Short Course Description
Course Description
Proteins form the molecular basis of all life, and yet, we lack reliable means to predict what they do, how they do it, where and when. Indeed, although their primary constituents - amino acids - are well-characterized, the size and diversity of proteins make physical simulations of their behavior extremely challenging. To overcome these challenges, Machine learning approaches have become increasingly popular since the 90?s for predicting how proteins fold, recognize one another and function. While initially only moderately successful, deep learning has enabled radical progress across tasks, culminating with the celebrated AlphaFold algorithm for protein structure prediction in 2021. This workshop is a joint introduction to machine learning and structural biology, with an emphasis on practical tools and current research topics. Prior knowledge of either domain is desirable but not necessary. In the first part of the semester, we will cover key concepts including protein structures & folding, supervised learning and deep learning. The second part of the semester will be dedicated to group research projects related to the topic. Evaluation will be based on homework, project participation, presentation and report. The course will be in English.
Syllabus
Week 1: Introduction to proteins and machine learning.
Week 2: Visual analysis of protein structures.
Week 3: Quantitative analysis of protein structures.
Week 4: Recap week
Week 5: Supervised machine learning (I)
Week 6: Supervised machine learning (II); Convolutional Neural Networks
Weeks 7-10: Project meetings
Week 11: Oral presentation
Evaluation
1. Homeworks (30%)
2. Project presentation (40%)
3. Project report (30%)
Full Syllabus
