A generative AI model that designs new antibiotics
A research team at Penn Engineering has developed and validated a new ‘diffusion model’ that can generate antibiotic candidates the same way AI creates images.
2 min. read
What if generative AI could design lifesaving antibiotics, not just art and text? In a new Cell Biomaterials paper, Penn researchers introduce AMP-Diffusion, a generative AI tool used to create tens of thousands of new antimicrobial peptides (AMPs)—short strings of amino acids, the building blocks of proteins—with bacteria-killing potential. In animal models, the most potent AMPs performed as well as FDA-approved drugs, without detectable adverse effects. “We’re leveraging the same AI algorithms that generate images, but augmenting them to design potent new molecules,” says Pranam Chatterjee, assistant professor in bioengineering and in computer and information science at the School of Engineering and Applied Science, and the paper’s senior co-author.
The lab of Pranam Chatterjee (pictured), in collaboration with the lab of César de la Fuente, developed and validated a new “diffusion model” that can generate antibiotic candidates the same way AI creates images.
(Image: Sylvia Zhang)
While some generative AI models like ChatGPT work by predicting the next word or element in a sequence, “diffusion” models start from random “noise” and iteratively refine it into a coherent output—the principle behind tools like DALL·E and Stable Diffusion.
AMP-Diffusion works the same way, only instead of “denoising” pixels, it refines sequences of amino acids. “It’s almost like adjusting the radio,” says César de la Fuente, Presidential Associate Professor in bioengineering and in chemical and biomolecular engineering at Penn Engineering, in psychiatry and microbiology in the Perelman School of Medicine, and in chemistry in the School of Arts & Sciences, and the paper’s other senior co-author. “You start with static, and then eventually the melody emerges.”
Because ESM-2, a widely-used protein language model, already has a rich “mental map” of how real proteins fit together, AMP-Diffusion doesn’t need to relearn basic biology. That means it can generate candidate AMPs faster, and its outputs are more likely to follow the intricate patterns that make peptides effective.
Chatterjee’s team also designed AMP-Diffusion to consult ESM-2’s built-in rules while “denoising,” essentially giving the new tool a coach that keeps it grounded in biological reality.
“Instead of teaching the model the ABCs of biology, we started with a fluent speaker,” says Chatterjee. “That shortcut lets us focus on designing peptides with a real shot at becoming drugs.”
Penn engineers and collaborators have developed a transparent, micro-engineered device that houses a living, vascularized model of human lung cancer—a “tumor on a chip”—and show that the diabetes drug vildagliptin helps more CAR T cells break through the tumor’s defenses and attack it effectively.
Tumor-on-a-chip offers insight into cancer-fighting cells in immunotherapy
Penn engineers and collaborators have built a living tumor on a chip to expose how cancers block immune attacks, and how one existing drug could make immunotherapy like CAR T more effective against solid tumors.
Xin Sun prepares samples collected from the Eastern Tropical North Pacific aboard a research vessel. By adding stable isotope tracers to these vials, Sun and her team can track how different microbial groups convert nitrogen compounds into nitrous oxide, revealing how subtle shifts in oxygen and organic matter change the ocean’s chemistry.
Can tiny ocean organisms offer the key to better climate modeling?
In the shadowy layers of the Pacific, microbes decide how much nitrous oxide—a potent greenhouse gas—rises skyward. New research from Penn’s Xin Sun offers an improved understanding of microbial ecology and geochemistry—key to forecasting global emissions in response to natural and man-made climate change.
Two X-ray plates from Arthur Goodspeed, believed to have created the world’s first X-ray image, were donated by his family to Penn’s University Archives.
Over 20,000 educators share insights on school cell phone policies
Preliminary findings in the landmark research initiative “Phones in Focus” suggest stricter cell phone policies are linked to less disruption and greater teacher satisfaction.
