A predictive based regression algorithm for gene network selection

Stéphane Guerrier, Nabil Mili, Roberto Molinari, Samuel Orso, Marco Avella-Medina, Yanyuan Ma

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

Gene selection has become a common task in most gene expression studies. The objective of such research is often to identify the smallest possible set of genes that can still achieve good predictive performance. To do so, many of the recently proposed classification methods require some form of dimension-reduction of the problem which finally provide a single model as an output and, in most cases, rely on the likelihood function in order to achieve variable selection. We propose a new prediction-based objective function that can be tailored to the requirements of practitioners and can be used to assess and interpret a given problem. Based on cross-validation techniques and the idea of importance sampling, our proposal scans low-dimensional models under the assumption of sparsity and, for each of them, estimates their objective function to assess their predictive power in order to select. Two applications on cancer data sets and a simulation study show that the proposal compares favorably with competing alternatives such as, for example, Elastic Net and Support Vector Machine. Indeed, the proposed method not only selects smaller models for better, or at least comparable, classification errors but also provides a set of selected models instead of a single one, allowing to construct a network of possible models for a target prediction accuracy level.

Original languageEnglish (US)
Article number97
JournalFrontiers in Genetics
Volume7
Issue numberJUN
DOIs
StatePublished - Jun 15 2016

Fingerprint

Gene Regulatory Networks
Likelihood Functions
Genes
Gene Expression
Research
Neoplasms
Support Vector Machine
Datasets

All Science Journal Classification (ASJC) codes

  • Molecular Medicine
  • Genetics
  • Genetics(clinical)

Cite this

Guerrier, Stéphane ; Mili, Nabil ; Molinari, Roberto ; Orso, Samuel ; Avella-Medina, Marco ; Ma, Yanyuan. / A predictive based regression algorithm for gene network selection. In: Frontiers in Genetics. 2016 ; Vol. 7, No. JUN.
@article{a65468fc886e41d6a6c488556b5a9a17,
title = "A predictive based regression algorithm for gene network selection",
abstract = "Gene selection has become a common task in most gene expression studies. The objective of such research is often to identify the smallest possible set of genes that can still achieve good predictive performance. To do so, many of the recently proposed classification methods require some form of dimension-reduction of the problem which finally provide a single model as an output and, in most cases, rely on the likelihood function in order to achieve variable selection. We propose a new prediction-based objective function that can be tailored to the requirements of practitioners and can be used to assess and interpret a given problem. Based on cross-validation techniques and the idea of importance sampling, our proposal scans low-dimensional models under the assumption of sparsity and, for each of them, estimates their objective function to assess their predictive power in order to select. Two applications on cancer data sets and a simulation study show that the proposal compares favorably with competing alternatives such as, for example, Elastic Net and Support Vector Machine. Indeed, the proposed method not only selects smaller models for better, or at least comparable, classification errors but also provides a set of selected models instead of a single one, allowing to construct a network of possible models for a target prediction accuracy level.",
author = "St{\'e}phane Guerrier and Nabil Mili and Roberto Molinari and Samuel Orso and Marco Avella-Medina and Yanyuan Ma",
year = "2016",
month = "6",
day = "15",
doi = "10.3389/fgene.2016.00097",
language = "English (US)",
volume = "7",
journal = "Frontiers in Genetics",
issn = "1664-8021",
publisher = "Frontiers Media S. A.",
number = "JUN",

}

A predictive based regression algorithm for gene network selection. / Guerrier, Stéphane; Mili, Nabil; Molinari, Roberto; Orso, Samuel; Avella-Medina, Marco; Ma, Yanyuan.

In: Frontiers in Genetics, Vol. 7, No. JUN, 97, 15.06.2016.

Research output: Contribution to journalArticle

TY - JOUR

T1 - A predictive based regression algorithm for gene network selection

AU - Guerrier, Stéphane

AU - Mili, Nabil

AU - Molinari, Roberto

AU - Orso, Samuel

AU - Avella-Medina, Marco

AU - Ma, Yanyuan

PY - 2016/6/15

Y1 - 2016/6/15

N2 - Gene selection has become a common task in most gene expression studies. The objective of such research is often to identify the smallest possible set of genes that can still achieve good predictive performance. To do so, many of the recently proposed classification methods require some form of dimension-reduction of the problem which finally provide a single model as an output and, in most cases, rely on the likelihood function in order to achieve variable selection. We propose a new prediction-based objective function that can be tailored to the requirements of practitioners and can be used to assess and interpret a given problem. Based on cross-validation techniques and the idea of importance sampling, our proposal scans low-dimensional models under the assumption of sparsity and, for each of them, estimates their objective function to assess their predictive power in order to select. Two applications on cancer data sets and a simulation study show that the proposal compares favorably with competing alternatives such as, for example, Elastic Net and Support Vector Machine. Indeed, the proposed method not only selects smaller models for better, or at least comparable, classification errors but also provides a set of selected models instead of a single one, allowing to construct a network of possible models for a target prediction accuracy level.

AB - Gene selection has become a common task in most gene expression studies. The objective of such research is often to identify the smallest possible set of genes that can still achieve good predictive performance. To do so, many of the recently proposed classification methods require some form of dimension-reduction of the problem which finally provide a single model as an output and, in most cases, rely on the likelihood function in order to achieve variable selection. We propose a new prediction-based objective function that can be tailored to the requirements of practitioners and can be used to assess and interpret a given problem. Based on cross-validation techniques and the idea of importance sampling, our proposal scans low-dimensional models under the assumption of sparsity and, for each of them, estimates their objective function to assess their predictive power in order to select. Two applications on cancer data sets and a simulation study show that the proposal compares favorably with competing alternatives such as, for example, Elastic Net and Support Vector Machine. Indeed, the proposed method not only selects smaller models for better, or at least comparable, classification errors but also provides a set of selected models instead of a single one, allowing to construct a network of possible models for a target prediction accuracy level.

UR - http://www.scopus.com/inward/record.url?scp=84977472940&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84977472940&partnerID=8YFLogxK

U2 - 10.3389/fgene.2016.00097

DO - 10.3389/fgene.2016.00097

M3 - Article

C2 - 27379155

AN - SCOPUS:84977472940

VL - 7

JO - Frontiers in Genetics

JF - Frontiers in Genetics

SN - 1664-8021

IS - JUN

M1 - 97

ER -