Applying Active Learning in Drug Discovery - There's No Free Lunch, but You Can Get a Discount
Offered By: Valence Labs via YouTube
Course Description
Overview
Explore the application of active learning in drug discovery through this 53-minute talk by Pat Walters and James Thompson from Valence Labs. Gain insights into how computational methods and machine learning techniques like active learning can streamline the drug discovery process. Learn about prioritizing molecules for synthesis, free energy perturbation, virtual screening strategies, and Thompson sampling. Discover how large molecular libraries can be efficiently searched using multi-armed bandit problems. Examine a collaborative case study on SARS-CoV-2 Nsp3 macrodomain and understand the broad impact of machine learning across various stages of drug discovery. The presentation concludes with a Q&A session, providing further clarification on the topics discussed.
Syllabus
- Intro
- Active Learning Example
- Prioritizing Molecules for Synthesis
- Free Energy Perturbation FEP: Transformation
- Active Learning Cycle
- Effect of Parameter Settings on Recall of Active Learning
- Virtual Screening as a Hit Identification Strategy
- Thompson Sampling - One Armed Bandits
- Large Libraries can be Decomposed Into Reagents
- Searching for Molecules: A Multi-Armed Bandit Problem
- Experiment
- Collaborative Work on SARS-Cov-2 Nsp3 Macrodomain
- ML has Impact Across the Drug Discovery Process
- Q+A
Taught by
Valence Labs
Related Courses
Inside TensorFlow - TF-AgentsTensorFlow via YouTube Provably Efficient Reinforcement Learning with Linear Function Approximation - Chi Jin
Institute for Advanced Study via YouTube Exploration with Limited Memory - Streaming Algorithms for Coin Tossing, Noisy Comparisons, and Multi-Armed Bandits
Association for Computing Machinery (ACM) via YouTube How Slot Machines Are Advancing the State of the Art in Computer Go AI
Churchill CompSci Talks via YouTube CS885: Multi-Armed Bandits
Pascal Poupart via YouTube