Applying Active Learning in Drug Discovery | Pat Walters & James Thompson

Try datamol.io - the open source toolkit that simplifies molecular processing and featurization workflows for machine learning scientists working in drug discovery: datamol.io/
Never miss another M2D2 talk, add the schedule to your calendar: m2d2.io/talks/m2d2/about/
Also consider joining the M2D2 Slack: m2d2group.slack.com/join/shar...
Full Title: There’s no Free Lunch, but you can get a Discount - Applying Active Learning in Drug Discovery
Abstract: While computational methods have become a mainstay in drug discovery programs, many calculations are too time-consuming to be applied to large datasets. Active learning (AL), a machine learning method used to direct a search iteratively, can enable the application of computationally expensive methods such as relative binding free energy (RBFE) calculations to sets containing thousands of molecules. Moreover, AL can also be applied to virtual screening, enabling the rapid processing of billions of molecules. This presentation will provide an overview of active learning and highlight some applications in drug discovery.
Speakers:
Pat Walters - relaytx.com/our-team/pat-walt...
James Thompson - / james-thompson-26865165
Twitter Prudencio: / tossouprudencio
Twitter Therence: / therence_mtl
Twitter Jonny: / hsu_jonny
Twitter datamol.io: / datamol_io
~
Chapters:
00:00 - Intro
04:49 - Active Learning Example
09:44 - Prioritizing Molecules for Synthesis
11:34 - Free Energy Perturbation (FEP): Transformation
14:37 - Active Learning Cycle
21:15 - Effect of Parameter Settings on Recall of Active Learning
25:54 - Virtual Screening as a Hit Identification Strategy
30:03 - Thompson Sampling - One Armed Bandits
34:09 - Large Libraries can be Decomposed Into Reagents
35:28 - Searching for Molecules: A Multi-Armed Bandit Problem
37:24 - Experiment
38:56 - Collaborative Work on SARS-Cov-2 Nsp3 Macrodomain
45:50 - ML has Impact Across the Drug Discovery Process
47:16 - Q+A