HiC-LEGO: Biologically Guided High-Resolution 3D Genome Reconstruction Preserves Chromatin Organization at Kilobase Resolution

Abstract

Three-dimensional (3D) chromosome reconstruction from Hi-C contact maps remains challenging because genome organization is hierarchical and fine-resolution models must reconcile local structure with chromosome-scale constraints. Here we present HiC-LEGO, a domain-aware hierarchical framework integrating ensemble chromatin domains with graph-based structural learning and progressive chromosome assembly. By combining ensemble domain selection with hierarchical reconstruction, HiC-LEGO reduces dependence on individual domain definitions while maintaining local organization during chromosome-scale assembly. Across five human cell lines at 5-kb resolution, HiC-LEGO achieves higher reconstruction concordance than evaluated state-of-the-art methods while better preserving domain organization. At 1-kb resolution, HiC-LEGO reconstructs complete GM12878 chromosome 8 and recovers close spatial proximity between an epigenomically supported distal MYC enhancer and its promoter. Reconstructions from 5-kb Micro-C data show that 249 experimentally defined RCMC microcompartment interactions at the Ppm1g locus occupy compact 3D configurations. In the breast cancer dataset, HiC-LEGO reconstructs structures that maintain stable TAD organization across healthy breast, primary tumors, and liver metastases, while revealing greater inter-patient structural heterogeneity in malignant pleural effusion samples. Pore-C validation shows that experimentally observed multi-way contacts spanning 1-5 Mb are enriched in compact reconstructed configurations across all 23 chromosomes. Thus, HiC-LEGO preserves regulatory interactions, disease-associated chromatin organization and higher-order spatial relationships beyond pairwise contact-map concordance.