Peptide Self-Driving Lab

Lab of Joseph S. Brown at the University of Toronto

Peptides sit between small molecules and proteins in size and complexity. With the right chemistry — cyclization, non-natural amino acids, methylation — they can match the potency and selectivity of antibodies while keeping the drug-like properties of small molecules. Peptides are no longer a niche modality: Blockbusters like Ozempic anchor a $72-billion-and-growing market, peptides now account for more than 8% of FDA approvals, and roughly 13% of Americans have tried one. Yet navigating the effectively infinite chemical space of non-natural peptides remains a fundamental challenge.

We are building a self-driving laboratory (SDL) for peptide drug discovery — an AI-directed loop where each round of wet-lab experiments generates data that improves the next round of model-driven design. We rely on direct-to-biology methods, particularly affinity-selection mass spectrometry (AS-MS), to evaluate molecules without purification and feed results immediately back to the models that design the next experiment.

About me

Joseph S. Brown is an Assistant Professor at the Leslie Dan Faculty of Pharmacy and Faculty Advisor to the Medicinal Chemistry Self-Driving Lab (MedChem SDL) at the University of Toronto. Before his faculty appointment, he was a PhRMA Foundation Drug Discovery Postdoctoral Fellow at MIT with Bradley Pentelute, specializing in combining machine learning with AS-MS to identify high-affinity ligands from diverse peptide and abiotic libraries. He earned his PhD in Chemical and Biomolecular Engineering from Cornell University with Christopher Alabi as a National Science Foundation Graduate Research Fellow.