Hi all,

Tomorrow's group meeting will be given by Ed. The title and abstract are included inline after this message.

Best,

Ian

-------------------------------------

SPEAKER: Ed Pyzer-Knapp
TITLE: Machine Learning in High Throughput Virtual Screening

ABSTRACT: With the ever increasing size of data sets enabled by the expansion of high throughput virtual screening, it becomes necessary to find creative ways to turn data into knowledge. I will demonstrate a number of different approaches to this challenge using methods inspired from the field of machine learning and information theory, and talk about how to choose the right solution for a range of problems. I will also discuss the importance of putting predictions in the context of the predictive variance. Finally I will demonstrate how we have integrated these techniques into improving the generation and interrogation of molecular libraries.