CryoETSim general subset - simulated cryo-electron tomograms of cellular molecular crowding

Synthetic cryo-electron tomography dataset of 300 simulated tomograms of generic cellular molecular crowding, generated for the CryoSiam self-supervised representation-learning framework (Stojanovska et al., bioRxiv 2025.11.11.687379). The cryo-TomoSim (CTS) simulator placed 141 PDB-derived macromolecular structures (10 kDa to >4 MDa), membrane vesicles and embedded complexes, cytosolic distractor proteins, actin filaments, and microtubules largest-to-smallest at up to ~80% crowding to emulate in-cell environments. Sample thicknesses span 60-100 nm. Each run provides four reconstructed tomogram variants plus voxel-wise ground-truth coarse and fine semantic masks and per-particle instance masks with coordinate and volume metadata. The full structure list is in the publication's Supplementary Table 2.