Deep Learning Extends De Novo Protein Modelling Coverage of Genomes Using Iteratively Predicted Structural Constraints

Overview

Journal Nat Commun

Specialty Biology

Date 2019 Sep 6

PMID 31484923

Citations 73

Authors

Joe G Greener

Shaun M Kandathil

David T Jones

Affiliations

Soon will be listed here.

Abstract

The inapplicability of amino acid covariation methods to small protein families has limited their use for structural annotation of whole genomes. Recently, deep learning has shown promise in allowing accurate residue-residue contact prediction even for shallow sequence alignments. Here we introduce DMPfold, which uses deep learning to predict inter-atomic distance bounds, the main chain hydrogen bond network, and torsion angles, which it uses to build models in an iterative fashion. DMPfold produces more accurate models than two popular methods for a test set of CASP12 domains, and works just as well for transmembrane proteins. Applied to all Pfam domains without known structures, confident models for 25% of these so-called dark families were produced in under a week on a small 200 core cluster. DMPfold provides models for 16% of human proteome UniProt entries without structures, generates accurate models with fewer than 100 sequences in some cases, and is freely available.

Citing Articles

The State-of-the-Art Overview to Application of Deep Learning in Accurate Protein Design and Structure Prediction.

Saharkhiz S, Mostafavi M, Birashk A, Karimian S, Khalilollah S, Jaferian S Top Curr Chem (Cham). 2024; 382(3):23.

PMID: 38965117 PMC: 11224075. DOI: 10.1007/s41061-024-00469-6.

Predicting therapeutic and side effects from drug binding affinities to human proteome structures.

Sawada R, Sakajiri Y, Shibata T, Yamanishi Y iScience. 2024; 27(6):110032.

PMID: 38868195 PMC: 11167438. DOI: 10.1016/j.isci.2024.110032.

Hippo and PI5P4K signaling intersect to control the transcriptional activation of YAP.

Palamiuc L, Johnson J, Haratipour Z, Loughran R, Choi W, Arora G Sci Signal. 2024; 17(838):eado6266.

PMID: 38805583 PMC: 11283293. DOI: 10.1126/scisignal.ado6266.

Deep learning for the PSIPRED Protein Analysis Workbench.

Buchan D, Moffat L, Lau A, Kandathil S, Jones D Nucleic Acids Res. 2024; 52(W1):W287-W293.

PMID: 38747351 PMC: 11223827. DOI: 10.1093/nar/gkae328.

Importance of Inter-residue Contacts for Understanding Protein Folding and Unfolding Rates, Remote Homology, and Drug Design.

Harihar B, Saravanan K, Gromiha M, Selvaraj S Mol Biotechnol. 2024; 67(3):862-884.

PMID: 38498284 DOI: 10.1007/s12033-024-01119-4.

References

Monastyrskyy B, DAndrea D, Fidelis K, Tramontano A, Kryshtafovych A . New encouraging developments in contact prediction: Assessment of the CASP11 results. Proteins. 2015; 84 Suppl 1:131-44. PMC: 4834069. DOI: 10.1002/prot.24943. View

Jones D . Protein secondary structure prediction based on position-specific scoring matrices. J Mol Biol. 1999; 292(2):195-202. DOI: 10.1006/jmbi.1999.3091. View

The UniProt Consortium . UniProt: the universal protein knowledgebase. Nucleic Acids Res. 2018; 46(5):2699. PMC: 5861450. DOI: 10.1093/nar/gky092. View

Jones D, Kandathil S . High precision in protein contact prediction using fully convolutional neural networks and minimal sequence features. Bioinformatics. 2018; 34(19):3308-3315. PMC: 6157083. DOI: 10.1093/bioinformatics/bty341. View

Lamb J, Jarmolinska A, Michel M, Menendez-Hurtado D, Sulkowska J, Elofsson A . PconsFam: An Interactive Database of Structure Predictions of Pfam Families. J Mol Biol. 2019; 431(13):2442-2448. DOI: 10.1016/j.jmb.2019.01.047. View

Potter S, Luciani A, Eddy S, Park Y, Lopez R, Finn R . HMMER web server: 2018 update. Nucleic Acids Res. 2018; 46(W1):W200-W204. PMC: 6030962. DOI: 10.1093/nar/gky448. View

de Juan D, Pazos F, Valencia A . Emerging methods in protein co-evolution. Nat Rev Genet. 2013; 14(4):249-61. DOI: 10.1038/nrg3414. View

Hopf T, Colwell L, Sheridan R, Rost B, Sander C, Marks D . Three-dimensional structures of membrane proteins from genomic sequencing. Cell. 2012; 149(7):1607-21. PMC: 3641781. DOI: 10.1016/j.cell.2012.04.012. View

Aszodi A, Gradwell M, Taylor W . Global fold determination from a small number of distance restraints. J Mol Biol. 1995; 251(2):308-26. DOI: 10.1006/jmbi.1995.0436. View

10.

Marks D, Colwell L, Sheridan R, Hopf T, Pagnani A, Zecchina R . Protein 3D structure computed from evolutionary sequence variation. PLoS One. 2011; 6(12):e28766. PMC: 3233603. DOI: 10.1371/journal.pone.0028766. View

11.

Kandathil S, Greener J, Jones D . Prediction of interresidue contacts with DeepMetaPSICOV in CASP13. Proteins. 2019; 87(12):1092-1099. PMC: 6899903. DOI: 10.1002/prot.25779. View

12.

Schaeffer R, Liao Y, Cheng H, Grishin N . ECOD: new developments in the evolutionary classification of domains. Nucleic Acids Res. 2016; 45(D1):D296-D302. PMC: 5210594. DOI: 10.1093/nar/gkw1137. View

13.

Michel M, Menendez Hurtado D, Uziela K, Elofsson A . Large-scale structure prediction by improved contact predictions and model quality assessment. Bioinformatics. 2017; 33(14):i23-i29. PMC: 5870574. DOI: 10.1093/bioinformatics/btx239. View

14.

Fu L, Niu B, Zhu Z, Wu S, Li W . CD-HIT: accelerated for clustering the next-generation sequencing data. Bioinformatics. 2012; 28(23):3150-2. PMC: 3516142. DOI: 10.1093/bioinformatics/bts565. View

15.

El-Gebali S, Mistry J, Bateman A, Eddy S, Luciani A, Potter S . The Pfam protein families database in 2019. Nucleic Acids Res. 2018; 47(D1):D427-D432. PMC: 6324024. DOI: 10.1093/nar/gky995. View

16.

Michel M, Hayat S, Skwark M, Sander C, Marks D, Elofsson A . PconsFold: improved contact predictions improve protein models. Bioinformatics. 2014; 30(17):i482-8. PMC: 4147911. DOI: 10.1093/bioinformatics/btu458. View

17.

Brunger A . Version 1.2 of the Crystallography and NMR system. Nat Protoc. 2007; 2(11):2728-33. DOI: 10.1038/nprot.2007.406. View

18.

Webb B, Sali A . Comparative Protein Structure Modeling Using MODELLER. Curr Protoc Bioinformatics. 2016; 54:5.6.1-5.6.37. PMC: 5031415. DOI: 10.1002/cpbi.3. View

19.

AlQuraishi M . End-to-End Differentiable Learning of Protein Structure. Cell Syst. 2019; 8(4):292-301.e3. PMC: 6513320. DOI: 10.1016/j.cels.2019.03.006. View

20.

Zimmermann L, Stephens A, Nam S, Rau D, Kubler J, Lozajic M . A Completely Reimplemented MPI Bioinformatics Toolkit with a New HHpred Server at its Core. J Mol Biol. 2017; 430(15):2237-2243. DOI: 10.1016/j.jmb.2017.12.007. View