Explore DeepMind's groundbreaking AlphaFold 2 system and its revolutionary impact on protein folding prediction in this comprehensive 55-minute video. Delve into the fundamentals of proteins and protein folding, examine the workings of AlphaFold 1, and gain insights into the potential architecture of AlphaFold 2. Learn about differentiable geometric models, spatial graph distance matrices, and multiple sequence alignment techniques. Discover how this AI breakthrough solves a 50-year-old problem in biology and its implications for scientific discovery. Conclude with an analysis of AlphaFold 2's performance and its significance in the field of structural biology.
DeepMind's AlphaFold 2 Explained - AI Breakthrough in Protein Folding - What We Know and What We Don't
Overview
Syllabus
- Intro & Overview
- Proteins & Protein Folding
- AlphaFold 1 Overview
- Optimizing a differentiable geometric model at inference
- Learning the Spatial Graph Distance Matrix
- Multiple Sequence Alignment of Evolutionarily Similar Sequences
- Distance Matrix Output Results
- Guessing AlphaFold 2 it's Transformers
- Conclusion & Comments
Taught by
Yannic Kilcher
