Prediction of ATP-binding sites in membrane proteins using a two-dimensional convolutional neural network

Trinh Trung Duong Nguyen, Nguyen Quoc Khanh Le, Rosdyana Mangir Irawan Kusuma, Yu Yen Ou

研究成果: 雜誌貢獻文章

2 引文 (Scopus)

摘要

Membrane proteins, the most important drug targets, account for around 30% of total proteins encoded by the genome of living organisms. An important role of these proteins is to bind adenosine triphosphate (ATP), facilitating crucial biological processes such as metabolism and cell signaling. There are several reports elucidating ATP-binding sites within proteins. However, such studies on membrane proteins are limited. Our prediction tool, DeepATP, combines evolutionary information in the form of Position Specific Scoring Matrix and two-dimensional Convolutional Neural Network to predict ATP-binding sites in membrane proteins with an MCC of 0.89 and an AUC of 99%. Compared to recently published ATP-binding site predictors and classifiers that use traditional machine learning algorithms, our approach performs significantly better. We suggest this method as a reliable tool for biologists for ATP-binding site prediction in membrane proteins.
原文英語
頁(從 - 到)86-93
頁數8
期刊Journal of Molecular Graphics and Modelling
92
DOIs
出版狀態已發佈 - 十一月 1 2019
對外發佈Yes

指紋

adenosine triphosphate
Binding sites
Membrane Proteins
Adenosine Triphosphate
Binding Sites
membranes
proteins
Neural networks
Proteins
Membranes
predictions
Cell signaling
Metabolism
Learning algorithms
Learning systems
machine learning
scoring
genome
Classifiers
Genes

ASJC Scopus subject areas

  • Spectroscopy
  • Physical and Theoretical Chemistry
  • Computer Graphics and Computer-Aided Design
  • Materials Chemistry

引用此文

Prediction of ATP-binding sites in membrane proteins using a two-dimensional convolutional neural network. / Nguyen, Trinh Trung Duong; Le, Nguyen Quoc Khanh; Kusuma, Rosdyana Mangir Irawan; Ou, Yu Yen.

於: Journal of Molecular Graphics and Modelling, 卷 92, 01.11.2019, p. 86-93.

研究成果: 雜誌貢獻文章

@article{4f097fcab8e241cfa7bc57c89978a4f6,
title = "Prediction of ATP-binding sites in membrane proteins using a two-dimensional convolutional neural network",
abstract = "Membrane proteins, the most important drug targets, account for around 30{\%} of total proteins encoded by the genome of living organisms. An important role of these proteins is to bind adenosine triphosphate (ATP), facilitating crucial biological processes such as metabolism and cell signaling. There are several reports elucidating ATP-binding sites within proteins. However, such studies on membrane proteins are limited. Our prediction tool, DeepATP, combines evolutionary information in the form of Position Specific Scoring Matrix and two-dimensional Convolutional Neural Network to predict ATP-binding sites in membrane proteins with an MCC of 0.89 and an AUC of 99{\%}. Compared to recently published ATP-binding site predictors and classifiers that use traditional machine learning algorithms, our approach performs significantly better. We suggest this method as a reliable tool for biologists for ATP-binding site prediction in membrane proteins.",
keywords = "Bioinformatics, Convolutional neural network, Deep learning, Imbalanced data, Membrane protein, Position specific scoring matrix",
author = "Nguyen, {Trinh Trung Duong} and Le, {Nguyen Quoc Khanh} and Kusuma, {Rosdyana Mangir Irawan} and Ou, {Yu Yen}",
year = "2019",
month = "11",
day = "1",
doi = "10.1016/j.jmgm.2019.07.003",
language = "English",
volume = "92",
pages = "86--93",
journal = "Journal of Molecular Graphics and Modelling",
issn = "1093-3263",
publisher = "Elsevier Inc.",

}

TY - JOUR

T1 - Prediction of ATP-binding sites in membrane proteins using a two-dimensional convolutional neural network

AU - Nguyen, Trinh Trung Duong

AU - Le, Nguyen Quoc Khanh

AU - Kusuma, Rosdyana Mangir Irawan

AU - Ou, Yu Yen

PY - 2019/11/1

Y1 - 2019/11/1

N2 - Membrane proteins, the most important drug targets, account for around 30% of total proteins encoded by the genome of living organisms. An important role of these proteins is to bind adenosine triphosphate (ATP), facilitating crucial biological processes such as metabolism and cell signaling. There are several reports elucidating ATP-binding sites within proteins. However, such studies on membrane proteins are limited. Our prediction tool, DeepATP, combines evolutionary information in the form of Position Specific Scoring Matrix and two-dimensional Convolutional Neural Network to predict ATP-binding sites in membrane proteins with an MCC of 0.89 and an AUC of 99%. Compared to recently published ATP-binding site predictors and classifiers that use traditional machine learning algorithms, our approach performs significantly better. We suggest this method as a reliable tool for biologists for ATP-binding site prediction in membrane proteins.

AB - Membrane proteins, the most important drug targets, account for around 30% of total proteins encoded by the genome of living organisms. An important role of these proteins is to bind adenosine triphosphate (ATP), facilitating crucial biological processes such as metabolism and cell signaling. There are several reports elucidating ATP-binding sites within proteins. However, such studies on membrane proteins are limited. Our prediction tool, DeepATP, combines evolutionary information in the form of Position Specific Scoring Matrix and two-dimensional Convolutional Neural Network to predict ATP-binding sites in membrane proteins with an MCC of 0.89 and an AUC of 99%. Compared to recently published ATP-binding site predictors and classifiers that use traditional machine learning algorithms, our approach performs significantly better. We suggest this method as a reliable tool for biologists for ATP-binding site prediction in membrane proteins.

KW - Bioinformatics

KW - Convolutional neural network

KW - Deep learning

KW - Imbalanced data

KW - Membrane protein

KW - Position specific scoring matrix

UR - http://www.scopus.com/inward/record.url?scp=85069720700&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85069720700&partnerID=8YFLogxK

U2 - 10.1016/j.jmgm.2019.07.003

DO - 10.1016/j.jmgm.2019.07.003

M3 - Article

C2 - 31344547

AN - SCOPUS:85069720700

VL - 92

SP - 86

EP - 93

JO - Journal of Molecular Graphics and Modelling

JF - Journal of Molecular Graphics and Modelling

SN - 1093-3263

ER -