Cesar de la Fuente
Presidential Associate Professor, University of Pennsylvania
AI for Antibiotic Discovery
Abstract
Traditional antibiotic discovery has long relied on physically exploring nature, collecting soil and water samples to isolate active compounds through a painstaking trial-and-error process. This approach has become increasingly unsustainable in the face of rising antibiotic resistance and the urgent need for new therapeutics. In this talk, I will discuss how our lab has moved beyond this paradigm over the past decade by leveraging artificial intelligence (AI) to digitally mine the world’s biological information—genomes, proteomes, and metagenomes. Computers excel at pattern recognition in images and text, but their application in biology and medicine is still nascent. In this talk, I will discuss our decade-long advances accelerating antibiotic discovery. We pioneered designing antibiotics using artificial intelligence (AI), achieving efficacy in preclinical animal models and demonstrating that machines could create therapeutic molecules. For the first time, we mined the human proteome to identify antibiotic candidates. Building on this work, we hypothesized that similar compounds exist throughout evolution. We expanded our efforts to extinct species, where our AI-driven approach led to the discovery of the first therapeutic molecules from organisms like Neanderthals and woolly mammoths. This work launched the field of molecular de-extinction and yielded preclinical candidates such as neanderthalin, mammuthusin, and elephasin. Furthermore, we expanded our antibiotic discovery efforts to explore other branches of the tree of life beyond eukaryotes. By computationally analyzing microbial dark matter, we identified nearly one million new antibiotic molecules, which have been made freely available to encourage global researchers to synthesize and develop them. Additionally, through computational exploration of thousands of human microbiomes, we discovered new antimicrobial agents, including prevotellin-2 from the gut microbe Prevotella copri. Collectively, our efforts have dramatically accelerated antibiotic discovery, reducing the time to identify preclinical candidates from years to just a few hours. We are on the cusp of a new era where AI advances will help control antibiotic resistance, infectious disease outbreaks, and pandemics.
Bio
César de la Fuente is a Presidential Associate Professor at the University of Pennsylvania, where he leads the Machine Biology Group. He completed postdoctoral research at the Massachusetts Institute of Technology (MIT) and earned a PhD from the University of British Columbia (UBC). He is best known for pioneering computational and artificial intelligence approaches to antibiotic discovery, which have drastically accelerated the time needed to identify preclinical candidates, from years to hours. These candidates show promise for therapeutic intervention against currently untreatable infections. Moreover, he spearheaded the discovery of therapeutic molecules from extinct organisms, and his lab has uncovered a myriad of novel peptide molecules across the tree of life, revealing a previously unrecognized branch of host immunity. Professor de la Fuente has received numerous awards for his contributions, including the Princess of Girona Prize and the Fleming Prize. He is a Fellow of the American Institute for Medical and Biological Engineering, a Sloan Fellow, and a National Academy of Medicine Emerging Leader. De la Fuente has authored more than 170 publications and holds multiple patents.