Chief Business Officer DeepCure Boston, Massachusetts
AI is a powerful tool with enormous potential to increase the success rates, speed and cost effectiveness of small molecule drug discovery programs. It can recognize patterns in large and complex datasets, generate testable predictions and learn from its successes and failures in ways that are impossible for other computational tools and humans. While the potential for AI is enormous, most drug discovery programs do not have the workflows and tools to take full advantage of its potential. In this presentation, we will review the paradigm shifts from traditional drug discovery that are necessary for a fully enabled AI drug discovery program. Specifically, we will first discuss the value of maximizing the amount of data collected on each compound at every stage of discovery for multi-parameter optimization, the importance of the type and quality of the data, and the necessity of shortening data cycles. We will then consider AI enabling technologies and workflows that are critical to harnessing the value of the data to accelerate AI learning and increase the probability of success for a drug discovery program.
Learning Objectives:
Upon completion, participant will be able to explain how AI can potentially contribute to small molecule preclinical drug discovery.
Upon completion, participant will be able to discuss factors that often limit the impact of AI in drug discovery.
Upon completion, participant will understand the importance of the type, amount, quality and timing of data for AI learning.
Upon completion, participant will be able to recognize AI enabling technologies and workflows that can help maximize the enormous potential of AI for drug discovery.
