A key benefit of autonomous labs isn't just speed but perfect documentation. AI-driven systems eliminate human variability—like slight changes in pipetting angle—that is impossible to document but critical for reproducibility. This creates the pristine, detailed data needed for advanced AI models to learn effectively.
Generate Biomedicines' AI learns the fundamental rules of protein structure and function, much like a language's grammar. This allows it to design entirely new proteins by generating novel "sentences" (sequences) that are biologically coherent and functional, rather than just mimicking existing ones found in nature.
The internet is an insufficient training ground for scientific AI because most crucial information—including failed experiments, negative data, and nuanced procedural details—is never published. This undocumented knowledge, what scientists call "good hands," represents a major data bottleneck for building truly intelligent scientific models.
AI thrives on learning from the vast, structured data evolution provides for proteins. Molly Gibson explains that small molecules lack this clear "language" or evolutionary history. This fundamental data gap is a primary reason generative AI has been slower to transform small molecule drug discovery compared to biologics.
Moving beyond traditional models focused on structural fit, Expedition's platform incorporates quantum chemistry. It uses Density Functional Theory (DFT) to model electron density and predict the actual probability of a covalent bond forming, enabling the design of specific molecules for previously "undruggable" targets.
The venture creation strategy for platform biotechs isn't about finding one blockbuster drug. It's a binary bet: either the underlying scientific platform is sound and can repeatedly generate many medicines, or the entire concept fails. There is no middle ground of succeeding with just one product from the platform.
Molly Gibson's venture, Lila Sciences, aims for AI that doesn't just analyze data but autonomously executes the entire scientific method. By connecting generative models to automated labs, the AI can formulate hypotheses, run physical experiments, and learn from the results in a continuous loop, achieving a superhuman pace of discovery.
The lengthy timelines of drug development create a significant perception lag for AI's impact. Molly Gibson clarifies that molecules currently in clinical trials were designed years ago using nascent AI models. The true capabilities of today's more advanced AI platforms won't be evident in approved drugs for several more years.