PT  - JOURNAL ARTICLE
AU  - F. Rohart
AU  - A. Eslami
AU  - N. Matigian
AU  - S. Bougeard
AU  - K-A. Lê Cao
TI  - MINT: A multivariate integrative method to identify reproducible molecular signatures across independent experiments and platforms
AID  - 10.1101/070813
DP  - 2016 Jan 01
TA  - bioRxiv
PG  - 070813
4099  - http://biorxiv.org/content/early/2016/08/22/070813.short
4100  - http://biorxiv.org/content/early/2016/08/22/070813.full
AB  - The solution to identify a reliable molecular signature in transcriptomics high-throughput experiments is to increase sample size by combining independent but related studies. However, those data sets are generated using different protocols and technological platforms, which results in unwanted systematic variation that strongly confounds the integrative analysis results. We introduce a Multi-variate INTegrative method, MINT, that identifies a highly reproducible, accurate and predictive gene signature to classify sample phenotypes while accounting for platform and study variation. MINT led to superior and unbiased classification performance compared to other existing methods, and identified highly relevant gene signatures when integrating two multi-transcriptomics studies.