TY - JOUR AU - Veytsman, Boris AU - Wang, Lei AU - Cui, Tiange AU - Bruskin, Sergey AU - Baranova, Ancha PY - 2014 DA - 2014/12/19 TI - Distance-based classifiers as potential diagnostic and prediction tools for human diseases JO - BMC Genomics SP - S10 VL - 15 IS - 12 AB - Typically, gene expression biomarkers are being discovered in course of high-throughput experiments, for example, RNAseq or microarray profiling. Analytic pipelines that extract so-called signatures suffer from the "Dimensionality curse": the number of genes expressed exceeds the number of patients we can enroll in the study and use to train the discriminator algorithm. Hence, problems with the reproducibility of gene signatures are more common than not; when the algorithm is executed using a different training set, the resulting diagnostic signature may turn out to be completely different. SN - 1471-2164 UR - https://doi.org/10.1186/1471-2164-15-S12-S10 DO - 10.1186/1471-2164-15-S12-S10 ID - Veytsman2014 ER -