Decoding Cell-type Specific Gene Regulation with CellReg3D by Integrating DNA Large Language Models and 3D Genome Structure

Gene regulation is a core biological mechanism crucial for organismal growth and development. Recent advances in deep learning, coupled with increasing computational resources, have enabled large-scale modelling of gene regulatory processes. While numerous models have been proposed, effectively capturing long-range genomic interactions remains a central challenge. Here, we introduce CellReg3D, a multiscale and multi-modal deep learning framework designed to model cell-type-specific gene regulation by integrating local sequence patterns with long-range genomic interactions. Existing approaches often overlook the contribution of 3D genome architecture and face limitations in combining sequence-based features with chromatin interaction data. Specifically, CellReg3D overcomes these gaps by leveraging a DNA language model to encode sequence-level information and incorporating Hi-C-derived 3D chromatin interactions to capture chromatin spatial organization. We demonstrate that CellReg3D effectively learns epigenetic patterns and chromatin activity states, achieving state-of-the-art performance in predicting epigenetic marks and gene expression profiles across multiple cell types. Using interpretable methods, we illustrate how the model identifies cell-type-specific regulatory mechanisms and prioritizes functional non-coding variants. Furthermore, we apply CellReg3D to enhance the interpretation of expression quantitative trait loci (eQTLs) and uncover novel potential gene regulatory interactions. Overall, CellReg3D offers a integrative framework for decoding regulatory genomics, unifying sequence and 3D genome structure data to advance variant prioritization, disease mechanism discovery, and personalized functional genomics.