Peanuts on a plate can be deadly for those with severe allergies, but an Israeli startup company wants to alleviate that fear.
People with life-threatening allergies live in constant fear of coming into contact with deadly allergens. Researchers estimate that about 32 million Americans have food allergies, with the most severe being milk, egg, peanut, tree nuts, wheat, soy, fish, and shellfish.
"It is important to understand that just several years ago, this would not have been possible."
Every three minutes, a food allergy reaction sends someone to the emergency room, and 200,000 people in the U.S. require emergency medical care each year for allergic reactions, according to Food Allergy Research and Education.
But what if there was a way you could easily detect if something you were about to eat contains any harmful allergens? Thanks to Israeli scientists, this will soon be the case — at least for peanuts. The team has been working to develop a handheld device called Allerguard, which analyzes the vapors in your meal and can detect allergens in 30 seconds.
Leapsmag spoke with the founder and CTO of Allerguard, Guy Ayal, about the groundbreaking technology, how it works, and when it will be available to purchase.
What prompted you to create this device? Do you have a personal connection with severe food allergies?
Guy Ayal: My eldest daughter's best friend suffers from a severe food allergy, and I experienced first-hand the effect it has on the person and their immediate surroundings. Most notable for me was the effect on the quality of life – the experience of living in constant fear. Everything we do at Allerguard is basically to alleviate some of that fear.
How exactly does the device work?
The device is built on two main pillars. The first is the nano-chemical stage, in which we developed specially attuned nanoparticles that selectively adhere only to the specific molecules that we are looking for. Those molecules, once bound to the nanoparticles, induce a change in their electrical behavior, which is measured and analyzed by the second main pillar -- highly advanced machine learning algorithms, which can surmise which molecules were collected, and thus whether or not peanuts (or in the future, other allergens) were detected.
It is important to understand that just several years ago, this would not have been possible, because both the nano-chemistry, and especially the entire world of machine learning, big data, and what is commonly known as AI only started to exist in the '90s, and reached applicability for handheld devices only in the past few years.
Where are you at in the development process and when will the device be available to consumers?
We have concluded the proof of concept and proof of capability phase, when we demonstrated successful detection of the minimal known clinical amount that may cause the slightest effect in the most severely allergic person – less than 1 mg of peanut (actually it is 0.7 mg). Over the next 18 months will be productization, qualification, and validation of our device, which should be ready to market in the latter half of 2021. The sensor will be available in the U.S., and after a year in Europe and Canada.
The Allerguard was made possible through recent advances in machine learning, big data, and AI.
(Courtesy)
How much will it cost?
Our target price is about $200 for the device, with a disposable SenseCard that will run for at least a full day and cost about $1. That card is for a specific allergen and will work for multiple scans in a day, not just one time.
[At a later stage, the company will have sensors for other allergens like tree nuts, eggs, and milk, and they'll develop a multi-SenseCard that works for a few allergens at once.]
Are there any other devices on the market that do something similar to Allerguard?
No other devices are even close to supplying the level of service that we promise. All known methods for allergen detection rely on sampling of the food, which is a viable solution for homogenous foodstuffs, such as a factory testing their raw ingredients, but not for something as heterogenous as an actual dish – especially not for solid allergens such as peanuts, treenuts, or sesame.
If there is a single peanut in your plate, and you sample from anywhere on that plate which is not where that peanut is located, you will find that your sample is perfectly clean – because it is. But the dish is not. That dish is a death trap for an allergic person. Allerguard is the only suggested solution that could indeed detect that peanut, no matter where in that plate it is hiding.
Anything else readers should know?
Our first-generation product will be for peanuts only. You have to understand, we are still a start-up company, and if we don't concentrate our limited resources to one specific goal, we will not be able to achieve anything at all. Once we are ready to market our first device, the peanut detector, we will be able to start the R&D for the 2nd product, which will be for another allergen – most likely tree nuts and/or sesame, but that will probably be in debate until we actually start it.
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.
