Research Interests

Artificial Intelligence in Healthcare

Developing machine learning and deep learning models for clinical decision support, disease prediction (e.g., liver fibrosis, cancer), and patient outcome modeling using EHR data.

Graph Machine Learning

Designing graph neural networks (GNNs), especially for biomedical applications like protein interactions, patient graphs, and knowledge graphs.

Bioinformatics & Computational Biology

Modeling biological sequences (e.g., proteins, genes) using transformer-based models for tasks like protein-protein interaction and host-pathogen modeling.

Multimodal and Cross-Domain Learning

Integrating heterogeneous data types (e.g., text, lab values, medical images, molecular sequences) and transferring knowledge across domains with limited supervision.

Natural Language Processing

Extracting clinical insights from free-text medical notes using large language models (LLMs) and rule-based systems.