Applying self-supervised AI to multi-modal electronic health records — integrating clinical notes, labs, and imaging — this project builds scalable diagnostic models to detect autoimmune diseases earlier and more precisely.
Identifying a novel molecular regulator of tolerogenic dendritic cell function, this project uncovers how its loss triggers spontaneous multiorgan autoimmunity and exacerbates lupus — revealing a clinically relevant pathway in immune tolerance.
By profiling genetic and molecular drivers of pemphigus vulgaris across patient skin and blood, this project uncovers genotype-driven inflammatory loops and actionable targets for personalized therapy.
Integrating clinical, imaging, and biological data from large real-world MS cohorts, this project builds a machine learning model to predict disability progression early and enable personalized treatment decisions.
Combining machine learning with microbiome and metabolomic data from 4,000+ IBD patients, this project develops tools to predict disease flares, identify therapeutic targets, and enable personalized flare prevention.
Applying advanced quantitative MRI to detect pathology invisible to current clinical tools, this project builds an AI model to predict MS progression and enable earlier, more personalized diagnosis and treatment.
Developing a bioavailable DNAseIL3 biologic to degrade pathogenic autoantibodies and treat lupus and related autoimmune diseases.
Building AI-powered digital avatars that simulate each patient's immune system to predict therapy response and accelerate precision immunotherapy development.
Identifying DNA methylation signatures in blood and urine as non-invasive biomarkers to classify lupus nephritis and guide treatment without repeated biopsies.
Using DIPS, a non-invasive skin sampling technique, to build cytokine-based biomarker panels that predict biologic treatment response in psoriasis and atopic dermatitis.
