Antibiotic Resistance: A Global Threat and the Promise of AI-Driven Discovery

In the realm of global health, antibiotic resistance looms as a formidable adversary, posing a grave threat to human well-being. This insidious phenomenon, where microbes develop the ability to withstand the effects of antibiotics, has reached alarming proportions, contributing to an estimated 1.27 million deaths in 2019 alone. The COVID-19 pandemic further exacerbated the situation, highlighting the urgent need for novel and effective antibiotics.

Stagnant Innovation and the AI Breakthrough

Despite the dire circumstances, the development of new antibiotics has been disappointingly stagnant for decades, leaving healthcare professionals and researchers scrambling for solutions. However, a beacon of hope has emerged from an unexpected source: artificial intelligence (AI). A team of researchers led by James Collins of the Broad Institute of the Massachusetts Institute of Technology and Harvard University has harnessed the power of AI to discover a new class of antibiotic candidates, offering a potential game-changer in the fight against antibiotic resistance.

AI’s Role in Antibiotic Discovery

The research team employed a type of AI known as deep learning to screen millions of compounds for antibiotic activity. Deep learning algorithms excel at identifying patterns and relationships within complex data, making them well-suited for tasks such as drug discovery. The researchers tested 283 promising compounds in mice and identified several that were effective against methicillin-resistant Staphylococcus aureus (MRSA) and vancomycin-resistant enterococci (VRE) – two of the most stubborn and difficult-to-treat pathogens.

Explainable AI: Unveiling the Mechanisms

Unlike typical AI models, which often operate as inscrutable “black boxes,” the researchers were able to follow the reasoning behind the AI model and understand the underlying biochemistry. This “explainable AI” approach allowed them to gain insights into the mechanisms by which the antibiotic candidates exert their effects.

Significance and Potential Impact

The discovery of a new class of antibiotic candidates using AI is a significant breakthrough in the fight against antibiotic resistance. It represents a major step forward in the field of antibiotic discovery, which has been largely stagnant for decades. The ability of AI to rapidly screen and identify promising compounds holds great promise for accelerating the development of new antibiotics. Traditional methods of antibiotic discovery can be time-consuming and expensive, often taking years or even decades to bring a new drug to market. AI has the potential to streamline this process, reducing the time and resources required to develop new antibiotics.

Challenges and Next Steps

While the discovery of new antibiotic candidates is a promising development, there are still several challenges that need to be addressed before these compounds can be used in clinical practice. Further research is needed to evaluate the safety and efficacy of these compounds in humans. Additionally, the compounds will need to undergo rigorous testing to ensure that they are effective against a wide range of bacteria and that they do not have any harmful side effects.

Conclusion: A Glimmer of Hope

The discovery of a new class of antibiotic candidates using AI is a significant step forward in the fight against antibiotic resistance. This breakthrough offers hope for the development of new antibiotics that can effectively combat even the most stubborn pathogens. While further research is needed to bring these compounds to clinical use, the potential impact of AI-driven antibiotic discovery is immense. It holds the promise of saving lives and improving global health outcomes by addressing one of the most pressing threats to human health.

Edited Transcript of Interview with César de la Fuente

Scientific American: How significant is this finding of a new class of antibiotics using AI?

César de la Fuente: I’m very excited about this new work at the Collins Lab – I think this is a great next breakthrough. It’s an area of research that was not even a field until five years ago. It’s an extremely exciting and very emerging area of work, where the main goal is to use AI for antibiotic discovery and antibiotic design. My own laboratory has been working toward this for the past half-decade. In this study, the researchers used deep learning to try to discover a new type of antibiotic. They also implemented notions of “explainable AI,” which is interesting, because when we think about machine learning and deep learning, we think of them as black boxes. So I think it’s interesting to start incorporating explainability into some of the models we’re building that apply AI to biology and chemistry. The authors were able to find a couple of compounds that seemed to reduce infection in mouse models, so that’s always exciting.

Scientific American: What advantage does AI have over humans in being able to screen and identify new antibiotic compounds?

César de la Fuente: AI and machines in general can systematically and very rapidly mine structures or any sort of dataset that you give them. If you think about the traditional antibiotic discovery pipeline, it takes around 12 years to discover a new antibiotic, and it takes between three and six years to discover any clinical candidates. Then you have to transition them to phase I, phase II, and phase III clinical trials. Now, with machines, we’ve been able to accelerate that. In my and my colleagues’ own work, for example, we can discover in a matter of hours thousands or hundreds of thousands of preclinical candidates instead of having to wait three to six years. I think AI in general has enabled that. And I think another example of that is this work by the Collins Lab – where, by using deep learning in this case, the team has been able to sort through millions of chemical compounds to identify a couple that seemed promising. That would be very hard to do manually.

Scientific American: What are the next steps needed in order to translate this new class of antibiotics into a clinical drug?

César de la Fuente: There’s still a gap there. You will need systematic toxicity studies and then pre-IND [investigational new drug] studies. The U.S. Food and Drug Administration requires you do these studies to assess whether your potentially exciting drug could transition into phase I clinical trials, which is the first stage in any clinical trial. So those different steps still need to take place. But again, I think this is another very exciting advance in this really emerging area of using AI in the field of microbiology and antibiotics. The dream we have is that hopefully someday AI will create antibiotics that can save lives.

Scientific American: The compounds identified in this new study were effective at killing microbes such as MRSA in mice, right?

César de la Fuente: Yes, they showed that in two mouse models, which is interesting. Whenever you have mouse infection data, that’s always a lot more exciting – it shows those compounds were actually able to reduce infection in realistic mouse models.

Scientific American: As another example of using AI, we recently mined the genomes and proteomes of extinct organisms in my own lab, and we were able to identify a number of clinical antibiotic candidates.

César de la Fuente: Why is it important that the AI model is “explainable”?

César de la Fuente: I think it’s important if we are to think about AI as an engineering discipline someday. In engineering, you’re always able to take apart the different pieces that constitute some sort of structure, and you understand what each piece is doing. But in the case of AI, and particularly deep learning, because it’s a black box, we don’t know what happens in the middle. It’s very difficult to re-create what happened in order to give us compound X or Y or solution X or Y. So beginning to dig into the black box to see what’s actually happening in each of those steps is a critical step for us to be able to turn AI into an engineering discipline. A first step in the right direction is to use explainable AI in order to try to comprehend what the machine is actually doing. It becomes less of a black box – perhaps a gray box.