A biotech company sold over 500,000 AI-powered health testing kits. Two C-suite leaders share how they kept science at the center.
This article is part of " Build IT: Connectivity," a series about tech powering better business.
Viome is aiming to transform disease detection, starting with the gut.
The Washington-based biotech startup offers at-home testing kits that analyze saliva, stool, and blood samples. Using RNA analysis, scientists at Viome can evaluate how genes and gut microbes are behaving in real time.
Once the tests are done, AI is applied to the results to generate personalized food and supplement recommendations. Users might be told to avoid spinach to reduce inflammation or take specific probiotics to support digestion and immunity.
So far, the company said it has sold more than half a million testing kits. Backed by Salesforce CEO Marc Benioff and venture capital firm Khosla Ventures, Viome is now scaling its tools to detect early signs of disease, including oral and throat cancer.
As Viome expands, the stakes are high. Grand View Research found that the global home care testing market is projected to grow more than 9% annually through 2030. As more consumers turn to medical testing kits for early disease detection and preventive care, the risks of misdiagnosis or ineffective treatment may surge if the tools aren't built with precision.
To ensure its technology is both scientifically accurate and commercially viable, Viome relies on tight, ongoing collaboration between its research, engineering, and product teams.
In a roundtable interview, Business Insider spoke with Momo Vuyisich, Viome's chief science officer, and Guru Banavar, the company's chief technology officer, to discuss how the science and technology teams work together to deliver products that are ready for market.
The following has been edited for length and clarity.
Business Insider: Viome offers a range of products, including microbiome kits and early-stage cancer detectors. How do your science and tech teams work together to keep the AI models accurate, safe, and compliant?
Momo Vuyisich: It's not just collaboration between science and tech — it's a companywide effort. On the science side, we focus on three areas: lab work, data analysis, and clinical research.
Whenever we're working on a health product, we rely on clinical research to guide development. This includes observational studies, where we learn from large groups of people, and interventional trials, where we test whether a tool works in real-world settings. For diagnostics, that means formal device trials.
In the lab, we use a method called metatranscriptomics, measuring RNA to understand what's happening in the body right now. Unlike DNA, which stays the same, RNA changes based on things like diet or environmental exposure. That allows us to detect early signs of disease like inflammation or even cancer, based on how genes are being expressed.
We measure gene activity across human cells, bacteria, and fungi, and we also identify the types of microbes present in a sample.
Guru Banavar: What makes our approach powerful is the scale and detail of the data we collect. Each customer sends us stool, blood, and saliva samples, which we use to generate tens of millions of data points showing what's happening in their gut, blood, and mouth.
Once that data hits Viome's cloud platform, my team steps in. We use AI to figure out not just what organisms are present, but what they're doing, like whether they're producing anti-inflammatory compounds or if certain biological systems are out of balance.
We work with molecular data, which is far more complex than the text data most AI tools are trained on. So we use a range of machine learning methods, such as generative AI and algorithms that learn from labeled examples and draw insights based on patterns, where it's appropriate. The key is using the right tool for the right problem, whether we're detecting disease, recommending foods, or flagging health risks.
And because this work spans many fields, our team includes experts in biology, computing, cloud engineering, and more. Today, everything runs in the cloud, which allows us to operate at scale.
Vuyisich: From the very beginning, we made clinical research a core part of how we operate. We didn't just start building products. We started by measuring biological markers that were already published to impact human health, especially those linked to micronutrients. That was our foundation.
One of our earliest major studies was on glycemic response, how people's blood sugar changes after eating. We spent millions of dollars running large-scale studies in the US and Japan, and we used that data to build machine learning models that predicted how a person would respond to certain foods. Afterward, we validated those models before we integrated them into our app.
We've followed that same process for everything from food and nutrition recommendations to our diagnostic test for cancer. We learn from both customer data and formal research, but the bottom line is we validate before we implement.
Banavar: On the tech side, we've built systems that help us move quickly while still being careful. We've automated a lot of the heavy lifting — like processing biological data and generating recommendations — so we're not starting from scratch every time. When a new cohort of users joins Viome, we often retrain our models to reflect new biological data and ensure relevance. Some parts of that process are automated, but the final checks and tuning are still done by hand to make sure the model meets our standards before it goes live.
Another important piece is user education. Our app is designed to let people engage however they want, whether they're just looking for simple guidance or want to dive deep into science. It's an important part of making sure our customer base understands and can follow our recommendations.
Have you ever had to resolve conflicts between business priorities and scientific standards?
Banavar: Yes, and it's natural in a multidisciplinary environment. We all come from different backgrounds. Biologists and machine learning engineers often describe the same process in totally different ways. Momo comes from the molecular side, I come from the computational side. Sometimes we talk past each other, meaning we miss things we say to one another that go beyond our domains of expertise. That's why ongoing communication is so important.
There's also the tension between speed and robustness. For example, when we're building a new feature in the app, I'm OK launching a minimum viable product, MVP for short, which is a working prototype with basic functionality. But when it comes to health models, we won't release them until we've validated the science. If it takes two more weeks to fine-tune, so be it. We'll put a message in the app saying that a specific score, or a health indicator based on a user's test results, is still being worked on — and that's fine with me.
Vuyisich: It all comes down to defining what the MVP is. If it provides enough value for someone to pay for it and feel good about it, that's the threshold. But an MVP for a toy can be rough and basic. An MVP for a cancer diagnostic needs to be very mature.
We don't have a dynamic where business tells science what to do. We sit at the same table and make decisions together. If the science can't hit the original target, we reassess. Can we lower the bar slightly and still provide value? If the answer is yes, we'll launch.
The worst-case scenario is launching something that isn't ready, but even that teaches you something. If no one buys it, you've learned a lot. Sometimes your friends and family say it's amazing, but no one pays for it. That's a signal.
But an even worse scenario is waiting too long for perfection. That's buried more companies than anything else. If Apple had waited until the iPhone had all the features of iPhone 16, it would've gone out of business. Instead, they launched the first iPhone. They could be embarrassed today about how poor it was. But it worked. People paid for it. That's what matters: bring it to market.
What lessons have you learned from building and scaling Viome that could help other companies trying to bring AI health products to market responsibly?
Banavar: First, there is no substitute for generating robust scientific data to support the value of health products. Second, when applying AI to health products, focus on areas and methods that can be independently validated and, ideally, interpretable, where companies can explain how the AI models reached their results to scientists, clinicians, and users. Finally, it's possible, even in the health domain, to build products with an MVP mindset and implement a process for continuous improvement.
Vuyisich: Deeply understand the problem you're trying to solve and identify a robust solution. At Viome, we set out to find the root causes of chronic diseases and cancer, which required measuring tens of thousands of human biomarkers relevant to health.
Also, use a method that's accurate, affordable, and scalable. We spent over six years optimizing one lab test — metatranscriptomics — to go beyond the gold standard. This one test gives us thousands of biomarkers across multiple sample types with high accuracy.
Finally, it's all about the people. Build a leadership team that deeply understands business and science, is aligned with the mission, and puts the company ahead of personal interests. Hire motivated, self-managed employees, train them well, and continuously coach them.
Try Our AI Features
Explore what Daily8 AI can do for you:
Comments
No comments yet...
Related Articles
Yahoo
an hour ago
- Yahoo
Satellites are polluting Earth's atmosphere with heavy metals. Could refueling them in orbit help?
When you buy through links on our articles, Future and its syndication partners may earn a commission. The world at large is working to stop the fast-progressing degradation of Earth's environment. In the space sector, however, one-use-only products still reign supreme. The advent of megaconstellations has, in fact, accelerated the rate at which the space industry burns through resources, shifting from big satellites with decades-long lifespans to cheaper birds designed to expire within a few short years. The disposable approach worries some researchers, as too much aluminum is burning up in the atmosphere these days, threatening to cause a new kind of environmental disaster in the decades to come. But what can we do? Should we roll back the space revolution and put a cap on what we can do in space? Or could a circular economy, life extension, recycling and reuse be the solution to the space industry's dirty side effects? Proponents of in-orbit servicing and refueling laud the technology's potential. But most analysts remain cautious: Without strict environmental regulations, the expected cost of in-orbit servicing may not entice satellite operators to switch to reusable technology en masse. Dave Barnhart, chief executive officer of the California-based aerospace company Arkisys, first began developing concepts of recyclable satellite technology some 15 years ago as part of a project he oversaw at DARPA (the Defense Advanced Research Projects Agency). He and his colleagues investigated how to set up a satellite recycling facility in geostationary orbit — the region about 22,000 miles (36,000 kilometers) above Earth's surface where satellites appear fixed above one spot above the equator. "We wanted to know whether we can use parts from old geo satellites to recreate new ones, because the mass is already there," Barnhart told The geostationary ring is home to some of the largest and most expensive satellites. On top of that, the long distance between Earth and this orbit makes geo missions inherently costly, as they require the most powerful rockets with a lot of fuel to reach their destination. Yet, Arkisys, the company Barnhart cofounded in 2015, is focusing on low Earth orbit (LEO) — the buzzing region closest to Earth up to altitudes of about 1,200 miles (2,000 km). Arkisyshopes to set up an in-orbit servicing and refueling depot called the Port in LEO. The main goal is to spearhead a green revolution in this region, which gives rise to thousands of tons of dangerous space debris every year. "To date, everything we have ever designed to go into space has been one mission, one life," Barnhart told "It's sort of crazy. Every other domain on Earth, we maintain, we sustain, we grow. Not in space." In 2023, Arkisys secured a $1.6 million deal from the U.S. Space Force to test satellite assembly in orbit using the Port demo module — a basic building block of a scalable orbiting garage and gas station. The company wants to launch the first component of this orbital depot next year — a last-mile transportation device called the Cutter, which is designed to help satellites to dock with the garage. In 2027, the main Port module, a hexagonal structure about 9 feet (3 meters) wide, will join the Cutter in orbit to test how the mechanical interfaces of the two work together in space. The Port, in addition to serving as a fuel depot, will arrive with a supply of components and payloads that could be attached to worn-out satellites to give them a new lease on life. "Today, everything on a satellite is done on the ground, and the satellite is launched with an end date," Barnhart said. "We want to shift that to allow extensions of both — life and business — post-launch. We want to be able to add new revenue streams post-launch. You can do that if you can add something, change something in orbit, or even sell that satellite to somebody else who could make it part of a larger platform." Cameras or antennas could be replaced with more powerful ones once those get developed, worn-out batteries could be swapped for brand-new ones, and fuel tanks would get refilled. It all makes sense on paper, but Dafni Christodoulopoulou, space industry analyst at the consultancy company Analysis Mason, warns that whether satellite operators would be inclined to ditch their disposable ways will come down to the cost of the in-orbit maintenance services. LEO is currently dominated by small, relatively cheap satellites, she says, which can be replaced more cheaply than they can be serviced and maintained. "Right now, we expect in-orbit services to come at a cost that might be quite high for operators of small satellites," Christodoulopoulou told "The operators might not be interested in those services, because the price of building a new satellite might not be higher than that of a servicing mission." Barnhart agrees that the fledgling in-orbit servicing industry is likely to face resistance not just from operators but also from satellite manufacturers, who might feel threatened by the idea of reusability and life extension. "Every time you want to make a big shift like this, it's going to be a threat," Barnhart said. "Satellite manufacturers make money by building more satellites to throw away. It might take some time for them to see that by fitting satellites with interfaces that allow them to be serviced, they could actually add some cool functionality to them after launch." Related stories: — Kessler Syndrome and the space debris problem — Pollution from rocket launches and burning satellites could cause the next environmental emergency — 2 private satellites undock after pioneering life-extension mission Still, Christodoulopoulou thinks that in-orbit servicing will eventually make a difference to how things are done in space, and also to the state of the orbital environment. "The number of satellite launches is not expected to go down, so there will be a high need for constellation management, flexibility, disposal and life extension," she said. "I think in-orbit services can definitely help prevent the buildup of space debris and maintain long-term sustainability in orbit." The U.S. government certainly appears to think that life extension is the way forward. In addition to funding the Arkisys experiment, the Space Force also funds the Tetra-5 and Tetra-6 missions to test in-orbit refueling technologies in space. The two missions, designed to test hardware developed by Orbit Fab, Astroscale and Northrop Grumman, are set to launch in 2026 and 2027, respectively. In addition, intensifying geopolitical tensions are increasing the need for quick deployment of new systems in space, which, Barnhart says, could be more speedily addressed with servicing systems such as the Port, than by building new spacecraft from scratch on Earth. "If there is a new threat that has been identified, you might need a new type of sensor or a new payload to observe it," Barnhart said. "If we can augment the satellites that the government has already put up and provide them with a new capability, a new sensor, we can address those threats much faster." Christodoulopoulou thinks that new regulations designed to protect the environment and curb the air pollution related to satellite reentries could further help move the needle toward a less throwaway culture in space utilization. "There need to be a few changes," Christodoulopoulou said. "There needs to be more awareness among satellite operators to understand that in-orbit servicing offers a value in the long term. But also on the government side, there need to be more regulations to support the in-orbit servicing providers."
Yahoo
an hour ago
- Yahoo
University of Utah students win NASA Lunobotics grand prize
A team of over 30 students from the University of Utah took home the prestigious grand prize from the NASA Lunobotics competition thanks to their robot. Their design won multiple awards and cemented many of the students' love of STEM, space and collaboration. The team was comprised of students from the Utah Students Robotics club. To compete, the team had to apply for the competition. Out of 70 universities, the team was selected to be one of the 30 official competitors based on their project management plan. The competition was held at the University of Central Florida May 15-17. Over the course of a year, the students prepared for the competition. Early on in the process, the students received a rubric and competition layout for what to expect. The teams then began working on the systems engineering paper, presentation demonstration and, most importantly, the robot itself. 'You are building a robot to compete in a simulated lunar environment,' explained Jeffrey Hansen, a University of Utah chemical and computer engineering student. 'The goal is to navigate through an obstacle zone and then do digging and dumping to build a berm.' Judges look at numerous factors, including the size of the berm compared to the size and energy usage and the different amounts of autonomous operations. Those areas all contributed to the four main areas of scoring: the systems engineering paper, the outreach paper, the presentation demonstration and the construction competition. After competing at Florida, the top 10 teams are chosen to go to the Kennedy Space Center and compete for the grand prize. The Utah-based team split into three different subteams, including mechanical, electrical and software teams. Supporting teams also included an admin and systems team. Frequent meetings, collaborations and trial and error were a must for the students. Hansen called their work an 'evolutionary design style.' 'We had a systems engineering approach. We did it a bit differently than we had done in the past,' Hansen elaborated. 'We decided to start with building a version of the robot that met the basic competition requirements. … Once we had that, we went through different versions to improve upon that design.' Working with 30 students was no small feat. With so many minds hard at work, it was sometimes difficult to find the direction the team wanted to take. Additionally, the challenge was extremely open-ended. As long as the robot was under the specified maximum weight and dimensions, the robot could do anything. Digging systems, electronics, batteries and microcontrollers could all be chosen by the students. Another key piece of the journey was the collaboration with the U. The students worked with the administration to build a lunar simulation to test the robot. The chance to practice before the competition was everything for the team. 'We didn't have (the simulation) done until close to the end of the year, but even that little bit of time helped,' Hansen said. 'It was quite a big process to get that approved.' When they brought their robot to the competition, the team knew they had something special. After taking home the first place in presentation and demonstration, first place in STEM engagement and outreach, second place in construction, special recognition for exceptional use of systems engineering tools and various judges' awards, the team thought they may have a chance to compete in the top 10. Their suspicions were correct. The team ecstatically welcomed the invitation to present their robot at the finals. After an excellent demonstration, the team was awarded the Artemis Award, or grand prize. 'The team just erupted in energy when we found out we won. It felt like we had accomplished everything we went there to do,' Hansen said. 'It was very emotional. It was so much work across a lot of time with so many people. It felt incredible to have all that work come together and walk on stage knowing we had done it.' The experience has helped to shape the students' futures. 'It's been absolutely incredible for getting hands-on experience. … There are real-world applications of participating in this team that I would've never experienced in any of my classes,' Hansen said. To supplement their work, the students also traveled around to numerous K-12 schools around Utah. Their presentations aimed to inspire the future generation of students to try new things, specifically in the STEM field. 'It's how we keep improving the world. It's how we've gotten to where we are today,' Hansen said. 'It's the most important thing out there.'
Yahoo
an hour ago
- Yahoo
AI is changing the tech job market, and Gen Z is struggling to keep up
This post originally appeared in the BI Tech Memo newsletter. Sign up for the weekly BI Tech Memo newsletter here. As my daughter can attest, it's a tough job market out there. She's a mechanical engineer, which seems steady demand-wise. But many of her college friends are struggling to find that crucial entry-level job or internship. Some are wondering if computer science and similar courses were the right decision, with AI automating software tasks at companies. Just look at what's happening at Amazon. CEO Andy Jassy said this week that his corporate workforce will shrink over the next few years as the company uses more generative AI tools and agents. Not so coincidentally, Business Insider just spent weeks interviewing Gen Z tech job seekers as AI transforms early-career experiences across the industry. Our findings are a must-read for anyone looking to break in here and find success. Jonathan, a 26-year-old software engineer, is emblematic of what we discovered. (He's not authorized to speak to the media, so we removed his last name.) After earning his degree in 2022, he sent out nearly 300 applications and got 12 responses. It took three months to land a full-time tech role. Less than a year later, he lost that job due to his employer shutting an office. Then, he found himself repeating the process, this time applying to 600 jobs and hearing back from only five. "Everyone tells you to get into computer science. That's where all the money is at, that's where the jobs are at," Jonathan told BI. "It's a lot harder than they make it out to be." He's not alone. Recent computer science grads face a 6.1% unemployment rate in the US, higher than the national average. Wow. I never thought I'd see a stat like that. Jonathan now works in defense tech, not the video game industry he originally aspired to join. Like many of his peers, he's focused on gaining experience — any experience. It's looking like a tech career is evolving from a sure thing into something similar to every other type of job: You have to hustle and network to get your foot in the door, and then work like hell to stay employed and build steadily from there. What else should you do as an aspiring tech worker? Our Gen Z survey story doesn't have all the answers, but there's great advice in here. Read the original article on Business Insider
