Yang Xu

multiVIB integrates single-cell multi-omics data across modalities and species with a probabilistic contrastive learning framework, achieving state-of-the-art performance while preserving biological variation.

scDecorr provides a self-supervised framework for integrating single-cell RNA-seq data by decorrelating features and adapting to domain differences, improving clustering and label transfer.

CellCap models the relationship between cell state and perturbation response in single-cell experiments, revealing novel insights into cellular behavior.

MASIv2 provides a framework for standardizing and integrating multi-modal single-cell and spatial omics data through shared and specific features.

sciCAN integrates single-cell chromatin accessibility and gene expression data using an adversarial network, outperforming existing methods in cross-modal transfer and preserving biological structure in hematopoietic data.

MASI provides a fast, model-free method for standardizing cell-type annotation and integrating single-cell transcriptomics datasets, achieving comparable or superior performance to existing methods.

MACA is a tool for automatic cell-type annotation in single-cell transcriptomics datasets, showing improved accuracy and speed compared to existing methods.

SMILE integrates single-cell omics data by learning discriminative representations through mutual information maximization, effectively removing batch effects and aligning diverse data types.

CoSTA uses a convolutional neural network to analyze spatial transcriptomics data, identifying gene relationships based on spatial patterns rather than pixel-level correlation.

This study examines how DNA damage and repair affect 3D genome organization using Hi-C in different cell types, finding cell-type-specific changes and TAD boundary strengthening in repair-proficient cells.