Deep learning models to segment emcapsulins in 2D TEM micrograph images from the manuscript:
Genetically encoded barcodes for correlative volume electron microscopy
The models are trained on 8-bit images with a pixel size: of 0.5525 per nanometer. We include some example input and output files for replication.
- Clone this repository:
git clone https://github.com/HelmholtzAI-Consultants-Munich/EMcapsulins_segmentation.git
- Go into the repository and install:
cd EMcapsulins_segmentation pip install -r requirements.txt pip install -e .
run_inference_tiff.py <-- Example script for inference creating tiff files
run_inference_nifti.py <-- Example script for inference creating nifti files
when using the software please cite https://www.nature.com/articles/s41587-023-01713-y
@article{sigmund2023genetically,
title={Genetically encoded barcodes for correlative volume electron microscopy},
author={Sigmund, Felix and Berezin, Oleksandr and Beliakova, Sofia and Magerl, Bernhard and Drawitsch, Martin and Piovesan, Alberto and Gon{\c{c}}alves, Filipa and Bodea, Silviu-Vasile and Winkler, Stefanie and Bousraou, Zoe and others},
journal={Nature Biotechnology},
pages={1--12},
year={2023},
publisher={Nature Publishing Group US New York}
}
- CUDA 11.4+
- Python 3.10+
- GPU with at least 8GB of VRAM
further details in requirements.txt
Please have a look at this repository
This project is licensed under the terms of the GNU Affero General Public License v3.0.
Contact us regarding licensing.
If possible please open a GitHub issue here.
For inquiries not suitable for GitHub issues:
felix.sigmund @ tum .de
gil.westmeyer @ tum .de