Shaoqing Jiao

Virtual spatial transcriptomics from histopathology enables prognostic and therapeutic response prediction in cancer

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

DiffuST: a latent diffusion model for spatial transcriptomics denoising

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

Designing AAV Capsid Protein with viability-guided Diffusion Model

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

A Multi-Property Optimizing Generative Adversarial Network for de novo Antimicrobial Peptide Design

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.

Identifying potential risk genes for clear cell renal cell carcinoma with deep reinforcement learning

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.

CellAgent: LLM-Driven Multi-Agent Framework for Natural Language-Based Single-Cell Analysis

CellAgent uses an LLM-driven multi-agent framework to automate scRNA-seq and spatial transcriptomics analysis through natural language interactions, achieving 60% efficiency improvement over manual methods.