Genome-scale high-resolution mapping of activating and repressive nucleotides in regulatory regions

Massively parallel reporter assays (MPRA) enable nucleotide-resolution dissection of transcriptional regulatory regions, such as enhancers, but only few regions at a time. Here, we present a combined experimental and computational approach, Sharpr-MPRA, that allows high-resolution analysis of thousands of regions simultaneously. Sharpr-MPRA combines dense tiling of overlapping MPRA constructs with a probabilistic graphical model to recognize functional regulatory nucleotides, and to distinguish activating and repressive nucleotides, using their inferred contribution to reporter gene expression. We use Sharpr-MPRA to test 4.6 million nucleotides spanning 15,000 putative regulatory regions tiled at 5-nucleotide resolution in two human cell types. Our results recover known cell type-specific regulatory motifs and evolutionarily-conserved nucleotides, and distinguish known activating and repressive motifs. Our results also show that endogenous chromatin state and DNA accessibility are both predictive of regulatory function in reporter assays, identify retroviral elements with activating roles, and uncover ‘attenuator’ motifs with repressive roles in active chromatin.