Naive Prediction of Protein Backbone Phi and Psi Dihedral Angles Using Deep Learning.
backbone dihedral angles
deep neural network
fully connected neural network (FCNN)
protein secondary structure prediction
protein structure prediction
ϕ and ψ angle prediction
Journal
Molecules (Basel, Switzerland)
ISSN: 1420-3049
Titre abrégé: Molecules
Pays: Switzerland
ID NLM: 100964009
Informations de publication
Date de publication:
12 Oct 2023
12 Oct 2023
Historique:
received:
01
09
2023
revised:
06
10
2023
accepted:
09
10
2023
medline:
30
10
2023
pubmed:
28
10
2023
entrez:
28
10
2023
Statut:
epublish
Résumé
Protein structure prediction represents a significant challenge in the field of bioinformatics, with the prediction of protein structures using backbone dihedral angles recently achieving significant progress due to the rise of deep neural network research. However, there is a trend in protein structure prediction research to employ increasingly complex neural networks and contributions from multiple models. This study, on the other hand, explores how a single model transparently behaves using sequence data only and what can be expected from the predicted angles. To this end, the current paper presents data acquisition, deep learning model definition, and training toward the final protein backbone angle prediction. The method applies a simple fully connected neural network (FCNN) model that takes only the primary structure of the protein with a sliding window of size 21 as input to predict protein backbone ϕ and ψ dihedral angles. Despite its simplicity, the model shows surprising accuracy for the ϕ angle prediction and somewhat lower accuracy for the ψ angle prediction. Moreover, this study demonstrates that protein secondary structure prediction is also possible with simple neural networks that take in only the protein amino-acid residue sequence, but more complex models are required for higher accuracies.
Identifiants
pubmed: 37894526
pii: molecules28207046
doi: 10.3390/molecules28207046
pmc: PMC10609058
pii:
doi:
Substances chimiques
Proteins
0
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Subventions
Organisme : Slovenian Research Agency
ID : P2-0046
Organisme : Slovenian Research Agency
ID : P1-0403
Organisme : Slovenian Research Agency
ID : L2-3175
Organisme : Slovenian Research Agency
ID : J1-2471
Organisme : Slovenian Research Agency
ID : P2-0438
Organisme : Slovenian Research Agency
ID : J4-4633
Organisme : Slovenian Research Agency
ID : J1-4398
Organisme : Slovenian Research Agency
ID : L2-4430
Organisme : Slovenian Research Agency
ID : J3-4498
Organisme : Slovenian Research Agency
ID : J7-4638
Organisme : Slovenian Research Agency
ID : J1-4414
Organisme : Slovenian Research Agency
ID : I0-E015
Organisme : Slovenian Research Agency
ID : J3-4497
Références
J Mol Biol. 1993 Jul 20;232(2):584-99
pubmed: 8345525
Proteins. 2018 May;86(5):592-598
pubmed: 29492997
Proteins. 2000 Aug 15;40(3):502-11
pubmed: 10861942
Antioxidants (Basel). 2022 Nov 27;11(12):
pubmed: 36552556
Biomolecules. 2022 Aug 26;12(9):
pubmed: 36139023
Sci Rep. 2015 Jun 22;5:11476
pubmed: 26098304
J Chem Inf Model. 2014 Jan 27;54(1):266-77
pubmed: 24364820
Nucleic Acids Res. 1997 Sep 1;25(17):3389-402
pubmed: 9254694
Bioinformatics. 2013 Aug 15;29(16):2056-8
pubmed: 23772049
Bioinformatics. 2003 Aug 12;19(12):1589-91
pubmed: 12912846
Proteins. 2002 May 1;47(2):228-35
pubmed: 11933069
BMC Bioinformatics. 2014;15 Suppl 8:S3
pubmed: 25080939
Proteins. 2021 Dec;89(12):1687-1699
pubmed: 34218458
Proteins. 2021 Feb;89(2):207-217
pubmed: 32893403
Proteins. 2007 Mar 1;66(4):838-45
pubmed: 17177203
Bioinformatics. 2009 Jun 1;25(11):1422-3
pubmed: 19304878
BMC Bioinformatics. 2018 Aug 3;19(1):293
pubmed: 30075707
Bioinformatics. 2019 Jul 15;35(14):2403-2410
pubmed: 30535134
J Mol Graph. 1996 Feb;14(1):33-8, 27-8
pubmed: 8744570
J Chem Inf Model. 2014 Mar 24;54(3):992-1002
pubmed: 24571803
J Mol Biol. 1999 Sep 17;292(2):195-202
pubmed: 10493868
Bioinformatics. 2019 Nov 1;35(22):4862-4865
pubmed: 31116374
BMC Bioinformatics. 2018 May 8;19(Suppl 4):100
pubmed: 29745828
J Am Chem Soc. 2006 Apr 19;128(15):5136-41
pubmed: 16608349
Theor Chem Acc. 2011 Jan;128(1):3-16
pubmed: 21423322
Methods Mol Biol. 2008;413:3-42
pubmed: 18075160
PLoS Biol. 2020 Mar 5;18(3):e3000654
pubmed: 32134919
J Struct Biol. 2001 May-Jun;134(2-3):204-18
pubmed: 11551180
Structure. 2009 Nov 11;17(11):1515-27
pubmed: 19913486
J Comput Chem. 2014 Mar 30;35(8):644-56
pubmed: 24523210
Bioinformatics. 2018 Dec 1;34(23):4039-4045
pubmed: 29931279
J Comput Chem. 2018 Oct 5;39(26):2210-2216
pubmed: 30368831
PLoS One. 2008;3(10):e3400
pubmed: 18923703
Nucleic Acids Res. 2000 Jan 1;28(1):235-42
pubmed: 10592235
Proteomics. 2011 Oct;11(19):3786-92
pubmed: 21805636
BMC Bioinformatics. 2022 Jan 4;23(1):6
pubmed: 34983370
Bioinformatics. 2017 Sep 15;33(18):2842-2849
pubmed: 28430949
Nucleic Acids Res. 2004 Jul 1;32(Web Server issue):W500-2
pubmed: 15215436
J Med Chem. 2021 May 27;64(10):6596-6607
pubmed: 33974430
Proteins. 1999 Jan 1;34(1):82-95
pubmed: 10336385
Proc Natl Acad Sci U S A. 1984 Oct;81(19):6014-8
pubmed: 16593516
Nature. 2021 Aug;596(7873):583-589
pubmed: 34265844
Sci Rep. 2020 Nov 10;10(1):19430
pubmed: 33173130
J Comput Chem. 2014 Oct 30;35(28):2040-6
pubmed: 25212657
PLoS Pathog. 2021 Sep 24;17(9):e1009543
pubmed: 34559844
Sci Rep. 2016 Jan 11;6:18962
pubmed: 26752681
J Chem Inf Model. 2012 Feb 27;52(2):545-56
pubmed: 22224407
Nucleic Acids Res. 2015 Jul 1;43(W1):W389-94
pubmed: 25883141
Nature. 2020 Jan;577(7792):706-710
pubmed: 31942072
Proc Natl Acad Sci U S A. 1951 Apr;37(4):205-11
pubmed: 14816373
J Med Chem. 2012 Jul 26;55(14):6413-26
pubmed: 22731783
Proc Natl Acad Sci U S A. 2012 Jan 3;109(1):107-12
pubmed: 22171006
Biopolymers. 1983 Dec;22(12):2577-637
pubmed: 6667333
Nat Methods. 2011 Dec 25;9(2):173-5
pubmed: 22198341
Proteins. 2019 Jun;87(6):520-527
pubmed: 30785653
Nat Struct Biol. 1995 Jul;2(7):596-603
pubmed: 7664128
Bioinformatics. 2020 Dec 22;36(20):5021-5026
pubmed: 32678893
J Comput Chem. 2012 Jan 30;33(3):259-67
pubmed: 22045506
J Struct Biol. 2017 Jul;199(1):68-75
pubmed: 28461152
J R Soc Interface. 2006 Feb 22;3(6):139-51
pubmed: 16849226
Proteins. 2019 Dec;87(12):1011-1020
pubmed: 31589781