CZII - CryoET Object Identification Challenge - Public Test Dataset

Dataset Overview

This dataset is comprised of movie stacks, tiltseries, alignments, tomograms and hand-curated ground truth annotations for the purpose of training object identification algorithms in the context of the CryoET Object Identification Challenge. The data was acquired on a Krios G4 using a Falcon 4i detector and SelctrisX energy filter. Tomograms were aligned using AreTomo3 v1.0.20, reconstructed using AreTomo3 v2.0.10 and post-processed using different methods. Each run provides denoised and ctf corrected tomograms. The labels were curated as described in the accompanying paper and include point labels for Apo-ferritin, Beta-amylase, Beta-galactosidase, cytosolic ribosomes, thyroglobulin and VLP. Public leaderboard scores on Kaggle were computed based on this dataset.