# Chrombus-XMBD: a graph convolution model predicting 3D-genome from chromatin features

## TL;DR

Chrombus-XMBD is a new model that predicts 3D genome structures from chromatin features, improving accuracy and generalizability across species.

## Contribution

Introduces a graph convolution model with multihead attention for accurate 3D-genome prediction from chromatin features.

## Key findings

- Chrombus-XMBD outperforms existing methods in predicting chromatin interactions over 1–2 Mb by 11.8%–48.7%.
- The model accurately predicts long-range interactions over 2 Mb with a Pearson’s coefficient of 0.243–0.582.
- It generalizes well across human and mouse cell lines and identifies biological mechanisms of cistrome.

## Abstract

The 3D conformation of the chromatin is crucial for transcriptional regulation. However, current experimental techniques for detecting the 3D structure of the genome are costly and limited to the biological conditions. Here, we described “ChrombusXMBD,” a graph convolution model capable of predicting chromatin interactions ab initio based on available chromatin features. Using dynamic edge convolution with multihead attention mechanism, Chrombus encodes the 2D-chromatin features into a learnable embedding space, thereby generating a genome-wide 3D-contactmap. In validation, Chrombus effectively recapitulated the topological associated domains, expression quantitative trait loci, and promoter/enhancer interactions. Especially, Chrombus outperforms existing algorithms in predicting chromatin interactions over 1–2 Mb, increasing prediction correlation by 11.8%–48.7%, and predicts long-range interactions over 2 Mb (Pearson’s coefficient 0.243–0.582). Chrombus also exhibits strong generalizability across human and mouse-derived cell lines. Additionally, the parameters of Chrombus inform the biological mechanisms underlying cistrome. Our model provides a new, generalizable analytical tool for understanding the complex dynamics of chromatin interactions and the landscape of cis-regulation of gene expression.