HiADN: Lightweight Resolution Enhancement of Hi-C Data Using High Information Attention Distillation Network

Due to limitations in experimental library preparation and in practical sequencing cost, currently available Hi-C data is often sparse, affecting the precise characterization of complex 3D chromatin structures. Providing efficaciously computational models to elevate the quality of sparse Hi-C sequencing data for restoring the fundamental traits of 3D chromatin is of substantial significance. Herein, we introduce HiADN, a deep learning-based approach to infer dense high-resolution matrices from sparse Hi-C matrices. In particular, we firstly design a specialized architecture HiFM to captures local spatial structures and the patterns of Hi-C data. Then, we develop large kernel convolutional decomposition and attention mechanisms to effectively explore global patterns across longer genomic distances. Using HiADN, it is possible to construct biologically significant regions at high-resolution (e.g., 10 Kb) while only using the 1/100 of original sequencing reads. The experimental results demonstrate that the effect of in silico libraries forecasted by computational models using HiADN is commensurate with that of experimental libraries, surpassing the state-of-the-art (SOTA) models. We further validated the effectiveness of HiADN in reconstructing the three-dimensional spatial structure of chromosomes on the GM12878, K562, and CH12-LX cell line datasets.