Fig. 1.

Overview of the HiCPlus pipeline. a HiCPlus leverages information from surrounding regions to estimate contact frequency for a given point in a Hi-C interaction matrix. b Conceptual view of the network structure in HiCPlus: regional interaction features (e.g., loops, domain borders) are learned using values at each position in the high-resolution matrix as the response variable and using its neighbouring points from the low-resolution matrix as the predictors. c HiCPlus divides the entire Hi-C matrix into small square samples and enhances them separately. After each block of interactions are predicted, those blocks are merged into chromosome-wide interaction matrix