Research

Overview

My research develops machine learning methods for understanding complex biological systems. I work at the intersection of artificial intelligence, graph learning, and computational biology, with applications in spatial omics and single-cell genomics.

The long-term goal of my research is to develop computational tools that enable scientific discovery from large-scale biological datasets.

Research Area 1: Spatial Omics

Spatial omics technologies measure molecular activity while preserving spatial organization within tissues.

My work develops computational approaches for:

• Spatial transcriptomics analysis
• Cellular interaction modeling
• Tissue organization studies
• Spatial representation learning

Research Area 2: Single-Cell Genomics

Single-cell technologies provide unprecedented insight into cellular heterogeneity.

Research directions include:

• Cell type identification
• Cell-state transition analysis
• Data integration across studies
• Multi-omic data fusion

Research Area 3: Graph Machine Learning

Many biological systems can naturally be represented as graphs.

Current interests include:

• Graph neural networks
• Biological network analysis
• Knowledge graphs
• Explainable graph learning

Research Area 4: Trustworthy AI for Scientific Discovery

Scientific applications require models that are robust, interpretable, and reproducible.

Research topics include:

• Model interpretability
• Uncertainty quantification
• Reproducible machine learning
• Responsible AI for biomedical applications