Email updates

Keep up to date with the latest news and content from BMC Bioinformatics and BioMed Central.

Open Access Research article

Ensemble analyses improve signatures of tumour hypoxia and reveal inter-platform differences

Natalie S Fox14, Maud HW Starmans12, Syed Haider13, Philippe Lambin2 and Paul C Boutros145*

Author Affiliations

1 Informatics and Bio-computing Platform, Ontario Institute for Cancer Research, Toronto, Canada

2 Department of Radiation Oncology (Maastro), GROW-School for Oncology and Developmental Biology, Maastricht University Medical Center, Maastricht, The Netherlands

3 Centre for Molecular Oncology, Barts Cancer Institute, London EC1M 6BQ, UK

4 Department of Medical Biophysics, University of Toronto, Toronto, ON, Canada

5 Department of Pharmacology and Toxicology, University of Toronto, Toronto, ON, Canada

For all author emails, please log on.

BMC Bioinformatics 2014, 15:170  doi:10.1186/1471-2105-15-170

Published: 6 June 2014

Abstract

Background

The reproducibility of transcriptomic biomarkers across datasets remains poor, limiting clinical application. We and others have suggested that this is in-part caused by differential error-structure between datasets, and their incomplete removal by pre-processing algorithms.

Methods

To test this hypothesis, we systematically assessed the effects of pre-processing on biomarker classification using 24 different pre-processing methods and 15 distinct signatures of tumour hypoxia in 10 datasets (2,143 patients).

Results

We confirm strong pre-processing effects for all datasets and signatures, and find that these differ between microarray versions. Importantly, exploiting different pre-processing techniques in an ensemble technique improved classification for a majority of signatures.

Conclusions

Assessing biomarkers using an ensemble of pre-processing techniques shows clear value across multiple diseases, datasets and biomarkers. Importantly, ensemble classification improves biomarkers with initially good results but does not result in spuriously improved performance for poor biomarkers. While further research is required, this approach has the potential to become a standard for transcriptomic biomarkers.