But de la Fuente is using artificial intelligence to bring about a different future. His team at the University of Pennsylvania is training AI tools to search far and wide the genome for peptides with antibiotic properties. Their vision is to assemble those peptides – molecules made of 50 amino acids linked together – into a variety of configurations, some of which have never been seen in nature. They hope the results may protect the body from germs that traditional treatments combat.
Their search has unearthed promising candidates in unexpected places. In August 2025, his team, which included 16 scientists from Penn’s Machine Biology Group, described peptides Hidden in the genetic code of ancient single-celled organisms called archaea. Earlier, he had prepared a list of candidates from the venoms of snakes, wasps and spiders. And in an ongoing project de la Fuente called “molecular de-extinction,” he and his colleagues are scanning published genetic sequences of extinct species for potentially functional molecules. Those species include hominids like Neanderthals and Denisovans and charismatic megafauna like woolly mammoths, as well as ancient zebras and penguins. In the history of life on Earth, De La Fuente reasons, perhaps some organisms evolved an antimicrobial defense that may be helpful today. Those long-gone codes have given rise to repurposed compounds, namely mammuthusin-2 (from woolly mammoth DNA), myelodonin-2 (from the giant sloth), and hydrodemin-1 (from the ancient sea cow). Over the years, this molecular binge has enabled de la Fuente to collect a library of more than one million genetic recipes.
At age 40, de la Fuente has also collected a trophy case of awards from the American Society for Microbiology, the American Chemical Society, and other organizations. (In 2019, this magazine named him one of “35 Innovators Under 35” for bringing computational approaches to antibiotic discovery.) He is widely recognized as a leader in the effort to apply AI to real-world problems. “He’s really helped advance that field,” says Collins, who works at MIT. (The two have not collaborated in the lab, but Collins has long been at the forefront of using AI for drug discovery, including the discovery of antibiotics. In 2020, Collins’ team used AI models to predict helicin, a broad-spectrum antibiotic that is now in preclinical development.)
Collins says the world of antibiotic development needs as much creativity and innovation as researchers can muster. And de la Fuente’s work on peptides has advanced the field: “César is amazingly talented, very innovative.”
a messy, noisy endeavor
De la Fuente describes antimicrobial resistance as an “almost impossible” problem, but he sees plenty of room for exploration in the term. About. “I like challenges,” he says, “and I think this is the ultimate challenge.”
He says the use, overuse and misuse of antibiotics increases antimicrobial resistance. And the problem is growing unchecked because traditional methods of finding, making, and testing drugs are prohibitively expensive and often lead to dead ends. “A lot of companies that tried to do antibiotic development in the past closed down because at the end of the day there wasn’t a good return on investment,” he says.
Antibiotic discovery has always been a messy, noisy endeavor, driven by chance and fraught with uncertainty and misdirection. For decades, researchers have largely relied on brute-force mechanical methods. “Scientists dig in the soil, they dig in the water,” de la Fuente says. “And then from that complex organic matter they try to extract antimicrobial molecules.”
But molecules can be exceptionally complex. Researchers have estimated the number of possible organic combinations that can be synthesized at around 10.60. For reference, Earth contains an estimated 1018 Sand particles. “Drug discovery in any field is a game of statistics,” says Jonathan Stokes, a chemical biologist at McMaster University in Canada who is using generic AI to design potential new antibiotics that can be synthesized in the laboratory, and who worked with Collins on Helicin. “To get a goal you need enough shots on goal.”
