Scientists discover new antibiotic with artificial intelligence

In a world first, scientists have discovered a new type of antibiotic with the help of artificial intelligence (AI).
It has been hailed by experts as a major breakthrough in the fight against the growing problem of drug resistance. Using a powerful algorithm, more than a hundred million chemical compounds could be analyzed within a few days. The newly discovered compound was able to kill 35 types of potentially deadly bacteria, according to the researchers. Antibiotic-resistant infections have increased in recent years – by 9% in England between 2017 and 2018 to almost 61,000. If antibiotics are taken improperly, harmful bacteria living in the body can become resistant to them, meaning the drugs may not work when truly needed. Applications of artificial intelligence, Parkinson’s and I NHS wants to set up a national artificial intelligence laboratory. The World Health Organization (WHO) has called the phenomenon “one of the greatest threats to global health security and development today.”

A new era
“As far as antibiotic discovery is concerned, this is absolutely a first,” said Regina Barzilay, a senior researcher on the project at the Massachusetts Institute of Technology (MIT). The discovery was made with 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 antibacterial properties that could kill E. coli.

They then selected about 100 candidates for physical testing before discovering halicin. “I believe this is one of the stronger antibiotics discovered to date,” said James Collins, a bioengineer on the MIT team. “We wanted to develop a platform that would allow us to harness the power of artificial intelligence to usher in a new age of antibiotic discovery.” Dr. Peter Bannister, chairman of the Healthcare Panel at the Institution of Engineering and Technology, said the method applied is already “well-established” in medical research. “The same approach has gained popularity in the development of new therapeutics, such as pharmaceuticals and, in the case of this research, antibiotics, where pattern recognition, including deep learning, can help sort through the vast number of molecules,” he told the BBC. “This paper goes beyond theoretical simulation and presents preclinical results, which, along with subsequent clinical trials, are essential to clearly demonstrate the efficacy and safety of these new ‘AI-discovered’ drugs.” Since 2014, the UK has reduced the number of antibiotics used by more than 7%, but the number of drug-resistant bloodstream infections increased by 35% from 2013 to 2017. The researchers added that using the machine to accelerate drug discovery could help reduce the cost of producing more antibiotics in the future.

Key breakthroughs
This comes just weeks after an AI-discovered drug molecule was set to be the first of its kind to enter 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 significant breakthroughs continue to be made. A recent study claimed that AI is more precise than doctors in diagnosing breast cancer from mammograms. An international team, including researchers from Google Health and Imperial College London, designed and trained a computer model using X-ray images from almost 29,000 women. The algorithm outperformed six radiologists in reading mammograms.

Machine translation of the source:

https://www.bbc.com/news/health-51586010