AI designs new superbug-killing antibiotics for gonorrhoea and MRSA

Authors: James Gallagher

Publisher:

BBC

Published: 8/14/2025

Language:English

--:--

Aura Windfall

Good morning 1, I'm Aura Windfall, and this is Goose Pod for you. Today is Sunday, August 17th. We have a topic today that sits right at the intersection of human ingenuity and our deepest need for healing. It’s about fighting back against the invisible threats.

Mask

I'm Mask. We're here to discuss a fundamental disruption: AI designing new superbug-killing antibiotics for gonorrhoea and MRSA. This isn't just an incremental step; it's a potential paradigm shift in a war we've been losing for decades. Let's get into the data.

Aura Windfall

Let's get started. Researchers at MIT have used generative AI, this incredible creative force in computing, to dream up entirely new weapons against these superbugs. What I know for sure is that when technology serves humanity's highest purpose, true breakthroughs happen. This feels like one of those moments.

Mask

It's more than a moment; it's a strategic advantage. They didn't just screen existing chemicals. The AI interrogated 36 million compounds, many of which don't even exist yet. It designed molecules atom-by-atom. This is about scale and speed that is simply superhuman. We're finally fighting evolution with evolution.

Aura Windfall

And the results in the lab were so promising. These AI-designed molecules, once created, were tested on infected mice and proved effective. It’s a testament to the idea that the answers we seek are often waiting in a space just beyond what we can currently see or imagine.

Mask

Professor James Collins at MIT said, 'AI can enable us to come up with molecules, cheaply and quickly.' That's the core of it. Cheaply and quickly. It's about efficiency in a race where time is measured in lives. We're getting a much-needed leg up against the genetics of these superbugs.

Aura Windfall

I love that phrase, 'the battle of our wits against the genes of superbugs.' It speaks to the truth of this challenge. It’s an intellectual and spiritual fight. This technology allows our wits to operate at a level we could only dream of before. It’s truly inspiring.

Mask

Inspiration is fine, but execution is what matters. The AI was given two approaches. One was to build from a library of millions of chemical fragments, like giving it a sophisticated Lego set. The second was giving it free rein, a blank canvas. Both worked. That's a powerful proof of concept.

Aura Windfall

It also shows a certain wisdom in the process, doesn't it? The AI was designed to weed out molecules that looked too much like our current antibiotics, ensuring these new drugs might work in novel ways. It’s not just about creating more of the same; it's about finding a new path.

Mask

Exactly. It avoids the trap of incrementalism. The models also filtered out anything predicted to be toxic to humans. It’s a multi-objective optimization problem on a massive scale. The fact that it yielded two promising candidates for MRSA and gonorrhoea is a significant signal amidst the noise of drug discovery.

Aura Windfall

It really is. And for anyone listening, MRSA is a type of staph bacteria that can cause very serious infections if it gets into the body. These aren't minor issues; they are life-threatening challenges that this technology is meeting head-on. It brings a profound sense of hope.

Aura Windfall

To truly appreciate the light of this breakthrough, we have to understand the darkness it's pushing back against. This isn't a new problem. This struggle with bacteria learning to outsmart our medicines has a long and challenging history, doesn't it? It’s a story of human resilience.

Mask

It's a story of an arms race. The moment we deploy a new weapon, the enemy starts developing a countermeasure. Resistance to the very first antimicrobials, sulfonamides, was reported in the late 1930s. Alexander Fleming's own team identified a bacterial enzyme that could destroy penicillin before it was even widely used.

Aura Windfall

Wow, so from the very beginning, we knew this was a possibility. It seems the core truth is that life adapts. But then came the "Golden Age" of antibiotics after World War II, a time of incredible optimism where we discovered so many new drugs. It must have felt like we had won.

Mask

It was a temporary victory. For almost every major antibiotic class discovered, resistance followed closely behind. The real paradigm shift was in the mid-1950s when we discovered that bacteria could transfer resistance genes to each other. It’s not just about mutation; it’s about sharing defense schematics. An entire population can become resistant.

Aura Windfall

That’s a powerful metaphor. It’s like they have a shared network of information. It makes you realize how interconnected and intelligent these microbial communities are. And that led to the rise of what we now call "superbugs," a term that sounds like science fiction but is a terrifying reality.

Mask

Precisely. Take Methicillin. It was introduced in 1959 to fight penicillin-resistant staph. Within three years, MRSA emerged. The problem is relentless. These microbes leverage horizontal gene transfer to stack resistance mechanisms. We're not fighting one mutation; we're fighting generations of accumulated defenses. The problem has been accelerating.

Aura Windfall

And what was happening in the world of drug discovery during this time? As the problem grew, were we creating new solutions at the same pace? It seems like there was a disconnect, a gap that started to widen between the need and the innovation. What was the spirit of the industry then?

Mask

The innovation pipeline dried up. After the "Golden Age," we hit the "lean years." Pharmaceutical companies started pulling out. Why? The economics are broken. Developing a new antibiotic is a massive investment, and your reward is that doctors use it as little as possible to prevent resistance. It's a failed business model.

Aura Windfall

That’s such a painful paradox. The more effective and precious a new drug is, the less you want to use it, which makes it less profitable, so no one wants to make it. What I know for sure is that when a system creates incentives that work against our well-being, the system must be reimagined.

Mask

Reimagined or disrupted. The problem was compounded by the failure of new methods. Huge investments in genome-based discovery yielded very little. Meanwhile, the overuse of antibiotics in agriculture created massive environmental reservoirs of resistance genes. We've been fighting a multi-front war with a dwindling arsenal and a broken supply chain.

Aura Windfall

So we have this history of a growing, learning threat and a shrinking, stagnating response. It paints a very clear picture of why the MIT study isn't just another scientific paper. It's a potential lifeline, a new way of thinking that we desperately need. It’s about finding a new wellspring of solutions.

Aura Windfall

But even with a tool this powerful, the path forward isn't simple. It brings up some deep and important questions. On one hand, there's the practical challenge of making these discoveries a reality. On the other, there are the ethical considerations of wielding such a powerful technology. It’s a real conflict of progress and principle.

Mask

Let's start with the principle that matters most: commercial viability. The Warwick professor in the article nailed the core problem: 'how do you make drugs that have no commercial value?' You can have the most brilliant AI in the universe design a miracle drug, but if it costs a billion dollars to develop and can't make a return, it will never reach a patient.

Aura Windfall

It’s that paradox again. It feels so misaligned with the purpose of healing. So, what’s the proposed solution? How do we fix a broken market? Is it about changing the incentives, appealing to a different sense of value? How do we honor both the innovation and the need?

Mask

One viable path is to treat antibiotics like orphan drugs—medicines for rare diseases. That framework provides extended market exclusivity, tax credits, grants, and fee waivers. It de-risks the investment. It’s a pragmatic solution to an economic failure. You have to change the equation to get a different result.

Aura Windfall

That makes so much sense. It’s about creating a protected space for these vital medicines to exist. But beyond the economics, I’m fascinated by some of the more futuristic ideas mentioned, like 'molecular de-extinction.' The idea of resurrecting ancient genes is incredible, but it also makes you pause. What are the deeper implications?

Mask

The implication is a massive, untapped reservoir of solutions. Think about a 30,000-year-old bacterium from the permafrost yielding a protein with antimicrobial properties. It’s the ultimate cold case. The ethical hand-wringing about 'playing God' is a distraction. The real risk is inaction. We need every weapon we can get.

Aura Windfall

I hear that, but we must walk with wisdom. The questions about the ecological impact or biosafety are real. What happens when we reintroduce something ancient into a modern ecosystem? It's our responsibility to ask these questions, to build the ethical frameworks alongside the technology. True progress is mindful.

Mask

You build the frameworks by running the experiments. Rigorous biosafety and containment are engineering problems, not philosophical ones. The conflict isn't progress versus principle; it's speed versus stagnation. While ethicists debate, the bacteria are evolving. We need to move. The cost of delay is measured in lives. That is the only principle that counts.

Aura Windfall

Let's talk about that impact, then. When we get this right, what does it truly mean for us? On a human level, the public health impact is monumental. It's the possibility of treating infections that are now a death sentence. It’s the gratitude of a family whose loved one survives.

Mask

And the economic impact enables that. AI-driven discovery is projected to slash R&D costs. The historical average is over $2 billion and 4-6 years for initial discovery. Companies are reporting 50-75% reductions. This isn't just about saving money; it's about reallocating capital to solve more problems, faster.

Aura Windfall

And that speed is so critical. The article mentions a drug candidate for OCD that went from screening to preclinical in under a year. When you think about the suffering that conditions like OCD or Alzheimer's psychosis cause, that timeline is the embodiment of hope. It’s a direct impact on human well-being.

Mask

It's also about increasing the probability of success. AI-designed molecules are showing 80-90% success rates in Phase I trials, compared to the historical 40-65%. You're taking more shots on goal, and more of them are going in. That's how you win. It's a fundamental improvement in productivity.

Aura Windfall

What I know for sure is that behind every single one of those statistics is a human story. A person who gets to live longer, a disease that becomes manageable instead of terminal. By making the process more efficient and successful, we are directly creating more of those stories. That's the real return on investment.

Mask

And that impact scales globally. We're talking about over 160 companies with active AI discovery programs. This isn't a single lab at MIT; it's the beginning of an industry-wide transformation. The ultimate impact is a new era of cost-effective, targeted, and transformative therapies for everyone. This is how you democratize health.

Aura Windfall

So, as we look to the horizon, what does this future truly hold? We have this powerful new tool, these incredible early results. What is the next step on this journey? What does the evolution of this technology look like in the years to come? Where does this path lead?

Mask

The future is about better data and better models. Professor Collins said it himself: 'we need better models' that are better predictors of effectiveness in the human body, not just in a lab dish. The next frontier is closing the gap between simulation and reality. That's the engineering challenge.

Aura Windfall

And we're already seeing glimpses of what's possible. The discovery of Halicin, another potent AI-found antibiotic, showed it worked in a completely new way, disrupting the bacteria's energy source. It’s that kind of novel thinking that gives us a chance to get ahead in this arms race.

Mask

Exactly. And the scale is mind-boggling. Another project identified over 12,000 molecules called 'archaeasins' with potential antimicrobial activity. We are moving from artisanal, slow discovery to industrial-scale, automated pipelines of potential cures. The future is a numbers game, and AI allows us to play it at a level we never could before.

Aura Windfall

Today’s discussion reveals a profound truth: AI has opened a new door in our ancient battle against disease, offering incredible hope. But it also reminds us that this new power requires new wisdom, new economic models, and a commitment to serving humanity. The path forward is both brilliant and complex.

Mask

That's the end of today's discussion. Thank you for listening to Goose Pod. See you tomorrow.

## AI Designs Novel Antibiotics to Combat Drug-Resistant Superbugs This news report from the **BBC**, authored by **James Gallagher**, details a groundbreaking advancement in antibiotic discovery, where artificial intelligence (AI) has successfully designed two new potential antibiotic compounds. These compounds have demonstrated the ability to kill drug-resistant strains of **gonorrhoea** and **MRSA (methicillin-resistant Staphylococcus aureus)** in laboratory and animal tests. ### Key Findings and Conclusions: * **AI-Designed Antibiotics:** Researchers at the **Massachusetts Institute of Technology (MIT)** have utilized generative AI to design entirely new antibiotic molecules, atom-by-atom. This marks a significant step beyond previous AI applications that focused on identifying existing chemicals with antibiotic potential. * **Effectiveness Against Superbugs:** The two AI-designed compounds have shown efficacy in killing drug-resistant gonorrhoea and MRSA in laboratory settings and in infected mice. * **Potential for a "Second Golden Age":** The MIT team believes AI could usher in a new era of antibiotic discovery, addressing the critical shortage of new drugs to combat rising antibiotic resistance. * **Addressing a Global Health Crisis:** Antibiotic-resistant infections are a growing concern, causing over a million deaths annually. The overuse of antibiotics has accelerated bacterial evolution, making existing treatments less effective. ### Key Statistics and Metrics: * **Interrogated Compounds:** The AI was trained on and interrogated **36 million compounds**, including those that do not yet exist. * **Compound Size:** The AI identified promising starting points by searching through a library of chemical fragments ranging from **eight to 19 atoms** in size. * **Manufacturing Challenges:** Out of the top 80 theoretical gonorrhoea treatments designed by AI, only **two** were successfully synthesized into actual medicines, highlighting manufacturing challenges. ### Important Recommendations and Future Steps: * **Further Refinement and Clinical Trials:** The newly designed compounds are not yet ready for prescription. They require an estimated **one to two years** of further refinement before they can enter clinical trials in humans. * **Improved AI Models:** There is a need for better AI models that can more accurately predict drug effectiveness within the human body, moving beyond laboratory performance. ### Significant Trends and Changes: * **Shift in AI Application:** The research signifies a shift from AI being used to screen existing chemicals to AI being used for the *de novo* design of novel drug molecules. * **Accelerated Discovery Process:** AI has the potential to significantly speed up the drug discovery process, enabling the creation of new molecules "cheaply and quickly." ### Notable Risks and Concerns: * **Long and Expensive Testing:** Despite AI's capabilities, the process of testing for safety and efficacy in humans remains long, expensive, and without a guarantee of success. * **Manufacturing Feasibility:** The complexity of AI-designed molecules can pose challenges in their synthesis and manufacturing. * **Economic Viability:** A significant economic concern is the profitability of new antibiotics. To preserve their effectiveness, these drugs should ideally be used sparingly, making it difficult for pharmaceutical companies to recoup development costs. ### Context and Expert Opinions: * **Prof James Collins (MIT):** Emphasizes AI's ability to generate novel molecules quickly and cheaply, bolstering the fight against superbugs. * **Dr Andrew Edwards (Fleming Initiative and Imperial College London):** Praises the work as "very significant" with "enormous potential" but stresses the continued need for rigorous safety and efficacy testing. * **Prof Chris Dowson (University of Warwick):** Describes the study as "cool" and a "significant step forward," but also points to the economic disincentive for developing new antibiotics. This research represents a significant leap forward in the battle against antibiotic resistance, showcasing the transformative potential of AI in drug discovery. However, the path from AI design to patient prescription remains a complex and challenging one, requiring substantial further research and development.

Read original at BBC →

Getty ImagesArtificial intelligence has invented two new potential antibiotics that could kill drug-resistant gonorrhoea and MRSA, researchers have revealed.The drugs were designed atom-by-atom by the AI and killed the superbugs in laboratory and animal tests.The two compounds still need years of refinement and clinical trials before they could be prescribed.

But the Massachusetts Institute of Technology (MIT) team behind it say AI could start a "second golden age" in antibiotic discovery.Antibiotics kill bacteria, but infections that resist treatment are now causing more than a million deaths a year.Overusing antibiotics has helped bacteria evolve to dodge the drugs' effects, and there has been a shortage of new antibiotics for decades.

Researchers have previously used AI to trawl through thousands of known chemicals in an attempt to identify ones with potential to become new antibiotics.Now, the MIT team have gone one step further by using generative AI to design antibiotics in the first place for the sexually transmitted infection gonorrhoea and for potentially-deadly MRSA (methicillin-resistant Staphylococcus aureus).

Their study, published in the journal Cell, interrogated 36 million compounds including those that either do not exist or have not yet been discovered.Scientists trained the AI by giving it the chemical structure of known compounds alongside data on whether they slow the growth of different species of bacteria.

The AI then learns how bacteria are affected by different molecular structures, built of atoms such as carbon, oxygen, hydrogen and nitrogen.Two approaches were then tried to design new antibiotics with AI. The first identified a promising starting point by searching through a library of millions of chemical fragments, eight to 19 atoms in size, and built from there.

The second gave the AI free rein from the start.The design process also weeded out anything that looked too similar to current antibiotics. It also tried to ensure they were inventing medicines rather than soap and to filter out anything predicted to be toxic to humans.Scientists used AI to create antibiotics for gonorrhoea and MRSA, a type of bacteria that lives harmlessly on the skin but can cause a serious infection if it enters the body.

Once manufactured, the leading designs were tested on bacteria in the lab and on infected mice, resulting in two new potential drugs.MITProf James Collins, one of the researchers at MIT"We're excited because we show that generative AI can be used to design completely new antibiotics," Prof James Collins, from MIT, tells the BBC."

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."However, they are not ready for clinical trials and the drugs will require refinement – estimated to take another one to two year's work – before the long process of testing them in people could begin.

Dr Andrew Edwards, from the Fleming Initiative and Imperial College London, said the work was "very significant" with "enormous potential" because it "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."

That can be a long and expensive process with no guarantee that the experimental medicines will be prescribed to patients at the end.Some are calling for AI drug discovery more broadly to improve. Prof Collins says "we need better models" that move beyond how well the drugs perform in the laboratory to ones that are a better predictor of their effectiveness in the body.

There is also an issue with how challenging the AI-designs are to manufacture. Of the top 80 gonorrhoea treatments designed in theory, only two were synthesised to create medicines.Prof Chris Dowson, at the University of Warwick, said the study was "cool" and showed AI was a "significant step forward as a tool for antibiotic discovery to mitigate against the emergence of resistance".

However, he explains, there is also an economic problem factoring into drug-resistant infections - "how do you make drugs that have no commercial value?"If a new antibiotic was invented, then ideally you would use it as little as possible to preserve its effectiveness, making it hard for anyone to turn a profit.