Solving one of the hardest problems in contemporary science: inferring the compact 3D structure of a protein given its amino acid sequence.
Working with deep neural network and advanced Bayesian inference techniques using frameworks like Pyro, PyTorch and JAX.
Making simulations efficient with structured approximations and higher-order Automatic Differentiation.
Our project of approaching protein folding from a deep probabilistic programming point of view. The goal is to use a framework like Pyro to perform Bayesian inference of protein structure and the folding process.
Associate Professor (PI)
Industrial PhD Fellow (Evaxion)
"If fallacious reasoning always led to absurd conclusions, it would be found out at once and corrected. But once an easy, shortcut mode of reasoning has led to a few correct results, almost everybody accepts it; those who try to warn against it are not listened to"
— E. T. Jaynes in "Probability Theory: Logic of Science"