Consistent metagenes from cancer expression profiles yield agent specific predictors of chemotherapy response

Qiyuan Li, Aron C. Eklund, Nicolai J. Birkbak, Christine Desmedt, Benjamin Haibe-Kains, Christos Sotiriou, W. Fraser Symmans, Lajos Pusztai, Søren Brunak, Andrea Richardson, Zoltan Szallasi

Research output: Contribution to journalArticle

Abstract

Background: Genome scale expression profiling of human tumor samples is likely to yield improved cancer treatment decisions. However, identification of clinically predictive or prognostic classifiers can be challenging when a large number of genes are measured in a small number of tumors.Results: We describe an unsupervised method to extract robust, consistent metagenes from multiple analogous data sets. We applied this method to expression profiles from five "double negative breast cancer" (DNBC) (not expressing ESR1 or HER2) cohorts and derived four metagenes. We assessed these metagenes in four similar but independent cohorts and found strong associations between three of the metagenes and agent-specific response to neoadjuvant therapy. Furthermore, we applied the method to ovarian and early stage lung cancer, two tumor types that lack reliable predictors of outcome, and found that the metagenes yield predictors of survival for both.Conclusions: These results suggest that the use of multiple data sets to derive potential biomarkers can filter out data set-specific noise and can increase the efficiency in identifying clinically accurate biomarkers.

Original languageEnglish (US)
Article number310
JournalBMC Bioinformatics
Volume12
DOIs
StatePublished - Jul 28 2011
Externally publishedYes

Fingerprint

Chemotherapy
Tumors
Predictors
Tumor
Cancer
Biomarkers
Drug Therapy
Genes
Neoplasms
Oncology
Lung Cancer
Profiling
Breast Cancer
Therapy
Neoadjuvant Therapy
Genome
Classifiers
Likely
Classifier
Filter

ASJC Scopus subject areas

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

Cite this

Li, Q., Eklund, A. C., Birkbak, N. J., Desmedt, C., Haibe-Kains, B., Sotiriou, C., ... Szallasi, Z. (2011). Consistent metagenes from cancer expression profiles yield agent specific predictors of chemotherapy response. BMC Bioinformatics, 12, [310]. https://doi.org/10.1186/1471-2105-12-310

Consistent metagenes from cancer expression profiles yield agent specific predictors of chemotherapy response. / Li, Qiyuan; Eklund, Aron C.; Birkbak, Nicolai J.; Desmedt, Christine; Haibe-Kains, Benjamin; Sotiriou, Christos; Symmans, W. Fraser; Pusztai, Lajos; Brunak, Søren; Richardson, Andrea; Szallasi, Zoltan.

In: BMC Bioinformatics, Vol. 12, 310, 28.07.2011.

Research output: Contribution to journalArticle

Li, Q, Eklund, AC, Birkbak, NJ, Desmedt, C, Haibe-Kains, B, Sotiriou, C, Symmans, WF, Pusztai, L, Brunak, S, Richardson, A & Szallasi, Z 2011, 'Consistent metagenes from cancer expression profiles yield agent specific predictors of chemotherapy response', BMC Bioinformatics, vol. 12, 310. https://doi.org/10.1186/1471-2105-12-310
Li, Qiyuan ; Eklund, Aron C. ; Birkbak, Nicolai J. ; Desmedt, Christine ; Haibe-Kains, Benjamin ; Sotiriou, Christos ; Symmans, W. Fraser ; Pusztai, Lajos ; Brunak, Søren ; Richardson, Andrea ; Szallasi, Zoltan. / Consistent metagenes from cancer expression profiles yield agent specific predictors of chemotherapy response. In: BMC Bioinformatics. 2011 ; Vol. 12.
@article{5e6d60ca3e154e348b847c9e6c98e5ad,
title = "Consistent metagenes from cancer expression profiles yield agent specific predictors of chemotherapy response",
abstract = "Background: Genome scale expression profiling of human tumor samples is likely to yield improved cancer treatment decisions. However, identification of clinically predictive or prognostic classifiers can be challenging when a large number of genes are measured in a small number of tumors.Results: We describe an unsupervised method to extract robust, consistent metagenes from multiple analogous data sets. We applied this method to expression profiles from five {"}double negative breast cancer{"} (DNBC) (not expressing ESR1 or HER2) cohorts and derived four metagenes. We assessed these metagenes in four similar but independent cohorts and found strong associations between three of the metagenes and agent-specific response to neoadjuvant therapy. Furthermore, we applied the method to ovarian and early stage lung cancer, two tumor types that lack reliable predictors of outcome, and found that the metagenes yield predictors of survival for both.Conclusions: These results suggest that the use of multiple data sets to derive potential biomarkers can filter out data set-specific noise and can increase the efficiency in identifying clinically accurate biomarkers.",
author = "Qiyuan Li and Eklund, {Aron C.} and Birkbak, {Nicolai J.} and Christine Desmedt and Benjamin Haibe-Kains and Christos Sotiriou and Symmans, {W. Fraser} and Lajos Pusztai and S{\o}ren Brunak and Andrea Richardson and Zoltan Szallasi",
year = "2011",
month = "7",
day = "28",
doi = "10.1186/1471-2105-12-310",
language = "English (US)",
volume = "12",
journal = "BMC Bioinformatics",
issn = "1471-2105",
publisher = "BioMed Central",

}

TY - JOUR

T1 - Consistent metagenes from cancer expression profiles yield agent specific predictors of chemotherapy response

AU - Li, Qiyuan

AU - Eklund, Aron C.

AU - Birkbak, Nicolai J.

AU - Desmedt, Christine

AU - Haibe-Kains, Benjamin

AU - Sotiriou, Christos

AU - Symmans, W. Fraser

AU - Pusztai, Lajos

AU - Brunak, Søren

AU - Richardson, Andrea

AU - Szallasi, Zoltan

PY - 2011/7/28

Y1 - 2011/7/28

N2 - Background: Genome scale expression profiling of human tumor samples is likely to yield improved cancer treatment decisions. However, identification of clinically predictive or prognostic classifiers can be challenging when a large number of genes are measured in a small number of tumors.Results: We describe an unsupervised method to extract robust, consistent metagenes from multiple analogous data sets. We applied this method to expression profiles from five "double negative breast cancer" (DNBC) (not expressing ESR1 or HER2) cohorts and derived four metagenes. We assessed these metagenes in four similar but independent cohorts and found strong associations between three of the metagenes and agent-specific response to neoadjuvant therapy. Furthermore, we applied the method to ovarian and early stage lung cancer, two tumor types that lack reliable predictors of outcome, and found that the metagenes yield predictors of survival for both.Conclusions: These results suggest that the use of multiple data sets to derive potential biomarkers can filter out data set-specific noise and can increase the efficiency in identifying clinically accurate biomarkers.

AB - Background: Genome scale expression profiling of human tumor samples is likely to yield improved cancer treatment decisions. However, identification of clinically predictive or prognostic classifiers can be challenging when a large number of genes are measured in a small number of tumors.Results: We describe an unsupervised method to extract robust, consistent metagenes from multiple analogous data sets. We applied this method to expression profiles from five "double negative breast cancer" (DNBC) (not expressing ESR1 or HER2) cohorts and derived four metagenes. We assessed these metagenes in four similar but independent cohorts and found strong associations between three of the metagenes and agent-specific response to neoadjuvant therapy. Furthermore, we applied the method to ovarian and early stage lung cancer, two tumor types that lack reliable predictors of outcome, and found that the metagenes yield predictors of survival for both.Conclusions: These results suggest that the use of multiple data sets to derive potential biomarkers can filter out data set-specific noise and can increase the efficiency in identifying clinically accurate biomarkers.

UR - http://www.scopus.com/inward/record.url?scp=79960653747&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79960653747&partnerID=8YFLogxK

U2 - 10.1186/1471-2105-12-310

DO - 10.1186/1471-2105-12-310

M3 - Article

C2 - 21798043

AN - SCOPUS:79960653747

VL - 12

JO - BMC Bioinformatics

JF - BMC Bioinformatics

SN - 1471-2105

M1 - 310

ER -