prerequisite: If you do not have the Anaconda Python distribution, install it here.
Create a Conda Environment for Cryo-forum:
- More information on managing conda environments can be found here.
conda create --name cryoforum python=3.10
conda activate cryoforum
Install Dependencies:
pip install mrcfile wandb ipyvolume seaborn tensorflow_probability==0.20.0 tensorflow==2.12 tensorflow-graphics tensorflow_similarity scikit-image ipython_genutils notebook quaternion
Clone the Repository and Change Directory:
git clone https://github.com/phonchi/Cryo-forum.git
cd Cryo-forum
- Explore the Example Notebook for detailed documentation and analysis on both synthetic and real datasets.
- Access the pretrained model and data at Pretrained Model and Data respectively.
Cryo-forum is released as open source software under the GNU General Public License, Version 3.
- This code base builds upon the work developed by Jelena Banjac and the code available at Bingham Rotation Learning Repository.
- The visualization code for the Bingham distribution is adapted from this source.