DconnLoop: a deep learning model for predicting chromatin loops based on multi-source data integration

• Published in: BMC bioinformatics Vol. 26; no. 1; pp. 96 - 27
• Main Authors: Wang, Junfeng, Cheng, Kuikui, Yan, Chaokun, Luo, Huimin, Luo, Junwei
• Format: Journal Article
• Language: English
• Published: London BioMed Central 01.04.2025; BioMed Central Ltd; Springer Nature B.V; BMC
• Subjects: Ablation; Algorithms; Binding sites; Binomial distribution; Bioinformatics; Biomedical and Life Sciences; Chromatin; Chromatin - chemistry; Chromatin - genetics; Chromatin Immunoprecipitation Sequencing; Chromatin loops; Clustering; Computational Biology - methods; Computational Biology/Bioinformatics; Computer Appl. in Life Sciences; Computer vision; Data integration; Datasets; Decoders; Deep Learning; Density; DNA methylation; DNA sequencing; Electronic data processing; Epigenetics; Feature extraction; Feature integration; Gene expression; Gene regulation; Genomes; Genomics; Humans; Life Sciences; Machine learning; Methods; Microarrays; Multi-source data; Mutation; Neural networks; Nucleotide sequencing; Proteins; Regulatory mechanisms (biology); Software; Structure; Transcription factors; China; Deep learning; Feature integration; Chromatin loops; Multi-source data; Clustering
• ISSN: 1471-2105; 1471-2105
• DOI: 10.1186/s12859-025-06092-6

Background Chromatin loops are critical for the three-dimensional organization of the genome and gene regulation. Accurate identification of chromatin loops is essential for understanding the regulatory mechanisms in disease. However, current mainstream detection methods rely primarily on single-source data, such as Hi-C, which limits these methods’ ability to capture the diverse features of chromatin loop structures. In contrast, multi-source data integration and deep learning approaches, though not yet widely applied, hold significant potential. Results In this study, we developed a method called DconnLoop to integrate Hi-C, ChIP-seq, and ATAC-seq data to predict chromatin loops. This method achieves feature extraction and fusion of multi-source data by integrating residual mechanisms, directional connectivity excitation modules, and interactive feature space decoders. Finally, we apply density estimation and density clustering to the genome-wide prediction results to identify more representative loops. The code is available from https://github.com/kuikui-C/DconnLoop . Conclusions The results demonstrate that DconnLoop outperforms existing methods in both precision and recall. In various experiments, including Aggregate Peak Analysis and peak enrichment comparisons, DconnLoop consistently shows advantages. Extensive ablation studies and validation across different sequencing depths further confirm DconnLoop’s robustness and generalizability.