Recently, we have made significant progress in understanding how DNA sequence features specify cell-type specific mammalian enhancer activity by using kmer-based SVM machine learning approaches. Our work uses functional genomics DNase-seq, ChIP-seq, RNA-seq, and chromatin state data to computationally identify combinations of transcription factor binding sites which operate to define the activity of cell-type specific enhancers.  Our models are then used to predict the impact of regulatory variation associated with common human disease, and have been validated in a wide range of cell-specific reporter assays.