Publications by authors named "Kailu Song"
The rapid advancement of single-cell technologies has created an urgent need for effective methods to integrate and harmonize single-cell data. Technical and biological variations across studies complicate data integration, while conventional tools often struggle with reliance on gene expression distribution assumptions and over-correction. Here, we present scCobra, a deep generative neural network designed to overcome these challenges through contrastive learning with domain adaptation.
View Article and Find Full Text PDFArticle Synopsis
- Transposable elements (TEs) play a key role in genetic diversity and gene regulation, yet current methods for quantifying them in single-cell data often overlook accurate mapping to specific loci.
- MATES is a new deep-learning tool that improves the allocation of multi-mapping reads to precise TE locations by leveraging adjacent read contexts, leading to better quantification.
- This method enhances the ability to explore single-cell differences and gene regulation tied to TEs, making it a valuable resource for researchers in single-cell genomics.