ETSAM Dataset - Annotations and Simulated Tomograms

Cryogenic Electron Tomography (cryo-ET) is an emerging experimental technique to visualize cell structures and macromolecules in their native cellular environment. Accurate segmentation of cell structures in cryo-ET tomograms, such as cell membranes, is crucial to advance our understanding of cellular organization and function. However, several inherent limitations in cryo-ET tomograms, including the very low signal-to-noise ratio, missing wedge artifacts from limited tilt angles, and other noise artifacts, collectively hinder the reliable identification and delineation of these structures. In this study, we introduce ETSAM - a two-stage, SAM2-based fine-tuned AI model - that effectively segments cell membranes in cryo-ET tomograms. It is trained on a diverse dataset comprising 83 experimental tomograms from the CryoET Data Portal (CDP) database and 28 simulated tomograms generated using PolNet. ETSAM achieves state-of-the-art performance on an independent test set comprising 10 simulated tomograms and 15 experimental tomograms for which ground-truth annotations are available. It robustly segments cell membranes with high sensitivity and strong precision, achieving a more favorable precision–recall trade-off than other deep-learning methods. Note: This deposit only contains annotations and simulated tomograms used in the train and test datasets. Corresponding experimental tomograms must be retrieved from the CryoET Data Portal database.