AI antibiotic discovery is revolutionizing the fight against antimicrobial resistance, with researchers like César de la Fuente leading the charge. Twenty years after identifying antimicrobial resistance as a critical global problem, de la Fuente is using artificial intelligence to develop new antibiotics, an issue that has only worsened with infections caused by resistant microbes now associated with over 4 million deaths per year. A recent analysis in _The Lancet_ predicts this number could surge past 8 million by 2050.
De la Fuente’s team at the University of Pennsylvania is training AI tools to search genomes for peptides with antibiotic properties, hoping to assemble novel configurations to combat drug-resistant microbes. His quest has revealed promising candidates in unexpected places, including archaea, venom, and even the genetic code of extinct species.
The Rise of AI in Antibiotic Research
In August 2025, his team described peptides hiding in archaea’s genetic code. They’ve also explored venom from snakes, wasps, and spiders, and are scanning extinct species’ genetic sequences for functional molecules in a project called “molecular de-extinction.” These efforts have yielded compounds like mammuthusin-2 (from woolly mammoth DNA) and mylodonin-2 (from the giant sloth), amassing a library of over a million genetic recipes. De la Fuente’s innovative approach has garnered numerous awards and recognition, with his work pushing the boundaries of what’s possible with AI.
“César is marvelously talented, very innovative.”
Why AI Antibiotic Discovery is Essential
De la Fuente describes antimicrobial resistance as an “almost impossible” problem, but sees room for exploration. The overuse and misuse of antibiotics drive resistance, and conventional drug discovery methods are expensive and often lead to dead ends. “A lot of the companies that have attempted to do antibiotic development in the past have ended up folding because there’s no good return on investment at the end of the day,” he says. AI offers a new approach by mining biological data for antimicrobial peptides (AMPs). These AMPs, already part of the body’s immune system, offer a multimodal attack on pathogens, potentially overcoming resistance to conventional drugs.
From Discovery to Delivery
De la Fuente’s group is one of many pushing the boundaries of using AI for antibiotics. While he focuses on peptides, others explore small-molecule discovery. Generative AI models are being used to design new molecules from scratch. Last year, de la Fuente’s team used a generative AI model to design synthetic peptides and tested two compounds on mice infected with a drug-resistant strain of _Acinetobacter baumannii_. Both successfully treated the infection.
Future of AI-Powered Antibiotics
De la Fuente is working to get candidates closer to clinical testing, developing ApexOracle, a multimodal model designed to analyze pathogens, pinpoint weaknesses, match them to AMPs, and predict antibiotic performance in lab tests. He believes AI can help researchers catch up to the threat of antimicrobial resistance.
The use of AI in antibiotic discovery is not just about finding new drugs; it’s about saving time and lives. related Industries news shows the potential of AI across various sectors. The potential of AI antibiotic discovery is enormous, offering a fighting chance against a growing global health crisis.
Source: MIT Technology Review
