Christina Theodoris, MD, PhD is an Assistant Investigator at Gladstone Institutes and University of California, San Francisco (UCSF). In her undergraduate research at the California Institute of Technology, she worked in the Eric Davidson Lab studying gene regulatory networks in early development (Smith, Theodoris, and Davidson, Science 2007). In her MD/PhD research at UCSF, she developed an innovative network-based approach to therapeutic design leveraging machine learning and iPS cell disease modeling, which ultimately discovered a candidate therapy for cardiac valve disease, currently under further development toward clinical trial (Theodoris et al, Cell 2015, JCI 2017, Science 2021).

As a postdoctoral fellow at the Broad Institute of MIT and Harvard and Dana-Farber Cancer Institute, she developed a pioneering foundational AI model, Geneformer, on a large-scale corpus of human single-cell transcriptomes (initially ~30 million in 2021, now >100 million) to enable context-specific predictions in gene network biology through transfer learning (Theodoris* et al, Nature 2023; *co-corresponding). She designed an in silico perturbation strategy using Geneformer that discovered a novel regulator in cardiomyocytes and candidate therapeutic targets for cardiomyopathy, which were experimentally verified to impact contractility of cardiac microtissues in an iPS cell model of the disease.

Dr. Theodoris has been recognized with honors including the NIH Director’s Early Independence Award (DP5), Searle Scholars Award, and Burroughs Wellcome Career Awards for Medical Scientists. She also completed her combined residency in Pediatrics-Medical Genetics at Boston Children’s Hospital and established an integrated Pediatric Cardiovascular Genetics clinic at UCSF where she cares for children with genetic cardiovascular disease.

Now at Gladstone and UCSF, the Theodoris Lab develops AI models that leverage the unprecedented volume of transcriptomic and epigenomic data now available to gain a fundamental understanding of network dynamics that can be democratized to a vast array of downstream applications, accelerating the discovery of network-correcting therapies for human disease.