AI is designing entirely new classes of antibiotics to fight superbugs
In short: As antibiotic resistance threatens to kill 10 million people annually by 2050, traditional drug discovery is failing. But at MIT, researchers are using generative AI to explore vast chemical spaces, designing molecules that have never existed in nature to destroy the world's deadliest pathogens.
The global antimicrobial resistance (AMR) crisis is accelerating. While drug-resistant bacterial infections currently cause nearly 5 million deaths per year, the United Nations estimates that by 2050, this figure could rise to 10 million annual deaths, surpassing cancer. The situation worsens as the pipeline for new discoveries shrinks; for 45 years, the FDA has approved just a few dozen antibiotics, most being simple variations of current drugs. This crisis is exacerbated by the fact that pharmaceutical and biotechnology firms have largely abandoned the sector to pursue more lucrative markets. Consequently, healthcare systems worldwide face a potential collapse without immediate intervention.
To break this cycle, the Antibiotics-AI Project at MIT, led by bioengineer Jim Collins, utilizes a 'lab-in-the-loop' system. This process creates a closed loop where experimental biology and deep learning teach one another. Researchers use generative AI to design more than 36 million possible compounds, which are then computationally screened for antimicrobial properties. This allows scientists to exploit chemical spaces that were previously inaccessible to traditional methods.
The results include the discovery of structurally distinct compounds like halicin and abaucin. By using unique mechanisms like membrane disruption, these candidates can tackle stubborn infections including multi-drug-resistant Staphylococcus aureus (MRSA) and drug-resistant Neisseria gonorrhoeae. Over the coming seven years, Collins and his group intend to find seven distinct antibiotic classes to fight pathogens such as Pseudomonas aeruginosa and Acinetobacter baumannii.
Opens the Intellect+ feed with this card first. Swipe up for the next one.
Sources
- Summary by Intellect · source: How we're using AI to discover new antibiotics | Jim Collins
- Also: Antibiotics-AI Project — Collins Lab, MIT
- Also: Using generative AI, researchers design compounds that can kill drug-resistant bacteria
To cite this card, link to https://intellectplus.co.uk/app/ideas-how-we-re-using-ai-to-discover-new-antibiotics-jim-collins.
How we source, check and correct cards: Editorial standards.
General information, not professional advice. Spotted an error? Flag the card or see corrections and complaints.
Intellect Plus is a visual educational discovery platform for exploring fascinating facts and ideas. Brain Food, Not Brain Rot. What is Intellect Plus?
Related
More in Artificial intelligence · More in Ideas & Philosophy · Latest · A–Z · All topics
