Artificial Intelligence (AI) is revolutionising medicine, aiding scientists in discovering the first new antibiotics in over 60 years.
This breakthrough could be pivotal in combating antibiotic resistance.
A team of researchers at the Massachusetts Institute of Technology (MIT) used a deep-learning model to predict the activity and toxicity of a new compound. Deep learning, a form of AI, uses artificial neural networks to learn and represent data features without explicit programming. It's increasingly being used in drug discovery to identify potential drug candidates, predict their properties, and optimise the drug development process.
The focus of the study was methicillin-resistant Staphylococcus aureus (MRSA), a drug-resistant bacterium causing thousands of deaths worldwide annually. The team trained the deep learning model using data from approximately 39,000 compounds evaluated for their antibiotic activity against MRSA.
"To open the black box" of the deep learning model, researchers integrated toxicity predictions with the antimicrobial activity data. This approach helped them identify compounds capable of effectively combating microbes with minimal harm to the human body.
The researchers screened around 12 million commercially available compounds using this set of models. This led to the identification of two promising antibiotic candidates that reduced the MRSA population by a factor of 10 in mouse model experiments. The discovery of these new antibiotics could mark a turning point in the fight against antibiotic resistance.
Made with TRUST_AI - see the Charter: https://www.modelprop.co.uk/trust-ai
Kommentare