Machine learning scientist and computational biologist
I’m a machine learning scientist and computational biologist developing AI methods for complex biomedical data. My work spans multimodal and self-supervised learning, with applications ranging from therapeutic discovery to precision medicine. I’m particularly interested in building models that can integrate diverse biological data, generalize across datasets and model systems, and produce insights that are biologically meaningful and clinically relevant.
I’m currently a Research Fellow in the Hovestadt Lab at Dana-Farber Cancer Institute, with affiliations at Harvard Medical School and the Broad Institute.
I am developing representation-learning methods that connect tumor molecular profiles, functional-genomic perturbations, and pharmacologic data to predict cancer dependencies and prioritize therapeutic targets.
Methylation profiling and Artificial Neural networks for Time-resolved Individualized Survival predictions
A multimodal, biologically guided deep-learning framework that integrates DNA methylation, copy-number, and clinical information for individualized outcome and treatment-effect prediction in childhood brain tumors.
Deep learning, simulation, and image-analysis methods for measuring and longitudinally tracking cerebral microvascular structure and function.
I completed my PhD in Biomedical Engineering at Brown University, where I worked at the intersection of deep learning and quantitative optical imaging. Before that, I studied bioinformatics, physics, and applied mathematics at the University of Cape Town.
Outside research, I enjoy Brazilian jiu-jitsu and spending time with my dog. I am based in Boston.