Normalization and De-noising of Single-cell Hi-C Data with BandNorm and 3DVI
Zheng, Y.; Shen, S.; Keles, S.
Show abstract
Single-cell high-throughput chromatin conformation capture methodologies (scHi-C) enable profiling long-range genomic interactions at the single-cell resolution; however, data from these technologies are prone to technical noise and bias that, when unaccounted for, hinder downstream analysis. Here we developed a fast band normalization approach, BandNorm, and a deep generative modeling framework, 3DVI, to explicitly account for scHi-C specific technical biases. We present robust performances of BandNorm and 3DVI compared to existing state-of-the-art methods. BandNorm is effective in separating cell types, identification of interaction features, and recovery of cell-cell relationship, whereas de-noising by 3DVI successfully enables 3D compartments and domains recovery, especially for rare cell types.
Matching journals
The top 4 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- INSTINCT: Multi-sample integration of spatial chromatin accessibility sequencing data via stochastic domain translation 97%
- PACS allows comprehensive dissection of multiple factors governing chromatin accessibility from snATAC-seq data 97%
- Pathway Centric Analysis for single-cell RNA-seq and Spatial Transcriptomics Data with GSDensity 97%
Similar papers in this journal
Similar papers in this journal
Similar papers in this journal
- Multi-omics integration and regulatory inference for unpaired single-cell data with a graph-linked unified embedding framework 97%
- Dictionary learning for integrative, multimodal, and scalable single-cell analysis 96%
- Cell-ID: gene signature extraction and cell identity recognition at individual cell level 96%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.