Huaxiu Yao

This study introduces VAE-PRS, a deep learning model that improves polygenic prediction for blood cell traits by capturing interaction effects and outperforming traditional methods in 14 out of 16 traits.

This study compares clustering methods for multi-slide spatial transcriptomics data using simulated and real datasets, evaluating preprocessing techniques' impact on performance.

MAST-Decon improves spatial transcriptomics deconvolution by incorporating spatial neighborhood and histological image features to enhance accuracy and reliability.