The rise of superbugs means the world needs powerful new antibiotics. A team at MIT says it has just made a major breakthrough using artificial intelligence for the first time. They discovered a compound that looks able to conquer some of the most dangerous bacteria in existence, including some that are resistant to current antibiotics. The scientists named it "halicin," after the computer HAL in 2001: A Space Odyssey. The discovery came after researchers created a machine-learning algorithm to assess volumes of data about bacteria-killing molecules. Crucially, they looked for compounds that worked but were different from existing antibiotics, notes the Guardian, thus raising the chances that the resulting drugs would fight bugs in novel ways. Essentially, the algorithm thought outside the box in looking for candidates.
"Our approach revealed this amazing molecule, which is arguably one of the more powerful antibiotics that has been discovered," says MIT's James Collins. The team identified other candidates in addition to halicin that will be the subject of further study. As STAT News notes, previous research into antibiotics involved digging into dirt—literally— and "breakthroughs were becoming as rare as new places to dig." The MIT study could be a game-changer, harnessing the power of computers to human expertise and giving researchers new places to look. "To use a crude analogy, it's like you show an AI all the different means of transportation, but you've not shown it an electric scooter," says Stanford's Nigam Shah, who was not involved in the MIT work. "And then it independently looks at an electronic scooter and says, 'Yeah, this could be useful for transportation.'" (Read more artificial intelligence stories.)