GRIP-Tomo 2.0 ML Model Training Data

Contains experimental and mock (simulated) subtomograms used as training/testing data for the GRIP-Tomo ML model as described by the GRIP-Tomo 2.0 manuscript. Each .tar.gz contains a directory with an included README.txt for more detailed information. experimental_data_EMPIAR_10787_ctf-corrected_Topaz-denoised_inverted.tar.gz contains horse-l-apoferritin and noise subtomograms from the EMPIAR 10787 dataset experimental_data_protein_mixture_preprocessed_bin0.5_inverted_2025_02.tar.gz contains β-galactosidase, horse-l-apoferritin and noise subtomograms from the PNNL Protein Mixture (Tilt Series 05) dataset experimental_data_protein_mixture_tomogram_sliding_window.tar.gz contains tomogram regions and subtomograms used with the sliding window script for particle picking from the PNNL Protein Mixture (Tilt Series 05) dataset. mock_data_simulated_EMPIAR_10787_after_calibration.tar.gz contains cisTEM simulated mock subtomograms (horse-l-apoferritin, noise) after calibration with the EMPIAR 10787 dataset. mock_data_simulated_EMPIAR_10787_varying_dosage_thickness.tar.gz contains cisTEM simulated mock subtomograms (horse-l-apoferritin, noise) with varying dosage and thickness (targeting the EMPIAR 10787 dataset). mock_data_simulated_protein_mixture_apoferritin_varying_dosage_thickness_2025_05.tar.gz contains cisTEM simulated mock subtomograms (horse-l-apoferritin) with varying dosage and thickness (targeting the PNNL Protein Mixture (Tilt Series 05) dataset). mock_data_simulated_protein_mixture_before_and_after_calibration.tar.gz contains cisTEM simulated mock subtomograms (β-galactosidase, horse-l-apoferritin and noise) before and after calibration with the PNNL Protein Mixture (Tilt Series 05) dataset.