TY - JOUR AU - Starmans, Maud HW AU - Pintilie, Melania AU - John, Thomas AU - Der, Sandy D. AU - Shepherd, Frances A. AU - Jurisica, Igor AU - Lambin, Philippe AU - Tsao, Ming-Sound AU - Boutros, Paul C. PY - 2012 DA - 2012/11/12 TI - Exploiting the noise: improving biomarkers with ensembles of data analysis methodologies JO - Genome Medicine SP - 84 VL - 4 IS - 11 AB - The advent of personalized medicine requires robust, reproducible biomarkers that indicate which treatment will maximize therapeutic benefit while minimizing side effects and costs. Numerous molecular signatures have been developed over the past decade to fill this need, but their validation and up-take into clinical settings has been poor. Here, we investigate the technical reasons underlying reported failures in biomarker validation for non-small cell lung cancer (NSCLC). SN - 1756-994X UR - https://doi.org/10.1186/gm385 DO - 10.1186/gm385 ID - Starmans2012 ER -