Mechanism-anchored profiling derived from epigenetic networks predicts outcome in acute lymphoblastic leukemia

Xinan Yang, Yong Huang, James L. Chen, Jianming Xie, Xiao Sun, Yves A Lussier

Research output: Contribution to journalArticle

6 Citations (Scopus)

Abstract

Background: Current outcome predictors based on "molecular profiling" rely on gene lists selected without consideration for their molecular mechanisms. This study was designed to demonstrate that we could learn about genes related to a specific mechanism and further use this knowledge to predict outcome in patients - a paradigm shift towards accurate "mechanism-anchored profiling". We propose a novel algorithm, PGnet, which predicts a tripartite mechanism-anchored network associated to epigenetic regulation consisting of phenotypes, genes and mechanisms. Genes termed as GEMs in this network meet all of the following criteria: (i) they are co-expressed with genes known to be involved in the biological mechanism of interest, (ii) they are also differentially expressed between distinct phenotypes relevant to the study, and (iii) as a biomodule, genes correlate with both the mechanism and the phenotype. Results: This proof-of-concept study, which focuses on epigenetic mechanisms, was conducted in a well-studied set of 132 acute lymphoblastic leukemia (ALL) microarrays annotated with nine distinct phenotypes and three measures of response to therapy. We used established parametric and non parametric statistics to derive the PGnet tripartite network that consisted of 10 phenotypes and 33 significant clusters of GEMs comprising 535 distinct genes. The significance of PGnet was estimated from empirical p-values, and a robust subnetwork derived from ALL outcome data was produced by repeated random sampling. The evaluation of derived robust network to predict outcome (relapse of ALL) was significant (p = 3%), using one hundred three-fold cross-validations and the shrunken centroids classifier. Conclusion: To our knowledge, this is the first method predicting co-expression networks of genes associated with epigenetic mechanisms and to demonstrate its inherent capability to predict therapeutic outcome. This PGnet approach can be applied to any regulatory mechanisms including transcriptional or microRNA regulation in order to derive predictive molecular profiles that are mechanistically anchored. The implementation of PGnet in R is freely available at http://Lussierlab.org/publication/PGnet.

Original languageEnglish (US)
Article number1471
JournalBMC Bioinformatics
Volume10
Issue numberSUPPL. 9
StatePublished - Sep 17 2009
Externally publishedYes

Fingerprint

Leukemia
Profiling
Precursor Cell Lymphoblastic Leukemia-Lymphoma
Epigenomics
Acute
Genes
Predict
Gene
Phenotype
Air cushion vehicles
Distinct
Gene Regulatory Networks
Nonparametric Statistics
MicroRNAs
Microarrays
Publications
MicroRNA
Random Sampling
p-Value
Threefolds

ASJC Scopus subject areas

  • Biochemistry
  • Molecular Biology
  • Computer Science Applications
  • Structural Biology
  • Applied Mathematics

Cite this

Mechanism-anchored profiling derived from epigenetic networks predicts outcome in acute lymphoblastic leukemia. / Yang, Xinan; Huang, Yong; Chen, James L.; Xie, Jianming; Sun, Xiao; Lussier, Yves A.

In: BMC Bioinformatics, Vol. 10, No. SUPPL. 9, 1471, 17.09.2009.

Research output: Contribution to journalArticle

Yang, Xinan ; Huang, Yong ; Chen, James L. ; Xie, Jianming ; Sun, Xiao ; Lussier, Yves A. / Mechanism-anchored profiling derived from epigenetic networks predicts outcome in acute lymphoblastic leukemia. In: BMC Bioinformatics. 2009 ; Vol. 10, No. SUPPL. 9.
@article{c066dd43478a4c1c8739a5a84a45c854,
title = "Mechanism-anchored profiling derived from epigenetic networks predicts outcome in acute lymphoblastic leukemia",
abstract = "Background: Current outcome predictors based on {"}molecular profiling{"} rely on gene lists selected without consideration for their molecular mechanisms. This study was designed to demonstrate that we could learn about genes related to a specific mechanism and further use this knowledge to predict outcome in patients - a paradigm shift towards accurate {"}mechanism-anchored profiling{"}. We propose a novel algorithm, PGnet, which predicts a tripartite mechanism-anchored network associated to epigenetic regulation consisting of phenotypes, genes and mechanisms. Genes termed as GEMs in this network meet all of the following criteria: (i) they are co-expressed with genes known to be involved in the biological mechanism of interest, (ii) they are also differentially expressed between distinct phenotypes relevant to the study, and (iii) as a biomodule, genes correlate with both the mechanism and the phenotype. Results: This proof-of-concept study, which focuses on epigenetic mechanisms, was conducted in a well-studied set of 132 acute lymphoblastic leukemia (ALL) microarrays annotated with nine distinct phenotypes and three measures of response to therapy. We used established parametric and non parametric statistics to derive the PGnet tripartite network that consisted of 10 phenotypes and 33 significant clusters of GEMs comprising 535 distinct genes. The significance of PGnet was estimated from empirical p-values, and a robust subnetwork derived from ALL outcome data was produced by repeated random sampling. The evaluation of derived robust network to predict outcome (relapse of ALL) was significant (p = 3{\%}), using one hundred three-fold cross-validations and the shrunken centroids classifier. Conclusion: To our knowledge, this is the first method predicting co-expression networks of genes associated with epigenetic mechanisms and to demonstrate its inherent capability to predict therapeutic outcome. This PGnet approach can be applied to any regulatory mechanisms including transcriptional or microRNA regulation in order to derive predictive molecular profiles that are mechanistically anchored. The implementation of PGnet in R is freely available at http://Lussierlab.org/publication/PGnet.",
author = "Xinan Yang and Yong Huang and Chen, {James L.} and Jianming Xie and Xiao Sun and Lussier, {Yves A}",
year = "2009",
month = "9",
day = "17",
language = "English (US)",
volume = "10",
journal = "BMC Bioinformatics",
issn = "1471-2105",
publisher = "BioMed Central",
number = "SUPPL. 9",

}

TY - JOUR

T1 - Mechanism-anchored profiling derived from epigenetic networks predicts outcome in acute lymphoblastic leukemia

AU - Yang, Xinan

AU - Huang, Yong

AU - Chen, James L.

AU - Xie, Jianming

AU - Sun, Xiao

AU - Lussier, Yves A

PY - 2009/9/17

Y1 - 2009/9/17

N2 - Background: Current outcome predictors based on "molecular profiling" rely on gene lists selected without consideration for their molecular mechanisms. This study was designed to demonstrate that we could learn about genes related to a specific mechanism and further use this knowledge to predict outcome in patients - a paradigm shift towards accurate "mechanism-anchored profiling". We propose a novel algorithm, PGnet, which predicts a tripartite mechanism-anchored network associated to epigenetic regulation consisting of phenotypes, genes and mechanisms. Genes termed as GEMs in this network meet all of the following criteria: (i) they are co-expressed with genes known to be involved in the biological mechanism of interest, (ii) they are also differentially expressed between distinct phenotypes relevant to the study, and (iii) as a biomodule, genes correlate with both the mechanism and the phenotype. Results: This proof-of-concept study, which focuses on epigenetic mechanisms, was conducted in a well-studied set of 132 acute lymphoblastic leukemia (ALL) microarrays annotated with nine distinct phenotypes and three measures of response to therapy. We used established parametric and non parametric statistics to derive the PGnet tripartite network that consisted of 10 phenotypes and 33 significant clusters of GEMs comprising 535 distinct genes. The significance of PGnet was estimated from empirical p-values, and a robust subnetwork derived from ALL outcome data was produced by repeated random sampling. The evaluation of derived robust network to predict outcome (relapse of ALL) was significant (p = 3%), using one hundred three-fold cross-validations and the shrunken centroids classifier. Conclusion: To our knowledge, this is the first method predicting co-expression networks of genes associated with epigenetic mechanisms and to demonstrate its inherent capability to predict therapeutic outcome. This PGnet approach can be applied to any regulatory mechanisms including transcriptional or microRNA regulation in order to derive predictive molecular profiles that are mechanistically anchored. The implementation of PGnet in R is freely available at http://Lussierlab.org/publication/PGnet.

AB - Background: Current outcome predictors based on "molecular profiling" rely on gene lists selected without consideration for their molecular mechanisms. This study was designed to demonstrate that we could learn about genes related to a specific mechanism and further use this knowledge to predict outcome in patients - a paradigm shift towards accurate "mechanism-anchored profiling". We propose a novel algorithm, PGnet, which predicts a tripartite mechanism-anchored network associated to epigenetic regulation consisting of phenotypes, genes and mechanisms. Genes termed as GEMs in this network meet all of the following criteria: (i) they are co-expressed with genes known to be involved in the biological mechanism of interest, (ii) they are also differentially expressed between distinct phenotypes relevant to the study, and (iii) as a biomodule, genes correlate with both the mechanism and the phenotype. Results: This proof-of-concept study, which focuses on epigenetic mechanisms, was conducted in a well-studied set of 132 acute lymphoblastic leukemia (ALL) microarrays annotated with nine distinct phenotypes and three measures of response to therapy. We used established parametric and non parametric statistics to derive the PGnet tripartite network that consisted of 10 phenotypes and 33 significant clusters of GEMs comprising 535 distinct genes. The significance of PGnet was estimated from empirical p-values, and a robust subnetwork derived from ALL outcome data was produced by repeated random sampling. The evaluation of derived robust network to predict outcome (relapse of ALL) was significant (p = 3%), using one hundred three-fold cross-validations and the shrunken centroids classifier. Conclusion: To our knowledge, this is the first method predicting co-expression networks of genes associated with epigenetic mechanisms and to demonstrate its inherent capability to predict therapeutic outcome. This PGnet approach can be applied to any regulatory mechanisms including transcriptional or microRNA regulation in order to derive predictive molecular profiles that are mechanistically anchored. The implementation of PGnet in R is freely available at http://Lussierlab.org/publication/PGnet.

UR - http://www.scopus.com/inward/record.url?scp=70349876894&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=70349876894&partnerID=8YFLogxK

M3 - Article

VL - 10

JO - BMC Bioinformatics

JF - BMC Bioinformatics

SN - 1471-2105

IS - SUPPL. 9

M1 - 1471

ER -