Autonomous, indoor farming gives a boost to crops
The glass-encased cabinet looks like a display meant to hold reasonably priced watches, or drugstore beauty creams shipped from France. But instead of this stagnant merchandise, each of its five shelves is overgrown with leaves — moss-soft pea sprouts, spikes of Lolla rosa lettuces, pale bok choy, dark kale, purple basil or red-veined sorrel or green wisps of dill. The glass structure isn’t a cabinet, but rather a “micro farm.”
The gadget is on display at the Richmond, Virginia headquarters of Babylon Micro-Farms, a company that aims to make indoor farming in the U.S. more accessible and sustainable. Babylon’s soilless hydroponic growing system, which feeds plants via nutrient-enriched water, allows chefs on cruise ships, cafeterias and elsewhere to provide home-grown produce to patrons, just seconds after it’s harvested. Currently, there are over 200 functioning systems, either sold or leased to customers, and more of them are on the way.
The chef-farmers choose from among 45 types of herb and leafy-greens seeds, plop them into grow trays, and a few weeks later they pick and serve. While success is predicated on at least a small amount of these humans’ care, the systems are autonomously surveilled round-the-clock from Babylon’s base of operations. And artificial intelligence is helping to run the show.
Babylon piloted the use of specialized cameras that take pictures in different spectrums to gather some less-obvious visual data about plants’ wellbeing and alert people if something seems off.
Imagine consistently perfect greens and tomatoes and strawberries, grown hyper-locally, using less water, without chemicals or environmental contaminants. This is the hefty promise of controlled environment agriculture (CEA) — basically, indoor farms that can be hydroponic, aeroponic (plant roots are suspended and fed through misting), or aquaponic (where fish play a role in fertilizing vegetables). But whether they grow 4,160 leafy-green servings per year, like one Babylon farm, or millions of servings, like some of the large, centralized facilities starting to supply supermarkets across the U.S., they seek to minimize failure as much as possible.
Babylon’s soilless hydroponic growing system
Courtesy Babylon Micro-Farms
Here, AI is starting to play a pivotal role. CEA growers use it to help “make sense of what’s happening” to the plants in their care, says Scott Lowman, vice president of applied research at the Institute for Advanced Learning and Research (IALR) in Virginia, a state that’s investing heavily in CEA companies. And although these companies say they’re not aiming for a future with zero human employees, AI is certainly poised to take a lot of human farming intervention out of the equation — for better and worse.
Most of these companies are compiling their own data sets to identify anything that might block the success of their systems. Babylon had already integrated sensor data into its farms to measure heat and humidity, the nutrient content of water, and the amount of light plants receive. Last year, they got a National Science Foundation grant that allowed them to pilot the use of specialized cameras that take pictures in different spectrums to gather some less-obvious visual data about plants’ wellbeing and alert people if something seems off. “Will this plant be healthy tomorrow? Are there things…that the human eye can't see that the plant starts expressing?” says Amandeep Ratte, the company’s head of data science. “If our system can say, Hey, this plant is unhealthy, we can reach out to [users] preemptively about what they’re doing wrong, or is there a disease at the farm?” Ratte says. The earlier the better, to avoid crop failures.
Natural light accounts for 70 percent of Greenswell Growers’ energy use on a sunny day.
Courtesy Greenswell Growers
IALR’s Lowman says that other CEA companies are developing their AI systems to account for the different crops they grow — lettuces come in all shapes and sizes, after all, and each has different growing needs than, for example, tomatoes. The ways they run their operations differs also. Babylon is unusual in its decentralized structure. But centralized growing systems with one main location have variabilities, too. AeroFarms, which recently declared bankruptcy but will continue to run its 140,000-square foot vertical operation in Danville, Virginia, is entirely enclosed and reliant on the intense violet glow of grow lights to produce microgreens.
Different companies have different data needs. What data is essential to AeroFarms isn’t quite the same as for Greenswell Growers located in Goochland County, Virginia. Raising four kinds of lettuce in a 77,000-square-foot automated hydroponic greenhouse, the vagaries of naturally available light, which accounts for 70 percent of Greenswell’s energy use on a sunny day, affect operations. Their tech needs to account for “outside weather impacts,” says president Carl Gupton. “What adjustments do we have to make inside of the greenhouse to offset what's going on outside environmentally, to give that plant optimal conditions? When it's 85 percent humidity outside, the system needs to do X, Y and Z to get the conditions that we want inside.”
AI will help identify diseases, as well as when a plant is thirsty or overly hydrated, when it needs more or less calcium, phosphorous, nitrogen.
Nevertheless, every CEA system has the same core needs — consistent yield of high quality crops to keep up year-round supply to customers. Additionally, “Everybody’s got the same set of problems,” Gupton says. Pests may come into a facility with seeds. A disease called pythium, one of the most common in CEA, can damage plant roots. “Then you have root disease pressures that can also come internally — a change in [growing] substrate can change the way the plant performs,” Gupton says.
AI will help identify diseases, as well as when a plant is thirsty or overly hydrated, when it needs more or less calcium, phosphorous, nitrogen. So, while companies amass their own hyper-specific data sets, Lowman foresees a time within the next decade “when there will be some type of [open-source] database that has the most common types of plant stress identified” that growers will be able to tap into. Such databases will “create a community and move the science forward,” says Lowman.
In fact, IALR is working on assembling images for just such a database now. On so-called “smart tables” inside an Institute lab, a team is growing greens and subjects them to various stressors. Then, they’re administering treatments while taking images of every plant every 15 minutes, says Lowman. Some experiments generate 80,000 images; the challenge lies in analyzing and annotating the vast trove of them, marking each one to reflect outcome—for example increasing the phosphate delivery and the plant’s response to it. Eventually, they’ll be fed into AI systems to help them learn.
For all the enthusiasm surrounding this technology, it’s not without downsides. Training just one AI system can emit over 250,000 pounds of carbon dioxide, according to MIT Technology Review. AI could also be used “to enhance environmental benefit for CEA and optimize [its] energy consumption,” says Rozita Dara, a computer science professor at the University of Guelph in Canada, specializing in AI and data governance, “but we first need to collect data to measure [it].”
The chef-farmers can choose from 45 types of herb and leafy-greens seeds.
Courtesy Babylon Micro-Farms
Any system connected to the Internet of Things is also vulnerable to hacking; if CEA grows to the point where “there are many of these similar farms, and you're depending on feeding a population based on those, it would be quite scary,” Dara says. And there are privacy concerns, too, in systems where imaging is happening constantly. It’s partly for this reason, says Babylon’s Ratte, that the company’s in-farm cameras all “face down into the trays, so the only thing [visible] is pictures of plants.”
Tweaks to improve AI for CEA are happening all the time. Greenswell made its first harvest in 2022 and now has annual data points they can use to start making more intelligent choices about how to feed, water, and supply light to plants, says Gupton. Ratte says he’s confident Babylon’s system can already “get our customers reliable harvests. But in terms of how far we have to go, it's a different problem,” he says. For example, if AI could detect whether the farm is mostly empty—meaning the farm’s user hasn’t planted a new crop of greens—it can alert Babylon to check “what's going on with engagement with this user?” Ratte says. “Do they need more training? Did the main person responsible for the farm quit?”
Lowman says more automation is coming, offering greater ability for systems to identify problems and mitigate them on the spot. “We still have to develop datasets that are specific, so you can have a very clear control plan, [because] artificial intelligence is only as smart as what we tell it, and in plant science, there's so much variation,” he says. He believes AI’s next level will be “looking at those first early days of plant growth: when the seed germinates, how fast it germinates, what it looks like when it germinates.” Imaging all that and pairing it with AI, “can be a really powerful tool, for sure.”
Talaris Therapeutics, Inc., a biotech company based in Louisville, Ky., is edging closer to eradicating the need for immunosuppressive drugs for kidney transplant patients.
In a series of research trials, Talaris is infusing patients with immune system stem cells from their kidney donor to create a donor-derived immune system that accepts the organ without the need for anti-rejection medications. That newly generated system does not attack other parts of the recipient’s body and also fights off infections and diseases as a healthy immune system would.
Talaris is now moving into the final clinical trial, phase III, before submitting for FDA approval. Known as Freedom-1, this trial has 17 sites open throughout the U.S., and Talaris will enroll a total of 120 kidney transplant recipients. One day after receiving their donor’s kidney, 80 people will undergo the company’s therapy, involving the donor’s stem cells and other critical cells that are processed at their facility. Forty will have a regular kidney transplant and remain on immunosuppression to provide a control group.
“The beauty of this procedure is that I don’t have to take all of the anti-rejection drugs,” says Robert Waddell, a finance professional. “I forget that I ever had any kidney issues. That’s how impactful it is.”
The procedure was pioneered decades ago by Suzanne Ildstad as a faculty member at the University of Pittsburgh before she became founding CEO of Talaris and then its Chief Scientific Officer. If approved by the FDA, the method could soon become the standard of care for patients in need of a kidney transplant.
“We are working to find a way to reprogram the immune system of transplant recipients so that it sees the donated organ as [belonging to one]self and doesn’t attack it,” explains Scott Requadt, CEO of Talaris. “That obviates the need for lifelong immunosuppression.”
Each year, there are roughly 20,000 kidney transplants, making kidneys the most transplanted organ. About 6,500 of those come from living donors, while deceased donors provide roughly 13,000.
One of the challenges, Requadt points out, is that kidney transplant recipients aren’t always aware of all the implications of immunosuppression. Typically, they will need to take about 20 anti-rejection drugs several times a day to provide immunosuppression as well as treat complications caused by the toxicities of immunosuppression medications. The side effects of chronic immunosuppression include weight gain, high blood pressure, and high cholesterol. These cardiovascular comorbidities, Requadt says, are “often more frequently the cause of death than failure of a transplanted organ.”
Patients who are chronically immunosuppressed generally have much higher rates of infections and cancers that have an immune component to them, such as skin cancers.
For the past couple of years, those patients have experienced heightened anxiety because of the COVID-19 pandemic. Immune-suppressing medicine used to protect their new organ also makes it hard for patients to build immunity to foreign invaders like COVID-19.
A study appearing in the Proceedings of the National Academy of Sciences found the probability of a pandemic with similar impact to COVID-19 is about 2 percent in any year, and estimated that the probability of novel disease outbreaks will grow three-fold in the next few decades. All the more reason to identify an FDA-approved alternative to harsh immunosuppressive drugs.
Of the 18 patients during the phase II research trial who received the Talaris therapy, didn’t take immunosuppression medication and were vaccinated, only two ended up with a COVID infection, according to a review of the data. Among patients who needed to continue taking immunosuppressants or those who didn’t have them but were unvaccinated, the rates of infection were between 40 and 60 percent.
In the earlier phase II study by Talaris with 37 patients, the combined transplantation approach allowed 70 percent of patients to get off all immunosuppression.
“We’ve followed that whole cohort for more than six and a half years and one of them for 12 years from transplant, and every single patient that we got off immunosuppression has been able to stay off,” Requadt says.
That one patient, Robert Waddell, 55, was especially thankful to be weaned off immunosuppressive drugs approximately one year after his transplant procedure. The Louisville resident had long watched his mother, sister and other family members with polycystic kidney disease, or PKD, suffer the effects of chronic immunosuppression. That became his greatest fear when he was diagnosed with end stage renal failure.
Waddell enrolled in the phase II research taking place in Louisville after learning about it in early 2006. He chose to remain in the study when it relocated its clinical headquarters to Northwestern University’s medical center in Chicago a couple years later.
Before surgery, he underwent an enervating regimen of chemotherapy and radiation. It’s required to clear out a patient’s bone marrow cells so that they can be replaced by the donor’s cells. Waddell says the result was worth it: he had his combined kidney and immune system stem cell transplant in May 2009, without any need for chronic immunosuppression.
“I call it ‘short-term pain, long-term gain,’ because it was difficult to go through the conditioning, but after that, it was great,” he says. “I’ve talked to so many kidney recipients who say, ‘I wish I would have done that,’ because most people don’t think about clinical trials, but I was very fortunate.”
Waddell has every reason to support the success of this research, especially given the genetic disorder, PKD, that has plagued his family. One of his four children has PKD. He is anxious for the procedure to become standard of care, if and when his son needs it.
The Talaris procedure was pioneered decades ago by Suzanne Ildstad, founding CEO of Talaris and the company's Chief Scientific Officer, pictured here with the current CEO, Scott Requadt.
Talaris
“The beauty of this procedure is that I don’t have to take all of the anti-rejection drugs,” says Waddell, a finance professional. “I forget that I ever had any kidney issues. That’s how impactful it is.”
Talaris will continue to follow Waddell and the rest of his cohort to track the effectiveness and safety of the procedure. According to Requadt, the average life of a transplanted kidney is 12 to 15 years, partly because the immunosuppressive drugs worsen the functioning of the organ each year.
“We were the first group to show that we could robustly and fairly reproducibly do this in a clinical setting in humans,” Requadt says. “Most important, we’ve been able to show that we can still get a good engraftment of the stem cells from the donor, even if there is a profound…mismatch between the donor and the recipient’s immune systems.”
In kidney transplantation, it’s important to match for human leukocyte antigens (HLA) because there is a better graft survival in HLA-identical kidney transplants compared with HLA mismatched transplants.
About three months after the transplant, Talaris researchers look for evidence that the donated immune cells and stem cells have engrafted, while making a donor immune system for the patient. If more than 50 percent of the T cells contain the donor’s DNA after six months, patients can start taking fewer immunosuppressants.
“We know from phase II that in our patients who were able to tolerize [accept the organ without rejection] to their donated organ, we saw completely preserved and in fact slightly increased kidney function,” Requadt says. “So, it stands to reason that if you eliminate the drugs that are associated with declining kidney function that you would preserve kidney function, so hopefully the patient will have that one kidney for life.”
Matthew Cooper, director of kidney and pancreas transplantation for MedStar Georgetown Transplant Institute in Washington, DC, states that, “Right now, the Achilles’ heel is we have such a long waiting list and few donors that people die every day waiting for a kidney transplant. Eventually, we will eliminate the organ shortage so that people won’t die from organ failure.”
Cooper, a nationally recognized clinical transplant surgeon for 20 years, says when he started his career, finding a way for patients to forgo immunosuppression was considered “the Holy Grail” of modern transplant medicine.
“Now that we’ve got the protocols in place and some personal examples of how that can happen, it’s pretty exciting to see that all coming together,” he adds.
Researchers advance drugs that treat pain without addiction
Opioids are one of the most common ways to treat pain. They can be effective but are also highly addictive, an issue that has fueled the ongoing opioid crisis. In 2020, an estimated 2.3 million Americans were dependent on prescription opioids.
Opioids bind to receptors at the end of nerve cells in the brain and body to prevent pain signals. In the process, they trigger endorphins, so the brain constantly craves more. There is a huge risk of addiction in patients using opioids for chronic long-term pain. Even patients using the drugs for acute short-term pain can become dependent on them.
Scientists have been looking for non-addictive drugs to target pain for over 30 years, but their attempts have been largely ineffective. “We desperately need alternatives for pain management,” says Stephen E. Nadeau, a professor of neurology at the University of Florida.
A “dimmer switch” for pain
Paul Blum is a professor of biological sciences at the University of Nebraska. He and his team at Neurocarrus have created a drug called N-001 for acute short-term pain. N-001 is made up of specially engineered bacterial proteins that target the body’s sensory neurons, which send pain signals to the brain. The proteins in N-001 turn down pain signals, but they’re too large to cross the blood-brain barrier, so they don’t trigger the release of endorphins. There is no chance of addiction.
When sensory neurons detect pain, they become overactive and send pain signals to the brain. “We wanted a way to tone down sensory neurons but not turn them off completely,” Blum reveals. The proteins in N-001 act “like a dimmer switch, and that's key because pain is sensation overstimulated.”
Blum spent six years developing the drug. He finally managed to identify two proteins that form what’s called a C2C complex that changes the structure of a subunit of axons, the parts of neurons that transmit electrical signals of pain. Changing the structure reduces pain signaling.
“It will be a long path to get to a successful clinical trial in humans," says Stephen E. Nadeau, professor of neurology at the University of Florida. "But it presents a very novel approach to pain reduction.”
Blum is currently focusing on pain after knee and ankle surgery. Typically, patients are treated with anesthetics for a short time after surgery. But anesthetics usually only last for 4 to 6 hours, and long-term use is toxic. For some, the pain subsides. Others continue to suffer after the anesthetics have worn off and start taking opioids.
N-001 numbs sensation. It lasts for up to 7 days, much longer than any anesthetic. “Our goal is to prolong the time before patients have to start opioids,” Blum says. “The hope is that they can switch from an anesthetic to our drug and thereby decrease the likelihood they're going to take the opioid in the first place.”
Their latest animal trial showed promising results. In mice, N-001 reduced pain-like behaviour by 90 percent compared to the control group. One dose became effective in two hours and lasted a week. A high dose had pain-relieving effects similar to an opioid.
Professor Stephen P. Cohen, director of pain operations at John Hopkins, believes the Neurocarrus approach has potential but highlights the need to go beyond animal testing. “While I think it's promising, it's an uphill battle,” he says. “They have shown some efficacy comparable to opioids, but animal studies don't translate well to people.”
Nadeau, the University of Florida neurologist, agrees. “It will be a long path to get to a successful clinical trial in humans. But it presents a very novel approach to pain reduction.”
Blum is now awaiting approval for phase I clinical trials for acute pain. He also hopes to start testing the drug's effect on chronic pain.
Learning from people who feel no pain
Like Blum, a pharmaceutical company called Vertex is focusing on treating acute pain after surgery. But they’re doing this in a different way, by targeting a sodium channel that plays a critical role in transmitting pain signals.
In 2004, Stephen Waxman, a neurology professor at Yale, led a search for genetic pain anomalies and found that biologically related people who felt no pain despite fractures, burns and even childbirth had mutations in the Nav1.7 sodium channel. Further studies in other families who experienced no pain showed similar mutations in the Nav1.8 sodium channel.
Scientists set out to modify these channels. Many unsuccessful efforts followed, but Vertex has now developed VX-548, a medicine to inhibit Nav1.8. Typically, sodium ions flow through sodium channels to generate rapid changes in voltage which create electrical pulses. When pain is detected, these pulses in the Nav1.8 channel transmit pain signals. VX-548 uses small molecules to inhibit the channel from opening. This blocks the flow of sodium ions and the pain signal. Because Nav1.8 operates only in peripheral nerves, located outside the brain, VX-548 can relieve pain without any risk of addiction.
"Frankly we need drugs for chronic pain more than acute pain," says Waxman.
The team just finished phase II clinical trials for patients following abdominoplasty surgery and bunionectomy surgery.
After abdominoplasty surgery, 76 patients were treated with a high dose of VX-548. Researchers then measured its effectiveness in reducing pain over 48 hours, using the SPID48 scale, in which higher scores are desirable. The score for Vertex’s drug was 110.5 compared to 72.7 in the placebo group, whereas the score for patients taking an opioid was 85.2. The study involving bunionectomy surgery showed positive results as well.
Waxman, who has been at the forefront of studies into Nav1.7 and Nav1.8, believes that Vertex's results are promising, though he highlights the need for further clinical trials.
“Blocking Nav1.8 is an attractive target,” he says. “[Vertex is] studying pain that is relatively simple and uniform, and that's key to having a drug trial that is informative. But the study needs to be replicated and frankly we need drugs for chronic pain more than acute pain. If this is borne out by additional studies, it's one important step in a journey.”
Vertex will be launching phase III trials later this year.
Finding just the right amount of Nerve Growth Factor
Whereas Neurocarrus and Vertex are targeting short-term pain, a company called Levicept is concentrating on relieving chronic osteoarthritis pain. Around 32.5 million Americans suffer from osteoarthritis. Patients commonly take NSAIDs, or non-steroidal anti-inflammatory drugs, but they cannot be taken long-term. Some take opioids but they aren't very effective.
Levicept’s drug, Levi-04, is designed to modify a signaling pathway associated with pain. Nerve Growth Factor (NGF) is a neurotrophin: it’s involved in nerve growth and function. NGF signals by attaching to receptors. In pain there are excess neurotrophins attaching to receptors and activating pain signals.
“What Levi-04 does is it returns the natural equilibrium of neurotrophins,” says Simon Westbrook, the CEO and founder of Levicept. It stabilizes excess neurotrophins so that the NGF pathway does not signal pain. Levi-04 isn't addictive since it works within joints and in nerves outside the brain.
Westbrook was initially involved in creating an anti-NGF molecule for Pfizer called Tanezumab. At first, Tanezumab seemed effective in clinical trials and other companies even started developing their own versions. However, a problem emerged. Tanezumab caused rapidly progressive osteoarthritis, or RPOA, in some patients because it completely removed NGF from the system. NGF is not just involved in pain signalling, it’s also involved in bone growth and maintenance.
Levicept has found a way to modify the NGF pathway without completely removing NGF. They have now finished a small-scale phase I trial mainly designed to test safety rather than efficacy. “We demonstrated that Levi-04 is safe and that it bound to its target, NGF,” says Westbrook. It has not caused RPOA.
Professor Philip Conaghan, director of the Leeds Institute of Rheumatic and Musculoskeletal Medicine, believes that Levi-04 has potential but urges the need for caution. “At this early stage of development, their molecule looks promising for osteoarthritis pain,” he says. “They will have to watch out for RPOA which is a potential problem.”
Westbrook starts phase II trials with 500 patients this summer to check for potential side effects and test the drug’s efficacy.
There is a real push to find an effective alternative to opioids. “We have a lot of work to do,” says Professor Waxman. “But I am confident that we will be able to develop new, much more effective pain therapies.”