ChromaFold predicts the 3D contact map from single-cell chromatin accessibility
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...
Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2024-11-01
|
| Series: | Nature Communications |
| Online Access: | https://doi.org/10.1038/s41467-024-53628-0 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832594634472161280 |
|---|---|
| author | 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 Christina S. Leslie |
| author_facet | 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 Christina S. Leslie |
| author_sort | Vianne R. Gao |
| collection | DOAJ |
| description | 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. |
| format | Article |
| id | doaj-art-9058f5eecd4a4599ae65bc3feace0303 |
| institution | Kabale University |
| issn | 2041-1723 |
| language | English |
| publishDate | 2024-11-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Nature Communications |
| spelling | doaj-art-9058f5eecd4a4599ae65bc3feace03032025-01-19T12:29:35ZengNature PortfolioNature Communications2041-17232024-11-0115111510.1038/s41467-024-53628-0ChromaFold predicts the 3D contact map from single-cell chromatin accessibilityVianne R. Gao0Rui Yang1Arnav Das2Renhe Luo3Hanzhi Luo4Dylan R. McNally5Ioannis Karagiannidis6Martin A. Rivas7Zhong-Min Wang8Darko Barisic9Alireza Karbalayghareh10Wilfred Wong11Yingqian A. Zhan12Christopher R. Chin13William S. Noble14Jeff A. Bilmes15Effie Apostolou16Michael G. Kharas17Wendy Béguelin18Aaron D. Viny19Danwei Huangfu20Alexander Y. Rudensky21Ari M. Melnick22Christina S. Leslie23Computational and Systems Biology Program, Memorial Sloan Kettering Cancer CenterComputational and Systems Biology Program, Memorial Sloan Kettering Cancer CenterUniversity of WashingtonDevelopmental Biology Program, Sloan Kettering InstituteMolecular Pharmacology Program, Experimental Therapeutics Center and Center for Stem Cell Biology, Memorial Sloan Kettering Cancer CenterCaryl and Israel Englander Institute for Precision Medicine, Institute for Computational Biomedicine, Weill Cornell Medicine, Cornell UniversityDivision of Hematology and Medical Oncology, Department of Medicine, Weill Cornell Medical CollegeDivision of Hematology and Medical Oncology, Department of Medicine, Weill Cornell Medical CollegeHoward Hughes Medical Institute and Immunology Program, Sloan Kettering Institute and Ludwig Center at Memorial Sloan Kettering Cancer CenterDivision of Hematology and Medical Oncology, Department of Medicine, Weill Cornell Medical CollegeComputational and Systems Biology Program, Memorial Sloan Kettering Cancer CenterComputational and Systems Biology Program, Memorial Sloan Kettering Cancer CenterCenter for Epigenetics Research, Memorial Sloan Kettering Cancer CenterDivision of Hematology and Medical Oncology, Department of Medicine, Weill Cornell Medical CollegeUniversity of WashingtonUniversity of WashingtonJoan and Sanford I. Weill Department of Medicine, Sandra and Edward Meyer Cancer Center, Weill Cornell MedicineMolecular Pharmacology Program, Experimental Therapeutics Center and Center for Stem Cell Biology, Memorial Sloan Kettering Cancer CenterDivision of Hematology and Medical Oncology, Department of Medicine, Weill Cornell Medical CollegeDepartments of Medicine, Division of Hematology & Oncology, and of Genetics & Development, Columbia Stem Cell Initiative, Herbert Irving Comprehensive Cancer Center, Columbia University Irving Medical CenterDevelopmental Biology Program, Sloan Kettering InstituteHoward Hughes Medical Institute and Immunology Program, Sloan Kettering Institute and Ludwig Center at Memorial Sloan Kettering Cancer CenterDivision of Hematology and Medical Oncology, Department of Medicine, Weill Cornell Medical CollegeComputational and Systems Biology Program, Memorial Sloan Kettering Cancer CenterAbstract 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.https://doi.org/10.1038/s41467-024-53628-0 |
| spellingShingle | 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 Christina S. Leslie ChromaFold predicts the 3D contact map from single-cell chromatin accessibility Nature Communications |
| title | ChromaFold predicts the 3D contact map from single-cell chromatin accessibility |
| title_full | ChromaFold predicts the 3D contact map from single-cell chromatin accessibility |
| title_fullStr | ChromaFold predicts the 3D contact map from single-cell chromatin accessibility |
| title_full_unstemmed | ChromaFold predicts the 3D contact map from single-cell chromatin accessibility |
| title_short | ChromaFold predicts the 3D contact map from single-cell chromatin accessibility |
| title_sort | chromafold predicts the 3d contact map from single cell chromatin accessibility |
| url | https://doi.org/10.1038/s41467-024-53628-0 |
| work_keys_str_mv | AT viannergao chromafoldpredictsthe3dcontactmapfromsinglecellchromatinaccessibility AT ruiyang chromafoldpredictsthe3dcontactmapfromsinglecellchromatinaccessibility AT arnavdas chromafoldpredictsthe3dcontactmapfromsinglecellchromatinaccessibility AT renheluo chromafoldpredictsthe3dcontactmapfromsinglecellchromatinaccessibility AT hanzhiluo chromafoldpredictsthe3dcontactmapfromsinglecellchromatinaccessibility AT dylanrmcnally chromafoldpredictsthe3dcontactmapfromsinglecellchromatinaccessibility AT ioanniskaragiannidis chromafoldpredictsthe3dcontactmapfromsinglecellchromatinaccessibility AT martinarivas chromafoldpredictsthe3dcontactmapfromsinglecellchromatinaccessibility AT zhongminwang chromafoldpredictsthe3dcontactmapfromsinglecellchromatinaccessibility AT darkobarisic chromafoldpredictsthe3dcontactmapfromsinglecellchromatinaccessibility AT alirezakarbalayghareh chromafoldpredictsthe3dcontactmapfromsinglecellchromatinaccessibility AT wilfredwong chromafoldpredictsthe3dcontactmapfromsinglecellchromatinaccessibility AT yingqianazhan chromafoldpredictsthe3dcontactmapfromsinglecellchromatinaccessibility AT christopherrchin chromafoldpredictsthe3dcontactmapfromsinglecellchromatinaccessibility AT williamsnoble chromafoldpredictsthe3dcontactmapfromsinglecellchromatinaccessibility AT jeffabilmes chromafoldpredictsthe3dcontactmapfromsinglecellchromatinaccessibility AT effieapostolou chromafoldpredictsthe3dcontactmapfromsinglecellchromatinaccessibility AT michaelgkharas chromafoldpredictsthe3dcontactmapfromsinglecellchromatinaccessibility AT wendybeguelin chromafoldpredictsthe3dcontactmapfromsinglecellchromatinaccessibility AT aarondviny chromafoldpredictsthe3dcontactmapfromsinglecellchromatinaccessibility AT danweihuangfu chromafoldpredictsthe3dcontactmapfromsinglecellchromatinaccessibility AT alexanderyrudensky chromafoldpredictsthe3dcontactmapfromsinglecellchromatinaccessibility AT arimmelnick chromafoldpredictsthe3dcontactmapfromsinglecellchromatinaccessibility AT christinasleslie chromafoldpredictsthe3dcontactmapfromsinglecellchromatinaccessibility |