AlphaFold Meets Flow Matching for Generating Protein Ensembles
Offered By: Valence Labs via YouTube
Course Description
Overview
Explore a groundbreaking approach to generating protein structural ensembles in this 57-minute conference talk by Bowen Jing from Valence Labs. Dive into the innovative combination of AlphaFold and flow matching techniques for modeling protein conformational landscapes. Learn how AlphaFlow and ESMFlow, sequence-conditioned generative models, outperform traditional methods in precision and diversity when trained on the Protein Data Bank. Discover how these models accurately capture conformational flexibility and ensemble properties for unseen proteins when trained on all-atom molecular dynamics simulations. Gain insights into the potential of this method as a faster alternative to expensive physics-based simulations for diversifying static protein structures. The talk covers background information, flow matching with AlphaFold, evaluation on PDB ensembles, assessment of molecular dynamics ensembles, and concludes with a discussion on MD ensembles.
Syllabus
- Intro + Background
- Flow Matching with AlphaFold
- Evaluating on PDB Ensembles
- Evaluating on MD Ensembles
- MD Ensembles Discussion
Taught by
Valence Labs
Related Courses
Deep Learning – Part 2Indian Institute of Technology Madras via Swayam Probabilistic Deep Learning with TensorFlow 2
Imperial College London via Coursera Introduction to Deep Learning
Massachusetts Institute of Technology via YouTube Spatial Computational Thinking
National University of Singapore via edX DALL-E - Zero-Shot Text-to-Image Generation - Paper Explained
Aleksa Gordić - The AI Epiphany via YouTube