DeepMILO: a deep learning approach to predict the impact of non-coding sequence variants on 3D chromatin structure

Genome Biol. 2020 Mar 26;21(1):79. doi: 10.1186/s13059-020-01987-4.

Abstract

Non-coding variants have been shown to be related to disease by alteration of 3D genome structures. We propose a deep learning method, DeepMILO, to predict the effects of variants on CTCF/cohesin-mediated insulator loops. Application of DeepMILO on variants from whole-genome sequences of 1834 patients of twelve cancer types revealed 672 insulator loops disrupted in at least 10% of patients. Our results show mutations at loop anchors are associated with upregulation of the cancer driver genes BCL2 and MYC in malignant lymphoma thus pointing to a possible new mechanism for their dysregulation via alteration of insulator loops.

Keywords: 3D genome; BCL2; Cancer; Deep learning; MYC; Non-coding mutation.

Publication types

  • Research Support, N.I.H., Extramural

MeSH terms

  • CCCTC-Binding Factor / metabolism
  • Cell Cycle Proteins / metabolism
  • Cell Line, Tumor
  • Chromatin / chemistry*
  • Chromosomal Proteins, Non-Histone / metabolism
  • Cohesins
  • Deep Learning*
  • Humans
  • Insulator Elements*
  • Mutation
  • Neoplasms / genetics*
  • Whole Genome Sequencing

Substances

  • CCCTC-Binding Factor
  • Cell Cycle Proteins
  • Chromatin
  • Chromosomal Proteins, Non-Histone