Can AI Discover a Vaccine for the Caronavirus?

It was wonderful news last week when MIT researchers announced they had used artificial intelligence to discover a powerful new antibiotic at a time when antibiotic-resistant diseases are proliferating.

When it comes to viral diseases, antibiotics are ineffective.  Vaccines are the weapon of choice against viral infections.

So, if the MIT wonks can use AI to unlock new antibiotics, can artificial intelligence also discover new vaccines?

It turns out the answer is yes. A team of Australian researchers did just that last summer.

For the first time ever, a human drug has been created entirely by artificial intelligence (AI). This news comes from a team at Flinders University in Australia, who claims to have created an enhanced influenza vaccine using an AI program known Search Algorithm for Ligands (SAM). Though computers have been used to make drugs before, this was the first time it was done independently by an AI system. 

The researchers described this drug as a flu vaccine with an added compound that better stimulates the human immune system. This addition causes more antibodies to be formed against the flu virus than with the traditional vaccination, increasing the vaccine’s efficacy.

Nikolai Petrovsky, of Flinders University, led the experiment. Like the MIT researchers, he described a process in which AI was unleashed to search for all possible compounds that could create an effective vaccine.

“We had to teach the AI program on a set of compounds that are known to activate the human immune system, and a set of compounds that don’t work,” he explained. “The job of the AI was then to work out for itself what distinguished a drug that worked from one that doesn’t. We then developed another program, called the synthetic chemist which generated trillions of different chemical compounds that we then fed to SAM so that it could sift through all of these to find candidates that it thought might be good human immune drugs.” Petrovsky also serves as the Research Director at Vaxine, an Australian biotechnology company.

Maybe it's time to give AI a shot at finding a response to the latest virus... and every one after that.

Judging by an article that appeared today in The Atlantic, there's a bit of urgency to this.

The disease (known as COVID-19) seems to have a fatality rate of less than 2 percent—exponentially lower than most outbreaks that make global news. The virus has raised alarm not despite that low fatality rate, but because of it.

Coronaviruses are similar to influenza viruses in that they are both single strands of RNA. Four coronaviruses commonly infect humans, causing colds. These are believed to have evolved in humans to maximize their own spread—which means sickening, but not killing, people. By contrast, the two prior novel coronavirus outbreaks—SARS (severe acute respiratory syndrome) and MERS (Middle East respiratory syndrome, named for where the first outbreak occurred)—were picked up from animals, as was H5N1. These diseases were highly fatal to humans. If there were mild or asymptomatic cases, they were extremely few. Had there been more of them, the disease would have spread widely. Ultimately, SARS and MERS each killed fewer than 1,000 people.

COVID-19 is already reported to have killed more than twice that number. With its potent mix of characteristics, this virus is unlike most that capture popular attention: It is deadly, but not too deadly. It makes people sick, but not in predictable, uniquely identifiable ways. Last week, 14 Americans tested positive on a cruise ship in Japan despite feeling fine—the new virus may be most dangerous because, it seems, it may sometimes cause no symptoms at all.

Is COVID-19 already unstoppable?

The Harvard epidemiology professor Marc Lipsitch is exacting in his diction, even for an epidemiologist. Twice in our conversation he started to say something, then paused and said, “Actually, let me start again.” So it’s striking when one of the points he wanted to get exactly right was this: “I think the likely outcome is that it will ultimately not be containable.”

Containment is the first step in responding to any outbreak. In the case of COVID-19, the possibility (however implausible) of preventing a pandemic seemed to play out in a matter of days. Starting in January, China began cordoning off progressively larger areas, radiating outward from Wuhan City and eventually encapsulating some 100 million people. People were barred from leaving home, and lectured by drones if they were caught outside. Nonetheless, the virus has now been found in 24 countries.

...Testing people who are already extremely sick is an imperfect strategy if people can spread the virus without even feeling bad enough to stay home from work.

Lipsitch predicts that, within the coming year, some 40 to 70 percent of people around the world will be infected with the virus that causes COVID-19. But, he clarifies emphatically, this does not mean that all will have severe illnesses. “It’s likely that many will have mild disease, or may be asymptomatic,” he said. As with influenza, which is often life threatening to people with chronic health conditions and of older age, most cases pass without medical care. (Overall, around 14 percent of people with influenza have no symptoms.)