The inherent similarities between natural language and biological sequences have inspired the use of large language models in genomics, but current models struggle to incorporate chromatin interactions or predict in unseen cellular contexts. To address this, we propose EpiGePT, a transformer-based model designed for predicting context-specific human epigenomic signals. By incorporating transcription factor activities and 3D genome interactions, EpiGePT outperforms existing methods in epigenomic signal prediction tasks, especially in cell-type-specific long-range interaction predictions and genetic variant impacts, advancing our understanding of gene regulation. A free online prediction service is available at http://health.tsinghua.edu.cn/epigept .

中文翻译：

---

EpiGePT：一种基于转换器的预训练语言模型，用于特定上下文的人类表观基因组学


自然语言和生物序列之间的内在相似性激发了在基因组学中使用大型语言模型的灵感，但目前的模型难以纳入染色质相互作用或在看不见的细胞环境中进行预测。为了解决这个问题，我们提出了 EpiGePT，这是一种基于 transformer 的模型，旨在预测特定环境的人类表观基因组信号。通过结合转录因子活性和 3D 基因组相互作用，EpiGePT 在表观基因组信号预测任务中优于现有方法，尤其是在细胞类型特异性远程相互作用预测和遗传变异影响方面，促进了我们对基因调控的理解。http://health.tsinghua.edu.cn/epigept 提供免费的在线预测服务。