Alexander Fleming first discovered penicillin in 1928. Although his work was based on the efforts of several researchers who came before him, he ultimately was awarded the Nobel Prize in medicine. At his acceptance speech, he warned that bacteria one day might adapt to penicillin and render it less useful, and that’s exactly what has happened. Today, there are many drug resistant bacteria that shrug off the palliative effect of penicillin and many other antibiotics that have been widely prescribed by doctors, often with the encouragement of drug companies.
Creating new drugs is a painstaking process that can be agonizingly slow. It can take years or sometimes decades to develop new drugs, which is one reason drug prices are often extremely high. Someone has to pay for all the laboratories and technicians carrying out research on new drugs for year after year. Many times, clinicians don’t even know if the drugs they are working on are effective until they are far along in their research.
Artificial intelligence may help reduce the time it takes to discover new drugs dramatically. Researchers at MIT say that using an AI algorithm, they have identified a new antibiotic that kills many drug resistant bacteria, according to a report by Science Daily. It also proved effective in two trials involving infected mice.
What makes this discovery all the more remarkable is that a computer was able to accomplish the task in only three days. The algorithm is designed to identify potential antibiotics that kill bacteria using different mechanisms that the ones utilized by existing drugs, according to MIT News.
“We wanted to develop a platform that would allow us to harness the power of artificial intelligence to usher in a new age of antibiotic drug discovery,” says James Collins, a professor of medical engineering and science. “Our approach revealed this amazing molecule which is arguably one of the more powerful antibiotics that has been discovered.”
“We’re facing a growing crisis around antibiotic resistance, and this situation is being generated by both an increasing number of pathogens becoming resistant to existing antibiotics, and an anemic pipeline in the biotech and pharmaceutical industries for new antibiotics,” Collins says.
The algorithm also identified several other potential antibiotics that will now undergo further testing. “The machine learning model can explore…..large chemical spaces that can be prohibitively expensive for traditional experimental approaches,” says Regina Barzilay, a professor of electrical engineering and computer science at MIT.
Until now, computer modeling was too inaccurate to yield useful results, but the latest neural networks can learn how to express potential antibiotics in computer terms automatically. The researchers designed their new model to look for chemical features that make molecules effective at killing E. coli bacteria. 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 bio-activities.
Once the model was trained, the researchers tested it on about 6,000 compounds. The model picked out one molecule that was predicted to have strong antibacterial activity and had a chemical structure different from any existing antibiotics. That molecule has been called halicine, a name derived from HAL, the computer featured in Stanley Kubrick’s movie 2001: A Space Odyssey.
[Extraneous side note #1: the first iPhone design was inspired by the black monolith shown in the opening sequence to that movie. Extraneous side note #2: it is believed Kubrick chose HAL because the letters all precede the initials IBM, which was the name of the dominant computer company in the world at the time of the movie. You’re welcome.]
The researchers tested it against dozens of bacterial strains isolated from patients and grown in lab dishes and found that it was able to kill many that are resistant to treatment, including Clostridium difficile, Acinetobacter baumannii, and Mycobacterium tuberculosis. The drug worked against every species that they tested, with the exception of Pseudomonas aeruginosa, a difficult-to-treat lung pathogen.
MIT News adds that halicin may kill bacteria by disrupting their ability to produce ATP, a molecule that cells use to store energy. The researchers think cells will have difficulty adapting to such a disruptive process. “When you’re dealing with a molecule that likely associates with membrane components, a cell can’t necessarily acquire a single mutation or a couple of mutations to change the chemistry of the outer membrane. Mutations like that tend to be far more complex to acquire evolutionarily,” Stokes says.
After identifying halicin, the researchers used their model to screen more than 100 million molecules selected from the ZINC15 database, an online collection of about 1.5 billion chemical compounds. This screen, which took only three days, identified 23 candidates that were structurally dissimilar from existing antibiotics and predicted to be nontoxic to human cells.
In laboratory tests against five species of bacteria, the researchers found that eight of the molecules showed antibacterial activity, and two were particularly powerful. The researchers now plan to test these molecules further, and also to screen more of the ZINC15 database.
The researchers also plan to use their model to design new antibiotics and to optimize existing molecules. For example, they could train the model to add features that would make a particular antibiotic target only certain bacteria, preventing it from killing beneficial bacteria in a patient’s digestive tract.
So scientists today can do in three days what normally takes months, years, or even decades to accomplish. Just imagine if that kind of research power could be applied to the search for antidotes to an overheating planet!
Have a tip for CleanTechnica? Want to advertise? Want to suggest a guest for our CleanTech Talk podcast? Contact us here.
CleanTechnica Holiday Wish Book
Our Latest EVObsession Video
CleanTechnica uses affiliate links. See our policy here.