ChromaFold predicts the 3D contact map from single-cell chromatin accessibility
Lists
Only you see this
Abstract
Identifying cell-type-specific 3D chromatin interactions between regulatory elements can help decipher gene regulation and interpret disease-associated non-coding variants. However, achieving this resolution with current 3D genomics technologies is often infeasible given limited input cell numbers. We therefore present ChromaFold, a deep learning model that predicts 3D contact maps, including regulatory interactions, from single-cell ATAC sequencing (scATAC-seq) data alone. ChromaFold uses pseudobulk chromatin accessibility, co-accessibility across metacells, and a CTCF motif track as inputs and employs a lightweight architecture to train on standard GPUs. Trained on paired scATAC-seq and Hi-C data in human samples, ChromaFold accurately predicts the 3D contact map and peak-level interactions across diverse human and mouse test cell types. Compared to leading contact map prediction models that use ATAC-seq and CTCF ChIP-seq, ChromaFold achieves state-of-the-art performance using only scATAC-seq. Finally, fine-tuning ChromaFold on paired scATAC-seq and Hi-C in a complex tissue enables deconvolution of chromatin interactions across cell subpopulations.
BibTeX
@inproceedings{gao2024chromafold,
author = {Vianne R. Gao and Rui Yang and Arnav Das and Renhe Luo and Hanzhi Luo and Dylan McNally and Ioannis Karagiannidis and Martín A. Rivas and Zhong-Min Wang and Darko Barišić and Alireza Karbalayghareh and Wilfred Wong and Yingqian A. Zhan and Christopher R. Chin and William Stafford Noble and Jeff Bilmes and Effie Apostolou and Michael G. Kharas and Wendy Béguelin and Aaron D. Viny and Danwei Huangfu and Alexander Y. Rudensky and Ari Melnick and Christina S. Leslie},
title = {{ChromaFold predicts the 3D contact map from single-cell chromatin accessibility}},
booktitle = {Nature Communications},
year = {2024},
doi = {10.1038/s41467-024-53628-0},
}Loading related content...