Antibiotic Against a Superbug

Context: In a major breakthrough for the use of Artificial Intelligence (AI) in the field of medicine, scientists from the United States and Canada have found a new antibiotic – powerful enough to kill a superbug – using AI. What is a Superbug?
  • Superbugs are strains of bacteria, viruses, parasites and fungi that are resistant to most of the antibiotics and other medications commonly used to treat the infections they cause.
  • A few examples of superbugs include resistant bacteria that can cause pneumonia, urinary tract infections and skin infections.
  • Each year these drug-resistant bacteria infect more than 2 million people in the US and kill at least 23,000, according to the US Centers for Disease Control and Prevention (CDC).
What is Antimicrobial Resistance?
  • Antimicrobial Resistance (AMR) occurs when bacteria, viruses, fungi and parasites change over time and no longer respond to medicines making infections harder to treat and increasing the risk of disease spread, severe illness and death.
  • As a result of drug resistance, antibiotics and other antimicrobial medicines become ineffective and infections become increasingly difficult or impossible to treat.
What is Acinetobacter Baumannii?
  • The bacterium was identified by the World Health Organization (WHO) as one of the world’s most dangerous antibiotic-resistant bacteria.
  • A. baumannii can cause pneumonia, meningitis and infect wounds, all of which can lead to death.
  • A. baumanni is usually found in hospital settings, where it can survive on surfaces for long periods.
How did researchers use AI in this case?
  • Exposure of superbug to chemical compounds: The researchers first exposed A. baumannii grown in a lab dish to about 7,500 different chemical compounds, to see which ones could help pause the growth of the bacterium.
  • Use of Machine Learning: The structure of each molecule was fed into the machine-learning model. The model was instructed whether each structure could prevent bacterial growth or not. This allowed the algorithm to learn chemical features associated with growth inhibition.
  • Analysis and Outcomes: Once the model was trained, the researchers used it to analyse a set of 6,680 compounds. This analysis yielded a few hundred results in less than two hours. Of these, the researchers chose 240 to test experimentally in the lab, focusing on compounds with structures that were different from those of existing antibiotics.
  • Discovery of Abaucin: Those tests yielded nine antibiotics, including one that was very potent and effective at killing A. baumannii. This has been named abaucin.
Source: The Indian Express
Share this with friends ->