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
The Quantum WorldHarvard University via edX Approximate Methods In Quantum Chemistry
Indian Institute of Technology, Kharagpur via Swayam Computational Chemistry and Classical Molecular Dynamics
NPTEL via YouTube A Mathematical Look at Electronic Structure Theory - JuliaCon 2021 Workshop
The Julia Programming Language via YouTube Breaking the Curse of Dimension in Quantum Mechanical Computations Through Analysis and Probability
Alan Turing Institute via YouTube