Abstract:
Biology is the most powerful technology on Earth—yet we still study it largely by hand. That is starting to change. We now have planetary-scale biological data, increasingly standardized measurements, and the compute to learn from them. AI can compress this complexity into usable representations—models that don’t just describe life, but let us predict, design, and engineer it.
In this talk, I will argue that biology is becoming increasingly digital: a domain where learning algorithms can turn sequences into discoveries at a pace that matches the urgency of humanity’s greatest challenges. Antibiotics provide the proving ground. For a century, discovery depended on “dirt mining”—slow, local sampling and brute-force screening—an approach that cannot keep up with accelerating antimicrobial resistance. Our lab has been building an alternative: digital discovery, where the tree of life becomes a searchable, programmable space.
To make biology programmable, we need a unit that is both information-rich and experimentally scalable. Peptides—life’s smallest functional biomolecules—are an ideal training ground for this shift: tractable to synthesize and test, scalable to iterate, and defined by an astronomical sequence space that remains largely unexplored. I will describe our early work using evolutionary computation to design new antibiotics; how we pioneered AI-driven antibiotic design, generating molecules with strong efficacy in preclinical animal models; and how we then used algorithms to systematically mine the human proteome—revealing thousands of antimicrobial peptides that appear to constitute a previously unrecognized layer of host defense we call encrypted immunity. From there, we pushed into evolutionary time: by mining ancient biology, we discovered therapeutic molecules from Neanderthals and the woolly mammoth—helping launch molecular de-extinction and yielding candidates including neanderthalin, mammuthusin, and elephasin.
Next, we expanded across the full breadth of life. By analyzing global microbiomes at scale, we identified nearly one million candidate antibiotic molecules and released them open access to accelerate worldwide collaboration. I will highlight discoveries from human microbiomes, including prevotellin-2 from Prevotella copri, and our most recent step: digitally mining Archaea—an underexplored domain of life—uncovering a new class of antibiotics we call archaeasins. Collectively, these efforts have dramatically accelerated antibiotic discovery, reducing the time required to identify preclinical candidates from years to just a few hours.
Finally, I’ll introduce our latest AI stack—APEX, ApexGO, ApexDuo, and ApexOracle—enabling sequence-to-function prediction, computational optimization, multimodal therapeutic design, and rapid-response discovery against emerging pathogens. I believe we are on the cusp of a new era in which AI helps us stay ahead of antibiotic resistance, respond faster to outbreaks and future pandemics, and accelerate discovery across biology and medicine.

Website: https://delafuentelab.seas.upenn.edu/
X (Twitter): @delafuentelab
Bluesky: @delafuentelab.bsky.social
LinkedIn: https://www.linkedin.com/in/cesardelafuentenunez/

Bio:
César de la Fuente is a Presidential Associate Professor at the University of Pennsylvania, where he is Director of the Machine Biology Group. He is one of the youngest tenured professors in the history of Penn Medicine. He completed postdoctoral research at the Massachusetts Institute of Technology (MIT) and earned a PhD from the University of British Columbia (UBC). 
De la Fuente’s research aims to use the power of machines to accelerate discovery in biology and medicine. He pioneered the development of the first computer-designed antibiotic with efficacy in animal models, helping establish AI-driven antibiotic discovery as an emerging field. His lab develops computational methods to mine the world’s biological information, enabling the identification of more than one million antimicrobial compounds and reframing the human body itself as a rich, systematic source of antibiotics. This work began with the first comprehensive exploration of the human proteome for antibiotics, which revealed a previously unrecognized branch of host immunity.
His group also launched the field of molecular de-extinction by becoming the first to identify therapeutic molecules in extinct organisms, an approach that has already yielded preclinical antibiotic candidates including neanderthalin, mammuthusin, and elephasin. Beyond eukaryotes, his lab has expanded antibiotic discovery across other branches of the tree of life. By computationally analyzing microbial dark matter, the team identified nearly one million additional antibiotic molecules and released them open access to accelerate worldwide synthesis, characterization, and development. This effort leveraged machine learning to analyze 63,410 metagenomes and 87,920 microbial genomes. In parallel, through computational exploration of thousands of human microbiomes, de la Fuente and collaborators discovered numerous antimicrobial agents, including prevotellin-2 from the gut microbe Prevotella copri.
Collectively, these initiatives have compressed the time required to identify preclinical candidates from years to hours, with estimated speedups on the order of several million-fold—saving years of human research and transforming what once demanded decades of collective effort into workflows that can be executed within hours. To support this work, his lab has developed the APEX AI stack—APEX, ApexGO, ApexDuo, and ApexOracle—for sequence-to-function prediction, computational optimization, multimodal therapeutic design, and rapid-response discovery. Additional advances from his lab include reprogramming venoms into antimicrobials, developing autonomous nanorobots to treat infections, creating resistance-proof antimicrobial materials, and inventing rapid, low-cost diagnostic devices for COVID-19 and other infections. He is an NIH MIRA investigator and has received recognition and research funding from numerous organizations.
De la Fuente has received numerous national and international awards. He is an elected Fellow of the American Institute for Medical and Biological Engineering (AIMBE), becoming one of the youngest ever inducted, and was recognized by MIT Technology Review as one of the world’s top innovators for “digitizing evolution to make better antibiotics.” His honors also include the inaugural Langer Prize, ACS Kavli Emerging Leader in Chemistry recognition, ASM Distinguished Lecturer, Waksman Foundation Lecturer, the Miklós Bodanszky Award, AIChE’s 35 Under 35 Award, the Society of Hispanic Professional Engineers Young Investigator Award, the ACS Infectious Diseases Young Investigator Award, the Thermo Fisher Award, and the EMBS Academic Early Career Achievement Award for pioneering the development of antibiotics designed using principles from computation, engineering, and biology. More recently, he has received the Princess of Girona Prize, the ASM Awards for Early Career Applied and Biotechnological Research and for Early Career Basic Research, the Rao Makineni Lectureship Award from the American Peptide Society, and the Fleming Prize, and was selected as a National Academy of Medicine Emerging Leader in Health and Medicine. He has been named a Sloan Fellow and selected by the World Economic Forum to the Young Global Leaders Class of 2025. In 2026, de la Fuente was elected as a Fellow of the Royal Society of Biology.
He serves on the editorial boards of numerous scholarly journals and is currently an Associate Editor of Drug Resistance Updates, Nature Communications Biology, Bioactive Materials, Bioengineering & Translational Medicine, and Digital Discovery. He has been named a Clarivate Highly Cited Researcher (top 1% most cited in the world) multiple times and received an Honorary Doctorate from the University of Leon at age 39. Prof. de la Fuente has delivered around 400 invited lectures, including many keynote and named lectures, and has also spoken at TEDx. He has co-authored an influential book on machine learning for drug discovery, secured multiple patents, and published around 200 peer-reviewed papers in journals including Cell, Science, Cell Host & Microbe, Nature Biomedical Engineering, Nature Microbiology, Nature Communications, and PNAS.