Dreyfus-ACS Symposium, 2023
The Dreyfus Foundation organized an American Chemical Society (ACS) Presidential Symposium on Machine Learning that was held at the fall National Meeting of the ACS in San Francisco on Tuesday, August 15, 2023. The symposium was the capstone to the Foundation’s Program in Machine Learning in the Chemical Sciences and Engineering that concluded in July 2022.
The distinguished speakers were Klavs Jensen (MIT), Yu-Shan Lin (Tufts University), Milad Abolhasani (North Carolina State University), Brett Savoie (Purdue University), Andrew Ferguson (University of Chicago), Thomas Miller (Entos, Inc.).
Dreyfus Foundation ACS Presidential Symposium on Machine Learning
10:00 am: Morning Welcome
- Scott Walter, President, The Camille and Henry Dreyfus Foundation
- Milan Mrksich, Symposium Chairman; Board Member, The Camille and Henry Dreyfus Foundation; and Vice President for Research and Henry Wade Rogers Professor of Biomedical Engineering, Northwestern University
- Richard Zare, Session Moderator; Board Member Emeritus, The Camille and Henry Dreyfus Foundation; and Marguerite Blake Wilbur Professor of Natural Science, Stanford University
10:20 am: Klavs Jensen, Chemical Engineering, MIT
Accelerating Chemical Discovery and Development with Machine Learning and Automation
Accelerating Chemical Discovery and Development with Machine Learning and Automation
10:55 am: Yu-Shan Lin, Chemistry, Tufts University
Overcoming the Structural Challenges of Cyclic Peptide Design with Machine Learning
Overcoming the Structural Challenges of Cyclic Peptide Design with Machine Learning
11:30 am: Milad Abolhasani, Chemical and Biomolecular Engineering, North Carolina State University
Accelerated Materials Discovery and Optimization Enabled by an Autonomous Fluidic Lab
Accelerated Materials Discovery and Optimization Enabled by an Autonomous Fluidic Lab
2:00 pm: Afternoon Welcome
- Milan Mrksich
- Richard Zare
2:05 pm: Brett Savoie, Chemical Engineering, Purdue University
General Machine Learning Strategies for Solving Chemical Deduction Problems
General Machine Learning Strategies for Solving Chemical Deduction Problems
2:40 pm: Andrew Ferguson, Pritzker School of Molecular Engineering, University of Chicago
Machine Learning-Guided Directed Evolution of Functional Proteins
Machine Learning-Guided Directed Evolution of Functional Proteins
3:05 pm: Thomas Miller, Entos, Inc.
How Generative AI Solved the 1000-Fold Selectivity Grand Challenge in HER2 Cancer Drug Discovery
How Generative AI Solved the 1000-Fold Selectivity Grand Challenge in HER2 Cancer Drug Discovery
3:40 pm: Closing Remarks
- Milan Mrksich