论文题目：CLAMP: predicting specific protein-mediated chromatin loops in diverse species with a chromatin accessibility language model
论文作者：Zhijie He, Yu Sun, Hao Li, Canzhuang Sun, Xianhui Yang, Hebing Chen, Mingzhi Liao & Xiaochen Bo
论文摘要：
Emerging DNA language models provide powerful tools to address the challenge of accurately predicting chromatin loops, fundamental structures governing 3D genome organization and gene regulation. Here we present CLAMP, which utilizes a deep language model pre-trained on broad cross-species chromatin accessibility data. CLAMP achieves superior performance compared to existing methods in predicting specific protein-mediated loops across 10 species, 18 proteins, and 24 cell types. CLAMP incorporates a novel CoVE explainer that reveals context-dependent genomic feature contributions, providing insights into the features driving predictions. CLAMP predictions effectively identify functionally significant chromatin loops and associated biological pathways.
新兴DNA语言模型为解决染色质环精准预测这一难题提供了强大工具 —— 染色质环是调控三维基因组构象与基因表达的关键结构。本文提出 CLAMP 模型，其采用基于跨物种染色质可及性大数据预训练的深度语言模型。在涵盖10个物种、18种蛋白质及24种细胞类型的特定蛋白质介导染色质环预测任务中，CLAMP 的性能优于现有方法。该模型整合了新型 CoVE 解释器，可揭示依赖于上下文的基因组特征贡献，为解析驱动预测的核心特征提供了思路。CLAMP 的预测结果能有效识别具有功能意义的染色质环及相关生物学通路。
论文链接：https://link.springer.com/article/10.1186/s13059-026-03948-9