Do Neural Networks Dream of Drug-Like Molecules? An Introduction and Critical Perspective to Generative AI for Chemical Space Exploration

The drug-like chemical space is vast and largely unexplored. Generative AI offers a structured framework for navigating it efficiently. This talk introduces key generative approaches and their integration into practical integrated in-silico pipelines. Moving beyond the technical narrative, we critically address the hype surrounding AI in pharma, focusing on generalizability, data scarcity, still-limited clinical evidence, and the challenge of reliably scoring and ranking candidate molecules: a discussion extended to the audience through a live interactive experiment.