Areas of Focus:

BioinformaticsData-Driven & QuantitativeDrug RepurposingEnvironmental ExposuresGene–Environment InteractionsMachine Learning & AIPopulation & Patient-CenteredTranslational & ClinicalCross-Cutting & Special Populations
  • Assistant Professor, Department of Biostatistics, Epidemiology and Informatics, Perelman School of Medicine, University of Pennsylvania

Dr. Joseph Romano is an Assistant Professor of Informatics and Biostatistics in the Department of Biostatistics, Epidemiology and Informatics at the Perelman School of Medicine, University of Pennsylvania. He received his BS from the University of Vermont and his PhD, MPhil, and MA in biomedical informatics from Columbia University.

The Romano laboratory applies machine learning and knowledge graph approaches to drug repurposing and environmental health, integrating chemical, toxicological, genetic, and clinical data to identify therapeutic candidates for complex diseases. His group is also an investigator within the Penn Center of Excellence in Environmental Toxicology (CEET), where his work examines how environmental exposures interact with genetic susceptibility to shape inflammatory and autoimmune disease risk.

Dr. Romano collaborates broadly across Penn’s informatics and immunology communities, including the Penn Colton Center for Autoimmunity, where his approaches to integrated drug repurposing complement clinical and translational efforts to identify new therapeutic options for rare and treatment-resistant autoimmune diseases.

Projects

Featured Pilot Projects

Biomarker Discovery for Early Prediction of Autoimmunity in Immunotherapy Patients Through Deep Immune Profiling and Temporal Graph Convolutional Networks
Project | University of Pennsylvania

Biomarker Discovery for Early Prediction of Autoimmunity in Immunotherapy Patients Through Deep Immune Profiling and Temporal Graph Convolutional Networks

Using temporal graph machine learning and deep immune profiling to predict which cancer immunotherapy patients will develop autoimmune adverse events before they occur.