Multiscale Modeling of Genome Organization: Bridging Polymer Physics, Molecular Dynamics, and AI

Abstract

The human genome is intricately organized within the nucleus, and its spatial arrangement plays a critical role in gene regulation, cellular function, and disease. Recent advances in high- throughput experiments have unveiled the heterogeneous and dynamic nature of chromatin organization at single-cell resolution. However, computational tools that can both simulate and predict such complex structures are still limited. In this thesis, we develop and apply computational frameworks to investigate nuclear genome organization at high spatial and temporal resolution. Our approaches integrate biophysical modeling and generative artificial intelligence to address complementary aspects of nuclear architecture.

In Chapter 1, we provide an overview of the hierarchical organization of the genome and discuss emerging principles that govern chromatin folding, nuclear compartmentalization, and their functional implications. We introduce data-driven, physics-based, and generative artificial intelligence modeling approaches, highlighting the need for interpretable and efficient models capable of capturing the structural diversity of the nucleus across individual cells.

In Chapter 2, we present OpenNucleome, a high-resolution molecular dynamics framework for simulating the entire human nucleus at 100-kilobase resolution. OpenNucleome incorpo- rates explicit representations of chromosomes, nuclear bodies, and the nuclear lamina, and faithfully reproduces experimental data from Hi-C, TSA-seq, DamID, and DNA-MERFISH. The developed software is fully open-source and GPU-accelerated, enabling large-scale simu- lations and mechanistic explorations.

In Chapter 3, we explore the impact of genome organization on various biological phe- nomena within the cell nucleus—focusing on telomere and telomere condensate dynamics, and nuclear deformation—using OpenNucleome. Our results demonstrate that the three- dimensional genome architecture plays a pivotal role in governing the dynamics of genomic loci such as telomeres, influencing the kinetics and outcomes of droplet coarsening. More- over, specific interactions between the genome and nuclear bodies form robustly across cells, providing strong support for a nuclear zoning model of genome function.

In Chapter 4, we introduce ChromoGen, a generative diffusion model that predicts single- cell chromatin conformations de novo from DNA sequence and DNase-seq data. Unlike traditional simulation frameworks, ChromoGen learns from experimental single-cell 3D structures to generate physically realistic, region- and cell type-specific ensembles. ChromoGen achieves high agreement with both experimental Dip-C and Hi-C data while maintaining computational efficiency, enabling rapid exploration of chromatin heterogeneity across the genome and cell types.

Together, these two frameworks—OpenNucleome and ChromoGen—provide powerful and complementary tools for understanding genome structure and function at the single-cell level, bridging physics-based modeling and deep generative artificial intelligence modeling.