We are searching data for your request:
Upon completion, a link will appear to access the found materials.
Breakthrough in antibiotic development
Using a machine learning algorithm, a powerful new antibiotic compound has now been identified that kills many of the world's most problematic disease-causing bacteria. These included some strains that are resistant to all known antibiotics.
The latest study by the internationally renowned Massachusetts Institute of Technology (MIT) found that a newly identified antibiotic compound also works on strains that are normally resistant to all known antibiotics. The results of the study were published in the English-language journal "Cell".
What was the aim of the study?
A computer model that can analyze more than a hundred million chemical compounds in a matter of days should try to identify potential antibiotics that kill bacteria with mechanisms other than those currently available.
A new age of antibiotics through artificial intelligence?
"We wanted to develop a platform that would enable us to use the power of artificial intelligence to usher in a new era in the discovery of antibiotics," said Professor James Collins of MIT in a press release. "Our approach revealed this amazing molecule, which is arguably one of the more effective antibiotics that have been discovered," added the expert.
Other promising antibiotic candidates have been identified
In their new study, the researchers also identified several other promising antibiotic candidates that they want to test further. The research group believes that the model could also be used to develop new drugs based on the knowledge of chemical structures that enable drugs to kill bacteria.
Difficulty developing antibiotics
Very few new antibiotics have been developed in the past few decades and most of these newly approved antibiotics are slightly different variants of existing drugs. Current methods for screening new antibiotics are often prohibitive, require a significant amount of time, and are usually limited to a narrow range of chemical diversity.
How was the model trained?
The researchers trained their model on around 2,500 molecules, including around 1,700 drugs approved by the FDA and a range of 800 natural products with different structures and a wide range of bioactivities.
Model chose a molecule with strong antibacterial activity
After the model was trained, the researchers tested it at the Broad Institute's Drug Repurposing Hub, a collection of around 6,000 compounds. The model selected a molecule (halicin) that was predicted to have strong antibacterial activity and that had a chemical structure that was different from all existing antibiotics.
Molecule appears to have low toxicity to human cells
Using another machine learning model, the researchers also showed that this molecule would likely have a low toxicity to human cells. The molecule has previously been studied as a possible diabetes drug. The researchers tested it on dozens of bacterial strains isolated from patients and grown in laboratory dishes.
Molecule was able to kill many resistant strains
They found that this molecule was able to kill many resistant strains, including Clostridium difficile, Acinetobacter baumannii and Mycobacterium tuberculosis. The drug was effective against all species tested, with the exception of Pseudomonas aeruginosa, a difficult-to-treat lung pathogen.
Ointment eliminates infection within 24 hours
To test the effectiveness of halicin on live animals, the researchers used it to treat mice infected with A. baumannii, a bacterium that had infected many US soldiers stationed in Iraq and Afghanistan. The A. baumannii strain they use is resistant to all known antibiotics, but by using a halicin-containing ointment, the infections were completely eliminated within 24 hours.
E. coli did not develop resistance to halicin
It was also found that E. coli did not develop resistance to halicin during a 30-day treatment period. In contrast, the bacteria began to develop resistance to the antibiotic ciprofloxacin within one to three days and after 30 days the bacteria were about 200 times more resistant to ciprofloxacin than at the beginning of the experiment.
Further research is planned
In the future, the researchers are planning further studies on halicin, which they want to carry out in collaboration with a pharmaceutical company or a non-profit organization, in the hope of making it usable for human use.
23 candidates for new antibiotics?
After identifying halicin, the researchers also used their model to screen more than 100 million molecules selected from the ZINC15 database, an online collection of approximately 1.5 billion chemical compounds. This screening only lasted three days; it identified 23 candidates that differed structurally from existing antibiotics and were predicted to be non-toxic to human cells.
Eight molecules showed antibacterial activity
In laboratory tests on five types of bacteria, it was found that eight of the molecules showed antibacterial activity and two were particularly strong. The researchers are now planning to continue testing these molecules and to continue searching the ZINC15 database.
The second breakthrough in a short time
Researchers at McMaster University in Canada recently discovered a new group of antibiotics that are capable of killing resistant bacteria using a mechanism that has never been seen before. The discovery has the potential to bring about a change in the fight against antimicrobial resistance. The research group is already successfully testing the antibiotics on resistant bacterial strains that can cause blood poisoning (sepsis). For more information, see the article: New antibiotic works against resistant sepsis bacteria. (as)
Author and source information
This text corresponds to the requirements of the medical literature, medical guidelines and current studies and has been checked by medical doctors.
- Jonathan M. Stokes, Kevin Yang, Kyle Swanson, Tommi S. Jaakkola, Regina Barzilay et al .: A Deep Learning Approach to Antibiotic Discovery, in Cell (Published Volume 180, Issue 4, Feb 13, 2020), Cell
- Artificial intelligence yields new antibiotic, Massachusetts Institute of Technology (Published Feb 20, 2020), MIT