# CZII CryoET Object Identification Challenge: Experimental Training Tomograms with Particle Labels

## Facts

- Provider: Peck, Paraan, Harrington et al. (CZ Imaging Institute)
- License: CC0-1.0 (https://raw.githubusercontent.com/awslabs/open-data-registry/main/datasets/cryoet-data-portal.yaml)
- Format: PNG (in sampled files)
- Stored at: Amazon S3, s3://cryoet-data-portal-public/10440 (us-west-2)
- Access: public, readable without an account
- DOI: https://doi.org/10.1101/2024.11.04.621686
- Category: Structural Biology
- Source: https://doi.org/10.1101/2024.11.04.621686
- Page: https://scigantic.com/archive/c527daeb-2232-5559-9348-75b97882c80f
- Keywords: Structural Biology, image segmentation, benchmark, PNG, AWS Open Data

## About

Training data of the CZ Imaging Institute CryoET Object Identification Challenge (run on Kaggle, 2024 to 2025): cryo-electron tomograms of a phantom sample mixing six protein complexes, with hand-curated point annotations for apo-ferritin, beta-amylase, beta-galactosidase, cytosolic 80S ribosome, thyroglobulin and virus-like particles (VLP). Movies were acquired on a Krios G4 with a Falcon 4i detector and Selectris X energy filter; tilt series were aligned with AreTomo3 and reconstructed at 10 Å and 5 Å voxel spacing, and each of the 7 runs provides denoised and CTF-corrected tomograms alongside raw movie stacks and alignments. The public and private test tomograms are portal datasets 10445 and 10446, and polnet-simulated training data is 10441. A standard benchmark for 3D particle picking, the copick toolkit reads it directly. Each run folder holds Frames (raw movies, where deposited), TiltSeries, Alignments and Reconstructions/VoxelSpacing*/ with Tomograms (MRC and OME-Zarr) and Annotations (point picks as ndjson, segmentation masks); read it with the cryoet_data_portal Python client, copick, mrcfile or zarr. Released CC0; cite Peck et al. (bioRxiv 2024.11.04.621686).

## Load the data

```python
import boto3
from botocore import UNSIGNED
from botocore.client import Config
s3 = boto3.client('s3', region_name='us-west-2', config=Config(signature_version=UNSIGNED))
s3.list_objects_v2(Bucket='cryoet-data-portal-public', Prefix='10440/', Delimiter='/')
```

Lists the files with anonymous access. Runs on any machine, with no cloud account.

## Data structure

File types in sampled files: PNG

Example file: `10440/Images/snapshot.png`

## Open it

- In a hosted notebook with the data mounted: https://scigantic.com/archive/c527daeb-2232-5559-9348-75b97882c80f
- Full record as JSON (schema card included): https://api.scigantic.com/api/archives/c527daeb-2232-5559-9348-75b97882c80f
- Over MCP: `get_schema_card` with id `c527daeb-2232-5559-9348-75b97882c80f` at https://api.scigantic.com/mcp

## Related topics

- [Benchmark datasets](https://scigantic.com/topics/benchmark)
- [Image segmentation datasets](https://scigantic.com/topics/image-segmentation)
- [PNG datasets](https://scigantic.com/topics/png)
- [Structural Biology datasets](https://scigantic.com/topics/structural-biology)
