TY - JOUR T1 - RGBM: Regularized Gradient Boosting Machines for the Identification of Transcriptional Regulators of Discrete Glioma Subtypes JF - bioRxiv DO - 10.1101/132670 SP - 132670 AU - Raghvendra Mall AU - Luigi Cerulo AU - Khalid Kunji AU - Halima Bensmail AU - Thais S. Sabedot AU - Houtan Noushmehr AU - Antonio Iavarone AU - Michele Ceccarelli Y1 - 2017/01/01 UR - http://biorxiv.org/content/early/2017/05/01/132670.abstract N2 - The transcription factors (TF) which regulate gene expressions are key determinants of cellular phenotypes. Reconstructing large-scale genome-wide networks which capture the influence of TFs on target genes are essential for understanding and accurate modelling of living cells. We propose RGBM: a gene regulatory network (GRN) inference algorithm, which can handle data from heterogeneous information sources including dynamic time-series, gene knockout, gene knockdown, DNA microarrays and RNA-Seq expression profiles. RGBM allows to use an a priori mecha-nistic of active biding network consisting of TFs and corresponding target genes. RGBM is evaluated on the DREAM challenge datasets where it surpasses the winners of the competitions and other established methods for two evaluation metrics by about 10-15%.We use RGBM to identify the main regulators of the molecular subtypes of brain tumors. Our analysis reveals the identity and corresponding biological activities of the master regulators driving transformation of the G-CIMP-high into the G-CIMP-low subtype of glioma and PA-like into LGm6-GBM, thus, providing a clue to the yet undetermined nature of the transcriptional events driving the evolution among these novel glioma subtypes.RGBM is available for download on CRAN at https://cran.rproject.org/web/packages/RGBM/index.html ER -