AI produces powerful new antibiotic
Artificial intelligence behind breakthrough in new drug discovery.
A powerful new antibiotic called Halicin has been developed using computer technology that analyses vast digital libraries of pharmaceutical compounds, reports The Guardian.
The breakthrough came when researchers at Massachusetts Institute of Technology (MIT) developed a “deep learning” algorithm to identify molecules that kill bacteria by feeding information on the atomic and molecular features of nearly 2500 drugs and natural compounds, and how well or not the substance blocked the growth of the bug E coli.
They then applied it to a library of more than 6000 compounds under investigation for treating various human diseases. The algorithm focused on compounds that looked effective but were unlike existing antibiotics, to boost the chances that the drugs would work in radical new ways.
Researchers say it only took hours for the algorithm to assess the compounds and come up with promising antibiotics including Halicin.
Tests showed that Halicin wiped out a range of antibiotic-resistant strains of bacteria, including Acinetobacter baumannii and Enterobacteriaceae, two of the three high-priority pathogens that the World Health Organization ranks as “critical” for new antibiotics to target.
“In terms of antibiotic discovery, this is absolutely a first,” said Regina Barzilay, a senior researcher on the project and specialist in machine learning at MIT.
The researchers have since applied the algorithm to a massive digital database of 107 million compounds. The program returned a shortlist of 23 potential antibiotics, of which two appear to be particularly potent.