bioRxivJClub
MintCNA: A Unified Framework for Integrative Copy Number Profiling with Single-Cell Multi-Omics Data
bioRxiv · · Preprint · Open access
Bao, Xiao
Abstract ↗AI summary
The abstract is read at the publisher; the summary is JClub's.
MintCNA detects chromosomal copy number alterations from paired single-cell multi-omics data, outperforming existing single-cell CNA callers across all simulated scenarios.
- Why it matters: Accurate CNA calling from single-cell measurements is difficult because most methods use only one molecular layer and are vulnerable to assay-specific noise.
- What they did: MintCNA combines deep-learning denoising with a missingness-adjusted multivariate change-point detection approach for paired single-cell multi-omics inputs.
- The result: In a colorectal cancer dataset, MintCNA shows the highest correlation with bulk whole-genome sequencing and tracks progressive loss of chromosome 17 during metastasis.
The findingWhy it mattersWhat they didThe result
AI summary of the abstract · may contain errors · not medical advice · read the paper.
- Open access