Hidden

Cryo-EM Single Particle Analysis — Hidden Tier

(5 scenes)

Fully blind server-side evaluation — no data download.

What you get

No data downloadable. Algorithm runs server-side on hidden measurements.

How to use

Package algorithm as Docker container / Python script. Submit via link.

What to submit

Containerized algorithm accepting y + H, outputting x_hat + corrected spec.

Parameter Specifications

🔒

True spec hidden — blind evaluation, only ranges available.

Parameter Spec Range Unit
defocus_error -70.0 – 230.0 nm
astigmatism -14.0 – 46.0 nm
beam_tilt -0.14 – 0.46 mrad
ice_thickness_variation 45.8 – 63.8 nm

Hidden Tier Leaderboard

# Method Score PSNR SSIM Consistency Trust Source
1 CryoSTAR + gradient 0.736 30.58 0.925 0.8 ✓ Certified Yang et al., Nat. Methods 2024
2 CryoFormer + gradient 0.687 27.49 0.87 0.82 ✓ Certified Gao et al., CVPR 2024
3 DiffusionCryo + gradient 0.667 26.86 0.855 0.78 ✓ Certified Luo et al., arXiv 2024
4 cryoDRGN + gradient 0.645 24.93 0.8 0.88 ✓ Certified Zhong et al., Nat. Methods 2021
5 cryoSPARC + gradient 0.626 24.53 0.787 0.83 ✓ Certified Punjani et al., Nat. Methods 2017
6 CryoGEM + gradient 0.606 23.93 0.766 0.8 ✓ Certified He et al., NeurIPS 2023
7 RELION-3D + gradient 0.540 20.92 0.642 0.87 ✓ Certified Scheres, J. Struct. Biol. 2012
8 IsoNet + gradient 0.453 18.63 0.531 0.77 ✓ Certified Liu et al., Nat. Commun. 2021
9 CTFFIND4 + gradient 0.440 17.93 0.497 0.81 ✓ Certified Rohou & Grigorieff, J. Struct. Biol. 2015

Dataset

Scenes: 5

Scoring Formula

0.4 × PSNR_norm + 0.4 × SSIM + 0.2 × (1 − ‖y − Ĥx̂‖/‖y‖)

PSNR: 40% SSIM: 40% Consistency: 20%
Back to Cryo-EM Single Particle Analysis