Stanford-affiliated research has been a regular source on this site for peptide chemistry, AI-driven discovery, and structural biology work. Recent threads: structural biology papers on macrocyclic peptide binding to undruggable targets, computational design platforms (often in collaboration with industry partners), and clinical work out of Stanford Medicine's metabolic-disease and oncology programs.
Programs that have appeared in this site's coverage include AI-designed peptide work in collaboration with Google DeepMind alumni, structural biology on KRAS and beta-catenin binders, and several preclinical peptide candidates moving toward IND.
Stories here cover the published work and the spinouts. See #drug-discovery and #ai-drug-discovery for adjacent threads.
Stanford researchers led by Eric Appel reported in the journal Matter, as described by phys.org on September 22, 2026, that they trained an AI model on known antimicrobial peptides and used it to screen 1.7 million candidate polyacrylamide polymers designed to mimic how those peptides kill bacteria. The team synthesized and tested 10 of the model's picks; all 10 performed well above expectations against E. coli, one was especially effective against biofilms, and the approach also worked against Staphylococcus aureus. Co-author Shoshana Williams called them among the most potent antimicrobial polymers ever reported. The polymers rip holes in bacterial membranes, a mechanism the researchers say makes resistance harder to evolve; clinical use remains a future goal.
A Stanford-led study published March 29 in Genome Medicine, with broad media coverage in late April, identifies two genetic variants that handicap the PAM enzyme (peptidyl-glycine alpha-amidating monooxygenase) responsible for activating GLP-1 and other peptide hormones. In a meta-analysis of three trials with 1,119 participants, carriers — roughly 10% of the general population — were less responsive to GLP-1 drugs and saw smaller HbA1c reductions despite higher circulating GLP-1 levels. The work is the first in-depth investigation of a 'GLP-1 resistance' phenotype, sits alongside the recent 23andMe GLP1R/GIPR variant paper, and opens a path toward genetically-stratified incretin prescribing.
Stanford scientists used AI to identify BRP, a naturally occurring peptide that acts directly on the hypothalamus to suppress appetite — avoiding the gut-related side effects of current GLP-1 drugs. In animal studies, BRP reduced body weight and fat without nausea, constipation, or muscle loss. Published in Nature, with human trials planned.
Stanford researchers found approximately 10% of people may have resistance to GLP-1 drugs, limiting effectiveness for glucose regulation and weight loss. The study examined individual variation in how GLP-1 drugs slow gastric emptying.
Stanford researchers developed a method converting peptide sequences into DNA for standard sequencing, published in Nature Biotechnology. Could dramatically accelerate peptide drug discovery.