Dacheng Tao

RegimeFormer identifies protein perturbation regimes using a large-scale model and atlas, improving prediction accuracy and enabling downstream applications.

This paper develops MSCNet, a cross-modal generative model for reconstructing and restoring prostate MRI sequences, showing improved image quality and diagnostic performance in multicentre validation.

The paper introduces SAT, a method that uses both paired and unpaired data to improve association tests between biomedical data types, showing better control of false discovery and increased power in real-world applications.

The paper introduces an autoencoder-based cluster ensemble framework for scRNA-seq data to improve cell type-specific clustering.