Decoding Cell-type Specific Gene Regulation with CellReg3D by Integrating DNA Large Language Models and 3D Genome Structure
- 1Monash University
Abstract
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.
Related
- Decoding MAPK cascades in plant immunity: Activation, regulation, integration, and pathogen manipulation
- Decoding Clade-Specific bNAb-HIV-1 Env Interactions Using Machine Learning
- Decoding stage-specific symbiotic programs in the Rhizophagus irregularis-tomato interaction using single-nucleus transcriptomics
- Decoding molecular heterogeneity in lupus nephritis: integrating single-cell and spatial multi-omics for endotype-driven precision therapeutics
- Decoding motor imagery EEG signals by a deep learning network integrating multiscale filtering and temporal-channel attention mechanisms
BibTeX
@misc{wang2026decoding,
title = {{Decoding Cell-type Specific Gene Regulation with CellReg3D by Integrating DNA Large Language Models and 3D Genome Structure}},
author = {X. Wang and Y. Zhang and S. Chen and S. Imoto and G. I. Webb and A. V. Vasilakos and F. Li and K. Wang and J. Song},
howpublished = {bioRxiv},
year = {2026},
month = nov,
doi = {10.64898/2026.11.01.763421},
url = {https://www.biorxiv.org/content/10.64898/2026.11.01.763421v1},
note = {CC BY-NC-ND},
}
RIS
TY - UNPB
TI - Decoding Cell-type Specific Gene Regulation with CellReg3D by Integrating DNA Large Language Models and 3D Genome Structure
AU - X. Wang
AU - Y. Zhang
AU - S. Chen
AU - S. Imoto
AU - G. I. Webb
AU - A. V. Vasilakos
AU - F. Li
AU - K. Wang
AU - J. Song
PY - 2026
DA - 2026/11/01
PB - bioRxiv
DO - 10.64898/2026.11.01.763421
UR - https://www.biorxiv.org/content/10.64898/2026.11.01.763421v1
AB - 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.
ER -