Machine learning tools promise to revolutionize drug discovery, greatly expand the set of druggable targets, and have shown unbelievably good performance on benchmarks for medicinal chemistry tasks. Unfortunately, recent analyses imply that such apparently-encouraging algorithmic performance is likely to be an artifact of weaknesses in the design of these benchmarks.
Therefore, Atomwise is running the largest assessment of machine learning for hit discovery in history, comprising over 550 projects with over 250 universities in 40 countries. Abraham Heifets will present results from this broad experiment, and report on lessons learned and best practices for medicinal chemists considering artificial intelligence tools and for academic researchers embarking on translational research.
Abraham Heifets is the CEO of Atomwise, which uses artificial intelligence to help discover new medicine. Abraham was a Massey Fellow at the University of Toronto and the Ontario Brain Institute, where his doctoral work used machine learning to help plan organic syntheses, a long-standing challenge in chemistry.
Previously, Abraham researched high-performance data processing at IBM’s T.J. Watson Research Center and contributed to the artificial intelligence system of the world-champion robotic soccer team at Cornell University, from which he holds two previous degrees.
Abraham has presented his work at the National Institutes of Health, the American Chemical Society, and the Association for the Advancement of Artificial Intelligence. He is an author on 19 papers, patents, and patent applications.