Identification of a robust subpathway-based signature for acute myeloid leukemia prognosis using an miRNA integrated strategy.

ABSTRACT: Acute myeloid leukemia (AML) is a heterogeneous disease, and survival signatures are urgently needed to better monitor treatment. MiRNAs displayed vital regulatory roles on target genes, which was necessary involved in the complex disease. We therefore examined the expression levels of miRNAs and genes to identify robust signatures for survival benefit analyses. First, we reconstructed subpathway graphs by embedding miRNA components that were derived from low-throughput miRNA-gene interactions. Then, we randomly divided the data sets from The Cancer Genome Atlas (TCGA) into training and testing sets, and further formed 100 subsets based on the training set. Using each subset, we identified survival-related miRNAs and genes, and identified survival subpathways based on the reconstructed sub

SUBMITTER: Chang H 

PROVIDER: S-EPMC5865743 | biostudies-literature | 2018

REPOSITORIES: biostudies-literature