Cumulatively, ~70% of the human genome are transcribed, whereas only ~1.5% of the genome encodes protein. Long non-coding RNAs (lncRNAs) are RNAs that are longer than 200 base pairs (bps), but with little protein coding capacity. Systematic efforts to catalogue lncRNAs have revealed that the human genome encodes over 10,000 lncRNAs. Although several dozens of lncRNAs have been functionally characterized, little is known about the function of most lncRNAs in normal physiology or disease. Advances in genomic technologies provide unparalleled opportunities to characterize the function of lncRNAs. However, integrating different types of omic datasets to generate testable hypotheses is challenging. In this talk, I will present my recent work on developing and utilizing integrative approaches to systematically identify the clinically relevant and/or functionally important lncRNAs in human cancer as well as to dissect the microRNA-mediated lncRNA regulatory network that influences the expression of cancer driver genes.