In a world first, scientists have discovered a new type of antibiotic with the help of artificial intelligence (AI).
It has been announced by experts as a major breakthrough in the fight against the growing drug resistance problem.
A powerful algorithm was used to analyze more than one hundred million chemical compounds in a few days.
The newly discovered compound was able to kill 35 species of potentially deadly bacteria, the researchers said.
Antibiotics-resistant infections have increased in recent years – in England by 9% between 2017 and 2018, to nearly 61,000.
If antibiotics are taken improperly, harmful bacteria that live in the body can become resistant to them, meaning that the drugs do not work if they are really needed.
- Artificial intelligence apps, Parkinson's and me
- NHS to set up a national laboratory for artificial intelligence
The World Health Organization (WHO) has called the phenomenon “one of the greatest threats to the safety and development of health in the world today”.
A new era
“In terms of antibiotic discovery, this is definitely a first,” says Regina Barzilay, a senior researcher at the Massachusetts Institute of Technology (MIT).
The discovery was made using an algorithm inspired by the architecture of the human brain.
Scientists trained it to analyze the structure of 2,500 drugs and other compounds to find those with the most antibacterial qualities that could kill E. coli.
They then selected around 100 candidates for physical tests before discovering halicin.
“I think this is one of the more powerful antibiotics that has been discovered so far,” said James Collins, a team engineer at MIT.
“We wanted to develop a platform that would allow us to use the power of artificial intelligence to herald a new era of antibiotic discovery.”
Dr. Peter Bannister, chairman of the Institution of Engineering and Technology healthcare panel, said the method used was already “well established” within medical research.
“The same approach has gained popularity in the development of new therapies, such as drugs and, in the case of this study, antibiotics where pattern recognition, including in-depth learning, can help sort the huge numbers of molecules,” he said. the BBC.
“This article goes beyond theoretical simulation and presents preclinical results, which are essential together with subsequent clinical trials to clearly demonstrate the efficacy and safety of these new” AI discovered “drugs.”
Since 2014, the UK has reduced the number of antibiotics it uses by more than 7%, but the number of drug-resistant bloodstream infections has increased by 35% between 2013 and 2017.
Researchers added that using the machine to speed up drug discovery could help lower the cost of generating more antibiotics in the future.
It only comes a few weeks after a drug molecule discovered by AI is the first of its kind to be used in human trials.
It will be used to treat patients with obsessive compulsive disorder (OCD).
The use of AI technology in healthcare is still in its infancy, but major breakthroughs are still being achieved.
A study recently claimed that AI is more accurate than doctors diagnosing breast cancer with mammography.
An international team, including researchers from Google Health and Imperial College London, designed and trained a computer model on X-rays of nearly 29,000 women.
The algorithm performed better than six radiologists when reading mammographies.Tags: #ArtificialIntelligence, #latestNewsAI, #researchAi, #Robotics, amsterdam, Artificial Intelligence