Part IV · Generative models & frontiers
13 · Generative models for molecules soon
Variational autoencoders, SMILES and SELFIES language models, and diffusion and flow models, with the evaluation questions that matter for generated molecules.
14 · Generative design loops soon
Closing the loop: multi-objective optimisation, docking-guided generation, active learning and an introduction to protein design.
15 · Capstone projects soon
Open-ended projects that combine the course: a property prediction benchmark, a virtual screening campaign, a sequence function predictor, and a design loop.
See the full roadmap for how the Parts connect.