Machine Learning-Based Design of Proteins and Small Molecules
Offered By: Simons Institute via YouTube
Course Description
Overview
Explore machine learning-based approaches for designing proteins and small molecules in this 46-minute lecture by Jennifer Listgarten from UC Berkeley. Delve into the motivations behind this research and its applications in directed evolution. Examine various methodologies, including model-based optimization and distribution estimation, while addressing challenges such as black holes and extrapolation. Discover how concepts from image generation and simulations are applied to protein design. Learn about collaborations in the field, domain adaptation techniques, and the importance of uncertainty calibration in deep neural networks. Gain insights into expectation-maximization algorithms and their role in advancing protein engineering and small molecule design.
Syllabus
Intro
Why do we want to do this
Proteins
Directed Evolution
How to think about this
First approach
Modelbased optimization
Distribution estimation
Challenges
Black Holes
Panda
Gibbon
Banana
Image Generation
Simulations
Model Based Optimization
Collaborations
Extrapolation
Domain Adaptation
Uncertainty Calibration
Deep Neural Networks
Expectationmaximization
Taught by
Simons Institute
Related Courses
Introduction to Deep LearningMassachusetts Institute of Technology via YouTube Taming Dataset Bias via Domain Adaptation
Alexander Amini via YouTube Making Our Models Robust to Changing Visual Environments
Andreas Geiger via YouTube Learning Compact Representation with Less Labeled Data from Sensors
tinyML via YouTube Geo-localization Framework for Real-world Scenarios - Defense Presentation
University of Central Florida via YouTube