Jay is a Scientist I at the Allen Institute, where he develops machine learning and AI methods, including deep generative models and multimodal foundation models, to map the trajectory of neurodegenerative diseases. He integrates multi-modal data such as single-cell and spatial transcriptomics, neuropathology, brain imaging, genetics, and clinical records into models that uncover the biological mechanisms driving disease.

Before joining the Institute, Jay was a postdoctoral research associate at the Data Science Institute at Brown University, working with Dr. Ying Ma. There he developed machine learning methods for spatially resolved transcriptomics that bridge population genomics cohorts and spatial tissue data, borrowing phenotype information from large patient cohorts to pinpoint the tissue microenvironments where disease-associated molecular programs are active, across conditions ranging from Alzheimer's disease to cancers.

Jay earned his Ph.D. in Genomics and Computational Biology from the Perelman School of Medicine at the University of Pennsylvania, co-advised by Dr. Li Shen and Dr. Qi Long. During his doctoral training, he built Bayesian and statistical learning methods for brain imaging genomics and led large-scale genome-wide and colocalization studies linking genetic variation to brain structure and Alzheimer's risk. He also holds master's degrees in Statistics and Data Sciences from the Wharton School and in Applied Mathematics and Computational Science from the University of Pennsylvania.