ICP

A novel approach to predict prognosis of prostate cancer with inner-class clustering of gene expression data

Hyunjin Kim, Jaegyoon Ahn, Chihyun Park, Youngmi Yoon, Sang Hyun Park

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

Prostate cancer has heterogeneous characteristics. For that reason, even if tumors appear histologically similar to each other, there are many cases in which they are actually different, based on their gene expression levels. A single tumor may have multiple expression levels with both high-risk cancer genes and low-risk cancer genes. We can produce more useful models for stratifying prostate cancers into high-risk cancer and low-risk cancer categories by considering the range in each class through inner-class clustering. In this paper, we attempt to classify cancers into high-risk (aggressive) prostate cancer and low-risk (non-aggressive) prostate cancer using ICP (Inner-class Clustering and Prediction). Our model classified more efficiently than the models of the algorithms used for comparison. After discovering a number of genes linked to prostate cancer from the gene pairs used in our classification, we discovered that the proposed method can be used to find new unknown genes and gene pairs which distinguish between high-risk cancer and low-risk cancer.

Original languageEnglish
Pages (from-to)1363-1373
Number of pages11
JournalComputers in Biology and Medicine
Volume43
Issue number10
DOIs
Publication statusPublished - 2013 Oct 1

Fingerprint

Gene expression
Cluster Analysis
Prostatic Neoplasms
Gene Expression
Genes
Neoplasm Genes
Neoplasms
Tumors

All Science Journal Classification (ASJC) codes

  • Computer Science Applications
  • Health Informatics

Cite this

Kim, Hyunjin ; Ahn, Jaegyoon ; Park, Chihyun ; Yoon, Youngmi ; Park, Sang Hyun. / ICP : A novel approach to predict prognosis of prostate cancer with inner-class clustering of gene expression data. In: Computers in Biology and Medicine. 2013 ; Vol. 43, No. 10. pp. 1363-1373.
@article{0bc03015c2894f94a304b430eec76bf3,
title = "ICP: A novel approach to predict prognosis of prostate cancer with inner-class clustering of gene expression data",
abstract = "Prostate cancer has heterogeneous characteristics. For that reason, even if tumors appear histologically similar to each other, there are many cases in which they are actually different, based on their gene expression levels. A single tumor may have multiple expression levels with both high-risk cancer genes and low-risk cancer genes. We can produce more useful models for stratifying prostate cancers into high-risk cancer and low-risk cancer categories by considering the range in each class through inner-class clustering. In this paper, we attempt to classify cancers into high-risk (aggressive) prostate cancer and low-risk (non-aggressive) prostate cancer using ICP (Inner-class Clustering and Prediction). Our model classified more efficiently than the models of the algorithms used for comparison. After discovering a number of genes linked to prostate cancer from the gene pairs used in our classification, we discovered that the proposed method can be used to find new unknown genes and gene pairs which distinguish between high-risk cancer and low-risk cancer.",
author = "Hyunjin Kim and Jaegyoon Ahn and Chihyun Park and Youngmi Yoon and Park, {Sang Hyun}",
year = "2013",
month = "10",
day = "1",
doi = "10.1016/j.compbiomed.2013.06.014",
language = "English",
volume = "43",
pages = "1363--1373",
journal = "Computers in Biology and Medicine",
issn = "0010-4825",
publisher = "Elsevier Limited",
number = "10",

}

ICP : A novel approach to predict prognosis of prostate cancer with inner-class clustering of gene expression data. / Kim, Hyunjin; Ahn, Jaegyoon; Park, Chihyun; Yoon, Youngmi; Park, Sang Hyun.

In: Computers in Biology and Medicine, Vol. 43, No. 10, 01.10.2013, p. 1363-1373.

Research output: Contribution to journalArticle

TY - JOUR

T1 - ICP

T2 - A novel approach to predict prognosis of prostate cancer with inner-class clustering of gene expression data

AU - Kim, Hyunjin

AU - Ahn, Jaegyoon

AU - Park, Chihyun

AU - Yoon, Youngmi

AU - Park, Sang Hyun

PY - 2013/10/1

Y1 - 2013/10/1

N2 - Prostate cancer has heterogeneous characteristics. For that reason, even if tumors appear histologically similar to each other, there are many cases in which they are actually different, based on their gene expression levels. A single tumor may have multiple expression levels with both high-risk cancer genes and low-risk cancer genes. We can produce more useful models for stratifying prostate cancers into high-risk cancer and low-risk cancer categories by considering the range in each class through inner-class clustering. In this paper, we attempt to classify cancers into high-risk (aggressive) prostate cancer and low-risk (non-aggressive) prostate cancer using ICP (Inner-class Clustering and Prediction). Our model classified more efficiently than the models of the algorithms used for comparison. After discovering a number of genes linked to prostate cancer from the gene pairs used in our classification, we discovered that the proposed method can be used to find new unknown genes and gene pairs which distinguish between high-risk cancer and low-risk cancer.

AB - Prostate cancer has heterogeneous characteristics. For that reason, even if tumors appear histologically similar to each other, there are many cases in which they are actually different, based on their gene expression levels. A single tumor may have multiple expression levels with both high-risk cancer genes and low-risk cancer genes. We can produce more useful models for stratifying prostate cancers into high-risk cancer and low-risk cancer categories by considering the range in each class through inner-class clustering. In this paper, we attempt to classify cancers into high-risk (aggressive) prostate cancer and low-risk (non-aggressive) prostate cancer using ICP (Inner-class Clustering and Prediction). Our model classified more efficiently than the models of the algorithms used for comparison. After discovering a number of genes linked to prostate cancer from the gene pairs used in our classification, we discovered that the proposed method can be used to find new unknown genes and gene pairs which distinguish between high-risk cancer and low-risk cancer.

UR - http://www.scopus.com/inward/record.url?scp=84883648472&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84883648472&partnerID=8YFLogxK

U2 - 10.1016/j.compbiomed.2013.06.014

DO - 10.1016/j.compbiomed.2013.06.014

M3 - Article

VL - 43

SP - 1363

EP - 1373

JO - Computers in Biology and Medicine

JF - Computers in Biology and Medicine

SN - 0010-4825

IS - 10

ER -