The Hu Li Lab: AI-Dirven Systems Biology for Precision Medicine
The Li Lab is committed to uncovering the fundamental rules that govern how genes, pathways, and cellular processes interact to shape complex human diseases. Our research is driven by the belief that biology is fundamentally a networked, dynamic system and that understanding disease requires moving beyond single-gene perspectives toward integrative, multiscale models of health and pathology. By bringing together systems biology, artificial intelligence (AI), and large-scale biomedical data, we aim to illuminate the hidden architecture of disease and accelerate the discovery of transformative therapeutics.

Mission
Our mission is to transform the expanding landscape of biomedical Big Data into actionable biological insight that accelerates precision medicine. We seek to understand why diseases emerge, how they progress, and when and what interventions can best restore healthy system states. Grounded in principles of network biology and systems pharmacology, we develop computational frameworks that uncover disease-driving mechanisms, predict therapeutic responses, and inform individualized treatment strategies. By integrating multi-scale data with mechanistic modeling, we aim to illuminate the dynamic processes that shape health and disease.

Vision
We envision a future in which complex diseases can be decoded computationally, allowing clinicians to intervene earlier, developers to design smarter therapeutics, and patients to receive optimized, personalized care. In this future:

• clinicians identify disease trajectories early, enabling timely and targeted intervention,
• therapeutic developers design smarter, mechanism-guided treatments, and
• patients receive personalized care tailored to their unique biology.

By bridging AI, computation, systems biology, and translational medicine, we aspire to enable healthcare that is proactive, precise, and restorative.

Research Themes
1. AI for Systems Biology and Disease Mechanisms
We develop machine learning and AI systems that reveal patterns and mechanistic interactions hidden in large, heterogeneous datasets. Our approaches integrate multi-omics, imaging, clinical, and experimental data to build predictive models of cellular behavior and disease evolution. These models help identify regulatory circuits, gene-gene interactions, and system vulnerabilities that may serve as biomarkers or therapeutic entry points.

2. Disease Network Architecture and Pathway Dynamics
A major focus of the lab is understanding the molecular circuitry that drives complex diseases-including cancer, digestive diseases, nutritional and metabolic disorders, immunological disorders, and neurodegenerative and neurological disorders. We build dynamic network models that explain how genetic perturbations propagate through biological systems, leading to disease phenotypes. These integrative frameworks allow us to distinguish core disease mechanisms from peripheral noise and uncover master regulators that may not be obvious from traditional analyses.

3. Systems Pharmacology and Drug Mechanism Discovery
We combine computational modeling with pharmacological principles to map how drugs modulate biological networks. Our tools identify drug targets, infer mechanisms of action, and predict combinatorial therapies that shift diseased systems toward restoration. This systems-level perspective enables us to anticipate off-target effects, drug resistance, and patient-specific response variability, key challenges in modern therapeutics.

4. Individualized Systems Medicine
Every patient's disease is unique. We are developing personalized computational pipelines that integrate patient-specific genomic, transcriptomic, and clinical data to construct individualized disease models. These models guide precision diagnostics and inform tailored treatment strategies. Through collaborations with clinicians and translational researchers, we aim to deploy AI-driven systems medicine approaches that bring computational precision into real-world healthcare.

Impact and Future Directions
Our work sits at the intersection of biology, computation, and medicine, and is driven by strong collaborations across biomedical engineering, molecular biology, clinical research, and data science. As biological datasets expand in scale and complexity, the need for powerful, mechanistic modeling frameworks grows ever more essential. Looking ahead, the Lab is focused on:

• Developing next-generation AI systems capable of causal reasoning in biological networks
• Building comprehensive multiscale disease models that span molecular interactions to patient-level outcomes
• Creating computational platforms for rapid drug repurposing and therapeutic discovery
• Advancing individualized systems medicine through integrative patient modeling

By advancing these efforts, we strive to transform our understanding of disease biology and catalyze the creation of highly precise, personalized therapies that improve patient outcomes.