Jeff A. Bilmes's Publications

• Sorted by Date • Classified by Publication Type • Classified by Research Category • Sorted by First Author Last Name • Classified by Author Last Name •

Epiphany: predicting Hi-C contact maps from 1D epigenomic signals

Rui Yang, Arnav Das, Vianne R. Gao, Alireza Karbalayghareh, William S. Noble, Jeffery A. Bilmes, and Christina S. Leslie. Epiphany: predicting Hi-C contact maps from 1D epigenomic signals. Genome Biology, 24(1):134, 2023.

Download

[PDF] [gzipped postscript] [postscript] [HTML] 

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.

@article{Yang2023,
  author = {Yang, Rui and Das, Arnav and Gao, Vianne R. and Karbalayghareh, Alireza and Noble, William S. and Bilmes, Jeffery A. and Leslie, Christina S.},
  title = {Epiphany: predicting {Hi-C} contact maps from 1{D} epigenomic signals},
  journal = {Genome Biology},
  year = {2023},
  volume = {24},
  number = {1},
  pages = {134},
  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.},
  issn = {1474-760X},
  doi = {10.1186/s13059-023-02934-9},
  url = {https://doi.org/10.1186/s13059-023-02934-9},
}

Share

Generated by bib2html.pl (written by Patrick Riley ) on Fri Oct 31, 2025 22:30:01