Contact-Guided 3D Genome Structure Generation of E. coli via Diffusion Transformers

TL;DR

This paper introduces a diffusion-transformer framework for generating diverse 3D genome conformations of E. coli that align with Hi-C contact data, advancing ensemble-based genome modeling.

Contribution

It develops a novel conditional generative model combining diffusion transformers and VAEs for ensemble 3D genome structure prediction from Hi-C data.

Findings

Generated structures match Hi-C contact patterns.

Models produce diverse conformations with accurate contact correlations.

Framework outperforms existing methods in ensemble reconstruction.

Abstract

In this study, we present a conditional diffusion-transformer framework for generating ensembles of three-dimensional Escherichia coli genome conformations guided by Hi-C contact maps. Instead of producing a single deterministic structure, we formulate genome reconstruction as a conditional generative modeling problem that samples heterogeneous conformations whose ensemble-averaged contacts are consistent with the input Hi-C data. A synthetic dataset is constructed using coarse-grained molecular dynamics simulations to generate chromatin ensembles and corresponding Hi-C maps under circular topology. Our models operate in a latent diffusion setting with a variational autoencoder that preserves per-bin alignment and supports replication-aware representations. Hi-C information is injected through a transformer-based encoder and cross-attention, enforcing a physically interpretable one-way constraint from Hi-C to structure. The model is trained using a flow-matching objective for stable optimization. On held-out ensembles, generated structures reproduce the input Hi-C distance-decay and structural correlation metrics while maintaining substantial conformational diversity, demonstrating the effectiveness of diffusion-based generative modeling for ensemble-level 3D genome reconstruction.