Zeng Yuanyuan, You Zhiyu, Guo Jiayang, Zhao Jialin, Zhou Ying, Huang Jialiang, Lyu Xiaowen, Chen Longbiao, Li Qiyuan
Department of Hematology, The First Affiliated Hospital of Xiamen University and Institute of Hematology, School of Medicine, Xiamen University, Xiamen, Fujian 361102, China.
National Institute for Data Science in Health and Medicine, School of Medicine, Xiamen University, Xiamen, Fujian 361102, China.
Brief Bioinform. 2025 May 1;26(3). doi: 10.1093/bib/bbaf183.
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.
染色质的三维构象对于转录调控至关重要。然而，目前用于检测基因组三维结构的实验技术成本高昂，且受限于生物学条件。在此，我们描述了“ChrombusXMBD”，这是一种基于可用的染色质特征能够从头预测染色质相互作用的图卷积模型。通过使用带有多头注意力机制的动态边卷积，Chrombus将二维染色质特征编码到一个可学习的嵌入空间中，从而生成全基因组的三维接触图谱。在验证过程中，Chrombus有效地重现了拓扑相关结构域、表达数量性状位点以及启动子/增强子相互作用。特别是，Chrombus在预测超过1-2兆碱基的染色质相互作用方面优于现有算法，预测相关性提高了11.8%-48.7%，并能预测超过2兆碱基的长程相互作用（皮尔逊系数为0.243-0.582）。Chrombus在人和小鼠来源的细胞系中也表现出很强的通用性。此外，Chrombus的参数揭示了顺式作用元件组学背后的生物学机制。我们的模型为理解染色质相互作用的复杂动态以及基因表达的顺式调控格局提供了一种新的、可推广的分析工具。
