Cancer subtype prediction from a pathway-level perspective by using a support vector machine based on integrated gene expression and protein network

Fei Hung Hung, Hung Wen Chiu

Research output: Contribution to journalArticle

6 Citations (Scopus)

Abstract

Background and objective Distinguishing cancer subtypes is critical for selecting the appropriate treatment strategy. Bioinformatics approaches have gradually taken the place of clinical observations and pathological experiments. However, these approaches are typically only used in gene expression profiling. Previous studies have primarily focused on the gene level or specific diseases, and thus pathway-level factors have not been considered. Therefore, a computational method that integrates gene expression and pathway is necessary. Methods This study presented an approach to determine potential fragments of activated pathways around protein networks in different stages of disease. We used a scored equation that integrates genomic and proteomic information and determined the intensity of the pathway link change. A support vector machine (SVM) was used to train and test subtype-predicted models. Results The performance of the proposed method was evaluated by calculating prediction accuracy. The average prediction accuracy was 67.64% for three subtypes in tumors of neuroepithelial tissues. The results demonstrate that the proposed method applies fewer features than gene expression methods used to obtain similar results Conclusions This study suggests a method to implement a cancer subtype classifier based on an SVM from a pathway-level perspective.

Original languageEnglish
Pages (from-to)27-34
Number of pages8
JournalComputer Methods and Programs in Biomedicine
Volume141
DOIs
Publication statusPublished - Apr 1 2017

Fingerprint

Gene expression
Support vector machines
Proteins
Gene Expression
Neoplasms
Bioinformatics
Computational methods
Tumors
Classifiers
Genes
Neuroepithelial Neoplasms
Tissue
Gene Expression Profiling
Computational Biology
Proteomics
Support Vector Machine
Experiments

Keywords

  • Cancer subtype
  • Computational method
  • Gene expression
  • Neuroepithelial tumor
  • Protein–protein interaction
  • Signaling pathway

ASJC Scopus subject areas

  • Software
  • Computer Science Applications
  • Health Informatics

Cite this

@article{af3ce5dff82e454dae0247e3c10a8d5c,
title = "Cancer subtype prediction from a pathway-level perspective by using a support vector machine based on integrated gene expression and protein network",
abstract = "Background and objective Distinguishing cancer subtypes is critical for selecting the appropriate treatment strategy. Bioinformatics approaches have gradually taken the place of clinical observations and pathological experiments. However, these approaches are typically only used in gene expression profiling. Previous studies have primarily focused on the gene level or specific diseases, and thus pathway-level factors have not been considered. Therefore, a computational method that integrates gene expression and pathway is necessary. Methods This study presented an approach to determine potential fragments of activated pathways around protein networks in different stages of disease. We used a scored equation that integrates genomic and proteomic information and determined the intensity of the pathway link change. A support vector machine (SVM) was used to train and test subtype-predicted models. Results The performance of the proposed method was evaluated by calculating prediction accuracy. The average prediction accuracy was 67.64{\%} for three subtypes in tumors of neuroepithelial tissues. The results demonstrate that the proposed method applies fewer features than gene expression methods used to obtain similar results Conclusions This study suggests a method to implement a cancer subtype classifier based on an SVM from a pathway-level perspective.",
keywords = "Cancer subtype, Computational method, Gene expression, Neuroepithelial tumor, Protein–protein interaction, Signaling pathway",
author = "Hung, {Fei Hung} and Chiu, {Hung Wen}",
year = "2017",
month = "4",
day = "1",
doi = "10.1016/j.cmpb.2017.01.006",
language = "English",
volume = "141",
pages = "27--34",
journal = "Computer Methods and Programs in Biomedicine",
issn = "0169-2607",
publisher = "Elsevier Ireland Ltd",

}

TY - JOUR

T1 - Cancer subtype prediction from a pathway-level perspective by using a support vector machine based on integrated gene expression and protein network

AU - Hung, Fei Hung

AU - Chiu, Hung Wen

PY - 2017/4/1

Y1 - 2017/4/1

N2 - Background and objective Distinguishing cancer subtypes is critical for selecting the appropriate treatment strategy. Bioinformatics approaches have gradually taken the place of clinical observations and pathological experiments. However, these approaches are typically only used in gene expression profiling. Previous studies have primarily focused on the gene level or specific diseases, and thus pathway-level factors have not been considered. Therefore, a computational method that integrates gene expression and pathway is necessary. Methods This study presented an approach to determine potential fragments of activated pathways around protein networks in different stages of disease. We used a scored equation that integrates genomic and proteomic information and determined the intensity of the pathway link change. A support vector machine (SVM) was used to train and test subtype-predicted models. Results The performance of the proposed method was evaluated by calculating prediction accuracy. The average prediction accuracy was 67.64% for three subtypes in tumors of neuroepithelial tissues. The results demonstrate that the proposed method applies fewer features than gene expression methods used to obtain similar results Conclusions This study suggests a method to implement a cancer subtype classifier based on an SVM from a pathway-level perspective.

AB - Background and objective Distinguishing cancer subtypes is critical for selecting the appropriate treatment strategy. Bioinformatics approaches have gradually taken the place of clinical observations and pathological experiments. However, these approaches are typically only used in gene expression profiling. Previous studies have primarily focused on the gene level or specific diseases, and thus pathway-level factors have not been considered. Therefore, a computational method that integrates gene expression and pathway is necessary. Methods This study presented an approach to determine potential fragments of activated pathways around protein networks in different stages of disease. We used a scored equation that integrates genomic and proteomic information and determined the intensity of the pathway link change. A support vector machine (SVM) was used to train and test subtype-predicted models. Results The performance of the proposed method was evaluated by calculating prediction accuracy. The average prediction accuracy was 67.64% for three subtypes in tumors of neuroepithelial tissues. The results demonstrate that the proposed method applies fewer features than gene expression methods used to obtain similar results Conclusions This study suggests a method to implement a cancer subtype classifier based on an SVM from a pathway-level perspective.

KW - Cancer subtype

KW - Computational method

KW - Gene expression

KW - Neuroepithelial tumor

KW - Protein–protein interaction

KW - Signaling pathway

UR - http://www.scopus.com/inward/record.url?scp=85010636362&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85010636362&partnerID=8YFLogxK

U2 - 10.1016/j.cmpb.2017.01.006

DO - 10.1016/j.cmpb.2017.01.006

M3 - Article

C2 - 28241965

AN - SCOPUS:85010636362

VL - 141

SP - 27

EP - 34

JO - Computer Methods and Programs in Biomedicine

JF - Computer Methods and Programs in Biomedicine

SN - 0169-2607

ER -