Estimating gene function with least squares nonnegative matrix factorization.

Guoli Wang, Michael F. Ochs

Research output: Contribution to journalArticle

Abstract

Nonnegative matrix factorization is a machine learning algorithm that has extracted information from data in a number of fields, including imaging and spectral analysis, text mining, and microarray data analysis. One limitation with the method for linking genes through microarray data in order to estimate gene function is the high variance observed in transcription levels between different genes. Least squares nonnegative matrix factorization uses estimates of the uncertainties on the mRNA levels for each gene in each condition, to guide the algorithm to a local minimum in normalized chi2, rather than a Euclidean distance or divergence between the reconstructed data and the data itself. Herein, application of this method to microarray data is demonstrated in order to predict gene function.

Original languageEnglish (US)
Pages (from-to)35-47
Number of pages13
JournalMethods in molecular biology (Clifton, N.J.)
Volume408
StatePublished - 2007
Externally publishedYes

Fingerprint

Least-Squares Analysis
Genes
Data Mining
Microarray Analysis
Uncertainty
Messenger RNA

ASJC Scopus subject areas

  • Molecular Biology
  • Genetics

Cite this

Estimating gene function with least squares nonnegative matrix factorization. / Wang, Guoli; Ochs, Michael F.

In: Methods in molecular biology (Clifton, N.J.), Vol. 408, 2007, p. 35-47.

Research output: Contribution to journalArticle

@article{9fc489599b1b4ff28aff041e8c23d07c,
title = "Estimating gene function with least squares nonnegative matrix factorization.",
abstract = "Nonnegative matrix factorization is a machine learning algorithm that has extracted information from data in a number of fields, including imaging and spectral analysis, text mining, and microarray data analysis. One limitation with the method for linking genes through microarray data in order to estimate gene function is the high variance observed in transcription levels between different genes. Least squares nonnegative matrix factorization uses estimates of the uncertainties on the mRNA levels for each gene in each condition, to guide the algorithm to a local minimum in normalized chi2, rather than a Euclidean distance or divergence between the reconstructed data and the data itself. Herein, application of this method to microarray data is demonstrated in order to predict gene function.",
author = "Guoli Wang and Ochs, {Michael F.}",
year = "2007",
language = "English (US)",
volume = "408",
pages = "35--47",
journal = "Methods in Molecular Biology",
issn = "1064-3745",
publisher = "Humana Press",

}

TY - JOUR

T1 - Estimating gene function with least squares nonnegative matrix factorization.

AU - Wang, Guoli

AU - Ochs, Michael F.

PY - 2007

Y1 - 2007

N2 - Nonnegative matrix factorization is a machine learning algorithm that has extracted information from data in a number of fields, including imaging and spectral analysis, text mining, and microarray data analysis. One limitation with the method for linking genes through microarray data in order to estimate gene function is the high variance observed in transcription levels between different genes. Least squares nonnegative matrix factorization uses estimates of the uncertainties on the mRNA levels for each gene in each condition, to guide the algorithm to a local minimum in normalized chi2, rather than a Euclidean distance or divergence between the reconstructed data and the data itself. Herein, application of this method to microarray data is demonstrated in order to predict gene function.

AB - Nonnegative matrix factorization is a machine learning algorithm that has extracted information from data in a number of fields, including imaging and spectral analysis, text mining, and microarray data analysis. One limitation with the method for linking genes through microarray data in order to estimate gene function is the high variance observed in transcription levels between different genes. Least squares nonnegative matrix factorization uses estimates of the uncertainties on the mRNA levels for each gene in each condition, to guide the algorithm to a local minimum in normalized chi2, rather than a Euclidean distance or divergence between the reconstructed data and the data itself. Herein, application of this method to microarray data is demonstrated in order to predict gene function.

UR - http://www.scopus.com/inward/record.url?scp=41449095706&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=41449095706&partnerID=8YFLogxK

M3 - Article

C2 - 18314576

AN - SCOPUS:41449095706

VL - 408

SP - 35

EP - 47

JO - Methods in Molecular Biology

JF - Methods in Molecular Biology

SN - 1064-3745

ER -