Automated Protein Secondary Structure Assignment from C<i>α</i> Positions Using Neural Networks
The assignment of secondary structure elements in protein conformations is necessary to interpret a protein model that has been established by computational methods. The process essentially involves labeling the amino acid residues with H (Helix), E (Strand), or C (Coil, also known as Loop). When pa...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-06-01
|
Series: | Biomolecules |
Subjects: | |
Online Access: | https://www.mdpi.com/2218-273X/12/6/841 |
_version_ | 1797489545230417920 |
---|---|
author | Mohammad N. Saqib Justyna D. Kryś Dominik Gront |
author_facet | Mohammad N. Saqib Justyna D. Kryś Dominik Gront |
author_sort | Mohammad N. Saqib |
collection | DOAJ |
description | The assignment of secondary structure elements in protein conformations is necessary to interpret a protein model that has been established by computational methods. The process essentially involves labeling the amino acid residues with H (Helix), E (Strand), or C (Coil, also known as Loop). When particular atoms are absent from an input protein structure, the procedure becomes more complicated, especially when only the alpha carbon locations are known. Various techniques have been tested and applied to this problem during the last forty years. The application of machine learning techniques is the most recent trend. This contribution presents the HECA classifier, which uses neural networks to assign protein secondary structure types. The technique exclusively employs C<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mi>α</mi></semantics></math></inline-formula> coordinates. The Keras (TensorFlow) library was used to implement and train the neural network model. The BioShell toolkit was used to calculate the neural network input features from raw coordinates. The study’s findings show that neural network-based methods may be successfully used to take on structure assignment challenges when only C<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mi>α</mi></semantics></math></inline-formula> trace is available. Thanks to the careful selection of input features, our approach’s accuracy (above 97%) exceeded that of the existing methods. |
first_indexed | 2024-03-10T00:18:07Z |
format | Article |
id | doaj.art-97932f3d1b524580a3cd936d8febd2f5 |
institution | Directory Open Access Journal |
issn | 2218-273X |
language | English |
last_indexed | 2024-03-10T00:18:07Z |
publishDate | 2022-06-01 |
publisher | MDPI AG |
record_format | Article |
series | Biomolecules |
spelling | doaj.art-97932f3d1b524580a3cd936d8febd2f52023-11-23T15:47:53ZengMDPI AGBiomolecules2218-273X2022-06-0112684110.3390/biom12060841Automated Protein Secondary Structure Assignment from C<i>α</i> Positions Using Neural NetworksMohammad N. Saqib0Justyna D. Kryś1Dominik Gront2Faculty of Chemistry, Biological and Chemical Research Center, University of Warsaw, Pasteura 1, 02-093 Warsaw, PolandFaculty of Chemistry, Biological and Chemical Research Center, University of Warsaw, Pasteura 1, 02-093 Warsaw, PolandFaculty of Chemistry, Biological and Chemical Research Center, University of Warsaw, Pasteura 1, 02-093 Warsaw, PolandThe assignment of secondary structure elements in protein conformations is necessary to interpret a protein model that has been established by computational methods. The process essentially involves labeling the amino acid residues with H (Helix), E (Strand), or C (Coil, also known as Loop). When particular atoms are absent from an input protein structure, the procedure becomes more complicated, especially when only the alpha carbon locations are known. Various techniques have been tested and applied to this problem during the last forty years. The application of machine learning techniques is the most recent trend. This contribution presents the HECA classifier, which uses neural networks to assign protein secondary structure types. The technique exclusively employs C<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mi>α</mi></semantics></math></inline-formula> coordinates. The Keras (TensorFlow) library was used to implement and train the neural network model. The BioShell toolkit was used to calculate the neural network input features from raw coordinates. The study’s findings show that neural network-based methods may be successfully used to take on structure assignment challenges when only C<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mi>α</mi></semantics></math></inline-formula> trace is available. Thanks to the careful selection of input features, our approach’s accuracy (above 97%) exceeded that of the existing methods.https://www.mdpi.com/2218-273X/12/6/841deep learningmachine learningmulti-class classifierneural networksprotein secondary structureprotein structure prediction |
spellingShingle | Mohammad N. Saqib Justyna D. Kryś Dominik Gront Automated Protein Secondary Structure Assignment from C<i>α</i> Positions Using Neural Networks Biomolecules deep learning machine learning multi-class classifier neural networks protein secondary structure protein structure prediction |
title | Automated Protein Secondary Structure Assignment from C<i>α</i> Positions Using Neural Networks |
title_full | Automated Protein Secondary Structure Assignment from C<i>α</i> Positions Using Neural Networks |
title_fullStr | Automated Protein Secondary Structure Assignment from C<i>α</i> Positions Using Neural Networks |
title_full_unstemmed | Automated Protein Secondary Structure Assignment from C<i>α</i> Positions Using Neural Networks |
title_short | Automated Protein Secondary Structure Assignment from C<i>α</i> Positions Using Neural Networks |
title_sort | automated protein secondary structure assignment from c i α i positions using neural networks |
topic | deep learning machine learning multi-class classifier neural networks protein secondary structure protein structure prediction |
url | https://www.mdpi.com/2218-273X/12/6/841 |
work_keys_str_mv | AT mohammadnsaqib automatedproteinsecondarystructureassignmentfromciaipositionsusingneuralnetworks AT justynadkrys automatedproteinsecondarystructureassignmentfromciaipositionsusingneuralnetworks AT dominikgront automatedproteinsecondarystructureassignmentfromciaipositionsusingneuralnetworks |