ETSAM Dataset - Annotations and Simulated Tomograms

Cryogenic Electron Tomography (cryo-ET) is an emerging experimental tech- nique 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 arti- facts from limited tilt angles, and other noise artifacts, collectively hinder the reliable identification and delineation of these structures. In this study, we intro- duce 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 10 experimental tomograms for which ground-truth annotations are available. It robustly segments cell membranes with high sen- sitivity and precision, achieving a more favorable precision–recall trade-off than other deep learning methods The ETSAM source code is freely available at https://github.com/jianlin-cheng/ETSAM. 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. We provide helper scripts in our GitHub repository to fetch the experimental tomograms.