"Inside a lab at the Massachusetts Institute of Technology late last year, scientists gave an AI system a new task: designing entirely new molecules for potential antibiotics from scratch. Within a day or two-following a few months of training-the algorithms had generated more than 29 million new molecules, unlike any that existed before. Traditional drug discovery is a slow, painstaking process. But AI is beginning to transform it. At MIT, the research is aimed at the growing challenge of antibiotic-resistant infections, which kill more than a million people globally each year. Existing antibiotics haven't kept up with the threat."
"The team tried making a small number of the compounds, and then used one to clear a drug-resistant infection in a mouse. In another part of the study, the researchers used a different approach to generate additional molecules, leading to another successful test in mice-and the possibility that novel, fully AI-designed drugs may eventually be available for the most dangerous infections."
Antibiotic-resistant infections cause over a million deaths globally each year while few truly novel antibiotics have been developed. An MIT laboratory trained AI systems to design entirely new molecules and generated more than 29 million unique compounds within days after months of training. Researchers synthesized a small number of those compounds and demonstrated that one cleared a drug-resistant infection in a mouse. A separate AI approach produced additional molecules and another successful mouse test. Traditional discovery methods screen existing compound libraries or soil samples and have mostly produced variations on existing drugs since the 1980s.
Read at Fast Company
Unable to calculate read time
Collection
[
|
...
]