CCA based multi-view feature selection for multiomics data integration

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Recent technological advances in high-throughput omics technologies and their applications in genomic medicine have opened up outstanding opportunities for individualized medicine. However, several challenges arise in the integrative analysis of such data including heterogeneity and high dimensionality of the omics data. In this study, we present a novel multi-view feature selection algorithm based on the wellknown canonical correlation analysis (CCA) statistical method for jointly selecting discriminative features from multi-omics data sources (multi-views). Our results demonstrate that models for predicting kidney renal clear cell carcinoma (KIRC) survival using our proposed method for jointly selecting discriminative features from copy number alteration (CNA), gene expression RNA-Seq, and reverse-phase protein arrays (RPPA) views outperform models trained using single-view data as well as three integrated models developed using data fusion approaches including CCA-based feature fusion.

Original languageEnglish (US)
Title of host publication2018 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology, CIBCB 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1-8
Number of pages8
ISBN (Electronic)9781538613993
DOIs
StatePublished - Jul 5 2018
Event2018 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology, CIBCB 2018 - Saint Louis, United States
Duration: May 30 2018Jun 2 2018

Publication series

Name2018 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology, CIBCB 2018

Conference

Conference2018 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology, CIBCB 2018
CountryUnited States
CitySaint Louis
Period5/30/186/2/18

Fingerprint

Data integration
Feature extraction
Kidney
Protein Array Analysis
Precision Medicine
Medicine
Information Storage and Retrieval
medicine
kidneys
Cell Survival
Data fusion
RNA
Technology
Gene Expression
Gene expression
carcinoma
data analysis
Statistical methods
statistical analysis
Cells

All Science Journal Classification (ASJC) codes

  • Agricultural and Biological Sciences (miscellaneous)
  • Artificial Intelligence
  • Computer Science Applications
  • Health Informatics

Cite this

Elmanzalawi, Y. (2018). CCA based multi-view feature selection for multiomics data integration. In 2018 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology, CIBCB 2018 (pp. 1-8). [8404968] (2018 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology, CIBCB 2018). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/CIBCB.2018.8404968
Elmanzalawi, Yasser. / CCA based multi-view feature selection for multiomics data integration. 2018 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology, CIBCB 2018. Institute of Electrical and Electronics Engineers Inc., 2018. pp. 1-8 (2018 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology, CIBCB 2018).
@inproceedings{c1704200f5c14b8ca7946405ce62a404,
title = "CCA based multi-view feature selection for multiomics data integration",
abstract = "Recent technological advances in high-throughput omics technologies and their applications in genomic medicine have opened up outstanding opportunities for individualized medicine. However, several challenges arise in the integrative analysis of such data including heterogeneity and high dimensionality of the omics data. In this study, we present a novel multi-view feature selection algorithm based on the wellknown canonical correlation analysis (CCA) statistical method for jointly selecting discriminative features from multi-omics data sources (multi-views). Our results demonstrate that models for predicting kidney renal clear cell carcinoma (KIRC) survival using our proposed method for jointly selecting discriminative features from copy number alteration (CNA), gene expression RNA-Seq, and reverse-phase protein arrays (RPPA) views outperform models trained using single-view data as well as three integrated models developed using data fusion approaches including CCA-based feature fusion.",
author = "Yasser Elmanzalawi",
year = "2018",
month = "7",
day = "5",
doi = "10.1109/CIBCB.2018.8404968",
language = "English (US)",
series = "2018 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology, CIBCB 2018",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "1--8",
booktitle = "2018 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology, CIBCB 2018",
address = "United States",

}

Elmanzalawi, Y 2018, CCA based multi-view feature selection for multiomics data integration. in 2018 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology, CIBCB 2018., 8404968, 2018 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology, CIBCB 2018, Institute of Electrical and Electronics Engineers Inc., pp. 1-8, 2018 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology, CIBCB 2018, Saint Louis, United States, 5/30/18. https://doi.org/10.1109/CIBCB.2018.8404968

CCA based multi-view feature selection for multiomics data integration. / Elmanzalawi, Yasser.

2018 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology, CIBCB 2018. Institute of Electrical and Electronics Engineers Inc., 2018. p. 1-8 8404968 (2018 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology, CIBCB 2018).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - CCA based multi-view feature selection for multiomics data integration

AU - Elmanzalawi, Yasser

PY - 2018/7/5

Y1 - 2018/7/5

N2 - Recent technological advances in high-throughput omics technologies and their applications in genomic medicine have opened up outstanding opportunities for individualized medicine. However, several challenges arise in the integrative analysis of such data including heterogeneity and high dimensionality of the omics data. In this study, we present a novel multi-view feature selection algorithm based on the wellknown canonical correlation analysis (CCA) statistical method for jointly selecting discriminative features from multi-omics data sources (multi-views). Our results demonstrate that models for predicting kidney renal clear cell carcinoma (KIRC) survival using our proposed method for jointly selecting discriminative features from copy number alteration (CNA), gene expression RNA-Seq, and reverse-phase protein arrays (RPPA) views outperform models trained using single-view data as well as three integrated models developed using data fusion approaches including CCA-based feature fusion.

AB - Recent technological advances in high-throughput omics technologies and their applications in genomic medicine have opened up outstanding opportunities for individualized medicine. However, several challenges arise in the integrative analysis of such data including heterogeneity and high dimensionality of the omics data. In this study, we present a novel multi-view feature selection algorithm based on the wellknown canonical correlation analysis (CCA) statistical method for jointly selecting discriminative features from multi-omics data sources (multi-views). Our results demonstrate that models for predicting kidney renal clear cell carcinoma (KIRC) survival using our proposed method for jointly selecting discriminative features from copy number alteration (CNA), gene expression RNA-Seq, and reverse-phase protein arrays (RPPA) views outperform models trained using single-view data as well as three integrated models developed using data fusion approaches including CCA-based feature fusion.

UR - http://www.scopus.com/inward/record.url?scp=85051017772&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85051017772&partnerID=8YFLogxK

U2 - 10.1109/CIBCB.2018.8404968

DO - 10.1109/CIBCB.2018.8404968

M3 - Conference contribution

T3 - 2018 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology, CIBCB 2018

SP - 1

EP - 8

BT - 2018 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology, CIBCB 2018

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Elmanzalawi Y. CCA based multi-view feature selection for multiomics data integration. In 2018 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology, CIBCB 2018. Institute of Electrical and Electronics Engineers Inc. 2018. p. 1-8. 8404968. (2018 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology, CIBCB 2018). https://doi.org/10.1109/CIBCB.2018.8404968