Machine Learning-Based Design of Proteins
Offered By: Simons Institute via YouTube
Course Description
Overview
Explore the cutting-edge intersection of machine learning and protein engineering in this 32-minute talk by Jennifer Listgarten from UC Berkeley. Delve into the challenges of navigating the vast combinatorial space of protein design and learn how directed evolution and predictive models work synergistically to overcome these obstacles. Discover the concept of epistemic uncertainty and its role in library design, followed by a real-life example demonstrating the optimization problem in protein engineering. Gain insights into the algorithm description, the language of probability, and its applications in gene therapy. Understand the innovative approaches used to tackle complex protein design challenges and their potential impact on future scientific advancements.
Syllabus
Introduction
Protein engineering
The combinatorial space
Directed evolution
Work synergistically
Predictive models
The problem
Epistemic uncertainty
Library design
Real life example
Optimization problem
Algorithm description
Language of probability
Gene therapy
How we did this
Taught by
Simons Institute
Related Courses
Access Bioinformatics Databases with BiopythonCoursera Project Network via Coursera Algorithms for DNA Sequencing
Johns Hopkins University via Coursera Advanced Reproducibility in Cancer Informatics
Johns Hopkins University via Coursera AI and Bioinformatics: Genomic Data Analysis
Taipei Medical University via FutureLearn AI for Efficient Programming: Harnessing the Power of LLMs
Fred Hutchinson Cancer Center via Coursera