Revealing Hi-C subcompartments by imputing high-resolution inter-chromosomal chromatin interactions

The higher-order genome organization and its variation in different cellular conditions remains poorly understood. Recent high-resolution genome-wide mapping of chromatin interactions using Hi-C has revealed that chromosomes in the human genome are spatially segregated into distinct subcompartments. However, due to the requirement on sequencing coverage of the Hi-C data to define subcompartments, to date subcompartment annotation is only available in the GM12878 cell line, making it impractical to compare Hi-C subcompartment patterns across multiple cell types. Here we develop a new computational approach, named SO_SCPLOWNIPERC_SCPLOW, based on an autoencoder and multilayer perceptron classifier to infer subcompartments using typical Hi-C datasets with moderate coverage. We demonstrated that SO_SCPLOWNIPERC_SCPLOW can accurately reveal subcompartments based on Hi-C datasets with moderate coverage and can significantly outperform an existing method that uses numerous epigenomic datasets as input features in GM12878. We applied SO_SCPLOWNIPERC_SCPLOW to eight additional cell lines to identify the variation of Hi-C subcompartments across different cell types. SO_SCPLOWNIPERC_SCPLOW revealed that chromosomal regions with conserved and more dynamic subcompartment annotations across cell types have different patterns of functional genomic features. This work demonstrates that SO_SCPLOWNIPERC_SCPLOW is effective in identifying subcompartments without the need of high-coverage Hi-C data and has the potential to provide new insights into the spatial genome organization variation across different cell types.