Our lab develops AI-enabled, mechanism-aware computational approaches to support basic, clinical and translational research. We focus on using AI as shared translational infrastructure, integrating complex biomedical data, generating biologically interpretable insight, and supporting decision-making rather than automation.
Mechanism-Aware Modeling of Biological Communication
A central theme of our research is modeling cell-to-cell communication and regulatory mechanisms, with particular focus on microRNA-mediated signaling. We reconstruct regulatory networks, identify sorting and transport mechanisms, and generate testable hypotheses relevant to cancer, metabolic disease, and systemic regulation.
AI-Guided Biomarker Discovery
We develop AI frameworks for discovering and prioritizing circulating and non-invasive biomarkers, especially secreted proteins and microRNAs. Our approaches integrate biological context with large-scale data to support pilot studies, cohort-based validation, and translational evaluation.
Nutrient-Aware, Multi-Scale Health Modeling
We study nutrition as a dynamic perturbation to metabolic systems, modeling diet-induced metabolic reprogramming across organ, single-cell, and gut microbiome scales. Our work includes metabolic flux modeling in the liver and systems-level integration of molecular, behavioral, and clinical data.
Longitudinal Health Trajectories & Decision Support
We focus on modeling health trajectories over time, enabling risk stratification, response-to-intervention analysis, and monitoring in real-world and translational settings. All systems are designed as human-in-the-loop decision-support tools, aligned with clinical workflows and translational goals.