AI designs breakthrough antibiotics to combat drug-resistant superbugs

Artificial Intelligence (AI) has been used to design two new antibiotics that have the potential to fight against drug-resistant gonorrhea and MRSA.

This marks a groundbreaking advancement in the fight against antimicrobial resistance.

The research conducted by MIT-based researchers utilised generative AI to construct these compounds atom by atom, reflecting their effectiveness in laboratory tests and during animal trials.

While it may take years of further refinement and clinical testing before it is ready for human use, scientists claim that the breakthrough research could herald a “second golden age” in antibiotic discovery.

For this study, the AI system assessed 36 million compounds, even hypothetical ones to analyse how molecular structures affect bacterial growth.

The research employed two innovative approaches, i.e., one building upon promising chemical fragments and another granting the AI complete creative freedom.

To avoid repetition, the AI system intentionally avoided similarities to existing antibiotics, ensuring safety and efficacy.

While speaking with the BBC, Prof. James Collis of MIT stated, “We're excited because we show that generative AI can be used to design completely new antibiotics.”

“ AI can enable us to come up with molecules, cheaply and quickly and in this way, expand our arsenal, and really give us a leg up in the battle of our wits against the genes of superbugs,” he further added.

Despite the promising results, some challenges pertain. It is noted that only two of 80 AI-generated gonorrhea treatments could be synthesised, highlighting manufacturing hurdles.

Dr. Andrew Edwards of the Fleming Initiative and Imperial College London appreciated the work as “very significant” and having “enormous potential” as the study “demonstrates a novel approach to identifying new antibiotics.”

But he added: “While AI promises to dramatically improve drug discovery and development, we still need to do the hard yards when it comes to testing safety and efficacy.”