Artificial Intelligence Driven Drug Discovery By Michelle Gill Abstract: At BenevolentAI, we use machine learning to facilitate drug discovery. This talk will introduce the drug discovery process and explain how machine learning maps to these stages. We will then cover challenges specifically related to using machine learning for scientific discovery, and conclude with a specific application of reinforcement learning to generate novel compounds in silico. Bio: Michelle Gill is a Senior Data Scientist at BenevolentAI, an AI healthcare company with capabilities from early discovery to late stage clinical development. At BenevolentAI, she utilizes data science and machine learning to facilitate both the target identification and lead optimization stages of drug discovery. Previously, Michelle was a deep learning consultant within NVIDIA’s Professional Services Group where she assisted clients in the pharmaceutical and materials science domains develop proof of concept deep learning pipelines. As a scientist at the National Cancer Institute, she developed software utilizing machine learning and compressed sensing algorithms. She holds a PhD in Molecular Biophysics and Biochemistry from Yale University and completed a postdoctoral research fellowship at Columbia University Medical School, where she developed and applied biophysical methods to study the function of cancer-associated enzymes. Michelle's scientific and machine learning work has been published in peer reviewed journals and covered by the press. Twitter: @modernscientist Presented at the 2019 New York Conference (May 10th, 2019)