Graph Neural Networks for Double-Strand DNA Breaks Prediction

TL;DR

This paper introduces GraphDSB, a graph neural network model that predicts DNA double-strand breaks by integrating DNA sequence and chromatin structure information, validated on human cell datasets.

Contribution

The paper presents a novel GNN-based method with structural encoding and Jumping Knowledge architecture for improved DSB prediction, including interpretability analysis.

Findings

Structural information improves prediction accuracy.

5-mer DNA sequence features are highly influential.

Chromatin interaction modes significantly contribute to DSB prediction.

Abstract

Double-strand DNA breaks (DSBs) are a form of DNA damage that can cause abnormal chromosomal rearrangements. Recent technologies based on high-throughput experiments have obvious high costs and technical challenges.Therefore, we design a graph neural network based method to predict DSBs (GraphDSB), using DNA sequence features and chromosome structure information. In order to improve the expression ability of the model, we introduce Jumping Knowledge architecture and several effective structural encoding methods. The contribution of structural information to the prediction of DSBs is verified by the experiments on datasets from normal human epidermal keratinocytes (NHEK) and chronic myeloid leukemia cell line (K562), and the ablation studies further demonstrate the effectiveness of the designed components in the proposed GraphDSB framework. Finally, we use GNNExplainer to analyze the contribution of node features and topology to DSBs prediction, and proved the high contribution of 5-mer DNA sequence features and two chromatin interaction modes.