Wenkai Han

Unify learns universal cell embeddings across species by integrating RNA expression with protein and general language model embeddings, enabling cross-species comparisons and accurate perturbation response prediction.

This study introduces STAG-seq, a method combining transcriptomics and genotyping to functionally analyze genetic variants in immune cells, revealing their impact on gene expression and disease mechanisms.

PPML-Omics is a privacy-preserving federated learning method that balances privacy protection and model utility across three omic data tasks.

CLEAR is a self-supervised contrastive learning framework for scRNA-seq that improves clustering, batch correction, and pseudo-time inference by reducing technical noise and heterogeneity.

DeeReCT-TSS improves TSS annotation across cell types using DNA sequences and RNA-seq data, outperforming sequence-only methods and enabling cell-type-specific TSS identification.