Automated Model Building and Protein Identification in Cryo-EM Maps

Overview

Journal Nature

Specialty Science

Date 2024 Feb 26

PMID 38408488

Authors

Kiarash Jamali

Lukas Kall

Rui Zhang

Alan Brown

Dari Kimanius

Sjors H W Scheres

Affiliations

Soon will be listed here.

Abstract

Interpreting electron cryo-microscopy (cryo-EM) maps with atomic models requires high levels of expertise and labour-intensive manual intervention in three-dimensional computer graphics programs. Here we present ModelAngelo, a machine-learning approach for automated atomic model building in cryo-EM maps. By combining information from the cryo-EM map with information from protein sequence and structure in a single graph neural network, ModelAngelo builds atomic models for proteins that are of similar quality to those generated by human experts. For nucleotides, ModelAngelo builds backbones with similar accuracy to those built by humans. By using its predicted amino acid probabilities for each residue in hidden Markov model sequence searches, ModelAngelo outperforms human experts in the identification of proteins with unknown sequences. ModelAngelo will therefore remove bottlenecks and increase objectivity in cryo-EM structure determination.

Citing Articles

AlphaFold as a Prior: Experimental Structure Determination Conditioned on a Pretrained Neural Network.

Fadini A, Li M, McCoy A, Terwilliger T, Read R, Hekstra D bioRxiv. 2025; .

PMID: 40027838 PMC: 11870471. DOI: 10.1101/2025.02.18.638828.

High-resolution structures of Myosin-IC reveal a unique actin-binding orientation, ADP release pathway, and power stroke trajectory.

Chavali S, Carman P, Shuman H, Ostap E, Sindelar C Proc Natl Acad Sci U S A. 2025; 122(9):e2415457122.

PMID: 40014570 PMC: 11892617. DOI: 10.1073/pnas.2415457122.

The conserved HIV-1 spacer peptide 2 triggers matrix lattice maturation.

Stacey J, Hrebik D, Nand E, Shetty S, Qu K, Boicu M Nature. 2025; .

PMID: 40011770 DOI: 10.1038/s41586-025-08624-9.

Structural insights into transmembrane helix S0 facilitated RyR1 channel gating by Ca/ATP.

Wei R, Chen Q, Zhang L, Liu C, Liu C, Yin C Nat Commun. 2025; 16(1):1936.

PMID: 39994184 PMC: 11850639. DOI: 10.1038/s41467-025-57074-4.

Short 5' UTRs serve as a marker for viral mRNA translation inhibition by the IFIT2-IFIT3 antiviral complex.

Glasner D, Todd C, Cook B, DUrso A, Khosla S, Estrada E bioRxiv. 2025; .

PMID: 39990370 PMC: 11844544. DOI: 10.1101/2025.02.11.637299.

References

Emsley P, Lohkamp B, Scott W, Cowtan K . Features and development of Coot. Acta Crystallogr D Biol Crystallogr. 2010; 66(Pt 4):486-501. PMC: 2852313. DOI: 10.1107/S0907444910007493. View

Nakane T, Kotecha A, Sente A, McMullan G, Masiulis S, Brown P . Single-particle cryo-EM at atomic resolution. Nature. 2020; 587(7832):152-156. PMC: 7611073. DOI: 10.1038/s41586-020-2829-0. View

Yip K, Fischer N, Paknia E, Chari A, Stark H . Atomic-resolution protein structure determination by cryo-EM. Nature. 2020; 587(7832):157-161. DOI: 10.1038/s41586-020-2833-4. View

Lawson C, Patwardhan A, Baker M, Hryc C, Sanz Garcia E, Hudson B . EMDataBank unified data resource for 3DEM. Nucleic Acids Res. 2015; 44(D1):D396-403. PMC: 4702818. DOI: 10.1093/nar/gkv1126. View

Russo C, Dickerson J, Naydenova K . Cryomicroscopy : what is the smallest molecule that can be directly identified without labels in a cell?. Faraday Discuss. 2022; 240(0):277-302. PMC: 9642008. DOI: 10.1039/d2fd00076h. View

Croll T, Diederichs K, Fischer F, Fyfe C, Gao Y, Horrell S . Making the invisible enemy visible. Nat Struct Mol Biol. 2021; 28(5):404-408. PMC: 8340564. DOI: 10.1038/s41594-021-00593-7. View

Schweighauser M, Arseni D, Bacioglu M, Huang M, Lovestam S, Shi Y . Age-dependent formation of TMEM106B amyloid filaments in human brains. Nature. 2022; 605(7909):310-314. PMC: 9095482. DOI: 10.1038/s41586-022-04650-z. View

Jiang Y, Cao Q, Sawaya M, Abskharon R, Ge P, DeTure M . Amyloid fibrils in FTLD-TDP are composed of TMEM106B and not TDP-43. Nature. 2022; 605(7909):304-309. PMC: 9844993. DOI: 10.1038/s41586-022-04670-9. View

Chang A, Xiang X, Wang J, Lee C, Arakhamia T, Simjanoska M . Homotypic fibrillization of TMEM106B across diverse neurodegenerative diseases. Cell. 2022; 185(8):1346-1355.e15. PMC: 9018563. DOI: 10.1016/j.cell.2022.02.026. View

10.

Gui M, Ma M, Sze-Tu E, Wang X, Koh F, Zhong E . Structures of radial spokes and associated complexes important for ciliary motility. Nat Struct Mol Biol. 2020; 28(1):29-37. PMC: 7855293. DOI: 10.1038/s41594-020-00530-0. View

11.

Gui M, Wang X, Dutcher S, Brown A, Zhang R . Ciliary central apparatus structure reveals mechanisms of microtubule patterning. Nat Struct Mol Biol. 2022; 29(5):483-492. PMC: 9930914. DOI: 10.1038/s41594-022-00770-2. View

12.

Lin Z, Akin H, Rao R, Hie B, Zhu Z, Lu W . Evolutionary-scale prediction of atomic-level protein structure with a language model. Science. 2023; 379(6637):1123-1130. DOI: 10.1126/science.ade2574. View

13.

Jumper J, Evans R, Pritzel A, Green T, Figurnov M, Ronneberger O . Highly accurate protein structure prediction with AlphaFold. Nature. 2021; 596(7873):583-589. PMC: 8371605. DOI: 10.1038/s41586-021-03819-2. View

14.

Varadi M, Anyango S, Deshpande M, Nair S, Natassia C, Yordanova G . AlphaFold Protein Structure Database: massively expanding the structural coverage of protein-sequence space with high-accuracy models. Nucleic Acids Res. 2021; 50(D1):D439-D444. PMC: 8728224. DOI: 10.1093/nar/gkab1061. View

15.

Terashi G, Kihara D . De novo main-chain modeling for EM maps using MAINMAST. Nat Commun. 2018; 9(1):1618. PMC: 5915429. DOI: 10.1038/s41467-018-04053-7. View

16.

Pfab J, Phan N, Si D . DeepTracer for fast de novo cryo-EM protein structure modeling and special studies on CoV-related complexes. Proc Natl Acad Sci U S A. 2020; 118(2). PMC: 7812826. DOI: 10.1073/pnas.2017525118. View

17.

Zhang X, Zhang B, Freddolino L, Freddolino P, Zhang Y . CR-I-TASSER: assemble protein structures from cryo-EM density maps using deep convolutional neural networks. Nat Methods. 2022; 19(2):195-204. PMC: 8852347. DOI: 10.1038/s41592-021-01389-9. View

18.

He J, Lin P, Chen J, Cao H, Huang S . Model building of protein complexes from intermediate-resolution cryo-EM maps with deep learning-guided automatic assembly. Nat Commun. 2022; 13(1):4066. PMC: 9279371. DOI: 10.1038/s41467-022-31748-9. View

19.

Nakamura A, Meng H, Zhao M, Wang F, Hou J, Cao R . Fast and automated protein-DNA/RNA macromolecular complex modeling from cryo-EM maps. Brief Bioinform. 2023; 24(2). PMC: 10399284. DOI: 10.1093/bib/bbac632. View

20.

Chojnowski G, Simpkin A, Leonardo D, Seifert-Davila W, Vivas-Ruiz D, Keegan R . : a neural-network-based approach for identification of unknown proteins in X-ray crystallography and cryo-EM. IUCrJ. 2022; 9(Pt 1):86-97. PMC: 8733886. DOI: 10.1107/S2052252521011088. View