Protein tertiary structure modeling driven by deep learning and contact distance prediction in CASP13.
contact prediction
deep learning
distance prediction
protein model quality assessment
protein structure prediction
template-based modeling
template-free modeling
Journal
Proteins
ISSN: 1097-0134
Titre abrégé: Proteins
Pays: United States
ID NLM: 8700181
Informations de publication
Date de publication:
12 2019
12 2019
Historique:
received:
16
02
2019
revised:
04
04
2019
accepted:
12
04
2019
pubmed:
16
4
2019
medline:
25
6
2020
entrez:
16
4
2019
Statut:
ppublish
Résumé
Predicting residue-residue distance relationships (eg, contacts) has become the key direction to advance protein structure prediction since 2014 CASP11 experiment, while deep learning has revolutionized the technology for contact and distance distribution prediction since its debut in 2012 CASP10 experiment. During 2018 CASP13 experiment, we enhanced our MULTICOM protein structure prediction system with three major components: contact distance prediction based on deep convolutional neural networks, distance-driven template-free (ab initio) modeling, and protein model ranking empowered by deep learning and contact prediction. Our experiment demonstrates that contact distance prediction and deep learning methods are the key reasons that MULTICOM was ranked 3rd out of all 98 predictors in both template-free and template-based structure modeling in CASP13. Deep convolutional neural network can utilize global information in pairwise residue-residue features such as coevolution scores to substantially improve contact distance prediction, which played a decisive role in correctly folding some free modeling and hard template-based modeling targets. Deep learning also successfully integrated one-dimensional structural features, two-dimensional contact information, and three-dimensional structural quality scores to improve protein model quality assessment, where the contact prediction was demonstrated to consistently enhance ranking of protein models for the first time. The success of MULTICOM system clearly shows that protein contact distance prediction and model selection driven by deep learning holds the key of solving protein structure prediction problem. However, there are still challenges in accurately predicting protein contact distance when there are few homologous sequences, folding proteins from noisy contact distances, and ranking models of hard targets.
Identifiants
pubmed: 30985027
doi: 10.1002/prot.25697
pmc: PMC6800999
mid: NIHMS1526945
doi:
Substances chimiques
Proteins
0
Types de publication
Journal Article
Research Support, N.I.H., Extramural
Research Support, U.S. Gov't, Non-P.H.S.
Langues
eng
Sous-ensembles de citation
IM
Pagination
1165-1178Subventions
Organisme : NIGMS NIH HHS
ID : R01 GM093123
Pays : United States
Informations de copyright
© 2019 The Authors. Proteins: Structure, Function, and Bioinformatics published by Wiley Periodicals, Inc.
Références
Bioinformatics. 2012 Jan 15;28(2):184-90
pubmed: 22101153
Bioinformatics. 2005 Apr 1;21(7):951-60
pubmed: 15531603
Nat Protoc. 2007;2(11):2728-33
pubmed: 18007608
Bioinformatics. 2014 Mar 1;30(5):660-7
pubmed: 24130308
Methods Mol Biol. 2014;1137:1-15
pubmed: 24573470
Proteins. 2015 Aug;83(8):1436-49
pubmed: 25974172
BMC Bioinformatics. 2017 Aug 29;18(1):380
pubmed: 28851269
Bioinformatics. 2008 Nov 15;24(22):2630-1
pubmed: 18845584
Proteins. 2016 Sep;84 Suppl 1:131-44
pubmed: 26474083
Proc Natl Acad Sci U S A. 2011 Dec 6;108(49):E1293-301
pubmed: 22106262
Bioinformatics. 2016 Sep 15;32(18):2791-9
pubmed: 27259540
Proteins. 2016 Sep;84 Suppl 1:51-66
pubmed: 26677002
Sci Rep. 2015 Nov 06;5:16332
pubmed: 26541939
BMC Struct Biol. 2014 Apr 15;14:13
pubmed: 24731387
Sci Rep. 2016 Oct 04;6:33509
pubmed: 27698390
Methods Mol Biol. 2014;1137:17-27
pubmed: 24573471
Protein Sci. 2006 Nov;15(11):2507-24
pubmed: 17075131
Bioinformatics. 2018 Dec 1;34(23):4039-4045
pubmed: 29931279
Bioinformatics. 2019 Aug 15;35(16):2801-2808
pubmed: 30590384
Methods Enzymol. 2011;487:545-74
pubmed: 21187238
Nat Protoc. 2010 Apr;5(4):725-38
pubmed: 20360767
Science. 2017 Jan 20;355(6322):294-298
pubmed: 28104891
Bioinformatics. 2012 Dec 1;28(23):3066-72
pubmed: 23047561
Proteins. 2004 Dec 1;57(4):702-10
pubmed: 15476259
Bioinformatics. 2017 Feb 15;33(4):586-588
pubmed: 28035027
BMC Struct Biol. 2013 Feb 27;13:2
pubmed: 23442819
Nucleic Acids Res. 2011 Jul;39(Web Server issue):W29-37
pubmed: 21593126
Nucleic Acids Res. 2016 Jul 8;44(W1):W406-9
pubmed: 27131371
BMC Bioinformatics. 2018 Jan 25;19(1):22
pubmed: 29370750
Bioinformatics. 2017 Sep 15;33(18):2842-2849
pubmed: 28430949
Proteins. 2019 Dec;87(12):1165-1178
pubmed: 30985027
BMC Bioinformatics. 2016 Dec 7;17(1):517
pubmed: 27923350
Proteins. 2007 May 15;67(3):559-68
pubmed: 17335003
Bioinformatics. 2010 Apr 1;26(7):882-8
pubmed: 20150411
Bioinformatics. 2018 Oct 1;34(19):3308-3315
pubmed: 29718112
Proteins. 2018 Mar;86 Suppl 1:51-66
pubmed: 29071738
PLoS One. 2010 Oct 27;5(10):e15386
pubmed: 21060880
Bioinformatics. 2018 May 1;34(9):1466-1472
pubmed: 29228185
Proteins. 2016 Sep;84 Suppl 1:247-59
pubmed: 26369671
J Mol Biol. 1997 Apr 18;267(5):1268-82
pubmed: 9150411
Bioinformatics. 2000 Dec;16(12):1091-104
pubmed: 11159328
Proc Natl Acad Sci U S A. 2009 Mar 10;106(10):3770-5
pubmed: 19234132
PLoS Comput Biol. 2017 Jan 5;13(1):e1005324
pubmed: 28056090
BMC Bioinformatics. 2016 Dec 5;17(1):495
pubmed: 27919220
Bioinformatics. 2011 Jun 15;27(12):1715-6
pubmed: 21546397
Protein Sci. 2001 Nov;10(11):2354-62
pubmed: 11604541
Bioinformatics. 2003 Feb 12;19(3):429-30
pubmed: 12584135
Bioinformatics. 2010 Jan 15;26(2):182-8
pubmed: 19897565
Proteins. 2018 Mar;86 Suppl 1:97-112
pubmed: 29139163
Bioinformatics. 2014 Nov 1;30(21):3128-30
pubmed: 25064567
BMC Bioinformatics. 2010 Aug 18;11:431
pubmed: 20718988
Nucleic Acids Res. 2014 Apr;42(7):e52
pubmed: 24465004
Biopolymers. 1983 Dec;22(12):2577-637
pubmed: 6667333
Nat Methods. 2011 Dec 25;9(2):173-5
pubmed: 22198341
Bioinformatics. 2013 Nov 1;29(21):2722-8
pubmed: 23986568
BMC Bioinformatics. 2012 Sep 10;13:224
pubmed: 22963006
Bioinformatics. 2014 Sep 15;30(18):2592-7
pubmed: 24860169
Nucleic Acids Res. 1997 Sep 1;25(17):3389-402
pubmed: 9254694
PLoS One. 2011;6(12):e28766
pubmed: 22163331
Bioinformatics. 2015 Jun 15;31(12):i116-23
pubmed: 26072473
J Comput Chem. 2014 Mar 30;35(8):672-81
pubmed: 24523197
Nucleic Acids Res. 2017 Feb 17;45(3):1049-1058
pubmed: 28180292
Proteins. 2016 Sep;84 Suppl 1:4-14
pubmed: 27171127
J Mol Biol. 2003 Feb 7;326(1):317-36
pubmed: 12547212
BMC Bioinformatics. 2014 Mar 26;15:85
pubmed: 24669753
BMC Bioinformatics. 2009 Dec 21;10:436
pubmed: 20025768
Bioinformatics. 2018 Apr 15;34(8):1295-1303
pubmed: 29228193
J Mol Biol. 2008 Feb 8;376(1):288-301
pubmed: 18177896
Bioinformatics. 2019 Aug 1;35(15):2677-2679
pubmed: 30590407
J Mol Biol. 1990 Oct 5;215(3):403-10
pubmed: 2231712
BMC Struct Biol. 2008 Mar 17;8:18
pubmed: 18366648
Proteins. 2008 Aug;72(2):547-56
pubmed: 18247410