{
  "abstract": "Three-dimensional chromatin interactions play essential roles in gene regulation, yet computational prediction of diverse interaction types remains largely dependent on specialized, single-task models. Here, we present UniLoopNet, a multi-task deep learning framework that predicts multiple types of chromatin interactions including enhancer–promoter interactions, enhancer–enhancer interactions, CTCF-mediated loops, and stripe-associated interactions from DNA sequences. UniLoopNet employs a shared encoder–decoder architecture with hierarchical adaptation strategies, integrating multi-task, transfer, and continual learning based on task semantic similarity. Comprehensive benchmarking across multiple cell lines demonstrates that UniLoopNet outperforms existing specialized and multi-task approaches, with AUROCs exceeding 0.90 in most tasks. Under stringent evaluation settings, including chromosome-matched, distance-matched, realistic imbalanced, and locus-disjoint tests, AUROCs range from 0.8934 to 0.9366. In the realistic 1:5 class-imbalance setting, the AUPRCs for enhancer–promoter and enhancer–enhancer interaction prediction are 0.7956 and 0.6935, respectively. Cross-cell-line transfer experiments further show that applying UniLoopNet to another cell line requires adaptation by supervised fine-tuning on target-cell-line data, after which performance is comparable to that of within-cell-line training. Notably, the framework exhibits data efficiency in experiments with substantially reduced training data. Interpretability analyses reveal that the learned sequence features are associated with known transcription factor binding sites and uncover differential regulatory effects of disease-associated variants. UniLoopNet provides a versatile and data-efficient framework for sequence-based prediction and interpretation of diverse 3D genome interactions, complementing existing sequence-to-map approaches while improving the understanding of sequence-encoded regulatory potential. Author summary: The three-dimensional organization of the genome plays a critical role in regulating gene expression by bringing distant regulatory regions into physical contact. However, current computational methods for predicting chromatin interactions are usually designed for individual interaction types, such as enhancer–promoter loops or protein-mediated contacts, requiring separate models for each task. This limits their ability to transfer knowledge across related genomic problems, especially when experimental data are limited. Here, we develop UniLoopNet, an extensible deep learning framework that can predict multiple types of chromatin interactions from DNA sequences. Instead of relying on a single learning strategy, UniLoopNet automatically adapts its knowledge-transfer strategy according to the similarity between different prediction tasks, enabling efficient learning of new interaction types. UniLoopNet achieves accurate predictions across diverse chromatin interaction tasks, is data-efficient, and identifies sequence patterns associated with different regulatory interactions. Applying UniLoopNet to disease-associated genetic variants further suggests how non-coding mutations may influence genome organization. Our study thus provides a flexible computational framework for studying genome regulation and interpreting functional genomic variation.",
  "abstract_shown": true,
  "affiliations": [
    "School of Biomedical Engineering, Anhui Medical University, Hefei, Anhui, China",
    "Department of Computer Science and Technology, Anhui Medical University, Hefei, Anhui, China",
    "Department of Pediatrics, The First Affiliated Hospital of Anhui Medical University, Hefei, Anhui, China",
    "The Affiliated Chuzhou Hospital of Anhui Medical University, The First People’s Hospital of Chuzhou, Chuzhou, Anhui, China",
    "Second Affiliated Hospital of Anhui Medical University, Hefei, Anhui, China"
  ],
  "article_type": "Research Article",
  "arxiv": null,
  "author_total": 7,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "Shuaibin Wang"
    },
    {
      "affs": [
        0
      ],
      "name": "Tong Chen"
    },
    {
      "affs": [
        1
      ],
      "name": "Weixu Liu"
    },
    {
      "affs": [
        2
      ],
      "name": "Xuejie Zheng"
    },
    {
      "affs": [
        0
      ],
      "name": "Zhongxin Yang"
    },
    {
      "affs": [
        0,
        3
      ],
      "name": "Zhen Liang"
    },
    {
      "affs": [
        0,
        4
      ],
      "name": "Yin Shen",
      "orcid": "0000-0001-7002-4022"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/7bqtc4nma7pc4.bib",
  "cited_by": 0,
  "doi": "10.1371/journal.pcbi.1014911",
  "fulltext_url": "https://journals.plos.org/ploscompbiol/article?id=10.1371/journal.pcbi.1014911",
  "id": "7bqtc4nma7pc4",
  "issns": [
    "1553-7358",
    "1553-734X"
  ],
  "landing_url": "https://journals.plos.org/ploscompbiol/article?id=10.1371/journal.pcbi.1014911",
  "language": "en",
  "licence": "CC-BY-4.0",
  "licence_label": "CC BY 4.0",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "heading",
      "Artificial Intelligence"
    ],
    [
      "heading",
      "Autoimmune Diseases"
    ],
    [
      "heading",
      "Biology and Life Sciences"
    ],
    [
      "heading",
      "Cell Biology"
    ],
    [
      "heading",
      "Chromatin"
    ],
    [
      "heading",
      "Chromosome Biology"
    ],
    [
      "heading",
      "Clinical Immunology"
    ],
    [
      "heading",
      "Clinical Medicine"
    ],
    [
      "heading",
      "Cognition"
    ],
    [
      "heading",
      "Cognitive Psychology"
    ],
    [
      "heading",
      "Cognitive Science"
    ],
    [
      "heading",
      "Computer and Information Sciences"
    ],
    [
      "heading",
      "Deep Learning"
    ],
    [
      "heading",
      "Epigenetics"
    ],
    [
      "heading",
      "Gene Expression"
    ],
    [
      "heading",
      "Gene Regulation"
    ],
    [
      "heading",
      "Genetics"
    ],
    [
      "heading",
      "Genomics"
    ],
    [
      "heading",
      "Immunology"
    ],
    [
      "heading",
      "Learning"
    ],
    [
      "heading",
      "Learning and Memory"
    ],
    [
      "heading",
      "Lupus Erythematosus"
    ],
    [
      "heading",
      "Machine Learning"
    ],
    [
      "heading",
      "Medicine and Health Sciences"
    ],
    [
      "heading",
      "Memory"
    ],
    [
      "heading",
      "Memory Recall"
    ],
    [
      "heading",
      "Neuroscience"
    ],
    [
      "heading",
      "Psychology"
    ],
    [
      "heading",
      "Research Article"
    ],
    [
      "heading",
      "Rheumatology"
    ],
    [
      "heading",
      "Social Sciences"
    ],
    [
      "heading",
      "Structural Genomics"
    ],
    [
      "heading",
      "Systemic Lupus Erythematosus"
    ],
    [
      "openalex",
      "1312|Genomics and Chromatin Dynamics"
    ],
    [
      "plos",
      "/Biology and life sciences/Cell biology/Chromosome biology/Chromatin"
    ],
    [
      "plos",
      "/Biology and life sciences/Genetics/Epigenetics/Chromatin"
    ],
    [
      "plos",
      "/Biology and life sciences/Genetics/Gene expression/Chromatin"
    ],
    [
      "plos",
      "/Biology and life sciences/Genetics/Gene expression/Gene regulation"
    ],
    [
      "plos",
      "/Biology and life sciences/Genetics/Genomics"
    ],
    [
      "plos",
      "/Biology and life sciences/Genetics/Genomics/Structural genomics"
    ],
    [
      "plos",
      "/Biology and life sciences/Immunology/Clinical immunology/Autoimmune diseases/Lupus erythematosus/Systemic lupus erythematosus"
    ],
    [
      "plos",
      "/Biology and life sciences/Neuroscience/Cognitive science/Cognition/Memory/Memory recall"
    ],
    [
      "plos",
      "/Biology and life sciences/Neuroscience/Cognitive science/Cognitive psychology/Learning"
    ],
    [
      "plos",
      "/Biology and life sciences/Neuroscience/Learning and memory/Learning"
    ],
    [
      "plos",
      "/Biology and life sciences/Neuroscience/Learning and memory/Memory/Memory recall"
    ],
    [
      "plos",
      "/Biology and life sciences/Psychology/Cognitive psychology/Learning"
    ],
    [
      "plos",
      "/Computer and information sciences/Artificial intelligence/Machine learning/Deep learning"
    ],
    [
      "plos",
      "/Medicine and health sciences/Clinical medicine/Clinical immunology/Autoimmune diseases/Lupus erythematosus/Systemic lupus erythematosus"
    ],
    [
      "plos",
      "/Medicine and health sciences/Immunology/Clinical immunology/Autoimmune diseases/Lupus erythematosus/Systemic lupus erythematosus"
    ],
    [
      "plos",
      "/Medicine and health sciences/Rheumatology/Systemic lupus erythematosus"
    ],
    [
      "plos",
      "/Social sciences/Psychology/Cognitive psychology/Learning"
    ]
  ],
  "openalex": "W7223783451",
  "pdf_url": "https://journals.plos.org/ploscompbiol/article/file?id=10.1371/journal.pcbi.1014911&type=printable",
  "pmcid": "PMC13730424",
  "pmid": "42945383",
  "published": "2026-10-27",
  "publisher": "Public Library of Science",
  "ris": "https://research.draconitic.com/paper/7bqtc4nma7pc4.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:17:17Z",
      "native_id": "10.1371/journal.pcbi.1014911",
      "source": "plos",
      "url": "https://journals.plos.org/ploscompbiol/article?id=10.1371/journal.pcbi.1014911"
    },
    {
      "first_seen": "2026-11-07T12:22:59Z",
      "native_id": "PMC13730424",
      "source": "pmc",
      "url": "https://doi.org/10.1371/journal.pcbi.1014911"
    }
  ],
  "subjects": [
    {
      "field": "biochemistry",
      "origin": "plos:gene expression",
      "subfield": "molecular-biology"
    },
    {
      "field": "biology",
      "origin": "heading:Cell Biology",
      "subfield": "cell-biology"
    },
    {
      "field": "biology",
      "origin": "plos:genetics",
      "subfield": "genetics-genomics"
    },
    {
      "field": "biology",
      "origin": "plos:neuroscience",
      "subfield": "neuroscience"
    },
    {
      "field": "medicine",
      "origin": "heading:Clinical Medicine",
      "subfield": "general"
    }
  ],
  "title": "An extensible deep learning framework for multi-type chromatin interaction prediction through hierarchical adaptation strategies",
  "title_text": "An extensible deep learning framework for multi-type chromatin interaction prediction through hierarchical adaptation strategies",
  "type": "peer-reviewed",
  "updated_at": "2026-11-07T12:22:59Z",
  "url": "https://research.draconitic.com/paper/7bqtc4nma7pc4",
  "venue": "PLOS Computational Biology",
  "versions": []
}