Here's how artificial intelligence could cure disease in the future

When you get right down to it, developing vaccines is about data and luck. Scientists start with a set of variables—what drugs a virus responds to, how effectively, and for whom—and then it’s a whole lot of trial and error until they stumble upon a cure.

One of the most exciting possibilities in medical research right now is how technology like machine learning could help researchers rapidly process those enormous sets of data, more quickly leading to cures. This is already starting to happen: In a study published Wednesday in the journal Macromolecules, researchers from IBM and Singapore’s Institute of Bioengineering and Nanotechnology reveal a breakthrough that could help prevent deadly virus infections. With the help of IBM super computer Watson, they hope their finding will soon make its way into vaccines.

The researchers report that they have identified a macromolecule with the ability to fight viral infection, replication, and drug resistance. Viruses like Zika and Ebola are typically hard to control because rapid mutations mean it’s hard to create a vaccine to treat them before the virus evolves again. The researchers’ macromolecule, though, may have the ability to change that, by binding to healthy immune cell receptors to protect them at the same time that it makes the environment inside of the viral cell too toxic to replicate and spread. Early testing showed that Ebola, dengue, Marburg, influenza, Chikungunya, Enterovirus 71 and herpes simplex all seemed to respond to it.

In the short-term, researchers say they could use this to develop an anti-viral wipe to act as a disinfectant in rooms infected with a virus. Eventually, though, researches hope this molecule will lead to the development of new kinds of vaccines, effective against a huge swath of some of the world’s most deadly viruses. It’s promising research, but in the very early stages. This is where Watson comes in.

Over the past few years, scientists have begun experimenting with using Watson for drug discovery and clinical trial matching. Watson, for example, can help doctors more easily find clinical trials for which a patient may be eligible and ensure the right patients are chosen who are most likely to complete the trial. This may sound like a small thing, but enrolling patients in clinical trials is actually one of the most burdensome aspects of medical research. Watson can also mine millions of patent filings and journals to hunt for potential chemical compounds that could be used in creating a vaccine. The idea here is that using Watson, scientists can find the right ingredients to develop a vaccine more quickly, and then run that vaccine more quickly through clinical trials, too.

The hope is that this increased speed will help scientists create vaccines before a virus gets out of hand, spreading the way Zika virus recently has in Brazil. Using technology like Watson, perhaps one day we will be able to engineer ourselves out of huge global health epidemics that take such a great human and economic toll.