Team at MIT says halicin kills some of the world’s most dangerous strains and it could wipe out resistant bacteria strains.
Artificial intelligence is providing a breakthrough in the medical field. Researchers at MIT have used AI to discover a compound, which will be able to kill even highly resistant bacteria efficiently.
The use of AI to discover medicine appears to be paying off. MIT scientists have revealed that their AI discovered an antibiotic compound, halicin (named after 2001‘s HAL 9000), that can not only kill many forms of resistant bacteria but do so in a novel way. Where many antibiotics are slight spins on existing medicine, halicin wipes out bacteria by wrecking their ability to maintain the electrochemical gradient necessary to produce energy-storing molecules. That’s difficult for bacteria to withstand — E. coli didn’t develop any resistance in 30 days where it fought off the more conventional antibiotic cipofloxacin within three days.
The team succeeded by developing a system that can find molecular structures with desired traits (say, killing bacteria) more effectively than past systems. Unlike previous methods, the neural networks learn representations of molecules automatically, mapping them into continuous vectors that help predict their behavior. Once ready, the researchers trained their AI on 2,500 molecules that included both 1,700 established drugs and 800 natural products. When tasked with looking at a library of 6,000 compounds, the AI found that halicin would be highly effective.
However, one should wait before hailing Halicin as a wonder drug for fighting bacterial infections. While, in laboratory conditions, researchers were able to eradicate infections such as A.baumanii in mice, no human trials have been held for the molecule as yet. There is a long way to go before it can get an FDA certification. The researchers have stated in the press release that they are working to partner with pharmaceutical companies and not-for-profit institutions for facilitating human trials, although they haven’t revealed a timeline for it yet.
The researchers are also trying to replicate the success they had with Halicin and are in the process of screening 100 million molecules for potential cures. They are also working on creating antibiotics from scratch and their side effects.
Over time, many strains of bacteria develop resistance to treatments and make all existing treatments nearly ineffective. The fact that AI can help speed up drug discovery using not just permutations and combinations to find new compounds but also analyze their impact using neural networks, can significantly help speed up the process of bringing new drugs to the market to combat diseases. It cannot just save precious time, but can also help cut down on the massive costs incurred during drug development.