What are convolutional neural networks (CNNs) and how are they used to predict sequence motifs in biological sequences? What is a transformer and how it is used by AlphaFold to predict protein structures? This course explores the major advances in deep learning, with a special emphasis on their applications to molecular biology and genomics. Starting from single neurons (perceptrons), it progresses to more complex architectures such as convolutional and recurrent neural networks, transformers, and generative neural networks. The course covers both the general principles of these methods as well as specific applications in genomics. This is a computationally rigorous course for students interested in computational biology.
A graduate level course that I taught as Harvard's MCB111.
The course is relevant for people interests in biology, mathematics, and computer science. The course is designed more around the student's work than the lectures. Lectures are just a vehicle to introduce a particular problem describing the question at hand (usually taken from some recent publication), of which the student have to implement on their own most of what I would describe in the lectures. A hands-on section and the weekly homework implementing the lectures are the most important component of the learning experience.