Dazhi Lu

VISTA infers spatial gene expression from H&E images, predicting gene expression and clinical outcomes in cancer samples.

DiffuST denoises spatial transcriptomics data by integrating spatial features and pathology images, improving downstream analysis and biological insights.

This paper introduces AAVDiffusion, a viability-guided diffusion model for designing viable AAV capsid proteins, showing improved performance in generating functional sequences.

This paper introduces MPOGAN, a generative adversarial network for designing antimicrobial peptides with multiple desired properties, showing improved performance in antimicrobial activity and reduced cytotoxicity.

This paper introduces RL-GenRisk, a deep reinforcement learning method for identifying ccRCC risk genes, which outperforms existing methods and identifies ten novel risk genes, including validated EGFR.