Predictive integration of gene functional similarity and co-expression defines treatment response of endothelial progenitor cells

Francisco Azuaje, Haiying Wang, Huiru Zheng, Frederique Leonard, Magali Rolland-Turner, Lu Zhang, Yvan Devaux, Wagner Daniel R

Research output: Contribution to journalArticle

7 Citations (Scopus)

Abstract

BackgroundEndothelial progenitor cells (EPCs) have been implicated in different processes crucial to vasculature repair, which may offer the basis for new therapeutic strategies in cardiovascular disease. Despite advances facilitated by functional genomics, there is a lack of systems-level understanding of treatment response mechanisms of EPCs. In this research we aimed to characterize the EPCs response to adenosine (Ado), a cardioprotective factor, based on the systems-level integration of gene expression data and prior functional knowledge. Specifically, we set out to identify novel biosignatures of Ado-treatment response in EPCs.ResultsThe predictive integration of gene expression data and standardized functional similarity information enabled us to identify new treatment response biosignatures. Gene expression data originated from Ado-treated and -untreated EPCs samples, and functional similarity was estimated with Gene Ontology (GO)-based similarity information. These information sources enabled us to implement and evaluate an integrated prediction approach based on the concept of k-nearest neighbours learning (kNN). The method can be executed by expert- and data-driven input queries to guide the search for biologically meaningful biosignatures. The resulting integrated kNN system identified new candidate EPC biosignatures that can offer high classification performance (areas under the operating characteristic curve > 0.8). We also showed that the proposed models can outperform those discovered by standard gene expression analysis. Furthermore, we report an initial independent in vitro experimental follow-up, which provides additional evidence of the potential validity of the top biosignature.ConclusionResponse to Ado treatment in EPCs can be accurately characterized with a new method based on the combination of gene co-expression data and GO-based similarity information. It also exploits the incorporation of human expert-driven queries as a strategy to guide the automated search for candidate biosignatures. The proposed biosignature improves the systems-level characterization of EPCs. The new integrative predictive modeling approach can also be applied to other phenotype characterization or biomarker discovery problems.
LanguageEnglish
JournalBMC Systems Biology
Volume5
Issue number46
DOIs
Publication statusPublished - 30 Mar 2011

Fingerprint

Adenosine
Genes
Gene Expression
Gene Ontology
Learning
Systems Integration
Endothelial Progenitor Cells
erucylphosphocholine
Genomics
Cardiovascular Diseases
Stem Cells
Biomarkers
Phenotype
Research
Therapeutics

Cite this

Azuaje, Francisco ; Wang, Haiying ; Zheng, Huiru ; Leonard, Frederique ; Rolland-Turner, Magali ; Zhang, Lu ; Devaux, Yvan ; Daniel R, Wagner. / Predictive integration of gene functional similarity and co-expression defines treatment response of endothelial progenitor cells. In: BMC Systems Biology. 2011 ; Vol. 5, No. 46.
@article{888cf2556464428a903ac9eee09e3fd3,
title = "Predictive integration of gene functional similarity and co-expression defines treatment response of endothelial progenitor cells",
abstract = "BackgroundEndothelial progenitor cells (EPCs) have been implicated in different processes crucial to vasculature repair, which may offer the basis for new therapeutic strategies in cardiovascular disease. Despite advances facilitated by functional genomics, there is a lack of systems-level understanding of treatment response mechanisms of EPCs. In this research we aimed to characterize the EPCs response to adenosine (Ado), a cardioprotective factor, based on the systems-level integration of gene expression data and prior functional knowledge. Specifically, we set out to identify novel biosignatures of Ado-treatment response in EPCs.ResultsThe predictive integration of gene expression data and standardized functional similarity information enabled us to identify new treatment response biosignatures. Gene expression data originated from Ado-treated and -untreated EPCs samples, and functional similarity was estimated with Gene Ontology (GO)-based similarity information. These information sources enabled us to implement and evaluate an integrated prediction approach based on the concept of k-nearest neighbours learning (kNN). The method can be executed by expert- and data-driven input queries to guide the search for biologically meaningful biosignatures. The resulting integrated kNN system identified new candidate EPC biosignatures that can offer high classification performance (areas under the operating characteristic curve > 0.8). We also showed that the proposed models can outperform those discovered by standard gene expression analysis. Furthermore, we report an initial independent in vitro experimental follow-up, which provides additional evidence of the potential validity of the top biosignature.ConclusionResponse to Ado treatment in EPCs can be accurately characterized with a new method based on the combination of gene co-expression data and GO-based similarity information. It also exploits the incorporation of human expert-driven queries as a strategy to guide the automated search for candidate biosignatures. The proposed biosignature improves the systems-level characterization of EPCs. The new integrative predictive modeling approach can also be applied to other phenotype characterization or biomarker discovery problems.",
author = "Francisco Azuaje and Haiying Wang and Huiru Zheng and Frederique Leonard and Magali Rolland-Turner and Lu Zhang and Yvan Devaux and {Daniel R}, Wagner",
year = "2011",
month = "3",
day = "30",
doi = "10.1186/1752-0509-5-46",
language = "English",
volume = "5",
journal = "BMC Systems Biology",
issn = "1752-0509",
publisher = "BioMed Central",
number = "46",

}

Predictive integration of gene functional similarity and co-expression defines treatment response of endothelial progenitor cells. / Azuaje, Francisco; Wang, Haiying; Zheng, Huiru; Leonard, Frederique; Rolland-Turner, Magali; Zhang, Lu; Devaux, Yvan; Daniel R, Wagner.

In: BMC Systems Biology, Vol. 5, No. 46, 30.03.2011.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Predictive integration of gene functional similarity and co-expression defines treatment response of endothelial progenitor cells

AU - Azuaje, Francisco

AU - Wang, Haiying

AU - Zheng, Huiru

AU - Leonard, Frederique

AU - Rolland-Turner, Magali

AU - Zhang, Lu

AU - Devaux, Yvan

AU - Daniel R, Wagner

PY - 2011/3/30

Y1 - 2011/3/30

N2 - BackgroundEndothelial progenitor cells (EPCs) have been implicated in different processes crucial to vasculature repair, which may offer the basis for new therapeutic strategies in cardiovascular disease. Despite advances facilitated by functional genomics, there is a lack of systems-level understanding of treatment response mechanisms of EPCs. In this research we aimed to characterize the EPCs response to adenosine (Ado), a cardioprotective factor, based on the systems-level integration of gene expression data and prior functional knowledge. Specifically, we set out to identify novel biosignatures of Ado-treatment response in EPCs.ResultsThe predictive integration of gene expression data and standardized functional similarity information enabled us to identify new treatment response biosignatures. Gene expression data originated from Ado-treated and -untreated EPCs samples, and functional similarity was estimated with Gene Ontology (GO)-based similarity information. These information sources enabled us to implement and evaluate an integrated prediction approach based on the concept of k-nearest neighbours learning (kNN). The method can be executed by expert- and data-driven input queries to guide the search for biologically meaningful biosignatures. The resulting integrated kNN system identified new candidate EPC biosignatures that can offer high classification performance (areas under the operating characteristic curve > 0.8). We also showed that the proposed models can outperform those discovered by standard gene expression analysis. Furthermore, we report an initial independent in vitro experimental follow-up, which provides additional evidence of the potential validity of the top biosignature.ConclusionResponse to Ado treatment in EPCs can be accurately characterized with a new method based on the combination of gene co-expression data and GO-based similarity information. It also exploits the incorporation of human expert-driven queries as a strategy to guide the automated search for candidate biosignatures. The proposed biosignature improves the systems-level characterization of EPCs. The new integrative predictive modeling approach can also be applied to other phenotype characterization or biomarker discovery problems.

AB - BackgroundEndothelial progenitor cells (EPCs) have been implicated in different processes crucial to vasculature repair, which may offer the basis for new therapeutic strategies in cardiovascular disease. Despite advances facilitated by functional genomics, there is a lack of systems-level understanding of treatment response mechanisms of EPCs. In this research we aimed to characterize the EPCs response to adenosine (Ado), a cardioprotective factor, based on the systems-level integration of gene expression data and prior functional knowledge. Specifically, we set out to identify novel biosignatures of Ado-treatment response in EPCs.ResultsThe predictive integration of gene expression data and standardized functional similarity information enabled us to identify new treatment response biosignatures. Gene expression data originated from Ado-treated and -untreated EPCs samples, and functional similarity was estimated with Gene Ontology (GO)-based similarity information. These information sources enabled us to implement and evaluate an integrated prediction approach based on the concept of k-nearest neighbours learning (kNN). The method can be executed by expert- and data-driven input queries to guide the search for biologically meaningful biosignatures. The resulting integrated kNN system identified new candidate EPC biosignatures that can offer high classification performance (areas under the operating characteristic curve > 0.8). We also showed that the proposed models can outperform those discovered by standard gene expression analysis. Furthermore, we report an initial independent in vitro experimental follow-up, which provides additional evidence of the potential validity of the top biosignature.ConclusionResponse to Ado treatment in EPCs can be accurately characterized with a new method based on the combination of gene co-expression data and GO-based similarity information. It also exploits the incorporation of human expert-driven queries as a strategy to guide the automated search for candidate biosignatures. The proposed biosignature improves the systems-level characterization of EPCs. The new integrative predictive modeling approach can also be applied to other phenotype characterization or biomarker discovery problems.

UR - http://www.biomedcentral.com/1752-0509/5/46

U2 - 10.1186/1752-0509-5-46

DO - 10.1186/1752-0509-5-46

M3 - Article

VL - 5

JO - BMC Systems Biology

T2 - BMC Systems Biology

JF - BMC Systems Biology

SN - 1752-0509

IS - 46

ER -