Benchmark RadarPOPSICLE
POPSICLE benchmarks cryoET segmentation and macromolecular localization using data from the CryoET Data Portal. It spans eukaryotic and prokaryotic systems, purified and in situ samples, and covers dense voxel-wise segmentation and sparse localization tasks. Built on the CryoET Data Portal, it can expand with new data.
- Released
- 2026-06-08
- Readiness
- Paper only
- Primary field
- General AI
Why it matters
CryoET lacks standardized, well-annotated benchmarks, limiting robust comparison across methods. POPSICLE provides an open, extensible foundation from a living repository, with baseline experiments showing task-dependent model rankings.
Motivation
Cryo-electron tomography (cryoET) has emerged as a powerful tool in structural and cellular biology by enabling direct visualization of macromolecular structures within intact cells, thereby linking molecular architecture to cellular organization in a native context.
Primary resources
Benchmark Radar records only publicly supported details and links back to primary sources for verification.