The team at the laboratory of James Collins of the Broad Institute of the Massachusetts Institute of Technology (MIT) and Harvard University has used artificial intelligence (AI) to discover a new class of antibiotic candidates.
Accelerating drug discovery
The researchers set out to address antibiotic resistance and were looking for antibiotics that would be effective against superbugs like methicillin-resistant Staphylococcus aureus (MRSA) and vancomycin-resistant enterococci, bacteria that are typically resistant to antibiotics.
The team successfully screened millions of compounds using a deep-learning AI model to unearth new potential antibiotic candidates. Traditional methods take years to yield results, but AI can rapidly parse through datasets to find promising candidates. Artificial intelligence could drastically shorten the lengthy process of drug discovery and development, offering a faster route to new treatments.
“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,” said César de la Fuente, an assistant professor in the Department of Psychiatry at the University of Pennsylvania’s Perelman School of Medicine.
“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,” he added.
The amount of time it takes to discover a new antibiotic can be significantly reduced thanks to AI. However, new antibiotic candidates still have to go through a long journey that involves rigorous testing and regulatory approvals after they are initially discovered. The U.S. Food and Drug Administration (FDA) requires comprehensive toxicity and investigational new drug studies before any clinical trials can commence to ensure the safety and efficacy of new drugs.
Breaking the black box
Unlike most AI models, which are often thought of as black boxes because there is not much insight into how or why they produce their outputs, the researchers at Collins Lab implemented elements of ‘explainable AI’ into their work, and were able to shed light on the biochemistry underlying the AI’s decisions. Explainable AI is an approach in artificial intelligence that emphasizes the ability to clearly explain how AI systems make decisions or predictions; it is vital for transparency, trust, and ethical considerations.
“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,” de la Fuente said.
AI’s impact on medical research
The work of the Collins Lab and its researchers presents a promising outlook on using AI in healthcare and is a significant scientific victory. This shift is not just about speed and efficiency in drug discovery; it’s about fundamentally changing our approach to medical research. Integrating AI, especially with explainable models, enables a more thorough understanding of drug interactions. These advancements are bound to have a significant impact on healthcare and the life sciences industry and will lead to a future where AI plays a crucial role in uncovering new treatment methods, enhancing disease prevention strategies, and more personalized patient care.
In order for artificial intelligence (AI) to work right within the law and thrive in the face of growing challenges, it needs to integrate an enterprise blockchain system that ensures data input quality and ownership—allowing it to keep data safe while also guaranteeing the immutability of data. Check out CoinGeek’s coverage on this emerging tech to learn more why Enterprise blockchain will be the backbone of AI.
Watch: Health care, life sciences, and blockchain
New to blockchain? Check out CoinGeek’s Blockchain for Beginners section, the ultimate resource guide to learn more about blockchain technology.
