CZII CryoET Object Identification Challenge: Simulated Training Tomograms (polnet)

Provider
Schwartz, Paraan, Harrington et al. (CZ Imaging Institute)
License
CC0-1.0 (source)
Format
PNG (in sampled files)
Stored at
Amazon S3, s3://cryoet-data-portal-public/10441 (us-west-2)
Access
Free and public. No account with the data provider is needed.
DOI
10.1101/2024.11.04.621686
Category
Structural Biology
Source
https://doi.org/10.1101/2024.11.04.621686

About this dataset

Simulated cryo-electron tilt series, tomograms and ground truth released with the CZ Imaging Institute CryoET Object Identification Challenge. Volumes were generated with polnet (Martinez-Sanchez et al., IEEE TMI 2024), projected with IMOD xyzproj, noised and reconstructed with IMOD tilt, so every particle position and membrane is known exactly. The 27 runs carry point labels and voxel-wise semantic masks for the six challenge complexes (apo-ferritin, beta-amylase, beta-galactosidase, 80S ribosome, thyroglobulin, virus-like particle) plus membranes, matching the classes of the experimental phantom in portal dataset 10440. Used to pretrain 3D U-Net and detection models for cryo-ET particle picking before fine-tuning on real data. 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. 2024 (bioRxiv 2024.11.04.621686) and the polnet paper (doi 10.1109/TMI.2024.3398401).

How to access this dataset in 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='10441/', Delimiter='/')

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

Data structure

File types in sampled files: PNG

Files

Example file: 10441/Images/snapshot.png

Analyze this dataset without downloading it

On Scigantic, CZII CryoET Object Identification Challenge: Simulated Training Tomograms (polnet) opens in a hosted JupyterLab notebook with the data already mounted, so you can read files where they are stored instead of copying them first. Each notebook includes an AI assistant that can see the mounted files and write and run analysis code. Open the dataset page to launch a notebook, or browse the full catalog.

This page is also available as Markdown and as JSON.

Related Structural Biology datasets