Google’s AI Solved An Antibiotic-Resistant Superbug Mystery That Took Scientists A Decade To Decode
It took scientists a decade to figure out how superbugs gain resistance to antibiotics, but Google’s new artificial intelligence (AI) tool was able to crack the problem in just two days.
Superbugs becoming resistant to antibiotics is a growing threat that results in the deaths of millions of people every year.
A team of scientists at Imperial College London led by José Penadés spent 10 years trying to come up with an answer.
When they asked Google’s “co-scientist” the same question in a short prompt, the AI produced the same conclusion the team did in just two days.
Penadés was shocked and emailed Google to see if they had access to his research. The company responded that they did not.
“What our findings show is that AI has the potential to synthesize all the available evidence and direct us to the most important questions and experimental designs,” said Tiago Dias da Costa, a co-author of the study and a lecturer in bacterial pathogenesis at Imperial College London.
“If the system works as well as we hope it could, this could be game-changing; ruling out ‘dead ends’ and effectively enabling us to progress at an extraordinary pace.”
Antimicrobial resistance (AMR) occurs when infectious microbes like bacteria, viruses, fungi, and parasites no longer respond to antibiotics, making the drugs ineffective.
AMR is one of the biggest health threats to humanity. The overuse and misuse of antibiotics in medicine and agriculture only help it to progress.
Sign up for Chip Chick’s newsletter and get stories like this delivered to your inbox.
According to a 2019 report from the Centers for Disease Control and Prevention (CDC), at least 1.27 million people across the globe died due to drug-resistant bacteria.
About 35,000 of those deaths were in the United States alone, which shows that fatalities from this issue in the U.S. have increased by 52 percent since the last report from 2013.
The research team investigated this problem by searching for ways that one type of superbug, known as capsid-forming phage-inducible chromosomal islands (cf-PICIs), can infect diverse species of bacteria.
Their theory was that these viruses did so by taking tails from different bacteria-infecting viruses. The tails are used to inject the viral genome into the host bacterial cell. After conducting experiments, they found that they were right.
The researchers then posed the same question to Google’s AI tool. Two days later, the AI returned some suggestions, one of which was the correct answer.
“This effectively meant that the algorithm was able to look at the available evidence, analyze the possibilities, ask questions, design experiments, and propose the very same hypothesis that we arrived at through years of painstaking scientific research, but in a fraction of the time,” said Penadés.
If they had used the AI from the start, they could’ve come up with the answer much sooner and saved themselves years of work, although they still would’ve had to conduct experiments to reach the conclusion.
The latest findings were published to the preprint server bioRxiv.
More About:News