Be first to read the latest tech news, Industry Leader's Insights, and CIO interviews of medium and large enterprises exclusively from Medical Tech Outlook
THANK YOU FOR SUBSCRIBING
By
MedTech Outlook | Thursday, July 02, 2020
With the help of the machine-learning algorithm, researchers have discovered a robust new antibiotic compound, which is a big step in the medical industry.
Fremont, CA: The computer model capable of screening above a hundred million chemical compounds in a matter of days is developed to identify the potential antibiotics that kill bacteria using various mechanisms that those of the existing drugs. In recent lab tests, the drug killed many of the world's most problematic disease-causing bacteria, which included some strains that are resistant to all known antibiotics; additionally, it cleared infections in two different mouse models. The researchers at MIT wanted to develop a platform that would enable them to harness the power of artificial intelligence to introduce a new age of antibiotic drug discovery. In their new study, the researchers also found various promising antibiotic candidates, which they are planning to test in the future. The researchers believe that the model can also utilize to formulate new drugs based on what it has understood about chemical structures that help the drug to kill the bacteria.
Stay ahead of the industry with exclusive feature stories on the top companies, expert insights and the latest news delivered straight to your inbox. Subscribe today.
A New Approach
Very[vendor_logo_first] few antibiotics have developed in the past few decades, out of which most of them are newly approved antibiotics, which are slightly different variants of the existing drugs. At present, screenings of new antibiotics are significantly higher on cost, require a substantial investment of time, and are generally limited to a narrow spectrum of chemical diversity.
The idea of leveraging predictive computer models for "in silico" screening is not very new. Until now, these models were not sufficiently accurate to alter drug discovery. The new neural networks can learn these representations automatically, mapping molecules into continuous vectors, that are subsequently used to predict their property.
Optimized Molecules
The researchers also used the model to screen more than 100 million molecules that are selected from a database, an online collection of nearly 1.5 billion chemical compounds. In lab tests conducted against five species of bacteria, it discovered that almost eight of the molecules displayed antibacterial activity, and two were particularly influential. The researchers are planning to test these molecules further, as well as screen more of the ZINC15 database. They also intend to use their model to design new antibiotics and to optimize the existing units.
More in News
I agree We use cookies on this website to enhance your user experience. By clicking any link on this page you are giving your consent for us to set cookies. More info
