Scholarlink

<p>Three-dimensional nuclear DNA architecture comprises well-studied intra-chromosomal (<i>cis</i>) folding and less characterized inter-chromosomal (<i>trans</i>) interfaces. Current predictive models of 3D genome folding overlook <i>trans</i>-genome organization. We present TwinC, an interpretable convolutional neural network model that reliably predicts <i>trans</i> contacts measurable through proximity ligation-dependent (in situ and intact Hi-C) and independent (DNA SPRITE) genome-wide chromatin conformation assays. TwinC achieves high predictive accuracy (AUROC=0.80) on a cross-chromosomal test set from in situ and intact Hi-C experiments in heart tissue. Furthermore, we train TwinC using in situ Hi-C data from the widely used GM12878 cell line and validate its performance with orthogonal DNA SPRITE assay in the same cell type. Mechanistically, the neural network learns the importance of compartments, chromatin accessibility, clustered transcription factor binding, and G-quadruplexes in forming <i>trans</i> contacts. In summary, TwinC models and interprets <i>trans</i> genome architecture, illuminating this poorly understood aspect of gene regulation.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Prediction and functional interpretation of inter-chromosomal genome architecture from DNA sequence with TwinC

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年4月20日

查看全文
  • Anupama Jha,
  • Borislav Hristov,
  • Xiao Wang,
  • Sheng Wang,
  • William J. Greenleaf,
  • Anshul Kundaje,
  • Erez Lieberman Aiden,
  • Alessandro Bertero,
  • William Stafford Noble

摘要

Three-dimensional nuclear DNA architecture comprises well-studied intra-chromosomal (cis) folding and less characterized inter-chromosomal (trans) interfaces. Current predictive models of 3D genome folding overlook trans-genome organization. We present TwinC, an interpretable convolutional neural network model that reliably predicts trans contacts measurable through proximity ligation-dependent (in situ and intact Hi-C) and independent (DNA SPRITE) genome-wide chromatin conformation assays. TwinC achieves high predictive accuracy (AUROC=0.80) on a cross-chromosomal test set from in situ and intact Hi-C experiments in heart tissue. Furthermore, we train TwinC using in situ Hi-C data from the widely used GM12878 cell line and validate its performance with orthogonal DNA SPRITE assay in the same cell type. Mechanistically, the neural network learns the importance of compartments, chromatin accessibility, clustered transcription factor binding, and G-quadruplexes in forming trans contacts. In summary, TwinC models and interprets trans genome architecture, illuminating this poorly understood aspect of gene regulation.