iMotor-CNN

Identifying molecular functions of cytoskeleton motor proteins using 2D convolutional neural network via Chou's 5-step rule

Nguyen Quoc Khanh Le, Edward Kien Yee Yapp, Yu Yen Ou, Hui Yuan Yeh

Research output: Contribution to journalArticle

5 Citations (Scopus)

Abstract

Motor proteins are the driving force behind muscle contraction and are responsible for the active transportation of most proteins and vesicles in the cytoplasm. There are three superfamilies of cytoskeletal motor proteins with various molecular functions and structures: dynein, kinesin, and myosin. The functional loss of a specific motor protein molecular function has linked to a variety of human diseases, e.g., Charcot-Marie-Tooth disease, kidney disease. Therefore, creating a precise model to classify motor proteins is essential for helping biologists understand their molecular functions and design drug targets according to their impact on human diseases. Here we attempt to classify cytoskeleton motor proteins using deep learning, which has been increasingly and widely used to address numerous problems in a variety of fields resulting in state-of-the-art results. Our effective deep convolutional neural network is able to achieve an independent test accuracy of 97.5%, 96.4%, and 96.1% for each superfamily, respectively. Compared to other state-of-the-art methods, our approach showed a significant improvement in performance across a range of evaluation metrics. Through the proposed study, we provide an effective model for classifying motor proteins and a basis for further research that can enhance the performance of protein function classification using deep learning.

Original languageEnglish
Pages (from-to)17-26
Number of pages10
JournalAnalytical Biochemistry
Volume575
DOIs
Publication statusPublished - Jun 15 2019
Externally publishedYes

Fingerprint

Cytoskeleton
Neural networks
Proteins
Molecular Motor Proteins
Learning
Charcot-Marie-Tooth Disease
Dyneins
Kinesin
Cytoskeletal Proteins
Drug Design
Kidney Diseases
Myosins
Muscle Contraction
Molecular Structure
Cytoplasm
Muscle
Research
Pharmaceutical Preparations

Keywords

  • Cytoskeletal filaments
  • Deep learning
  • Dynein and kinesin
  • Myosin light chain
  • Position specific scoring matrix
  • Protein function prediction

ASJC Scopus subject areas

  • Biophysics
  • Biochemistry
  • Molecular Biology
  • Cell Biology

Cite this

iMotor-CNN : Identifying molecular functions of cytoskeleton motor proteins using 2D convolutional neural network via Chou's 5-step rule. / Le, Nguyen Quoc Khanh; Yapp, Edward Kien Yee; Ou, Yu Yen; Yeh, Hui Yuan.

In: Analytical Biochemistry, Vol. 575, 15.06.2019, p. 17-26.

Research output: Contribution to journalArticle

@article{47ab9e9203d14f11a38290c0b7721bf2,
title = "iMotor-CNN: Identifying molecular functions of cytoskeleton motor proteins using 2D convolutional neural network via Chou's 5-step rule",
abstract = "Motor proteins are the driving force behind muscle contraction and are responsible for the active transportation of most proteins and vesicles in the cytoplasm. There are three superfamilies of cytoskeletal motor proteins with various molecular functions and structures: dynein, kinesin, and myosin. The functional loss of a specific motor protein molecular function has linked to a variety of human diseases, e.g., Charcot-Marie-Tooth disease, kidney disease. Therefore, creating a precise model to classify motor proteins is essential for helping biologists understand their molecular functions and design drug targets according to their impact on human diseases. Here we attempt to classify cytoskeleton motor proteins using deep learning, which has been increasingly and widely used to address numerous problems in a variety of fields resulting in state-of-the-art results. Our effective deep convolutional neural network is able to achieve an independent test accuracy of 97.5{\%}, 96.4{\%}, and 96.1{\%} for each superfamily, respectively. Compared to other state-of-the-art methods, our approach showed a significant improvement in performance across a range of evaluation metrics. Through the proposed study, we provide an effective model for classifying motor proteins and a basis for further research that can enhance the performance of protein function classification using deep learning.",
keywords = "Cytoskeletal filaments, Deep learning, Dynein and kinesin, Myosin light chain, Position specific scoring matrix, Protein function prediction",
author = "Le, {Nguyen Quoc Khanh} and Yapp, {Edward Kien Yee} and Ou, {Yu Yen} and Yeh, {Hui Yuan}",
year = "2019",
month = "6",
day = "15",
doi = "10.1016/j.ab.2019.03.017",
language = "English",
volume = "575",
pages = "17--26",
journal = "Analytical Biochemistry",
issn = "0003-2697",
publisher = "Academic Press Inc.",

}

TY - JOUR

T1 - iMotor-CNN

T2 - Identifying molecular functions of cytoskeleton motor proteins using 2D convolutional neural network via Chou's 5-step rule

AU - Le, Nguyen Quoc Khanh

AU - Yapp, Edward Kien Yee

AU - Ou, Yu Yen

AU - Yeh, Hui Yuan

PY - 2019/6/15

Y1 - 2019/6/15

N2 - Motor proteins are the driving force behind muscle contraction and are responsible for the active transportation of most proteins and vesicles in the cytoplasm. There are three superfamilies of cytoskeletal motor proteins with various molecular functions and structures: dynein, kinesin, and myosin. The functional loss of a specific motor protein molecular function has linked to a variety of human diseases, e.g., Charcot-Marie-Tooth disease, kidney disease. Therefore, creating a precise model to classify motor proteins is essential for helping biologists understand their molecular functions and design drug targets according to their impact on human diseases. Here we attempt to classify cytoskeleton motor proteins using deep learning, which has been increasingly and widely used to address numerous problems in a variety of fields resulting in state-of-the-art results. Our effective deep convolutional neural network is able to achieve an independent test accuracy of 97.5%, 96.4%, and 96.1% for each superfamily, respectively. Compared to other state-of-the-art methods, our approach showed a significant improvement in performance across a range of evaluation metrics. Through the proposed study, we provide an effective model for classifying motor proteins and a basis for further research that can enhance the performance of protein function classification using deep learning.

AB - Motor proteins are the driving force behind muscle contraction and are responsible for the active transportation of most proteins and vesicles in the cytoplasm. There are three superfamilies of cytoskeletal motor proteins with various molecular functions and structures: dynein, kinesin, and myosin. The functional loss of a specific motor protein molecular function has linked to a variety of human diseases, e.g., Charcot-Marie-Tooth disease, kidney disease. Therefore, creating a precise model to classify motor proteins is essential for helping biologists understand their molecular functions and design drug targets according to their impact on human diseases. Here we attempt to classify cytoskeleton motor proteins using deep learning, which has been increasingly and widely used to address numerous problems in a variety of fields resulting in state-of-the-art results. Our effective deep convolutional neural network is able to achieve an independent test accuracy of 97.5%, 96.4%, and 96.1% for each superfamily, respectively. Compared to other state-of-the-art methods, our approach showed a significant improvement in performance across a range of evaluation metrics. Through the proposed study, we provide an effective model for classifying motor proteins and a basis for further research that can enhance the performance of protein function classification using deep learning.

KW - Cytoskeletal filaments

KW - Deep learning

KW - Dynein and kinesin

KW - Myosin light chain

KW - Position specific scoring matrix

KW - Protein function prediction

UR - http://www.scopus.com/inward/record.url?scp=85063631665&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85063631665&partnerID=8YFLogxK

U2 - 10.1016/j.ab.2019.03.017

DO - 10.1016/j.ab.2019.03.017

M3 - Article

VL - 575

SP - 17

EP - 26

JO - Analytical Biochemistry

JF - Analytical Biochemistry

SN - 0003-2697

ER -