Incorporating deep learning with convolutional neural networks and position specific scoring matrices for identifying electron transport proteins

Nguyen Quoc Khanh Le, Quang Thai Ho, Yu Yen Ou

Research output: Contribution to journalArticle

16 Citations (Scopus)

Abstract

In several years, deep learning is a modern machine learning technique using in a variety of fields with state-of-the-art performance. Therefore, utilization of deep learning to enhance performance is also an important solution for current bioinformatics field. In this study, we try to use deep learning via convolutional neural networks and position specific scoring matrices to identify electron transport proteins, which is an important molecular function in transmembrane proteins. Our deep learning method can approach a precise model for identifying of electron transport proteins with achieved sensitivity of 80.3%, specificity of 94.4%, and accuracy of 92.3%, with MCC of 0.71 for independent dataset. The proposed technique can serve as a powerful tool for identifying electron transport proteins and can help biologists understand the function of the electron transport proteins. Moreover, this study provides a basis for further research that can enrich a field of applying deep learning in bioinformatics.

Original languageEnglish
Pages (from-to)2000-2006
Number of pages7
JournalJournal of Computational Chemistry
Volume38
Issue number23
DOIs
Publication statusPublished - Sep 5 2017
Externally publishedYes

Fingerprint

Electron Transport
Scoring
Carrier Proteins
Neural Networks
Neural networks
Protein
Bioinformatics
Specificity
Learning systems
Machine Learning
Learning
Deep learning
Proteins

Keywords

  • bioinformatics
  • convolutional neural network
  • deep learning
  • electron transport protein
  • position specific scoring matrix

ASJC Scopus subject areas

  • Chemistry(all)
  • Computational Mathematics

Cite this

@article{3df0089464a74c219877b8c9ba29d9df,
title = "Incorporating deep learning with convolutional neural networks and position specific scoring matrices for identifying electron transport proteins",
abstract = "In several years, deep learning is a modern machine learning technique using in a variety of fields with state-of-the-art performance. Therefore, utilization of deep learning to enhance performance is also an important solution for current bioinformatics field. In this study, we try to use deep learning via convolutional neural networks and position specific scoring matrices to identify electron transport proteins, which is an important molecular function in transmembrane proteins. Our deep learning method can approach a precise model for identifying of electron transport proteins with achieved sensitivity of 80.3{\%}, specificity of 94.4{\%}, and accuracy of 92.3{\%}, with MCC of 0.71 for independent dataset. The proposed technique can serve as a powerful tool for identifying electron transport proteins and can help biologists understand the function of the electron transport proteins. Moreover, this study provides a basis for further research that can enrich a field of applying deep learning in bioinformatics.",
keywords = "bioinformatics, convolutional neural network, deep learning, electron transport protein, position specific scoring matrix",
author = "Le, {Nguyen Quoc Khanh} and Ho, {Quang Thai} and Ou, {Yu Yen}",
year = "2017",
month = "9",
day = "5",
doi = "10.1002/jcc.24842",
language = "English",
volume = "38",
pages = "2000--2006",
journal = "Journal of Computational Chemistry",
issn = "0192-8651",
publisher = "John Wiley and Sons Inc.",
number = "23",

}

TY - JOUR

T1 - Incorporating deep learning with convolutional neural networks and position specific scoring matrices for identifying electron transport proteins

AU - Le, Nguyen Quoc Khanh

AU - Ho, Quang Thai

AU - Ou, Yu Yen

PY - 2017/9/5

Y1 - 2017/9/5

N2 - In several years, deep learning is a modern machine learning technique using in a variety of fields with state-of-the-art performance. Therefore, utilization of deep learning to enhance performance is also an important solution for current bioinformatics field. In this study, we try to use deep learning via convolutional neural networks and position specific scoring matrices to identify electron transport proteins, which is an important molecular function in transmembrane proteins. Our deep learning method can approach a precise model for identifying of electron transport proteins with achieved sensitivity of 80.3%, specificity of 94.4%, and accuracy of 92.3%, with MCC of 0.71 for independent dataset. The proposed technique can serve as a powerful tool for identifying electron transport proteins and can help biologists understand the function of the electron transport proteins. Moreover, this study provides a basis for further research that can enrich a field of applying deep learning in bioinformatics.

AB - In several years, deep learning is a modern machine learning technique using in a variety of fields with state-of-the-art performance. Therefore, utilization of deep learning to enhance performance is also an important solution for current bioinformatics field. In this study, we try to use deep learning via convolutional neural networks and position specific scoring matrices to identify electron transport proteins, which is an important molecular function in transmembrane proteins. Our deep learning method can approach a precise model for identifying of electron transport proteins with achieved sensitivity of 80.3%, specificity of 94.4%, and accuracy of 92.3%, with MCC of 0.71 for independent dataset. The proposed technique can serve as a powerful tool for identifying electron transport proteins and can help biologists understand the function of the electron transport proteins. Moreover, this study provides a basis for further research that can enrich a field of applying deep learning in bioinformatics.

KW - bioinformatics

KW - convolutional neural network

KW - deep learning

KW - electron transport protein

KW - position specific scoring matrix

UR - http://www.scopus.com/inward/record.url?scp=85021306883&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85021306883&partnerID=8YFLogxK

U2 - 10.1002/jcc.24842

DO - 10.1002/jcc.24842

M3 - Article

VL - 38

SP - 2000

EP - 2006

JO - Journal of Computational Chemistry

JF - Journal of Computational Chemistry

SN - 0192-8651

IS - 23

ER -