Artificial Intelligence for the Life Sciences

Catalog description

Modern AI systems extend beyond classical machine learning by using deep learning and large-scale representation learning to build models that transfer across tasks, data types, and scientific domains. This class complements existing instruction in classical machine learning by introducing the principles behind contemporary AI systems. Students will explore the principles of neural networks, representation learning, embeddings, and foundation models that underpin widely used commercial and open-source AI platforms. Students will select, evaluate, and interpret models using modern tools and APIs. Through applied case studies and guided hands-on activities, students will examine AI applications in the life sciences such as genomics, protein-science, drug discovery, clinical development, regulatory intelligence, and market analytics. Particular attention is given to system limitations, interpretability, reproducibility, validation, and deployment considerations in regulated environments.