My research program focuses on leveraging large-scale, multimodal datasets to understand the cellular, molecular, and circuit-level mechanisms underlying major neurological diseases, and to translate these insights into predictive and therapeutic frameworks. We develop and apply integrative approaches that combine single-cell and spatial genomics, epigenomics, proteomics, and high-content imaging with advanced computational methods, including machine learning, network inference, and AI-driven pattern discovery. A central goal of the laboratory is to build comprehensive, data-driven models of brain function and dysfunction by capturing how diverse brain cell types, vascular and immune interfaces, and regional microenvironments contribute to disease-associated changes in gene expression, regulatory architecture, and cellular states.

Using scalable analytic pipelines and AI-based classification tools, we identify disease-linked cellular programs, molecular signatures, and predictive biomarkers across patient cohorts and experimental models. We integrate these findings with perturbation data, functional genomics, and computational drug-repurposing strategies to nominate candidate pathways for therapeutic targeting. Our team also develops computational frameworks for harmonizing large, heterogeneous datasets, spanning human cohorts, model systems, and multi-omic modalities, to enable robust comparative analyses and reproducible discovery.

Ultimately, our program aims to advance a precision-medicine framework for neurological disorders by unifying high-resolution molecular mapping with machine-learning approaches for classification, characterization, and treatment prioritization. By bridging quantitative biology, systems neuroscience, and AI, the laboratory seeks to generate foundational datasets, analytical tools, and mechanistic insights that accelerate the development of targeted interventions and improve clinical translation across a broad spectrum of neurological diseases.