Boadu, F., Cao, H. & Cheng, J. Protein sequences and structures are combined with transformers and iso-rimmed graph neural networks to predict protein function. Bioinformatics 39I318 – I325 (2023).
Bai, X.-C., McMullan, G. & Scheres, the way Sh sh cryo-em is revolutionizing structural biology. Trend Biochem. SCI. 4049–57 (2015).
Lawson, CL, etc. emdataresource cryo-em ligand modeling challenge results. nut. method twenty one1340–1348 (2024).
Dhakal, A., Gyawali, R., Wang, L. & Cheng, J. SCI. data 10392 (2023).
Dhakal, A., Gyawali, R., Wang, L. & Cheng, J. Cryotransformer: A transformer model for picking protein particles from Cryo-EM micrographs. Bioinformatics 40Btae109 (2024).
Giri, N., Roy, RS & Cheng, J. Deep learning to reconstruct protein structures from Cryo-EM density maps: Recent advances and future directions. Curr. opinion. struct. Biol. 79102536 (2023).
Emsley, P., Lohkamp, B., Scott, W. G. & Cowtan, K. Coot features and development. Acta Crystallogr. Denomination. D Biol. Christalog log. 66486–501 (2010).
Crawl, Ti Isolde: The physically realistic environment for model building will be low-resolution electron density maps. Acta Crystallogr. Denomination. D:struct. Biol. 74519–530 (2018).
Gao, Y., Thorn, V. & Thorn, A. Structural biology errors are no exception. Acta Crystallogr. Denomination. D structure. Biol. 79206–211 (2023).
Croll, Ti et al. Makes you see invisible enemies. nut. struct. Mol. Biol. 28404–408 (2021).
Zhong, Ed, Bepler, T., Berger, B. & Davis, JH Cryodrgn: Reconstructing non-uniform Cryo-EM structures using neural networks. nut. method 18176–185 (2021).
Langan, R. Etal. cryodrgn-et: Deep reconstruction of a generative network for visualizing dynamic biomolecules within cells. nut. method twenty one1537–1545 (2024).
Levy, A., Wetzstein, G., Martel, J.N., Poitevin, F. & Zhong, E. Amortization inference for uneven reconstruction of Cryo-Em. Adv. Nerve inf. process. syst. 3513038–13049 (2022).
Google Scholar
Pfab, J., Phan, NM&SI, D. Special studies on Deeptracer and COV-related complexes for fast Do novo cryo-em protein structural modeling. Proc. Natl Acad. SCI. united states of america 118E2017525118 (2021).
Ronneberger, O., Fischer, P. &Brox, T. U-Net: A convolutional network for biomedical image segmentation. in Proc. Medical Image Computing and Computer-Assisted Interventions – Miccai 2015: 18th International Conference, Part III Vol. 18, 234–241 (Springer, 2015).
Hoffman, KL & Padberg, M. Etal. Travel salesman issue. regular. Operation. res. manager. SCI. 11573–1578 (2013).
Google Scholar
Jamari, K. Etal. Automatic model construction and protein identification of Cryo-EM maps. Nature 628450–457 (2024).
Rabiner, L. & Juang, B. Introducing the hidden Markov model. IEEE ASSP MAG. 34–16 (1986).
Terashi, G., Wang, X., Prasad, D., Nakamura, T. & Kihara, D. Deepmainmast: An integrated protocol for protein structure modeling in Cryo-EM with deep learning and structural prediction. nut. method twenty one122–131 (2024).
Jumper, J. Etal. Very accurate protein structure prediction with Alphafold. Nature 596583–589 (2021).
Giri, N. & Cheng, J. Modeling of CRYOEM density maps using de novo atomic protein structure 3D trans and HMM. nut. commune. 155511 (2024).
Vaswani, A. Care is required. in Proc. Advances in neural information processing systems Vol. 30 (eds Guyon, I. et al.) 6000–6010 (Curran Associates, 2017).
Lawson, CL, etc. emdatabank unified data resource for 3DEM. Nucleic acid res. 44D396 – D403 (2016).
Zhang, Y. & Skolnick, J. TM-Align: A protein structure alignment algorithm based on TM scores. Nucleic acid res. 332302–2309 (2005).
Chen, C.-Fr, Fan, Q. & Panda, R. Crossvit: Cross-attention multi-scale vision transformer for image classification. in Proc. International Conference on IEEE/CVF Computer Vision 357–366 (IEEE, 2021).
Satorras, VG, Hoogeboom, E. & Welling, M. E(n) Equivariant graph neural network. in Proc. International Conference on Machine Learning 9323–9332 (PMLR, 2021).
Han, J., Rong, Y., Xu, T. & Huang, W. Geometrically Equal Graph Neural Networks: A Study. Preprinted at https://arxiv.org/abs/2202.07230 (2022).
Giri, N., Wang, L. & Cheng, J. Cryo2structdata: A large labelled Cryo-EM density map data set for AI-based modeling of protein structures. SCI. data 11458 (2024).
Terwilliger, TC, Adams, PD, Afonine, PV & Sobolev, ov ov a generates a fully automated method to generate initial models from high-resolution frozen electron microscope maps. nut. method 15905–908 (2018).
Mariani, V., Biasini, M., Barbato, A. & Schwede, T. Lddt: Local superposition scores for comparing protein structures and models using distance difference tests. Bioinformatics 292722–2728 (2013).
Basu, S. &Wallner, B. Dockq: Quality measure of interprotein protein docking model. PLOS 1 11E0161879 (2016).
Pintilie, G. Etal. Measurement of atomic resolution of cryo-em maps Q– Score. nut. method 17328–334 (2020).
Van Heel, M. & Schatz, M. Forhier Shell correlation threshold criteria. J. struct. Biol. 151250–262 (2005).
Yamashita, K., Palmer, CM, Burnley, T. & Murshudov, Gn cryo-em Refining of single particle structures and map calculations using serval cat. Biol. Christalog log. 771282–1291 (2021).
Google Scholar
Allegretti, M., Mills, D.J., McMullan, G., Kühlbrandt, W. & Vonck, J. Atomic Model of F420– Decrease [NiFe] Hydrogenase by electron freeze microscopy using a direct electron detector. Elif 3E01963 (2014).
Bartesaghi, A., Matthies, D., Banerjee, S., Merk, A. & Subramaniam, S. structure Beta-Galactosidase at 3.2 Å resolution obtained by Cryo-Electron microscopy. Proc. Natl Acad. SCI. united states of america 11111709–11714 (2014).
Hattne, J. Etal. Analysis of global and site-specific radiation damage in cryo-em. structure 26759–766 (2018).
Rin, Z. Etal. Prediction of evolutionary scale of atomic-level protein structures using language models. Science 3791123–1130 (2023).
Recursive implementation of Young, It&van Vliet, and LJ Gaussian filters. Signal process. 44139–151 (1995).
Loshchilov, I. Etal. Correcting Adam's regularization of weight loss. Preprinted at https://arxiv.org/abs/1711.05101 (2017).
Smith, Periodic Learning Rate for Training LN Neural Networks. in Proc. 2017 IEEE Winter Computer Vision Application Meeting (WACV) 464–472 (IEEE, 2017).
Gao, Z., Tan, C. &Li, SZ Foldtoken4: Consistency and hierarchical fold language. With preprint biorxiv https://doi.org/10.1101/2024.08.04.606514 (2024).
Ingraham, JB, et al. Illumination of protein space with programmable generative models. Nature 6231070–1078 (2023).
Chomboon, K., Chujai, P., Teerarassamee, P., Kerdprasop, K. & Kerdprasop, N. k– Minimal adjacent algorithm. in Proc. 3rd International Conference on Industrial Application Engineering Vol. 2, p. 4 (Institute of Industrial Applications Engineers, 2015).
Giri, N., Wang, L. & Cheng, J. Cryo2structData: Complete dataset. Harvard Dataverse https://doi.org/10.7910/dvn/fcdg0w (2023).
Giri, N., Wang, L. & Cheng, J. Cryo2structData: Test data set. Harvard Dataverse https://doi.org/10.7910/DVN/2GSSC9 (2023).
Wang, J. Cryofold_source_data.zip. figshare https://doi.org/10.6084/m9.figshare.28530359.v1 (2025).
Wang, J. & Tan, C. Determination of end-to-end Cryo-EM complex structures at high accuracy and ultra-fast. Xenod https://doi.org/10.5281/zenodo.14970359 (2025).
Hodson, Root Mean Square Error (RMSE) or Mean Absolute Error (MAE): Whether to use them. Geosci. Model development. 155481–5487 (2022).
