Epiphany: Predicting Hi-C contact maps from 1D epigenomic signals Journal Article


Authors: Yang, R.; Das, A.; Gao, V. R.; Karbalayghareh, A.; Noble, W. S.; Bilmes, J. A.; Leslie, C. S.
Article Title: Epiphany: Predicting Hi-C contact maps from 1D epigenomic signals
Abstract: Recent deep learning models that predict the Hi-C contact map from DNA sequence achieve promising accuracy but cannot generalize to new cell types and or even capture differences among training cell types. We propose Epiphany, a neural network to predict cell-type-specific Hi-C contact maps from widely available epigenomic tracks. Epiphany uses bidirectional long short-term memory layers to capture long-range dependencies and optionally a generative adversarial network architecture to encourage contact map realism. Epiphany shows excellent generalization to held-out chromosomes within and across cell types, yields accurate TAD and interaction calls, and predicts structural changes caused by perturbations of epigenomic signals. © 2023, The Author(s).
Keywords: chromosome; epigenetics; dna sequence; epigenomics; short term memory; article; deep learning; 3d genome
Journal Title: Genome Biology
Volume: 24
ISSN: 1465-6906
Publisher: Biomed Central Ltd  
Date Published: 2023-06-06
Start Page: 134
Language: English
DOI: 10.1186/s13059-023-02934-9
PUBMED: 37280678
PROVIDER: scopus
PMCID: PMC10242996
DOI/URL:
Notes: Article -- MSK corresponding author is Christina Leslie -- Erratum issued, see DOI: 10.1186/s13059-024-03281-z -- Source: Scopus
Altmetric
Citation Impact
BMJ Impact Analytics
MSK Authors
  1. Rui Yang
    23 Yang
  2. Christina Leslie
    189 Leslie
  3. Vianne Ran Gao
    12 Gao