Introduction
Antimicrobial resistance (AMR) is one of the greatest threats facing humanity today, making the need for new antibiotics more critical than ever. Traditional approaches to antibiotic discovery are painstakingly slow, often taking years to identify preclinical candidates. In a groundbreaking study published in Nature Biomedical Engineering, our team introduces APEX, a new AI model designed to expedite the discovery of new antibiotics. This innovative system marks the culmination of several years of research, building on decades of prior work developing sequencing methods for ancient genetic material.
Introducing APEX
APEX represents a significant advancement in antibiotic discovery by leveraging deep learning to mine the genetic material of extinct organisms, a resource we term the “extinctome”. Through a process we call “molecular de-extinction,” APEX has successfully identified numerous antibiotic compounds from ancient creatures, including the woolly mammoth.
Molecular De-Extinction: A New Frontier in Antibiotics
The molecular de-extinction process employed by APEX has uncovered a diverse array of antibiotic compounds from extinct organisms. These rediscovered molecules, such as mammuthusin, mylodonin, elephasin, megalocerin, and hydrodamin, have demonstrated promising results both in vitro and in preclinical mouse models. Remarkably, their efficacy rivals that of the standard-of-care antibiotic polymyxin B.
Accelerating Discovery with AI
One of the most significant advantages of APEX is its ability to accelerate the antibiotic discovery process dramatically. Traditional methods can take up to six years to discover new preclinical candidates. In contrast, APEX can idenfity thousands of potential candidates in just a few hours. This rapid pace of discovery has the potential to transform the field of antibiotic research, providing a powerful tool in the fight against antimicrobial resistance.
Conclusion
The development of APEX marks a significant milestone in the field of antibiotic discovery. By leveraging the power of AI, we can now identify thousands of potential antibiotic candidates in a fraction of the time required by traditional methods. This breakthrough accelerates the discovery process, offering a faster and more efficient approach to combating antimicrobial resistance.
For more information on this study, please refer to the full paper published in Nature Biomedical Engineering: https://www.nature.com/articles/s41551-024-01201-x.
For more information, please contact:
Machine Biology Group
University of Pennsylvania
Authors:
Fangping Wan, Marcelo D.T. Torres, Jacqueline Peng, and Cesar de la Fuente-Nunez.
Published:
June 11, 2024
About Machine Biology Group:
The mission statement of the Machine Biology Group at the University of Pennsylvania is to use the power of machines to accelerate discoveries in biology and medicine.