Structural Class Classification of 3D Protein Structure Based on Multi-View 2D Images

Chendra Hadi Suryanto, Hiroto Saigo, Kazuhiro Fukui

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

Computing similarity or dissimilarity between protein structures is an important task in structural biology. A conventional method to compute protein structure dissimilarity requires structural alignment of the proteins. However, defining one best alignment is difficult, especially when the structures are very different. In this paper, we propose a new similarity measure for protein structure comparisons using a set of multi-view 2D images of 3D protein structures. In this approach, each protein structure is represented by a subspace from the image set. The similarity between two protein structures is then characterized by the canonical angles between the two subspaces. The primary advantage of our method is that precise alignment is not needed. We employed Grassmann Discriminant Analysis (GDA) as the subspace-based learning in the classification framework. We applied our method for the classification problem of seven SCOP structural classes of protein 3D structures. The proposed method outperformed the k-nearest neighbor method (k-NN) based on conventional alignment-based methods CE, FATCAT, and TM-align. Our method was also applied to the classification of SCOP folds of membrane proteins, where the proposed method could recognize the fold HEM-binding four-helical bundle (f.21) much better than TM-Align.

Original languageEnglish
Article number7555308
Pages (from-to)286-299
Number of pages14
JournalIEEE/ACM Transactions on Computational Biology and Bioinformatics
Volume15
Issue number1
DOIs
Publication statusPublished - Jan 1 2018

Fingerprint

Protein Structure
Proteins
Alignment
Subspace
Dissimilarity
Fold
Protein
Nearest Neighbor Method
Membrane Protein
Class
Discriminant Analysis
Similarity Measure
Classification Problems
Biology
Bundle
Discriminant analysis
Membrane Proteins
Angle
Learning
Computing

All Science Journal Classification (ASJC) codes

  • Biotechnology
  • Genetics
  • Applied Mathematics

Cite this

Structural Class Classification of 3D Protein Structure Based on Multi-View 2D Images. / Suryanto, Chendra Hadi; Saigo, Hiroto; Fukui, Kazuhiro.

In: IEEE/ACM Transactions on Computational Biology and Bioinformatics, Vol. 15, No. 1, 7555308, 01.01.2018, p. 286-299.

Research output: Contribution to journalArticle

@article{5af433ad67a2480ab3d705082151dcba,
title = "Structural Class Classification of 3D Protein Structure Based on Multi-View 2D Images",
abstract = "Computing similarity or dissimilarity between protein structures is an important task in structural biology. A conventional method to compute protein structure dissimilarity requires structural alignment of the proteins. However, defining one best alignment is difficult, especially when the structures are very different. In this paper, we propose a new similarity measure for protein structure comparisons using a set of multi-view 2D images of 3D protein structures. In this approach, each protein structure is represented by a subspace from the image set. The similarity between two protein structures is then characterized by the canonical angles between the two subspaces. The primary advantage of our method is that precise alignment is not needed. We employed Grassmann Discriminant Analysis (GDA) as the subspace-based learning in the classification framework. We applied our method for the classification problem of seven SCOP structural classes of protein 3D structures. The proposed method outperformed the k-nearest neighbor method (k-NN) based on conventional alignment-based methods CE, FATCAT, and TM-align. Our method was also applied to the classification of SCOP folds of membrane proteins, where the proposed method could recognize the fold HEM-binding four-helical bundle (f.21) much better than TM-Align.",
author = "Suryanto, {Chendra Hadi} and Hiroto Saigo and Kazuhiro Fukui",
year = "2018",
month = "1",
day = "1",
doi = "10.1109/TCBB.2016.2603987",
language = "English",
volume = "15",
pages = "286--299",
journal = "IEEE/ACM Transactions on Computational Biology and Bioinformatics",
issn = "1545-5963",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "1",

}

TY - JOUR

T1 - Structural Class Classification of 3D Protein Structure Based on Multi-View 2D Images

AU - Suryanto, Chendra Hadi

AU - Saigo, Hiroto

AU - Fukui, Kazuhiro

PY - 2018/1/1

Y1 - 2018/1/1

N2 - Computing similarity or dissimilarity between protein structures is an important task in structural biology. A conventional method to compute protein structure dissimilarity requires structural alignment of the proteins. However, defining one best alignment is difficult, especially when the structures are very different. In this paper, we propose a new similarity measure for protein structure comparisons using a set of multi-view 2D images of 3D protein structures. In this approach, each protein structure is represented by a subspace from the image set. The similarity between two protein structures is then characterized by the canonical angles between the two subspaces. The primary advantage of our method is that precise alignment is not needed. We employed Grassmann Discriminant Analysis (GDA) as the subspace-based learning in the classification framework. We applied our method for the classification problem of seven SCOP structural classes of protein 3D structures. The proposed method outperformed the k-nearest neighbor method (k-NN) based on conventional alignment-based methods CE, FATCAT, and TM-align. Our method was also applied to the classification of SCOP folds of membrane proteins, where the proposed method could recognize the fold HEM-binding four-helical bundle (f.21) much better than TM-Align.

AB - Computing similarity or dissimilarity between protein structures is an important task in structural biology. A conventional method to compute protein structure dissimilarity requires structural alignment of the proteins. However, defining one best alignment is difficult, especially when the structures are very different. In this paper, we propose a new similarity measure for protein structure comparisons using a set of multi-view 2D images of 3D protein structures. In this approach, each protein structure is represented by a subspace from the image set. The similarity between two protein structures is then characterized by the canonical angles between the two subspaces. The primary advantage of our method is that precise alignment is not needed. We employed Grassmann Discriminant Analysis (GDA) as the subspace-based learning in the classification framework. We applied our method for the classification problem of seven SCOP structural classes of protein 3D structures. The proposed method outperformed the k-nearest neighbor method (k-NN) based on conventional alignment-based methods CE, FATCAT, and TM-align. Our method was also applied to the classification of SCOP folds of membrane proteins, where the proposed method could recognize the fold HEM-binding four-helical bundle (f.21) much better than TM-Align.

UR - http://www.scopus.com/inward/record.url?scp=85041929058&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85041929058&partnerID=8YFLogxK

U2 - 10.1109/TCBB.2016.2603987

DO - 10.1109/TCBB.2016.2603987

M3 - Article

C2 - 28113600

AN - SCOPUS:85041929058

VL - 15

SP - 286

EP - 299

JO - IEEE/ACM Transactions on Computational Biology and Bioinformatics

JF - IEEE/ACM Transactions on Computational Biology and Bioinformatics

SN - 1545-5963

IS - 1

M1 - 7555308

ER -