Nearest template prediction: A single-sample-based flexible class prediction with confidence assessment

Research output: Contribution to journalArticle

78 Citations (Scopus)

Abstract

Gene-expression signature-based disease classification and clinical outcome prediction has not been widely introduced in clinical medicine as initially expected, mainly due to the lack of extensive validation needed for its clinical deployment. Obstacles include variable measurement in microarray assay, inconsistent assay platform, analytical requirement for comparable pair of training and test datasets, etc. Furthermore, as medical device helping clinical decision making, the prediction needs to be made for each single patient with a measure of its reliability. To address these issues, there is a need for flexible prediction method less sensitive to difference in experimental and analytical conditions, applicable to each single patient, and providing measure of prediction confidence. The nearest template prediction (NTP) method provides a convenient way to make class prediction with assessment of prediction confidence computed in each single patient's geneexpression data using only a list of signature genes and a test dataset. We demonstrate that the method can be flexibly applied to cross-platform, cross-species, and multiclass predictions without any optimization of analysis parameters.

Original languageEnglish (US)
Article numbere15543
JournalPloS one
Volume5
Issue number11
DOIs
StatePublished - Dec 3 2010
Externally publishedYes

Fingerprint

prediction
Clinical Medicine
Transcriptome
sampling
Assays
Equipment and Supplies
medical equipment
Genes
assays
Microarrays
Gene expression
Medicine
decision making
medicine
Datasets
Decision making
methodology
testing
gene expression
genes

ASJC Scopus subject areas

  • Biochemistry, Genetics and Molecular Biology(all)
  • Agricultural and Biological Sciences(all)

Cite this

Nearest template prediction : A single-sample-based flexible class prediction with confidence assessment. / Hoshida, Yujin.

In: PloS one, Vol. 5, No. 11, e15543, 03.12.2010.

Research output: Contribution to journalArticle

@article{a44dfdfdb0144684ba54df1c99c5756e,
title = "Nearest template prediction: A single-sample-based flexible class prediction with confidence assessment",
abstract = "Gene-expression signature-based disease classification and clinical outcome prediction has not been widely introduced in clinical medicine as initially expected, mainly due to the lack of extensive validation needed for its clinical deployment. Obstacles include variable measurement in microarray assay, inconsistent assay platform, analytical requirement for comparable pair of training and test datasets, etc. Furthermore, as medical device helping clinical decision making, the prediction needs to be made for each single patient with a measure of its reliability. To address these issues, there is a need for flexible prediction method less sensitive to difference in experimental and analytical conditions, applicable to each single patient, and providing measure of prediction confidence. The nearest template prediction (NTP) method provides a convenient way to make class prediction with assessment of prediction confidence computed in each single patient's geneexpression data using only a list of signature genes and a test dataset. We demonstrate that the method can be flexibly applied to cross-platform, cross-species, and multiclass predictions without any optimization of analysis parameters.",
author = "Yujin Hoshida",
year = "2010",
month = "12",
day = "3",
doi = "10.1371/journal.pone.0015543",
language = "English (US)",
volume = "5",
journal = "PLoS One",
issn = "1932-6203",
publisher = "Public Library of Science",
number = "11",

}

TY - JOUR

T1 - Nearest template prediction

T2 - A single-sample-based flexible class prediction with confidence assessment

AU - Hoshida, Yujin

PY - 2010/12/3

Y1 - 2010/12/3

N2 - Gene-expression signature-based disease classification and clinical outcome prediction has not been widely introduced in clinical medicine as initially expected, mainly due to the lack of extensive validation needed for its clinical deployment. Obstacles include variable measurement in microarray assay, inconsistent assay platform, analytical requirement for comparable pair of training and test datasets, etc. Furthermore, as medical device helping clinical decision making, the prediction needs to be made for each single patient with a measure of its reliability. To address these issues, there is a need for flexible prediction method less sensitive to difference in experimental and analytical conditions, applicable to each single patient, and providing measure of prediction confidence. The nearest template prediction (NTP) method provides a convenient way to make class prediction with assessment of prediction confidence computed in each single patient's geneexpression data using only a list of signature genes and a test dataset. We demonstrate that the method can be flexibly applied to cross-platform, cross-species, and multiclass predictions without any optimization of analysis parameters.

AB - Gene-expression signature-based disease classification and clinical outcome prediction has not been widely introduced in clinical medicine as initially expected, mainly due to the lack of extensive validation needed for its clinical deployment. Obstacles include variable measurement in microarray assay, inconsistent assay platform, analytical requirement for comparable pair of training and test datasets, etc. Furthermore, as medical device helping clinical decision making, the prediction needs to be made for each single patient with a measure of its reliability. To address these issues, there is a need for flexible prediction method less sensitive to difference in experimental and analytical conditions, applicable to each single patient, and providing measure of prediction confidence. The nearest template prediction (NTP) method provides a convenient way to make class prediction with assessment of prediction confidence computed in each single patient's geneexpression data using only a list of signature genes and a test dataset. We demonstrate that the method can be flexibly applied to cross-platform, cross-species, and multiclass predictions without any optimization of analysis parameters.

UR - http://www.scopus.com/inward/record.url?scp=78649508797&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=78649508797&partnerID=8YFLogxK

U2 - 10.1371/journal.pone.0015543

DO - 10.1371/journal.pone.0015543

M3 - Article

C2 - 21124904

AN - SCOPUS:78649508797

VL - 5

JO - PLoS One

JF - PLoS One

SN - 1932-6203

IS - 11

M1 - e15543

ER -