iScience (Aug 2024)

Deep learning-enhanced R-loop prediction provides mechanistic implications for repeat expansion diseases

  • Jiyun Hu,
  • Zetong Xing,
  • Hongbing Yang,
  • Yongli Zhou,
  • Liufei Guo,
  • Xianhong Zhang,
  • Longsheng Xu,
  • Qiong Liu,
  • Jing Ye,
  • Xiaoming Zhong,
  • Jixin Wang,
  • Ruoyao Lin,
  • Erping Long,
  • Jiewei Jiang,
  • Liang Chen,
  • Yongcheng Pan,
  • Lang He,
  • Jia-Yu Chen

Journal volume & issue
Vol. 27, no. 8
p. 110584

Abstract

Read online

Summary: R-loops play diverse functional roles, but controversial genomic localization of R-loops have emerged from experimental approaches, posing significant challenges for R-loop research. The development and application of an accurate computational tool for studying human R-loops remains an unmet need. Here, we introduce DeepER, a deep learning-enhanced R-loop prediction tool. DeepER showcases outstanding performance compared to existing tools, facilitating accurate genome-wide annotation of R-loops and a deeper understanding of the position- and context-dependent effects of nucleotide composition on R-loop formation. DeepER also unveils a strong association between certain tandem repeats and R-loop formation, opening a new avenue for understanding the mechanisms underlying some repeat expansion diseases. To facilitate broader utilization, we have developed a user-friendly web server as an integral component of R-loopBase. We anticipate that DeepER will find extensive applications in the field of R-loop research.

Keywords