Researchers at MIT have successfully developed innovative antibiotics through the application of artificial intelligence, specifically targeting two challenging pathogens: multi-drug-resistant Neisseria gonorrhoeae and Staphylococcus aureus (MRSA). This groundbreaking work utilizes two distinct methodologies.
Initially, the team employed generative AI to create molecular structures derived from a chemical fragment identified by their model as likely to exhibit antimicrobial properties. In addition, they allowed the algorithms to generate molecules without any limitations. This comprehensive approach led to the design of over 36 million potential compounds, which were subsequently screened computationally for their antimicrobial efficacy.
The most promising candidates identified are structurally unique compared to existing antibiotics and seem to operate through innovative mechanisms that disrupt bacterial cell membranes. This characteristic may make them less susceptible to the growing issue of antibiotic resistance, a critical global health concern responsible for approximately 5 million fatalities annually.
With the capability to generate and assess compounds that have not been previously discovered, the researchers express optimism about applying this strategy to develop drugs against a broader array of bacterial species. “We”re excited about the new possibilities that this project opens up for antibiotics development,” stated James Collins, a professor of biological engineering and the senior author of the study. “Our work demonstrates the potential of AI in drug design and enables us to explore much larger chemical spaces that were previously out of reach.”
