Enforcing co-expression in multimodal regression framework

Pascal Zille, Vince Daniel Calhoun, Yu Ping Wang

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

Abstract

We consider the problem of multimodal data integration for the study of complex neurological diseases (e.g. schizophrenia). Among the challenges arising in such situation, estimating the link between genetic and neurological variability within a population sample has been a promising direction. A wide variety of statistical models arose from such applications. For example, Lasso regression and its multitask extension are often used to fit a multivariate linear relationship between given pheno-type(s) and associated observations. Other approaches, such as canonical correlation analysis (CCA), are widely used to extract relationships between sets of variables from different modalities. In this paper, we propose an exploratory multivariate method combining these two methods. More Specifically, we rely on a ’CCA-type’ formulation in order to regularize the classical multimodal Lasso regression problem. The underlying motivation is to extract discriminative variables that display are also co-expressed across modalities. We first evaluate the method on a simulated dataset, and further validate it using Single Nucleotide Polymorphisms (SNP) and functional Magnetic Resonance Imaging (fMRI) data for the study of schizophrenia.

Original languageEnglish (US)
Title of host publicationPACIFIC SYMPOSIUM ON BIOCOMPUTING 2017
PublisherWorld Scientific Publishing Co. Pte. Ltd.
Pages105-116
Number of pages12
Edition212679
ISBN (Print)9789813207813
DOIs
StatePublished - Jan 1 2017
Externally publishedYes
Event22nd Pacific Symposium on Biocomputing, PSB 2017 - Kohala Coast, United States
Duration: Jan 4 2017Jan 8 2017

Other

Other22nd Pacific Symposium on Biocomputing, PSB 2017
CountryUnited States
CityKohala Coast
Period1/4/171/8/17

Fingerprint

Data integration
Nucleotides
Polymorphism
Display devices
Schizophrenia
Statistical Models
Single Nucleotide Polymorphism
Motivation
Magnetic Resonance Imaging
Population
alachlor

Keywords

  • CCA
  • Collaborative regression
  • Multimodal analysis
  • Schizophrenia
  • Sparse models

ASJC Scopus subject areas

  • Biomedical Engineering
  • Computational Theory and Mathematics
  • Medicine(all)

Cite this

Zille, P., Calhoun, V. D., & Wang, Y. P. (2017). Enforcing co-expression in multimodal regression framework. In PACIFIC SYMPOSIUM ON BIOCOMPUTING 2017 (212679 ed., pp. 105-116). World Scientific Publishing Co. Pte. Ltd.. https://doi.org/10.1142/9789813207813_0011

Enforcing co-expression in multimodal regression framework. / Zille, Pascal; Calhoun, Vince Daniel; Wang, Yu Ping.

PACIFIC SYMPOSIUM ON BIOCOMPUTING 2017. 212679. ed. World Scientific Publishing Co. Pte. Ltd., 2017. p. 105-116.

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

Zille, P, Calhoun, VD & Wang, YP 2017, Enforcing co-expression in multimodal regression framework. in PACIFIC SYMPOSIUM ON BIOCOMPUTING 2017. 212679 edn, World Scientific Publishing Co. Pte. Ltd., pp. 105-116, 22nd Pacific Symposium on Biocomputing, PSB 2017, Kohala Coast, United States, 1/4/17. https://doi.org/10.1142/9789813207813_0011
Zille P, Calhoun VD, Wang YP. Enforcing co-expression in multimodal regression framework. In PACIFIC SYMPOSIUM ON BIOCOMPUTING 2017. 212679 ed. World Scientific Publishing Co. Pte. Ltd. 2017. p. 105-116 https://doi.org/10.1142/9789813207813_0011
Zille, Pascal ; Calhoun, Vince Daniel ; Wang, Yu Ping. / Enforcing co-expression in multimodal regression framework. PACIFIC SYMPOSIUM ON BIOCOMPUTING 2017. 212679. ed. World Scientific Publishing Co. Pte. Ltd., 2017. pp. 105-116
@inproceedings{fcd26493fd8040b285cce7407f1618c0,
title = "Enforcing co-expression in multimodal regression framework",
abstract = "We consider the problem of multimodal data integration for the study of complex neurological diseases (e.g. schizophrenia). Among the challenges arising in such situation, estimating the link between genetic and neurological variability within a population sample has been a promising direction. A wide variety of statistical models arose from such applications. For example, Lasso regression and its multitask extension are often used to fit a multivariate linear relationship between given pheno-type(s) and associated observations. Other approaches, such as canonical correlation analysis (CCA), are widely used to extract relationships between sets of variables from different modalities. In this paper, we propose an exploratory multivariate method combining these two methods. More Specifically, we rely on a ’CCA-type’ formulation in order to regularize the classical multimodal Lasso regression problem. The underlying motivation is to extract discriminative variables that display are also co-expressed across modalities. We first evaluate the method on a simulated dataset, and further validate it using Single Nucleotide Polymorphisms (SNP) and functional Magnetic Resonance Imaging (fMRI) data for the study of schizophrenia.",
keywords = "CCA, Collaborative regression, Multimodal analysis, Schizophrenia, Sparse models",
author = "Pascal Zille and Calhoun, {Vince Daniel} and Wang, {Yu Ping}",
year = "2017",
month = "1",
day = "1",
doi = "10.1142/9789813207813_0011",
language = "English (US)",
isbn = "9789813207813",
pages = "105--116",
booktitle = "PACIFIC SYMPOSIUM ON BIOCOMPUTING 2017",
publisher = "World Scientific Publishing Co. Pte. Ltd.",
edition = "212679",

}

TY - GEN

T1 - Enforcing co-expression in multimodal regression framework

AU - Zille, Pascal

AU - Calhoun, Vince Daniel

AU - Wang, Yu Ping

PY - 2017/1/1

Y1 - 2017/1/1

N2 - We consider the problem of multimodal data integration for the study of complex neurological diseases (e.g. schizophrenia). Among the challenges arising in such situation, estimating the link between genetic and neurological variability within a population sample has been a promising direction. A wide variety of statistical models arose from such applications. For example, Lasso regression and its multitask extension are often used to fit a multivariate linear relationship between given pheno-type(s) and associated observations. Other approaches, such as canonical correlation analysis (CCA), are widely used to extract relationships between sets of variables from different modalities. In this paper, we propose an exploratory multivariate method combining these two methods. More Specifically, we rely on a ’CCA-type’ formulation in order to regularize the classical multimodal Lasso regression problem. The underlying motivation is to extract discriminative variables that display are also co-expressed across modalities. We first evaluate the method on a simulated dataset, and further validate it using Single Nucleotide Polymorphisms (SNP) and functional Magnetic Resonance Imaging (fMRI) data for the study of schizophrenia.

AB - We consider the problem of multimodal data integration for the study of complex neurological diseases (e.g. schizophrenia). Among the challenges arising in such situation, estimating the link between genetic and neurological variability within a population sample has been a promising direction. A wide variety of statistical models arose from such applications. For example, Lasso regression and its multitask extension are often used to fit a multivariate linear relationship between given pheno-type(s) and associated observations. Other approaches, such as canonical correlation analysis (CCA), are widely used to extract relationships between sets of variables from different modalities. In this paper, we propose an exploratory multivariate method combining these two methods. More Specifically, we rely on a ’CCA-type’ formulation in order to regularize the classical multimodal Lasso regression problem. The underlying motivation is to extract discriminative variables that display are also co-expressed across modalities. We first evaluate the method on a simulated dataset, and further validate it using Single Nucleotide Polymorphisms (SNP) and functional Magnetic Resonance Imaging (fMRI) data for the study of schizophrenia.

KW - CCA

KW - Collaborative regression

KW - Multimodal analysis

KW - Schizophrenia

KW - Sparse models

UR - http://www.scopus.com/inward/record.url?scp=85024374018&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85024374018&partnerID=8YFLogxK

U2 - 10.1142/9789813207813_0011

DO - 10.1142/9789813207813_0011

M3 - Conference contribution

C2 - 27896966

AN - SCOPUS:85024374018

SN - 9789813207813

SP - 105

EP - 116

BT - PACIFIC SYMPOSIUM ON BIOCOMPUTING 2017

PB - World Scientific Publishing Co. Pte. Ltd.

ER -