AI for Drug Discovery


In recent years, artificial intelligence (AI) and machine learning (ML) have ignited a revolution in Biology and Medicine, with important implications for the pharmaceutical and biotech industries. From elucidating protein folding at the microscopic, molecular scale, to modeling cellular perturbations at a whole-organism level, AI/ML is poised to accelerate drug discovery in the next decade. Further applications include improved target identification, prediction of drug-drug interactions, and design and optimization of lead compounds. AI-driven approaches can enable researchers to sift through vast datasets, identifying potential drug candidates more efficiently, reducing costs, and hopefully accelerating the timeline from discovery to market. AI/ML approaches can assist in tailoring treatments to individual patients based on their omic profiles, ushering in an era of more precise and effective therapeutic interventions. Despite the immense promise, potential pitfalls and challenges related to data quality, model interpretability, transparency and safety in drug development. Additionally, the need for robust regulations and ethical frameworks to govern AI applications in healthcare is a pressing concern. The "AI for Drug Discovery" Track brings together leading researchers and experts from both the AI and pharmaceutical domains to explore the cutting-edge advancements, challenges, and opportunities in this rapidly evolving field. In our first session AI for molecules, we will delve into the molecular world and discuss applications of AI/ML for de novo molecular design, molecule generation, and creation of novel therapeutic candidates. In our second session AI for cells and tissues, we will examine how drug interventions affect organisms at the cellular level, and discuss the latest advancements in exploiting omics data for biomarker discovery and drug response prediction. The scientific presentations will be followed by a panel discussion entitled “Beyond the Buzz: Large Language Models (LLMs) and the Future of Drug Discovery” which will provide a platform to discuss the use of LLMs in drug discovery, fostering discussion on their potential, challenges and on responsible AI adoption in drug discovery.