RABIT: Regression Analysis with Background InTegration

RABIT is a very efficient feature selection algorithm. Run this application to find regulator genes in shaping your gene expression patterns. The gene expression regulators are transcription factors (TF) or RNA binding proteins (RBP), with their binding profiles from ENCODE3 project.

Note: You can download some sample files to test. Please make sure Entrez ID or Gene Symbol are used for human.

example 1: Differential gene expression averaged in TCGA cancer types. Gene expression difference between the average profiles of tumor samples and normal tissues in TCGA.
example 2: Invivo CRISPR screen for immunotherapy resistance. Log fold change of CRISPR gRNA frequencies between immunotherapy (GVAX, anti-PD1) conditions and control (TCRalpha) conditions. This screen is done in mouse focused on ~2000 genes (Manguso et al., 2017), we translated all mouse gene names to their human orthologs.

Besides the application here, you can use RABIT as a general algorithm for feature selection. Please install RABIT locally for full function.