/CryoBench

Diverse and challenging datasets for the heterogeneity problem in cryo-EM

Primary LanguageJupyter Notebook

CryoBench: Diverse and challenging datasets for the heterogeneity problem in cryo-EM

Documentation

The latest documentation for CryoBench is available at our homepage and also at our manual.

For any feedback, questions, or bugs, please file a Github issue, start a Github discussion, or email.

Installation

To run the metrics, you have to install cryodrgn. cryodrgn may be installed via pip, and we recommend installing cryodrgn in a clean conda environment.

# Create and activate conda environment
(base) $ conda create --name cryodrgn python=3.9
(cryodrgn) $ conda activate cryodrgn

# install cryodrgn
(cryodrgn) $ pip install cryodrgn

More installation instructions are found in the documentation.

Datasets are available for download at Zenodo.

  1. Conf-het: https://zenodo.org/records/11629428.
  2. Comp-het: https://zenodo.org/records/12528292.
  3. Spike-MD: https://zenodo.org/records/12528784.

Image Formation

Look at the repo cryosim.

Metrics

1. Per-image FSCs

Look at the repo metrics/fsc

2. UMAP visualization

Look at the repo metrics/visualization

References:

Jeon, Minkyu, et al. "CryoBench: Diverse and challenging datasets for the heterogeneity problem in cryo-EM." arXiv preprint arXiv:2408.05526 (2024) paper.

Contact

Please submit any bug reports, feature requests, or general usage feedback as a github issue or discussion.