ChromatinHD

ChromatinHD connects single-cell DNA accessibility and conformation to gene expression through scale-adaptive machine learning.

Key Features:

• Scale-adaptive modeling: Uses raw accessibility data without peak-calling or windows to link regions to gene expression and determine differentially accessible chromatin.
• Regulatory region collaboration analysis: Delineates collaborating regulatory regions, including their preferential genomic conformations, that drive gene expression.
• Transcription factor binding identification: Uses changes in ATAC-seq fragment lengths to identify dense binding of transcription factors, a feature not captured by footprinting methods.

Scientific Applications:

• Gene regulatory network analysis: Connects chromatin accessibility and gene expression in single-cell ATAC+RNA data to understand gene regulatory networks.
• Functional chromatin change detection: Identifies functional accessibility changes within and outside of putative cis-regulatory regions that are uniquely captured compared to peak and window-based approaches.
• Multiscale chromatin accessibility analysis: Enables a data-driven understanding of chromatin accessibility at various scales and how it relates to gene expression.

Methodology:

ChromatinHD employs a pair of scale-adaptive models that use raw accessibility data without peak-calling or windows.