FEBRUARY 23, 2020
It could unleash a new method for finding must-have medication. – DNY59 – Getty Images
- A chemistry-combing algorithm uncovered a promising new antibiotic molecule called halicin.
- Researchers have spent tons of time and money searching for something to replace traditional antibiotics.
- Halicin worked well against three major resistant disease pathogens, including C. diff.
Researchers at MIT have used brute-force computer power and artificial intelligence to identify a potentially game-changing new antibiotic medication. Using machine learning to comb through millions of options can help scientists think outside the box both chemically and financially.
This idea has floated in the public imagination for a while—that a computer algorithm could pick out which medications work against which pathogens. But just recently, scientists have finally developed neural networks that can fully contextualize what molecules do and don’t work against.
“In this case, the researchers designed their model to look for chemical features that make molecules effective at killing E. coli,” MIT wrote in a statement. “To do so, they trained the model on about 2,500 molecules, including about 1,700 FDA-approved drugs and a set of 800 natural products with diverse structures and a wide range of bioactivities.”
That means the algorithm identified all the chemical features that marked effective E. coli killers, including some that are counterintuitive to human brains accustomed to thinking in specific contexts or patterns. After that, the scientists turned their algorithm loose in a database of 6,000 known and named chemical compounds.
What the algorithm shook loose is a molecule the researchers named halicin. The researchers say it was previously investigated to treat diabetes, but in their tests, it showed immediate success across a variety of bacteria and pathogens. It’s also relatively nontoxic to human cells. (Many medicines are at least a little bit damaging, unfortunately.)
Halicin works by disrupting the cellular equilibrium that helps to physically hold cells together, meaning it kind of dissolves bacteria from the outside by disabling their ability to preserve this electromagnetic equilibrium. This is different than how traditional antibiotics work, which is by physically destroying the cells—researchers say this small-seeming difference in mechanism is likely why the new molecule can kill bacteria that other antibiotics cannot.
In the lab, the research subjected halicin to dozens of bacterial strains, including a few that are notoriously resistant to antibiotics: Clostridium difficile, Acinetobacter baumannii, and Mycobacterium tuberculosis. Respectively, these are C. diff, a virulent bacterial infection made famous by comedian Tig Notaro’s battle with it; a tenacious, colonizing bacterial family that killed 700 people in 2017; and one of the oldest diseases in the world, regular old tuberculosis, aka “consumption.”
Halicin worked on all three of these in petri dish-type testing, and in fact killed all the species they tested except one difficult lung pathogen. Then they moved on to mice. “To test halicin’s effectiveness in living animals, the researchers used it to treat mice infected with A. baumannii, a bacterium that has infected many U.S. soldiers stationed in Iraq and Afghanistan. The strain of A. baumannii that they used is resistant to all known antibiotics, but application of a halicin-containing ointment completely cleared the infections within 24 hours,” MIT says in their statement.
In addition to their ongoing studies of halicin, the team used the AI-discovered model to uncover 23 other candidate molecules that could have antibiotic abilities as well.
Courtesy/Source: Popular Mechanics
