Mathematical Approaches at the Interface of Machine Learning and Synthetic Biology

Machine learning has enabled advances in protein design and genetic circuits, but biological engineering still faces problems of interpretability, uncertainty and connections between molecular and system-level behaviour. Applied mathematicians, learning researchers and synthetic biologists will explore statistical methods for complex biological data, models that expose mechanisms, stochastic descriptions of noisy systems, multiscale modelling from molecules to populations and robust optimization for design under uncertainty. The workshop aims to develop mathematical foundations for more dependable biotechnology.