scAURA: Alignment- and Uniformity-based Graph DebiasedContrastive Representation Architecture for Self-SupervisedClustering of Single-Cell Transcriptomics
Jubair Ibn Malik Rifat, Sarthak Engala, Serdar Bozdag
scAURA improves cell type clustering in scRNA-seq by integrating graph debiased contrastive learning, outperforming existing methods across multiple datasets.
bioRxiv · Jan 27, 2026 · PreprintBioinformatics