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

Vianne R. Gao, Rui Yang, Arnav Das, Renhe Luo, Hanzhi Luo, Dylan R. McNally, Ioannis Karagiannidis, Martin A. Rivas, Zhong-Min Wang, Darko Barisic, Alireza Karbalayghareh, Wilfred Wong, Yingqian A. Zhan, Christopher R. Chin, William S. Noble, Jeff A. Bilmes, Effie Apostolou, Michael G. Kharas, Wendy Béguelin, Aaron D. Viny, Danwei Huangfu, Alexander Y. Rudensky, Ari M. Melnick and Christina S. Leslie ()
Additional contact information
Vianne R. Gao: Memorial Sloan Kettering Cancer Center
Rui Yang: Memorial Sloan Kettering Cancer Center
Arnav Das: University of Washington
Renhe Luo: Sloan Kettering Institute
Hanzhi Luo: Memorial Sloan Kettering Cancer Center
Dylan R. McNally: Cornell University
Ioannis Karagiannidis: Weill Cornell Medical College
Martin A. Rivas: Weill Cornell Medical College
Zhong-Min Wang: Sloan Kettering Institute and Ludwig Center at Memorial Sloan Kettering Cancer Center
Darko Barisic: Weill Cornell Medical College
Alireza Karbalayghareh: Memorial Sloan Kettering Cancer Center
Wilfred Wong: Memorial Sloan Kettering Cancer Center
Yingqian A. Zhan: Memorial Sloan Kettering Cancer Center
Christopher R. Chin: Weill Cornell Medical College
William S. Noble: University of Washington
Jeff A. Bilmes: University of Washington
Effie Apostolou: Weill Cornell Medicine
Michael G. Kharas: Memorial Sloan Kettering Cancer Center
Wendy Béguelin: Weill Cornell Medical College
Aaron D. Viny: Columbia University Irving Medical Center
Danwei Huangfu: Sloan Kettering Institute
Alexander Y. Rudensky: Sloan Kettering Institute and Ludwig Center at Memorial Sloan Kettering Cancer Center
Ari M. Melnick: Weill Cornell Medical College
Christina S. Leslie: Memorial Sloan Kettering Cancer Center

Nature Communications, 2024, vol. 15, issue 1, 1-15

Abstract: 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.

Date: 2024
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.nature.com/articles/s41467-024-53628-0 Abstract (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:nat:natcom:v:15:y:2024:i:1:d:10.1038_s41467-024-53628-0

Ordering information: This journal article can be ordered from
https://www.nature.com/ncomms/

DOI: 10.1038/s41467-024-53628-0

Access Statistics for this article

Nature Communications is currently edited by Nathalie Le Bot, Enda Bergin and Fiona Gillespie

More articles in Nature Communications from Nature
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().