ChromatinHD connects single-cell DNA accessibility and conformation to gene expression through scale-adaptive machine learning
Abstract Gene regulation is inherently multiscale, but scale-adaptive machine learning methods that fully exploit this property in single-nucleus accessibility data are still lacking. Here, we develop ChromatinHD, a pair of scale-adaptive models that uses the raw accessibility data, without peak-cal...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-01-01
|
| Series: | Nature Communications |
| Online Access: | https://doi.org/10.1038/s41467-024-55447-9 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841559237284593664 |
|---|---|
| author | Wouter Saelens Olga Pushkarev Bart Deplancke |
| author_facet | Wouter Saelens Olga Pushkarev Bart Deplancke |
| author_sort | Wouter Saelens |
| collection | DOAJ |
| description | Abstract Gene regulation is inherently multiscale, but scale-adaptive machine learning methods that fully exploit this property in single-nucleus accessibility data are still lacking. Here, we develop ChromatinHD, a pair of scale-adaptive models that uses the raw accessibility data, without peak-calling or windows, to link regions to gene expression and determine differentially accessible chromatin. We show how ChromatinHD consistently outperforms existing peak and window-based approaches and find that this is due to a large number of uniquely captured, functional accessibility changes within and outside of putative cis-regulatory regions. Furthermore, ChromatinHD can delineate collaborating regulatory regions, including their preferential genomic conformations, that drive gene expression. Finally, our models also use changes in ATAC-seq fragment lengths to identify dense binding of transcription factors, a feature not captured by footprinting methods. Altogether, ChromatinHD, available at https://chromatinhd.org , is a suite of computational tools that enables a data-driven understanding of chromatin accessibility at various scales and how it relates to gene expression. |
| format | Article |
| id | doaj-art-b6c79a29d6b24a288d9db0a4740d6824 |
| institution | Kabale University |
| issn | 2041-1723 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Nature Communications |
| spelling | doaj-art-b6c79a29d6b24a288d9db0a4740d68242025-01-05T12:41:01ZengNature PortfolioNature Communications2041-17232025-01-0116111810.1038/s41467-024-55447-9ChromatinHD connects single-cell DNA accessibility and conformation to gene expression through scale-adaptive machine learningWouter Saelens0Olga Pushkarev1Bart Deplancke2Laboratory of Systems Biology and Genetics, Institute of Bio-engineering and Global Health Institute, School of Life Sciences, Swiss Federal Institute of Technology (EPFL)Laboratory of Systems Biology and Genetics, Institute of Bio-engineering and Global Health Institute, School of Life Sciences, Swiss Federal Institute of Technology (EPFL)Laboratory of Systems Biology and Genetics, Institute of Bio-engineering and Global Health Institute, School of Life Sciences, Swiss Federal Institute of Technology (EPFL)Abstract Gene regulation is inherently multiscale, but scale-adaptive machine learning methods that fully exploit this property in single-nucleus accessibility data are still lacking. Here, we develop ChromatinHD, a pair of scale-adaptive models that uses the raw accessibility data, without peak-calling or windows, to link regions to gene expression and determine differentially accessible chromatin. We show how ChromatinHD consistently outperforms existing peak and window-based approaches and find that this is due to a large number of uniquely captured, functional accessibility changes within and outside of putative cis-regulatory regions. Furthermore, ChromatinHD can delineate collaborating regulatory regions, including their preferential genomic conformations, that drive gene expression. Finally, our models also use changes in ATAC-seq fragment lengths to identify dense binding of transcription factors, a feature not captured by footprinting methods. Altogether, ChromatinHD, available at https://chromatinhd.org , is a suite of computational tools that enables a data-driven understanding of chromatin accessibility at various scales and how it relates to gene expression.https://doi.org/10.1038/s41467-024-55447-9 |
| spellingShingle | Wouter Saelens Olga Pushkarev Bart Deplancke ChromatinHD connects single-cell DNA accessibility and conformation to gene expression through scale-adaptive machine learning Nature Communications |
| title | ChromatinHD connects single-cell DNA accessibility and conformation to gene expression through scale-adaptive machine learning |
| title_full | ChromatinHD connects single-cell DNA accessibility and conformation to gene expression through scale-adaptive machine learning |
| title_fullStr | ChromatinHD connects single-cell DNA accessibility and conformation to gene expression through scale-adaptive machine learning |
| title_full_unstemmed | ChromatinHD connects single-cell DNA accessibility and conformation to gene expression through scale-adaptive machine learning |
| title_short | ChromatinHD connects single-cell DNA accessibility and conformation to gene expression through scale-adaptive machine learning |
| title_sort | chromatinhd connects single cell dna accessibility and conformation to gene expression through scale adaptive machine learning |
| url | https://doi.org/10.1038/s41467-024-55447-9 |
| work_keys_str_mv | AT woutersaelens chromatinhdconnectssinglecelldnaaccessibilityandconformationtogeneexpressionthroughscaleadaptivemachinelearning AT olgapushkarev chromatinhdconnectssinglecelldnaaccessibilityandconformationtogeneexpressionthroughscaleadaptivemachinelearning AT bartdeplancke chromatinhdconnectssinglecelldnaaccessibilityandconformationtogeneexpressionthroughscaleadaptivemachinelearning |