
nocred
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.
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.”
Read more at Penn Engineering Today.
Ian Scheffler
nocred
Image: fcafotodigital via Getty Images
nocred
Image: Mininyx Doodle via Getty Images