Englander Institute for Precision Medicine

ChromaFold predicts the 3D contact map from single-cell chromatin accessibility.

TitleChromaFold predicts the 3D contact map from single-cell chromatin accessibility.
Publication TypeJournal Article
Year of Publication2023
AuthorsGao VR, Yang R, Das A, Luo R, Luo H, McNally DR, Karagiannidis I, Rivas MA, Wang Z-M, Barisic D, Karbalayghareh A, Wong W, Zhan YA, Chin CR, Noble W, Bilmes JA, Apostolou E, Kharas MG, Béguelin W, Viny AD, Huangfu D, Rudensky AY, Melnick AM, Leslie CS
JournalbioRxiv
Date Published2023 Jul 28
Abstract

The identification of cell-type-specific 3D chromatin interactions between regulatory elements can help to decipher gene regulation and to interpret the function of disease-associated non-coding variants. However, current chromosome conformation capture (3C) technologies are unable to resolve interactions at this resolution when only small numbers of cells are available as input. We therefore present ChromaFold, a deep learning model that predicts 3D contact maps and regulatory interactions from single-cell ATAC sequencing (scATAC-seq) data alone. ChromaFold uses pseudobulk chromatin accessibility, co-accessibility profiles across metacells, and predicted CTCF motif tracks as input features and employs a lightweight architecture to enable training on standard GPUs. Once trained on paired scATAC-seq and Hi-C data in human cell lines and tissues, ChromaFold can accurately predict both the 3D contact map and peak-level interactions across diverse human and mouse test cell types. In benchmarking against a recent deep learning method that uses bulk ATAC-seq, DNA sequence, and CTCF ChIP-seq to make cell-type-specific predictions, ChromaFold yields superior prediction performance when including CTCF ChIP-seq data as an input and comparable performance without. Finally, fine-tuning ChromaFold on paired scATAC-seq and Hi-C in a complex tissue enables deconvolution of chromatin interactions across cell subpopulations. ChromaFold thus achieves state-of-the-art prediction of 3D contact maps and regulatory interactions using scATAC-seq alone as input data, enabling accurate inference of cell-type-specific interactions in settings where 3C-based assays are infeasible.

DOI10.1101/2023.07.27.550836
Alternate JournalbioRxiv
PubMed ID37546906
PubMed Central IDPMC10402156
Grant ListK99 DK128602 / DK / NIDDK NIH HHS / United States
R01 CA270245 / CA / NCI NIH HHS / United States
U01 DK128852 / DK / NIDDK NIH HHS / United States
U01 HG012103 / HG / NHGRI NIH HHS / United States

Weill Cornell Medicine Englander Institute for Precision Medicine 413 E 69th Street
Belfer Research Building
New York, NY 10021