Prediction of Protein Function from Tertiary Structure of the Active Site in Heme Proteins by Convolutional Neural Network
Structure–function relationships in proteins have been one of the crucial scientific topics in recent research. Heme proteins have diverse and pivotal biological functions. Therefore, clarifying their structure–function correlation is significant to understand their functional mechanism and is infor...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2023-01-01
|
Series: | Biomolecules |
Subjects: | |
Online Access: | https://www.mdpi.com/2218-273X/13/1/137 |
_version_ | 1797445446187089920 |
---|---|
author | Hiroko X. Kondo Hiroyuki Iizuka Gen Masumoto Yuichi Kabaya Yusuke Kanematsu Yu Takano |
author_facet | Hiroko X. Kondo Hiroyuki Iizuka Gen Masumoto Yuichi Kabaya Yusuke Kanematsu Yu Takano |
author_sort | Hiroko X. Kondo |
collection | DOAJ |
description | Structure–function relationships in proteins have been one of the crucial scientific topics in recent research. Heme proteins have diverse and pivotal biological functions. Therefore, clarifying their structure–function correlation is significant to understand their functional mechanism and is informative for various fields of science. In this study, we constructed convolutional neural network models for predicting protein functions from the tertiary structures of heme-binding sites (active sites) of heme proteins to examine the structure–function correlation. As a result, we succeeded in the classification of oxygen-binding protein (OB), oxidoreductase (OR), proteins with both functions (OB–OR), and electron transport protein (ET) with high accuracy. Although the misclassification rate for OR and ET was high, the rates between OB and ET and between OB and OR were almost zero, indicating that the prediction model works well between protein groups with quite different functions. However, predicting the function of proteins modified with amino acid mutation(s) remains a challenge. Our findings indicate a structure–function correlation in the active site of heme proteins. This study is expected to be applied to the prediction of more detailed protein functions such as catalytic reactions. |
first_indexed | 2024-03-09T13:25:56Z |
format | Article |
id | doaj.art-0ed8187b3aa84f30932efb9bd67bf713 |
institution | Directory Open Access Journal |
issn | 2218-273X |
language | English |
last_indexed | 2024-03-09T13:25:56Z |
publishDate | 2023-01-01 |
publisher | MDPI AG |
record_format | Article |
series | Biomolecules |
spelling | doaj.art-0ed8187b3aa84f30932efb9bd67bf7132023-11-30T21:23:17ZengMDPI AGBiomolecules2218-273X2023-01-0113113710.3390/biom13010137Prediction of Protein Function from Tertiary Structure of the Active Site in Heme Proteins by Convolutional Neural NetworkHiroko X. Kondo0Hiroyuki Iizuka1Gen Masumoto2Yuichi Kabaya3Yusuke Kanematsu4Yu Takano5Faculty of Engineering, Kitami Institute of Technology, 165 Koen-cho, Kitami 090-8507, JapanGraduate School of Information Science and Technology, Hokkaido University, Kita 14, Nishi 9, Kitaku, Sapporo 060-0814, JapanInformation Systems Division, RIKEN Information R&D and Strategy Headquarters, 2-1 Hirosawa, Wako 351-0198, JapanFaculty of Engineering, Kitami Institute of Technology, 165 Koen-cho, Kitami 090-8507, JapanGraduate School of Information Sciences, Hiroshima City University, 3-4-1 Ozukahigashi Asaminamiku, Hiroshima 731-3194, JapanGraduate School of Information Sciences, Hiroshima City University, 3-4-1 Ozukahigashi Asaminamiku, Hiroshima 731-3194, JapanStructure–function relationships in proteins have been one of the crucial scientific topics in recent research. Heme proteins have diverse and pivotal biological functions. Therefore, clarifying their structure–function correlation is significant to understand their functional mechanism and is informative for various fields of science. In this study, we constructed convolutional neural network models for predicting protein functions from the tertiary structures of heme-binding sites (active sites) of heme proteins to examine the structure–function correlation. As a result, we succeeded in the classification of oxygen-binding protein (OB), oxidoreductase (OR), proteins with both functions (OB–OR), and electron transport protein (ET) with high accuracy. Although the misclassification rate for OR and ET was high, the rates between OB and ET and between OB and OR were almost zero, indicating that the prediction model works well between protein groups with quite different functions. However, predicting the function of proteins modified with amino acid mutation(s) remains a challenge. Our findings indicate a structure–function correlation in the active site of heme proteins. This study is expected to be applied to the prediction of more detailed protein functions such as catalytic reactions.https://www.mdpi.com/2218-273X/13/1/137structure–function correlationactive site conformationconvolutional neural networkmachine learning |
spellingShingle | Hiroko X. Kondo Hiroyuki Iizuka Gen Masumoto Yuichi Kabaya Yusuke Kanematsu Yu Takano Prediction of Protein Function from Tertiary Structure of the Active Site in Heme Proteins by Convolutional Neural Network Biomolecules structure–function correlation active site conformation convolutional neural network machine learning |
title | Prediction of Protein Function from Tertiary Structure of the Active Site in Heme Proteins by Convolutional Neural Network |
title_full | Prediction of Protein Function from Tertiary Structure of the Active Site in Heme Proteins by Convolutional Neural Network |
title_fullStr | Prediction of Protein Function from Tertiary Structure of the Active Site in Heme Proteins by Convolutional Neural Network |
title_full_unstemmed | Prediction of Protein Function from Tertiary Structure of the Active Site in Heme Proteins by Convolutional Neural Network |
title_short | Prediction of Protein Function from Tertiary Structure of the Active Site in Heme Proteins by Convolutional Neural Network |
title_sort | prediction of protein function from tertiary structure of the active site in heme proteins by convolutional neural network |
topic | structure–function correlation active site conformation convolutional neural network machine learning |
url | https://www.mdpi.com/2218-273X/13/1/137 |
work_keys_str_mv | AT hirokoxkondo predictionofproteinfunctionfromtertiarystructureoftheactivesiteinhemeproteinsbyconvolutionalneuralnetwork AT hiroyukiiizuka predictionofproteinfunctionfromtertiarystructureoftheactivesiteinhemeproteinsbyconvolutionalneuralnetwork AT genmasumoto predictionofproteinfunctionfromtertiarystructureoftheactivesiteinhemeproteinsbyconvolutionalneuralnetwork AT yuichikabaya predictionofproteinfunctionfromtertiarystructureoftheactivesiteinhemeproteinsbyconvolutionalneuralnetwork AT yusukekanematsu predictionofproteinfunctionfromtertiarystructureoftheactivesiteinhemeproteinsbyconvolutionalneuralnetwork AT yutakano predictionofproteinfunctionfromtertiarystructureoftheactivesiteinhemeproteinsbyconvolutionalneuralnetwork |