CryoETSim minimal-bacterium subset - simulated cryo-electron tomograms of bacterial transcription/translation

Synthetic cryo-electron tomography dataset of 50 simulated tomograms representing a minimal-bacterium cellular volume, generated for the CryoSiam self-supervised representation-learning framework (Stojanovska et al., bioRxiv 2025.11.11.687379). The cryo-TomoSim (CTS) simulator was populated with bacterial 70S ribosomes and 50S/30S subunits, RNA polymerase, membrane and receptor complexes, smaller cytosolic distractor proteins, and PolymerCpp wormlike-chain DNA filaments (50-1000 bp, persistence 5-20 bp). Sample thicknesses span 35-100 nm. The content emulates a minimal bacterium; the model trained on this subset is later applied to experimental Mycoplasma pneumoniae tomograms (EMPIAR-10499), though the simulated runs are not modeled as any specific organism. Each run provides four reconstructed tomogram variants and voxel-wise ground-truth semantic masks. The structures used are enumerated in the publication's Supplementary Table 2.