Min-redundancy and max-relevance multi-view feature selection for predicting ovarian cancer survival using multi-omics data 06 Biological Sciences 0604 Genetics

Yasser Elmanzalawi, Tsung Yu Hsieh, Manu Shivakumar, Dokyoon Kim, Vasant Gajanan Honavar

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

Background: Large-scale collaborative precision medicine initiatives (e.g., The Cancer Genome Atlas (TCGA)) are yielding rich multi-omics data. Integrative analyses of the resulting multi-omics data, such as somatic mutation, copy number alteration (CNA), DNA methylation, miRNA, gene expression, and protein expression, offer tantalizing possibilities for realizing the promise and potential of precision medicine in cancer prevention, diagnosis, and treatment by substantially improving our understanding of underlying mechanisms as well as the discovery of novel biomarkers for different types of cancers. However, such analyses present a number of challenges, including heterogeneity, and high-dimensionality of omics data. Methods: We propose a novel framework for multi-omics data integration using multi-view feature selection. We introduce a novel multi-view feature selection algorithm, MRMR-mv, an adaptation of the well-known Min-Redundancy and Maximum-Relevance (MRMR) single-view feature selection algorithm to the multi-view setting. Results: We report results of experiments using an ovarian cancer multi-omics dataset derived from the TCGA database on the task of predicting ovarian cancer survival. Our results suggest that multi-view models outperform both view-specific models (i.e., models trained and tested using a single type of omics data) and models based on two baseline data fusion methods. Conclusions: Our results demonstrate the potential of multi-view feature selection in integrative analyses and predictive modeling from multi-omics data.

Original languageEnglish (US)
Article number71
JournalBMC Medical Genomics
Volume11
DOIs
StatePublished - Sep 14 2018

Fingerprint

Biological Science Disciplines
Ovarian Neoplasms
Precision Medicine
Atlases
Genome
Neoplasms
DNA Methylation
Tumor Biomarkers
MicroRNAs
Databases
Gene Expression
Mutation
Proteins
Therapeutics

All Science Journal Classification (ASJC) codes

  • Genetics
  • Genetics(clinical)

Cite this

@article{9d7347103140470594183ea619492a92,
title = "Min-redundancy and max-relevance multi-view feature selection for predicting ovarian cancer survival using multi-omics data 06 Biological Sciences 0604 Genetics",
abstract = "Background: Large-scale collaborative precision medicine initiatives (e.g., The Cancer Genome Atlas (TCGA)) are yielding rich multi-omics data. Integrative analyses of the resulting multi-omics data, such as somatic mutation, copy number alteration (CNA), DNA methylation, miRNA, gene expression, and protein expression, offer tantalizing possibilities for realizing the promise and potential of precision medicine in cancer prevention, diagnosis, and treatment by substantially improving our understanding of underlying mechanisms as well as the discovery of novel biomarkers for different types of cancers. However, such analyses present a number of challenges, including heterogeneity, and high-dimensionality of omics data. Methods: We propose a novel framework for multi-omics data integration using multi-view feature selection. We introduce a novel multi-view feature selection algorithm, MRMR-mv, an adaptation of the well-known Min-Redundancy and Maximum-Relevance (MRMR) single-view feature selection algorithm to the multi-view setting. Results: We report results of experiments using an ovarian cancer multi-omics dataset derived from the TCGA database on the task of predicting ovarian cancer survival. Our results suggest that multi-view models outperform both view-specific models (i.e., models trained and tested using a single type of omics data) and models based on two baseline data fusion methods. Conclusions: Our results demonstrate the potential of multi-view feature selection in integrative analyses and predictive modeling from multi-omics data.",
author = "Yasser Elmanzalawi and Hsieh, {Tsung Yu} and Manu Shivakumar and Dokyoon Kim and Honavar, {Vasant Gajanan}",
year = "2018",
month = "9",
day = "14",
doi = "10.1186/s12920-018-0388-0",
language = "English (US)",
volume = "11",
journal = "BMC Medical Genomics",
issn = "1755-8794",
publisher = "BioMed Central",

}

TY - JOUR

T1 - Min-redundancy and max-relevance multi-view feature selection for predicting ovarian cancer survival using multi-omics data 06 Biological Sciences 0604 Genetics

AU - Elmanzalawi, Yasser

AU - Hsieh, Tsung Yu

AU - Shivakumar, Manu

AU - Kim, Dokyoon

AU - Honavar, Vasant Gajanan

PY - 2018/9/14

Y1 - 2018/9/14

N2 - Background: Large-scale collaborative precision medicine initiatives (e.g., The Cancer Genome Atlas (TCGA)) are yielding rich multi-omics data. Integrative analyses of the resulting multi-omics data, such as somatic mutation, copy number alteration (CNA), DNA methylation, miRNA, gene expression, and protein expression, offer tantalizing possibilities for realizing the promise and potential of precision medicine in cancer prevention, diagnosis, and treatment by substantially improving our understanding of underlying mechanisms as well as the discovery of novel biomarkers for different types of cancers. However, such analyses present a number of challenges, including heterogeneity, and high-dimensionality of omics data. Methods: We propose a novel framework for multi-omics data integration using multi-view feature selection. We introduce a novel multi-view feature selection algorithm, MRMR-mv, an adaptation of the well-known Min-Redundancy and Maximum-Relevance (MRMR) single-view feature selection algorithm to the multi-view setting. Results: We report results of experiments using an ovarian cancer multi-omics dataset derived from the TCGA database on the task of predicting ovarian cancer survival. Our results suggest that multi-view models outperform both view-specific models (i.e., models trained and tested using a single type of omics data) and models based on two baseline data fusion methods. Conclusions: Our results demonstrate the potential of multi-view feature selection in integrative analyses and predictive modeling from multi-omics data.

AB - Background: Large-scale collaborative precision medicine initiatives (e.g., The Cancer Genome Atlas (TCGA)) are yielding rich multi-omics data. Integrative analyses of the resulting multi-omics data, such as somatic mutation, copy number alteration (CNA), DNA methylation, miRNA, gene expression, and protein expression, offer tantalizing possibilities for realizing the promise and potential of precision medicine in cancer prevention, diagnosis, and treatment by substantially improving our understanding of underlying mechanisms as well as the discovery of novel biomarkers for different types of cancers. However, such analyses present a number of challenges, including heterogeneity, and high-dimensionality of omics data. Methods: We propose a novel framework for multi-omics data integration using multi-view feature selection. We introduce a novel multi-view feature selection algorithm, MRMR-mv, an adaptation of the well-known Min-Redundancy and Maximum-Relevance (MRMR) single-view feature selection algorithm to the multi-view setting. Results: We report results of experiments using an ovarian cancer multi-omics dataset derived from the TCGA database on the task of predicting ovarian cancer survival. Our results suggest that multi-view models outperform both view-specific models (i.e., models trained and tested using a single type of omics data) and models based on two baseline data fusion methods. Conclusions: Our results demonstrate the potential of multi-view feature selection in integrative analyses and predictive modeling from multi-omics data.

UR - http://www.scopus.com/inward/record.url?scp=85053333410&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85053333410&partnerID=8YFLogxK

U2 - 10.1186/s12920-018-0388-0

DO - 10.1186/s12920-018-0388-0

M3 - Article

C2 - 30255801

AN - SCOPUS:85053333410

VL - 11

JO - BMC Medical Genomics

JF - BMC Medical Genomics

SN - 1755-8794

M1 - 71

ER -