A bioengineer at the University of California, Riverside, may have found a way to prevent counterfeit medications: pill coatings inspired by the sprinkles on baked goods and candies.
The idea was borne out of pandemic boredom. Confined to his home, Grover was struck by the patterns of nonpareils he saw on candies, and found himself counting the number of little balls on each one. “It’s random, how they’re applied,” he says. “I wondered if it ever repeats itself or if each of these candies is unique in the entire world.” He suspected the latter, and some quick math proved his hypothesis: Given dozens of nonpareils per candy in a handful of different colors, it’s highly unlikely that the sprinklings on any two candies would be identical.
He quickly realized his finding could have practical applications: pills or capsules could be coated with similar “sprinkles,” with the manufacturer photographing each pill or capsule before selling its products. Consumers looking to weed out fakes could potentially take a photo with their cell phones and go online to compare images of their own pills to the manufacturer’s database, with the help of an algorithm that would determine their authenticity. Or, a computer could generate another type of unique identifier, such as a text-based code, tracking to the color and location of the sprinkles. This would allow for a speedier validation than a photo-based comparison, Grover says. “It could be done very quickly, in a fraction of a second.”
Researchers and manufacturers have already developed some anti-counterfeit tools, including built-in identifiers like edible papers with scannable QR codes. But such methods, while functional, can be costly to implement, Grover says.
It wouldn’t be paranoid to take such precautions. Counterfeits are a growing problem, according to Young Kim, a biomedical engineer at Purdue University who was not involved in the CandyCodes study. “There are approximately 40,000 online pharmacies that one can access via the Internet,” he says. “Only three to four percent of them are operated legally.” Purchases from online pharmacies rose dramatically during the pandemic, and Kim expects a boom in counterfeit medical products alongside it.
The FDA warns that U.S. consumers can be exposed to counterfeits through online purchases, in particular. The problem is magnified in low- to middle-income nations, where one in 10 medical products are counterfeit, according to a World Health Organization estimate. Cost doesn’t seem to be a factor, either; antimalarials and antibiotics are most often reported as counterfeits or fakes, and generic medications are swapped as often as brand-name drugs, according to the same WHO report.
Counterfeits weren’t tracked globally until 2013; since then, there have been 1,500 reports to the WHO, with actual incidences of counterfeiting likely much higher. Fake medicines have been estimated to result in costs of $200 billion each year, and are blamed for more than 72,000 pneumonia- and 116,000 malaria-related deaths.
Researchers and manufacturers have already developed some anti-counterfeit tools, including built-in identifiers like edible papers with scannable QR codes or barcodes that are stamped onto or otherwise incorporated into pills and other medical products. But such methods, while functional, can be costly to implement, Grover says.
CandyCodes could provide unique identifiers for at least 41 million pills for every person on the planet.
William Grover
“Putting universal codes on each pill and each dosage is attractive,” he says. “The challenge is, how can we do it in a way that requires as little modification to the existing manufacturing process as possible? That's where I hope CandyCodes have an edge. It's not zero modification, but I hope it is as minor a modification of the manufacturing process as possible.”
Kim calls the concept “a clever idea to introduce entropy for high-level security” even if it may not be as close to market as other emerging technologies, including some edible watermarks he’s helped develop. He points out that CandyCodes still needs to be tested for reproducibility and readability.
The possibilities are already intriguing, though. Grover’s recent research, published in Scientific Reports, predicts that unique codes could be used for at least 41 million pills for every person on the planet.
Sadly, CandyCodes’ multicolored bits probably won’t taste like candy. They must be made of non-caloric ingredients to meet the international regulatory standards that govern food dyes and colorants. But Grover hopes CandyCodes represent a simple, accessible solution to a heart-wrenching issue. “This feels like trying to track down and go after bad guys,” he says. “Someone who would pass off a medicine intended for a child or a sick person and pass it off as something effective, I can't imagine anything much more evil than that. It's fun and, and a little fulfilling to try to develop technologies that chip away at that.”
AI was integral to creating Moderna's mRNA vaccine against COVID.
But the truth is that before ChatGPT nabbed the public’s attention, AI was already here, and it was doing more important things than writing essays for lazy college students. Case in point: It was key to saving the lives of tens of millions of people.
AI-designed mRNA vaccines
As Dave Johnson, chief data and AI officer at Moderna, told MIT Technology Review‘s In Machines We Trust podcast in 2022, AI was integral to creating the company’s highly effective mRNA vaccine against COVID. Moderna and Pfizer/BioNTech’s mRNA vaccines collectively saved between 15 and 20 million lives, according to one estimate from 2022.
Johnson described how AI was hard at work at Moderna, well before COVID arose to infect billions. The pharmaceutical company focuses on finding mRNA therapies to fight off infectious disease, treat cancer, or thwart genetic illness, among other medical applications. Messenger RNA molecules are essentially molecular instructions for cells that tell them how to create specific proteins, which do everything from fighting infection, to catalyzing reactions, to relaying cellular messages.
Johnson and his team put AI and automated robots to work making lots of different mRNAs for scientists to experiment with. Moderna quickly went from making about 30 per month to more than one thousand. They then created AI algorithms to optimize mRNA to maximize protein production in the body — more bang for the biological buck.
For Johnson and his team’s next trick, they used AI to automate science, itself. Once Moderna’s scientists have an mRNA to experiment with, they do pre-clinical tests in the lab. They then pore over reams of data to see which mRNAs could progress to the next stage: animal trials. This process is long, repetitive, and soul-sucking — ill-suited to a creative scientist but great for a mindless AI algorithm. With scientists’ input, models were made to automate this tedious process.
“We don’t think about AI in the context of replacing humans,” says Dave Johnson, chief data and AI officer at Moderna. “We always think about it in terms of this human-machine collaboration, because they’re good at different things. Humans are really good at creativity and flexibility and insight, whereas machines are really good at precision and giving the exact same result every single time and doing it at scale and speed.”
All these AI systems were in put in place over the past decade. Then COVID showed up. So when the genome sequence of the coronavirus was made public in January 2020, Moderna was off to the races pumping out and testing mRNAs that would tell cells how to manufacture the coronavirus’s spike protein so that the body’s immune system would recognize and destroy it. Within 42 days, the company had an mRNA vaccine ready to be tested in humans. It eventually went into hundreds of millions of arms.
Biotech harnesses the power of AI
Moderna is now turning its attention to other ailments that could be solved with mRNA, and the company is continuing to lean on AI. Scientists are still coming to Johnson with automation requests, which he happily obliges.
“We don’t think about AI in the context of replacing humans,” he told the Me, Myself, and AI podcast. “We always think about it in terms of this human-machine collaboration, because they’re good at different things. Humans are really good at creativity and flexibility and insight, whereas machines are really good at precision and giving the exact same result every single time and doing it at scale and speed.”
Moderna, which was founded as a “digital biotech,” is undoubtedly the poster child of AI use in mRNA vaccines. Moderna recently signed a deal with IBM to use the company’s quantum computers as well as its proprietary generative AI, MoLFormer.
Moderna’s success is encouraging other companies to follow its example. In January, BioNTech, which partnered with Pfizer to make the other highly effective mRNA vaccine against COVID, acquired the company InstaDeep for $440 million to implement its machine learning AI across its mRNA medicine platform. And in May, Chinese technology giant Baidu announced an AI tool that designs super-optimized mRNA sequences in minutes. A nearly countless number of mRNA molecules can code for the same protein, but some are more stable and result in the production of more proteins. Baidu’s AI, called “LinearDesign,” finds these mRNAs. The company licensed the tool to French pharmaceutical company Sanofi.
Writing in the journal Accounts of Chemical Research in late 2021, Sebastian M. Castillo-Hair and Georg Seelig, computer engineers who focus on synthetic biology at the University of Washington, forecast that AI machine learning models will further accelerate the biotechnology research process, putting mRNA medicine into overdrive to the benefit of all.
This article originally appeared on Big Think, home of the brightest minds and biggest ideas of all time.
