AI has found a new cure
Scientists claim that it is one of the most powerful antibiotics
Kirill Chebotarev, NV
Researchers from The Massachusetts Institute of Technology (MIT) has discovered a powerful antibiotic with the help of artificial intelligence. It is capable of killing superbugs that are resistant to conventional antibiotics.
This is the first antibiotic that has been discovered with the help of AI. Experts declared it a major breakthrough in the fight against the growing problem of drug resistance. The fact is that bacteria are able to develop resistance to certain types of antibiotics if they are taken incorrectly. Over time, such medications can become completely useless.
WHO calls it "one of the biggest threats to global health security and development today," writes the BBC.
Scientists have trained AI analyzes the structure of 2,500 drugs and other compounds to find those that have the most antibacterial properties that can kill E. coli. Of these, they selected 100 candidates for physical use before they discovered halicin. They wrote about their research in the journal Cell (Stokes et al., A Deep Learning Approach to Antibiotic Discovery)
"I think this is one of the most powerful antibiotics discovered to date," says James Collins, a bioengineer from the MIT team.
A new antibiotic is capable of killing 35 types of potentially deadly bacteria, writes the MIT website. Among them are tuberculosis, E. coli, salmonella and other drug–resistant bacteria that can cause infections of the blood, urinary tract and lungs.
For example, the E. coli bacterium already on the third day began to develop resistance to the antibiotic ciprofloxacin. A month later, the drug acted on the bacterium 200 times weaker than at the beginning of the experiment. At the same time, the bacterium did not have any resistance to halicin at all.
After that , researchers using AI analyzed more than 100 million molecules, from which 23 potential antibiotics were selected, structurally different from existing ones, and predicted to be non-toxic to human cells.
In laboratory tests against five types of bacteria, the researchers found that eight molecules showed antibacterial activity, and two were particularly potent. Now the researchers plan to further test these molecules, as well as analyze additional amounts of data to search for new antibiotics.
The researchers also plan to use their model to develop new antibiotics and optimize existing ones. For example, they can train the model to add functions that will cause a particular antibiotic to target only certain bacteria, preventing it from killing beneficial bacteria in the patient's digestive tract.
"This revolutionary work marks a paradigm shift in the field of antibiotic discovery and in the field of drug discovery in general," says Roy Kishoni, professor of biology and computer science at the Israel Institute of Technology.
The use of artificial intelligence technologies in healthcare remains in its infancy, but major breakthroughs are still being made. Researchers are confident that the use of AI to accelerate drug discovery could help reduce the cost of creating more antibiotics in the future.
Portal "Eternal youth" http://vechnayamolodost.ru