Towards mechanism classifiers

expression-anchored Gene Ontology signature predicts clinical outcome in lung adenocarcinoma patients.

Xinan Yang, Haiquan Li, Kelly Regan, Jianrong Li, Yong Huang, Yves A Lussier

Research output: Contribution to journalArticle

6 Citations (Scopus)

Abstract

We aim to provide clinically applicable, reproducible, mechanistic interpretations of gene expression changes that lack in gene overlap among predictive gene-signatures. Using a method we recently developed, Functional Analysis of Individual Microarray Expression (FAIME), we provide evidence that Gene Ontology-anchored signatures (GO-signatures) show reliable prognosis in lung cancer. In order to demonstrate the biological congruence and reproducibility of FAIME-derived mechanism classifiers, we chose a disease where gene expression classifiers signatures alone had failed to significantly stratify a larger collection of samples and that exhibited poor or no genetic overlap. For each patient in the two lung adenocarcinoma studies, personalized FAIME-profiles of GO biological processes are generated from genome-wide expression profiles. For both training studies, GO-signatures significantly associated to patient mortality were identified (Prediction Analysis for Microarrays; three-fold cross-validation). These two GO-signatures could effectively stratify patients from an independent validation cohort into sub-groups that show significant differences in disease-free survival (log-rank test P=0.019; P=0.001). Importantly, significant mechanism overlaps assessed by information-theory similarity were detected between the two GO-signatures (Fischer Exact Test p=0.001). Hence, together with machine learning technologies, FAIME could be utilized to develop an ontology-driven and expression-anchored prognostic signature that is personalized for an individual patient.

Original languageEnglish (US)
Pages (from-to)1040-1049
Number of pages10
JournalAMIA ... Annual Symposium proceedings / AMIA Symposium. AMIA Symposium
Volume2012
StatePublished - 2012
Externally publishedYes

Fingerprint

Gene Ontology
Microarray Analysis
Information Theory
Biological Phenomena
Transcriptome
Genes
Disease-Free Survival
Lung Neoplasms
Adenocarcinoma of lung
Genome
Technology
Gene Expression
Mortality

ASJC Scopus subject areas

  • Medicine(all)

Cite this

@article{81ce6d825be04c3db9bb6588387f74cc,
title = "Towards mechanism classifiers: expression-anchored Gene Ontology signature predicts clinical outcome in lung adenocarcinoma patients.",
abstract = "We aim to provide clinically applicable, reproducible, mechanistic interpretations of gene expression changes that lack in gene overlap among predictive gene-signatures. Using a method we recently developed, Functional Analysis of Individual Microarray Expression (FAIME), we provide evidence that Gene Ontology-anchored signatures (GO-signatures) show reliable prognosis in lung cancer. In order to demonstrate the biological congruence and reproducibility of FAIME-derived mechanism classifiers, we chose a disease where gene expression classifiers signatures alone had failed to significantly stratify a larger collection of samples and that exhibited poor or no genetic overlap. For each patient in the two lung adenocarcinoma studies, personalized FAIME-profiles of GO biological processes are generated from genome-wide expression profiles. For both training studies, GO-signatures significantly associated to patient mortality were identified (Prediction Analysis for Microarrays; three-fold cross-validation). These two GO-signatures could effectively stratify patients from an independent validation cohort into sub-groups that show significant differences in disease-free survival (log-rank test P=0.019; P=0.001). Importantly, significant mechanism overlaps assessed by information-theory similarity were detected between the two GO-signatures (Fischer Exact Test p=0.001). Hence, together with machine learning technologies, FAIME could be utilized to develop an ontology-driven and expression-anchored prognostic signature that is personalized for an individual patient.",
author = "Xinan Yang and Haiquan Li and Kelly Regan and Jianrong Li and Yong Huang and Lussier, {Yves A}",
year = "2012",
language = "English (US)",
volume = "2012",
pages = "1040--1049",
journal = "AMIA ... Annual Symposium proceedings / AMIA Symposium. AMIA Symposium",
issn = "1559-4076",
publisher = "American Medical Informatics Association",

}

TY - JOUR

T1 - Towards mechanism classifiers

T2 - expression-anchored Gene Ontology signature predicts clinical outcome in lung adenocarcinoma patients.

AU - Yang, Xinan

AU - Li, Haiquan

AU - Regan, Kelly

AU - Li, Jianrong

AU - Huang, Yong

AU - Lussier, Yves A

PY - 2012

Y1 - 2012

N2 - We aim to provide clinically applicable, reproducible, mechanistic interpretations of gene expression changes that lack in gene overlap among predictive gene-signatures. Using a method we recently developed, Functional Analysis of Individual Microarray Expression (FAIME), we provide evidence that Gene Ontology-anchored signatures (GO-signatures) show reliable prognosis in lung cancer. In order to demonstrate the biological congruence and reproducibility of FAIME-derived mechanism classifiers, we chose a disease where gene expression classifiers signatures alone had failed to significantly stratify a larger collection of samples and that exhibited poor or no genetic overlap. For each patient in the two lung adenocarcinoma studies, personalized FAIME-profiles of GO biological processes are generated from genome-wide expression profiles. For both training studies, GO-signatures significantly associated to patient mortality were identified (Prediction Analysis for Microarrays; three-fold cross-validation). These two GO-signatures could effectively stratify patients from an independent validation cohort into sub-groups that show significant differences in disease-free survival (log-rank test P=0.019; P=0.001). Importantly, significant mechanism overlaps assessed by information-theory similarity were detected between the two GO-signatures (Fischer Exact Test p=0.001). Hence, together with machine learning technologies, FAIME could be utilized to develop an ontology-driven and expression-anchored prognostic signature that is personalized for an individual patient.

AB - We aim to provide clinically applicable, reproducible, mechanistic interpretations of gene expression changes that lack in gene overlap among predictive gene-signatures. Using a method we recently developed, Functional Analysis of Individual Microarray Expression (FAIME), we provide evidence that Gene Ontology-anchored signatures (GO-signatures) show reliable prognosis in lung cancer. In order to demonstrate the biological congruence and reproducibility of FAIME-derived mechanism classifiers, we chose a disease where gene expression classifiers signatures alone had failed to significantly stratify a larger collection of samples and that exhibited poor or no genetic overlap. For each patient in the two lung adenocarcinoma studies, personalized FAIME-profiles of GO biological processes are generated from genome-wide expression profiles. For both training studies, GO-signatures significantly associated to patient mortality were identified (Prediction Analysis for Microarrays; three-fold cross-validation). These two GO-signatures could effectively stratify patients from an independent validation cohort into sub-groups that show significant differences in disease-free survival (log-rank test P=0.019; P=0.001). Importantly, significant mechanism overlaps assessed by information-theory similarity were detected between the two GO-signatures (Fischer Exact Test p=0.001). Hence, together with machine learning technologies, FAIME could be utilized to develop an ontology-driven and expression-anchored prognostic signature that is personalized for an individual patient.

UR - http://www.scopus.com/inward/record.url?scp=84880842718&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84880842718&partnerID=8YFLogxK

M3 - Article

VL - 2012

SP - 1040

EP - 1049

JO - AMIA ... Annual Symposium proceedings / AMIA Symposium. AMIA Symposium

JF - AMIA ... Annual Symposium proceedings / AMIA Symposium. AMIA Symposium

SN - 1559-4076

ER -