| | SLO | ENG | Cookies and privacy

Bigger font | Smaller font
First page > Show document

Show document Help

Title:Naive prediction of protein backbone phi and psi dihedral angles using deep learning
Authors:ID Broz, Matic (Author)
ID Jukič, Marko (Author)
ID Bren, Urban (Author)
Files:.pdf molecules-28-07046.pdf (3,60 MB)
MD5: 9667B704BA6EECBE99A508438ACE2A15
 
URL https://www.mdpi.com/1420-3049/28/20/7046
 
Language:English
Work type:Article
Typology:1.01 - Original Scientific Article
Organization:FKKT - Faculty of Chemistry and Chemical Engineering
Abstract: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.
Keywords:protein structure prediction, backbone dihedral angles, deep neural network, fully connected neural network, FCNN, protein secondary structure prediction
Publication status:Published
Publication version:Version of Record
Submitted for review:01.09.2023
Article acceptance date:09.10.2023
Publication date:12.10.2023
Publisher:MDPI
Year of publishing:2023
Number of pages:19 str.
Numbering:Vol. 28, iss. 20, [article no.] 7046
PID:20.500.12556/DKUM-86438 New window
UDC:54
ISSN on article:1420-3049
COBISS.SI-ID:168255235 New window
DOI:10.3390/molecules28207046 New window
Publication date in DKUM:01.12.2023
Views:421
Downloads:167
Metadata:XML DC-XML DC-RDF
Categories:Misc.
:
BROZ, Matic, JUKIČ, Marko and BREN, Urban, 2023, Naive prediction of protein backbone phi and psi dihedral angles using deep learning. Molecules [online]. 2023. Vol. 28, no. 20,  7046. [Accessed 12 April 2025]. DOI 10.3390/molecules28207046. Retrieved from: https://dk.um.si/IzpisGradiva.php?lang=eng&id=86438
Copy citation
  
Average score:
0.5
1
1.5
2
2.5
3
3.5
4
4.5
5
(0 votes)
Your score:Voting is allowed only for logged in users.
Share:Bookmark and Share



Similar works from other repositories:
  1. Osnovne značilnosti raka jajčnikov
Hover the mouse pointer over a document title to show the abstract or click on the title to get all document metadata.

Record is a part of a journal

Title:Molecules
Shortened title:Molecules
Publisher:MDPI
ISSN:1420-3049
COBISS.SI-ID:18462981 New window

Document is financed by a project

Funder:ARRS - Slovenian Research Agency
Project number:P2-0046-2019
Name:Separacijski procesi in produktna tehnika
Funder:ARRS - Slovenian Research Agency
Project number:P1-0403-2019
Name:Računsko intenzivni kompleksni sistemi
Funder:ARRS - Slovenian Research Agency
Project number:L2-3175-2021
Name:Napredna ekstrakcija in formulacija funkcionalnih taninskih prahranskih dopolnil z blagodejnimi zdravstvenimi učinki
Funder:ARRS - Slovenian Research Agency
Project number:J1-2471-2020
Name:Kemijska karcinogeneza: Mehanistični vpogled
Funder:ARRS - Slovenian Research Agency
Project number:P2-0438-2022
Name:Optični kemijski/bio senzorski sistemi (OPTISENS)
Funder:ARRS - Slovenian Research Agency
Project number:J4-4633-2023
Name:Razumevanje mehanizmov in preprečevanje agregacije biofarmacevtskih proteinov
Funder:ARRS - Slovenian Research Agency
Project number:J1-4398-2022
Name:Kemijska karcinogeneza in nevrodegeneracija: Molekularni mehanizem vpliva mikrovalovnega sevanja
Funder:ARRS - Slovenian Research Agency
Project number:L2-4430-2022
Name:Proizvodnja, izolacija in formulacija zdravju koristnih substanc iz Helichrysum Italicum za uporabo v kozmetični industriji
Funder:ARRS - Slovenian Research Agency
Project number:J3-4498-2022
Name:Multi-omska raziskava signalne poti NFkB pri multipli sklerozi
Funder:ARRS - Slovenian Research Agency
Project number:J7-4638-2022
Name:Načrtovanje selektivnih katalitskih postopkov pretvorbe CO2 v etanol – UliSess
Funder:ARRS - Slovenian Research Agency
Project number:J1-4414-2022
Name:ProBiS-Fold pristop za določanje vezavnih mest za celoten strukturni človeški proteom pri odkrivanju zdravil
Funder:ARRS - Slovenian Research Agency
Project number:I0-E015-2022
Name:Sofinanciranje izvajanja mednarodnega infrastrukturnega projekta BBMRI
Funder:ARRS - Slovenian Research Agency
Project number:J3-4497-2022
Name:Neinvazivni multi-omski biooznačevalci v podtipih imunskih celic za personalizirano zdravljenje otroške astme in molekularni mehanizmi neodzivnosti na inhalacijske kortikosteroide
Funder:ARIS - Slovenian Research and Innovation Agency
Project number:J1-50034
Name:Knjižnica korelacij med vezavnimi vzorci opioidov in njihovimi neželenimi stranskimi učinki
Funder:ARIS - Slovenian Research and Innovation Agency
Project number:J7-50043
Name:Mutacijska platforma koronavirusnih terapevtskih tarč za študij vpliva mutacij na učinkovitost in izbiro zdravil ter načrtovanje novih pan-koronavirusnih zaviralcev

Licences

License:CC BY 4.0, Creative Commons Attribution 4.0 International
Link:http://creativecommons.org/licenses/by/4.0/
Description:This is the standard Creative Commons license that gives others maximum freedom to do what they want with the work as long as they credit the author.

Secondary language

Language:Slovenian
Keywords:globoke nevronske mreže, proteinske strukture, kotne napovedi


Comments

Leave comment

You must log in to leave a comment.

Comments (0)
0 - 0 / 0
 
There are no comments!

Back
Logos of partners University of Maribor University of Ljubljana University of Primorska University of Nova Gorica