Emerging Applications of Machine Learning in Biomedical Discovery

3.0 credits · Graduate

This one-semester course will focus on emerging applications of machine learning for biomedical discovery, design, and experimentation. Here we will examine how modern AI methods are being integrated into scientific workflows to accelerate biomaterials research, therapeutic development, and biomedical engineering. Topics will include surrogate modeling, Bayesian optimization, active learning, molecular embeddings, graph neural networks, materials informatics, protein language models, digital twins, and closed-loop experimentation. Students will learn how machine learning can be used to guide experiments, model complex biological systems, identify promising candidate materials and therapeutics, and enable autonomous or semi-autonomous discovery pipelines. Course materials will be implemented in Python using commonly used scientific computing and machine learning packages, as well as publicly available biomedical and materials datasets. Students are expected to have prior exposure to statistics, basic machine learning architectures, and Python programming.