The POPSICLE Yeast Segmentation Dataset: consolidated multi-class organelle segmentations for S. pombe cryo-ET tomograms

Deposition Overview

The yeast segmentation dataset of POPSICLE (Particle/Object Picking & Segmentation In CryoET Learning & Evaluation), a benchmark suite released to support reproducible evaluation of machine-learning models for dense voxel-wise compartment segmentation in eukaryotic cellular cryo-ET. This deposition is a consolidated re-release of manually-curated semantic segmentations covering six organelle classes (cytoplasm, nucleus, nuclear envelope, vesicle, membrane-enclosed lumen, mitochondrion) across 19 cryo-electron tomograms of Schizosaccharomyces pombe drawn from CryoET Data Portal datasets 10000 (defocus) and 10001 (Volta phase plate). Annotations were assembled with the copick toolkit at 13.48 Å voxel spacing and serve as a low-data, high-variance organelle-segmentation regime that complements the bacterial deposition (10350) within the POPSICLE benchmark suite.