Combined analysis of chromosomal instabilities and gene expression for colon cancer progression inference

Claudia Cava, Italo Zoppis, Manuela Gariboldi, Isabella Castiglioni, Giancarlo Mauri, Marco Antoniotti

Research output: Contribution to journalArticle

14 Citations (Scopus)

Abstract

Background: Copy number alterations (CNAs) represent an important component of genetic variations. Such alterations are related with certain type of cancer including those of the pancreas, colon, and breast, among others. CNAs have been used as biomarkers for cancer prognosis in multiple studies, but few works report on the relation of CNAs with the disease progression. Moreover, most studies do not consider the following two important issues. (I) The identification of CNAs in genes which are responsible for expression regulation is fundamental in order to define genetic events leading to malignant transformation and progression. (II) Most real domains are best described by structured data where instances of multiple types are related to each other in complex ways.Results: Our main interest is to check whether the colorectal cancer (CRC) progression inference benefits when considering both (I) the expression levels of genes with CNAs, and (II) relationships (i.e. dissimilarities) between patients due to expression level differences of the altered genes. We first evaluate the accuracy performance of a state-of-the-art inference method (support vector machine) when subjects are represented only through sets of available attribute values (i.e. gene expression level). Then we check whether the inference accuracy improves, when explicitly exploiting the information mentioned above. Our results suggest that the CRC progression inference improves when the combined data (i.e. CNA and expression level) and the considered dissimilarity measures are applied.Conclusions: Through our approach, classification is intuitively appealing and can be conveniently obtained in the resulting dissimilarity spaces. Different public datasets from Gene Expression Omnibus (GEO) were used to validate the results.

Original languageEnglish
Article number2
JournalJournal of Clinical Bioinformatics
Volume4
Issue number1
DOIs
Publication statusPublished - Jan 24 2014

Fingerprint

Chromosomal Instability
Colonic Neoplasms
Colorectal Neoplasms
Gene Expression
Gene Dosage
Tumor Biomarkers
Genes
Disease Progression
Pancreas
Colon
Breast
Neoplasms
Datasets
Support Vector Machine

Keywords

  • Colorectal cancer
  • Copy number alteration
  • Dissimilarity representation
  • Support vector machine

ASJC Scopus subject areas

  • Health Informatics

Cite this

Combined analysis of chromosomal instabilities and gene expression for colon cancer progression inference. / Cava, Claudia; Zoppis, Italo; Gariboldi, Manuela; Castiglioni, Isabella; Mauri, Giancarlo; Antoniotti, Marco.

In: Journal of Clinical Bioinformatics, Vol. 4, No. 1, 2, 24.01.2014.

Research output: Contribution to journalArticle

Cava, Claudia ; Zoppis, Italo ; Gariboldi, Manuela ; Castiglioni, Isabella ; Mauri, Giancarlo ; Antoniotti, Marco. / Combined analysis of chromosomal instabilities and gene expression for colon cancer progression inference. In: Journal of Clinical Bioinformatics. 2014 ; Vol. 4, No. 1.
@article{31f459beaf2745f98e6b9310325006b6,
title = "Combined analysis of chromosomal instabilities and gene expression for colon cancer progression inference",
abstract = "Background: Copy number alterations (CNAs) represent an important component of genetic variations. Such alterations are related with certain type of cancer including those of the pancreas, colon, and breast, among others. CNAs have been used as biomarkers for cancer prognosis in multiple studies, but few works report on the relation of CNAs with the disease progression. Moreover, most studies do not consider the following two important issues. (I) The identification of CNAs in genes which are responsible for expression regulation is fundamental in order to define genetic events leading to malignant transformation and progression. (II) Most real domains are best described by structured data where instances of multiple types are related to each other in complex ways.Results: Our main interest is to check whether the colorectal cancer (CRC) progression inference benefits when considering both (I) the expression levels of genes with CNAs, and (II) relationships (i.e. dissimilarities) between patients due to expression level differences of the altered genes. We first evaluate the accuracy performance of a state-of-the-art inference method (support vector machine) when subjects are represented only through sets of available attribute values (i.e. gene expression level). Then we check whether the inference accuracy improves, when explicitly exploiting the information mentioned above. Our results suggest that the CRC progression inference improves when the combined data (i.e. CNA and expression level) and the considered dissimilarity measures are applied.Conclusions: Through our approach, classification is intuitively appealing and can be conveniently obtained in the resulting dissimilarity spaces. Different public datasets from Gene Expression Omnibus (GEO) were used to validate the results.",
keywords = "Colorectal cancer, Copy number alteration, Dissimilarity representation, Support vector machine",
author = "Claudia Cava and Italo Zoppis and Manuela Gariboldi and Isabella Castiglioni and Giancarlo Mauri and Marco Antoniotti",
year = "2014",
month = "1",
day = "24",
doi = "10.1186/2043-9113-4-2",
language = "English",
volume = "4",
journal = "Journal of Clinical Bioinformatics",
issn = "2043-9113",
publisher = "BioMed Central",
number = "1",

}

TY - JOUR

T1 - Combined analysis of chromosomal instabilities and gene expression for colon cancer progression inference

AU - Cava, Claudia

AU - Zoppis, Italo

AU - Gariboldi, Manuela

AU - Castiglioni, Isabella

AU - Mauri, Giancarlo

AU - Antoniotti, Marco

PY - 2014/1/24

Y1 - 2014/1/24

N2 - Background: Copy number alterations (CNAs) represent an important component of genetic variations. Such alterations are related with certain type of cancer including those of the pancreas, colon, and breast, among others. CNAs have been used as biomarkers for cancer prognosis in multiple studies, but few works report on the relation of CNAs with the disease progression. Moreover, most studies do not consider the following two important issues. (I) The identification of CNAs in genes which are responsible for expression regulation is fundamental in order to define genetic events leading to malignant transformation and progression. (II) Most real domains are best described by structured data where instances of multiple types are related to each other in complex ways.Results: Our main interest is to check whether the colorectal cancer (CRC) progression inference benefits when considering both (I) the expression levels of genes with CNAs, and (II) relationships (i.e. dissimilarities) between patients due to expression level differences of the altered genes. We first evaluate the accuracy performance of a state-of-the-art inference method (support vector machine) when subjects are represented only through sets of available attribute values (i.e. gene expression level). Then we check whether the inference accuracy improves, when explicitly exploiting the information mentioned above. Our results suggest that the CRC progression inference improves when the combined data (i.e. CNA and expression level) and the considered dissimilarity measures are applied.Conclusions: Through our approach, classification is intuitively appealing and can be conveniently obtained in the resulting dissimilarity spaces. Different public datasets from Gene Expression Omnibus (GEO) were used to validate the results.

AB - Background: Copy number alterations (CNAs) represent an important component of genetic variations. Such alterations are related with certain type of cancer including those of the pancreas, colon, and breast, among others. CNAs have been used as biomarkers for cancer prognosis in multiple studies, but few works report on the relation of CNAs with the disease progression. Moreover, most studies do not consider the following two important issues. (I) The identification of CNAs in genes which are responsible for expression regulation is fundamental in order to define genetic events leading to malignant transformation and progression. (II) Most real domains are best described by structured data where instances of multiple types are related to each other in complex ways.Results: Our main interest is to check whether the colorectal cancer (CRC) progression inference benefits when considering both (I) the expression levels of genes with CNAs, and (II) relationships (i.e. dissimilarities) between patients due to expression level differences of the altered genes. We first evaluate the accuracy performance of a state-of-the-art inference method (support vector machine) when subjects are represented only through sets of available attribute values (i.e. gene expression level). Then we check whether the inference accuracy improves, when explicitly exploiting the information mentioned above. Our results suggest that the CRC progression inference improves when the combined data (i.e. CNA and expression level) and the considered dissimilarity measures are applied.Conclusions: Through our approach, classification is intuitively appealing and can be conveniently obtained in the resulting dissimilarity spaces. Different public datasets from Gene Expression Omnibus (GEO) were used to validate the results.

KW - Colorectal cancer

KW - Copy number alteration

KW - Dissimilarity representation

KW - Support vector machine

UR - http://www.scopus.com/inward/record.url?scp=84896375557&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84896375557&partnerID=8YFLogxK

U2 - 10.1186/2043-9113-4-2

DO - 10.1186/2043-9113-4-2

M3 - Article

VL - 4

JO - Journal of Clinical Bioinformatics

JF - Journal of Clinical Bioinformatics

SN - 2043-9113

IS - 1

M1 - 2

ER -