genomics
Auto Added by WPeMatico
Sano Genetics, a startup helping with Long COVID research, raises £2.5M in seed funding
Sano Genetics, a startup with a broad mission to support personalised medicine research by increasing participation in clinical trials, has raised £2.5 million in seed funding.
The round is led by Episode1 Ventures, alongside Seedcamp, Cambridge Enterprise, January Ventures and several Europe and U.S.-based angel investors. It adds to £500,000 in pre-seed funding from 2018.
Sano Genetics says part of the new capital will be to fund free at-home DNA testing kits for 3,000 people affected by Long COVID. It will also further invest in the development of its tech platform and grow the team.
Founded in 2017 by Charlotte Guzzo, Patrick Short and William Jones after they met at Cambridge University while studying genomics as postgrads, Sano Genetics has built what it describes as a “private-by-design” tech platform to help patients take part in medical research and clinical trials. This includes at-home genetic testing capabilities, and is seeing the company support research into multiple sclerosis, ankylosing spondylitis, NAFLD and ulcerative colitis2, with a research programme for Parkinson’s disease on the agenda for later in 2021.
“For participants in medical research, the process is not user friendly,” says Sano Genetics CEO Patrick Short. “There is usually little to no benefit for participants beyond altruism, taking part is difficult and time-consuming and people are also concerned about the privacy of their sensitive genetic and medical information.
“[Therefore], for researchers in biotech, pharma and academia, it is very difficult to attract and retain research participants, which adds substantial costs and time to their research. In particular for research involving genetics and precision therapies, it is doubly challenging to find the ‘right’ patients because genetic testing is not routine in the healthcare system”.
To help solve this, Sano Genetics matches relevant participants to research via its platform. It then makes participation easier by enabling at-home genetic testing and by guiding participants through the process.
“The system is designed so users know exactly what will happen with their data, and we give them straightforward ways to control their data,” explains Short. “We keep our users engaged and involved in the research process by giving them updates on the research they have been a part of, and with free personalised content including genetic reports, and stories from other people like them on our blog”.
A typical end user is someone who has a chronic or rare disease and is using the platform to take part in research that helps them personally (e.g. access to a new therapy via a clinical trial) or to help others like them.
Meanwhile, Sano Genetics generates revenue by charging biotech and pharma companies fees to find the right patients for their studies. “The typical study for us consists of a set-up fee, a per-test fee for our at-home genetic testing and analysis, and a fee for each referral we make of an interested and eligible participant to their research study,” adds the Sano Genetics CEO.
Powered by WPeMatico
Carbon Health to launch 100 pop-up COVID-19 testing clinics across the US
Primary care health tech startup Carbon Health has added a new element to its “omnichannel” healthcare approach with the launch of a new pop-up clinic model that is already live in San Francisco, LA, Seattle, Brooklyn and Manhattan, with Detroit to follow soon – and that will be rolling out over the next weeks and months across a variety of major markets in the U.S., ultimately resulting in 100 new COVID-19 testing sites that will add testing capacity on the order of around an additional 100,000 patients per month across the country.
So far, Carbon Health has focused its COVID-19 efforts around its existing facilities in the Bay Area, and also around pop-up testing sites set up in and around San Francisco through collaboration with genomics startup Color, and municipal authorities. Now, Carbon Health CEO and co-founder Even Bali tells me in an interview that the company believes the time is right for it to take what it has learned and apply that on a more national scale, with a model that allows for flexible and rapid deployment. In fact, Bali says the they realized and began working towards this goal as early as March.
“We started working on COVID response as early as February, because we were seeing patients who are literally coming from Wuhan, China to our clinics,” Bali said. “We expected the pandemic to hit any time. And partially because of the failure of federal government control, we decided to do everything we can to be able to help out with certain things.”
That began with things that Carbon could do locally, more close to home in its existing footprint. But it was obvious early on to Bali and his team that there would be a need to scale efforts more broadly. To do that, Carbon was able to draw on its early experience.
“We have been doing on-site, we have been going to nursing homes, we have been working with companies to help them reopen,” he told me. “At this point, I think we’ve done more than 200,000 COVID tests by ourselves. And I think I do more than half of all the Bay Area, if you include that the San Francisco City initiative is also partly powered by Carbon Health, so we’re already trying to scale as much as possible, but at some point we were hitting some physical space limits, and had the idea back in March to scale with more pop-up, more mobile clinics that you can actually put up like faster than a physical location.”
Interior of one of Carbon Health’s COVID-19 testing pop-up clinics in Brooklyn.
To this end, Carbon Health also began using a mobile trailer that would travel from town to town in order to provide testing to communities that weren’t typically well-served. That ended up being a kind of prototype of this model, which employs construction trailers like you’d see at a new condo under development acting as a foreman’s office, but refurbished and equipped with everything needed for on-site COVID testing run by medical professionals. These, too, are a more temporary solution, as Carbon Health is working with a manufacturing company to create a more fit-for-purpose custom design that can be manufactured at scale to help them ramp deployment of these even faster.
Carbon Health is partnering with Reef Technologies, a SoftBank -backed startup that turns parking garage spots into locations for businesses, including foodservice, fulfilment, and now Carbon’s medical clinics. This has helped immensely with the complications of local permitting and real estate regulations, Bali says. That means that Carbon Health’s pop-up clinics can bypass a lot of the red tape that slows the process of opening more traditional, permanent locations.
While cost is one advantage of using this model, Bali says that actually it’s not nearly as inexpensive as you might think relative to opening a more traditional clinic – at least until their custom manufacturing and economies of scale kick in. But speed is the big advantage, and that’s what is helping Carbon Health look ahead from this particular moment, to how these might be used either post-pandemic, or during the eventual vaccine distribution phase of the COVID crisis. Bali points out that any approved vaccine will need administration to patients, which will require as much, if not more infrastructure than testing.
Exterior of one of Carbon Health’s COVID-19 testing pop-up clinics in Brooklyn.
Meanwhile, Carbon Health’s pop-up model could bridge the gap between traditional primary care and telehealth, for ongoing care needs unrelated to COVID.
“A lot of the problems that telemedicine is not a good solution for, are the things where a video check-in with a doctor is nearly enough, but you do need some diagnostic tests – maybe you might you may need some administration, or you may need like a really simple physical examination that nursing staff can do with the instructions of the doctor. So if you think about those cases, pretty much 90% of all visits can actually be done with a doctor on video, and nursing staff in person.”
COVID testing is an imminent, important need nationwide – and COVID vaccine administration will hopefully soon replace it, with just as much urgency. But even after the pandemic has passed, healthcare in general will change dramatically, and Carbon Health’s model could be a more permanent and scalable way to address the needs of distributed care everywhere.
Powered by WPeMatico
Mammoth Biosciences aims to be Illumina for the gene editing generation
In 1998, the startup company Illumina launched a revolution in the life sciences industry by developing technology to slash the costs of identifying and mapping genetic material.
Now, a little over 20 years later, Mammoth Biosciences is hoping to do the same thing for gene editing tools.
The company, co-founded by Jennifer Doudna, who did some of the pioneering work to discover the gene editing enzyme known as CRISPR, has just raised $45 million as it looks to bring to market products that can be used not only for disease detection, but are more precise editing tools for genetic material.
Rather than get bogged down in the patent dispute that raged over the provenance and ownership of applications for the original CRISPR enzyme — the Cas9 discovered by Doudna and developed for clinical applications at the Broad Institute — Mammoth has joined a number of startups in identifying new enzymes with a broader array of properties.
“From the very beginning of the company we’ve only worked with novel new enzymes to create these diagnostic products and the new novel diagnostic and editing,” says Trevor Martin, Mammoth Biosciences co-founder and chief executive.
Chiefly, the company is touting its Cas14 enzyme, which the company says opens up new possibilities for programmable biology thanks to its small size, diverse targeting ability and high fidelity — meaning that there are no unforeseen side effects to edits made using the enzyme (something that has arisen with Cas9 applications).
“There’s not one protein that’s going to be the best at everything,” says Martin. “For any particular product that you’re building, at Mammoth, we have the broadest toolbox.”
The Cas14 enzyme can be used to make gene edits in-vivo, meaning in live organisms, instead of ex-vivo, or outside of an organism. The in-vivo use-case could accelerate the time it takes to conduct experiments or develop treatments.
“Twenty years from now, when the umpteenth drug gets approved using Crispr and some nuclease named Cas132013, people are going to look back on this patent battle and think, ‘what a godawful waste of money,’ ” Jacob Sherkow a patent law scholar at New York Law School told Wired back in 2018.
Already, Horizon Discovery, a Cambridge, U.K.-based gene editing technology developer, is using the new tools developed by Mammoth Bioscience to create new CRISPR tools for Chinese Hamster Ovary cell line editing.
That partnership is an example of how Mammoth is thinking about the commercialization of the new Cas14 enzyme line and its role in biological engineering.
“You will need a full toolbox of CRISPR proteins,” says Martin. “That will allow you to interact with biology in the same way that we interact with software and computers. “From first principles, companies will programmatically modify biology to cure a disease or decrease risk for a disease. That’s going to be really kind of a turning point.”
To achieve its vision, Mammoth has managed to nab top talent from the life sciences industry, including Peter Nell, a co-founder of Casebia (a joint venture between Bayer and CRISPR Therapeutics), who came on board as chief business officer, and Ted Tisch, a former executive at Synthego and Bio-Rad, who joined the company as chief operating officer.
The company also nabbed $45 million of funding, including investment firms Mayfield, NFX, Verily (the Alphabet subsidiary) and Brook Byers, which was led by Decheng Capital — bringing the company to more than $70 million in funding.
“There are a dozen or so products that are in clinical development with CRISPR,” says Ursheet Parikh, a partner with Mayfield. “Maybe that number would go up by five or 10 without Mammoth, but it will go up by one or two orders of magnitude with Mammoth.”
To Parikh, Mammoth is the best positioned of the CRISPR development tools, because the company is building a whole platform that customers can license and use to develop products using gene editing.
The thinking, according to Parikh, is as follows, “if this technology can power lots of applications, let’s basically ensure that lots of these applications can come to market and as that happens I get my app store cut.”
“It’s an Illumina-like business,” Parikh says. “Just as anybody who is innovating with genomics needs an Illumina sequencer because they want to be able to do the sequencing… if someone wants to do editing… This gives them the access to do the right sequencing.”
Powered by WPeMatico
$125 million for Inscripta may usher in the next wave of genetic engineering
In these waning days of the second decade of the twenty-first century, technologists and investors are beginning to lay the foundations for new, truly transformational technologies that have the potential to reshape entire industries and rewrite the rules of human understanding.
It may sound lofty, but new achievements from businesses and research institutions in areas like machine learning, quantum computing and genetic engineering mean that the futures imagined in science fiction are simply becoming science.
And among the technologies that could potentially have the biggest effect on the way we live, nothing looms larger than genetic engineering.
Investors and entrepreneurs are deploying hundreds of millions of dollars to create the tools that researchers, scientists and industry will use to re-engineer the building blocks of life to perform different functions in agriculture, manufacturing and medicine.
One of these companies, 10X Genomics, which gives users hardware and software to determine the functionality of different genetic code, has already proven how lucrative this early market can be. The company, which had its initial public offering earlier this year, is now worth $6 billion.
Another, the still-private company Inscripta, is helmed by a former 10X Genomics executive. The Boulder, Colo.-based startup is commercializing a machine that can let researchers design and manufacture small quantities of new organisms. If 10X Genomics is giving scientists and businesses a better way to read and understand the genome, then Inscripta is giving those same users a new way to write their own genetic code and make their own organisms.
It’s a technology that investors are falling over themselves to finance. The company, which closed on $105 million in financing earlier in the year (through several tranches, which began in late 2018), has just raised another $125 million on the heels of launching its first commercial product. Investors in the round include new and previous investors like Paladin Capital Group, JS Capital Management, Oak HC/FT and Venrock.
“Biology has unlimited potential to positively change this world,” says Kevin Ness, the chief executive of Inscripta . “It’s one of the most important new technology forces that will be a major player in the global economy.”
Ness sees Inscripta as breaking down one of the biggest barriers to the commercialization of genetic engineering, which is access to the technology.
While genome centers and biology foundries can manufacture massive quantities of new biological material for industrial uses, it’s too costly and centralized for most researchers. “We can put the biofoundry capabilities into a box that can be pushed to a global researcher,” says Ness.
Earlier this year, the company announced that it was taking orders for its first bio-manufacturing product; the new capital is designed to pay for expanding its manufacturing capabilities.
That wasn’t the only barrier that Inscripta felt that it needed to break down. The company also developed a proprietary biochemistry for gene editing, hoping to avoid having to pay fees to one of the two laboratories that were engaged in a pitched legal battle over who owned the CRISPR technology (the Broad Institute and the University of California both had claims to the technology).
Powered by WPeMatico
Biotech researchers venture into the wild to start their own business
Jorge Conde is a General Partner at Andreessen Horowitz where he leads investments at the cross section of biology, computer science and engineering.
Much of Silicon Valley mythology is centered on the founder-as-hero narrative. But historically, scientific founders leading the charge for bio companies have been far less common.
Developing new drugs is slow, risky and expensive. Big clinical failures are all too common. As such, bio requires incredibly specialized knowledge and experience. But at the same time, the potential for value creation is enormous today more than ever with breakthrough new medicines like engineered cell, gene and digital therapies.
What these breakthroughs are bringing along with them are entirely new models — of founders, of company creation, of the businesses themselves — that will require scientists, entrepreneurs and investors to reimagine and reinvent how they create bio companies.
In the past, biotech VC firms handled this combination of specialized knowledge + binary risk + outsized opportunity with a unique “company creation” model. In this model, there are scientific founders, yes; but the VC firm essentially founded and built the company itself — all the way from matching a scientific advance with an unmet medical need, to licensing IP, to having partners take on key roles such as CEO in the early stages, to then recruiting a seasoned management team to execute on the vision.
Image: PASIEKA/SCIENCE PHOTO LIBRARY/Getty Images
You could call this the startup equivalent of being born and bred in captivity — where great care and feeding early in life helps ensure that the company is able to thrive. Here the scientific founders tend to play more of an advisory role (usually keeping day jobs in academia to create new knowledge and frontiers), while experienced “drug hunters” operate the machinery of bringing new discoveries to the patient’s bedside. This model’s core purpose is to bring the right expertise to the table to de-risk these incredibly challenging enterprises — nobody is born knowing how to make a medicine.
But the ecosystem this model evolved from is evolving itself. Emerging fields like computational biology and biological engineering have created a new breed of founder, native to biology, engineering and computer science, that are already, by definition, the leading experts in their fledgling fields. Their advances are helping change the industry, shifting drug discovery away from a highly bespoke process — where little knowledge carries over from the success or failure of one drug to the next — to a more iterative, building-block approach like engineering.
Take gene therapy: once we learn how to deliver a gene to a specific cell in a given disease, it is significantly more likely we will be able to deliver a different gene to a different cell for another disease. Which means there’s an opportunity not only for novel therapies but also the potential for new business models. Imagine a company that provides gene delivery capability to an entire industry — GaaS: gene-delivery as a service!
Once a founder has an idea, the costs of testing it out have changed too. The days of having to set up an entire lab before you could run your first experiments are gone. In the same way that AWS made starting a tech company vastly faster and easier, innovations like shared lab spaces and wetlab accelerators have dramatically reduced the cost and speed required to get a bio startup off the ground. Today it costs thousands, not millions, for a “killer experiment” that will give a founding team (and investors) early conviction.
What all this amounts to is scientific founders now have the option of launching bio companies without relying on VCs to create them on their behalf. And many are. The new generation of bio companies being launched by these founders are more akin to being born in the wild. It isn’t easy; in fact, it’s a jungle out there, so you need to make mistakes, learn quickly, hone your instincts, and be well-equipped for survival. On the other hand, given the transformative potential of engineering-based bio platforms, the cubs that do survive can grow into lions.
Image via Getty Images / KTSDESIGN/SCIENCE PHOTO LIBRARY
So, which is better for a bio startup today: to be born in the wild — with all the risk and reward that entails — or to be raised in captivity
The “bred in captivity” model promises sureness, safety, security. A VC-created bio company has cache and credibility right off the bat. Launch capital is essentially guaranteed. It attracts all-star scientists, executives and advisors — drawn by the balance of an innovative, agile environment and a well-funded, well-connected support network. I was fortunate enough to be an early executive in one of these companies, giving me the opportunity to work alongside industry luminaries and benefit from their well-versed knowledge of how to build a world-class bio company with all its complex component parts: basic, translational, clinical research, from scratch. But this all comes at a price.
Because it’s a heavy lift for the VCs, scientific founders are usually left with a relatively small slug of equity — even founding CEOs can end up with ~5% ownership. While these companies often launch with headline-grabbing funding rounds of $50m or above, the capital is tranched — meaning money is doled out as planned milestones are achieved. But the problem is, things rarely go according to plan. Tranched capital can be a safety net, but you can get tangled in that net if you miss a milestone.
Being born in the wild, on the other hand, trades safety for freedom. No one is building the company on your behalf; you’re in charge, and you bear the risk. As a recent graduate, I co-founded a company with Harvard geneticist George Church. The company was bootstrapped — a funding strategy that was more famine than feast — but we were at liberty to try new things and run (un)controlled experiments like sequencing heavy metal wildman Ozzy Osbourne.
It was the early, Wild West days of the genomics revolution and many of the earliest biotech companies mirrored that experience — they weren’t incepted by VCs; they were created by scrappy entrepreneurs and scientists-turned-CEO. Take Joshua Boger, organic chemist and founder of Vertex Pharmaceuticals: starting in 1989 his efforts to will into existence a new way to develop drugs, thrillingly captured in Barry Werth’s The Billion-Dollar Molecule and its sequel The Antidote in all its warts and nail-biting glory, ultimately transformed how we treat HIV, hepatitis C and cystic fibrosis.
Today we’re in a back-to-the-future moment and the industry is being increasingly pushed forward by this new breed of scientist-entrepreneur. Students-turned-founder like Diego Rey of in vitro diagnostics company GeneWEAVE and Ramji Srinivasan of clinical laboratory Counsyl helped transform how we diagnose disease and each led their companies to successful acquisitions by larger rivals.
Popular accelerators like Y Combinator and IndieBio are filled with bio companies driven by this founder phenotype. Ginkgo Bioworks, the first bio company in Y Combinator and today a unicorn, was founded by Jason Kelly and three of his MIT biological engineering classmates, along with former MIT professor and synthetic biology legend Tom Knight. The company is not only innovating new ways to program biology in order to disrupt a broad range of industries, but it’s also pioneering an innovative conglomerate business model it has dubbed the “Berkshire for biotech.”
Like the Ginkgo founders, Alec Nielsen and Raja Srinivas launched their startup Asimov, an ambitious effort to program cells using genetic circuits, shortly after receiving their PhDs in biological engineering from MIT. And, like Boger, renowned machine learning Stanford professor Daphne Koller is working to once again transform drug discovery as the founder and CEO of Instiro.
Just like making a medicine, no one is born knowing how to build a company. But in this new world, these technical founders with deep domain expertise may even be more capable of traversing the idea maze than seasoned operators. Engineering-based platforms have the potential to create entirely new applications with unprecedented productivity, creating opportunities for new breakthroughs, novel business models, and new ways to build bio companies. The well-worn playbooks may be out of date.
Founders that choose to create their own companies still need investors to scrub in and contribute to the arduous labor of company-building — but via support, guidance, and with access to networks instead. And like this new generation of founders, bio investors today need to rethink (and re-value) the promise of the new, and still appreciate the hard-earned wisdom of the old. In other words, bio investors also need to be multidisciplinary. And they need to be comfortable with a different kind of risk: backing an unproven founder in a new, emerging space. As a founder, if you’re willing to take your chances in the wild, you should have an investor that understands you, believes in you, can support you and, importantly, is willing to dream big with you.
Powered by WPeMatico
What tech gets right about healthcare
Why is tech still aiming for the healthcare industry? It seems full of endless regulatory hurdles or stories of misguided founders with no knowledge of the space, running headlong into it, only to fall on their faces.
Theranos is a prime example of a founder with zero health background or understanding of the industry — and just look what happened there! The company folded not long after founder Elizabeth Holmes came under criminal investigation and was barred from operating in her own labs for carelessly handling sensitive health data and test results.
But sometimes tech figures it out. It took years for 23andMe to breakthrough FDA regulations — it’s since more than tripled its business and moved into drug discovery.
And then there’s Oscar Health, which first made a mint on Obamacare and has since ventured into Medicare. Combined with Bright, the two health insurance startups have pulled in a whopping $3 billion so far.
It’s easy to shake our fists at fool-hardy founders hoping to cash in on an industry that cannot rely on the old motto “move fast and break things.” But it doesn’t have to be the code tech lives or dies by.
So which startups have the mojo to keep at it and rise to the top? Venture capitalists often get to see a lot before deciding to invest. So we asked a few of our favorite health VC’s to share their insights.
Phin Barnes – First Round Capital
Powered by WPeMatico
Driving down the cost of preserving genetic material, Acorn Biolabs raises $3.3 million
Acorn Biolabs wants consumers to pay them to store genetic material in a bet that the increasing advances in targeted genetic therapies will yield better healthcare results down the line.
The company’s pitch is to “Save young cells today, live a longer, better, tomorrow.” It’s a gamble on the frontiers of healthcare technology that has managed to net the company $3.3 million in seed financing from some of Canada’s busiest investors.
For the Toronto-based company, the pitch isn’t just around banking genetic material — a practice that’s been around for years — it’s about making that process cheaper and easier.
Acorn has come up with a way to collect and preserve the genetic material contained in hair follicles, giving its customers a way to collect full-genome information at home rather than having to come in to a facility and getting bone marrow drawn (the practice at one of its competitors, Forever Labs) .
“We have developed a proprietary media that cells are submerged in that maintains the viability of those cells as they’re being transported to our labs for processing,” says Acorn Biolabs chief executive Dr. Drew Taylor.
“Rapid advancements in the therapeutic use of cells, including the ability to grow human tissue sections, cartilage, artificial skin and stem cells, are already being delivered. Entire heart, liver and kidneys are really just around the corner. The urgency around collecting, preserving and banking youthful cells for future use is real and freezing the clock on your cells will ensure you can leverage them later when you need them,” Taylor said in a statement.
Typically, the cost of banking a full genome test is roughly $2,000 to $3,000, and Acorn says they can drop that cost to less than $1,000. Beyond the cost of taking the sample and storing it, Acorn says it will reduce to roughly $100 a year the fees to store such genetic materials.
It’s important to note that healthcare doesn’t cover any of this. It’s a voluntary service for those neurotic enough or concerned enough about the future of healthcare and their potential health.
There’s also no services that Acorn will provide on the back end of the storage… yet.
“What people do need to realize is that there is power with that data that can improve healthcare. Down the road we will be able to use that data to help people collect that data and power studies,” says Taylor.
The $3.3 million the company raised came from Real Ventures, Globalive Technology, Pool Global Partners and Epic Capital Management and other undisclosed investors.
“Until now, any live cell collection solutions have been highly expensive, invasive and often painful, as well as being geographically limited to specialized clinics,” said Anthony Lacavera, founder and chairman at Globalive. “Acorn is an industry-leading example of how technology can bring real innovation to enable future healthcare solutions that will have meaningful impact on people’s wellbeing and longevity, while at the same time — make it easy, affordable and frictionless for everyone.”
Powered by WPeMatico
Agtech startup Imago AI is using computer vision to boost crop yields
Presenting onstage today in the 2018 TC Disrupt Berlin Battlefield is Indian agtech startup Imago AI, which is applying AI to help feed the world’s growing population by increasing crop yields and reducing food waste. As startup missions go, it’s an impressively ambitious one.
The team, which is based out of Gurgaon near New Delhi, is using computer vision and machine learning technology to fully automate the laborious task of measuring crop output and quality — speeding up what can be a very manual and time-consuming process to quantify plant traits, often involving tools like calipers and weighing scales, toward the goal of developing higher-yielding, more disease-resistant crop varieties.
Currently they say it can take seed companies between six and eight years to develop a new seed variety. So anything that increases efficiency stands to be a major boon.
And they claim their technology can reduce the time it takes to measure crop traits by up to 75 percent.
In the case of one pilot, they say a client had previously been taking two days to manually measure the grades of their crops using traditional methods like scales. “Now using this image-based AI system they’re able to do it in just 30 to 40 minutes,” says co-founder Abhishek Goyal.
Using AI-based image processing technology, they can also crucially capture more data points than the human eye can (or easily can), because their algorithms can measure and asses finer-grained phenotypic differences than a person might pick up on or be easily able to quantify just judging by eye alone.
“Some of the phenotypic traits they are not possible to identify manually,” says co-founder Shweta Gupta. “Maybe very tedious or for whatever all these laborious reasons. So now with this AI-enabled [process] we are now able to capture more phenotypic traits.
“So more coverage of phenotypic traits… and with this more coverage we are having more scope to select the next cycle of this seed. So this further improves the seed quality in the longer run.”
The wordy phrase they use to describe what their technology delivers is: “High throughput precision phenotyping.”
Or, put another way, they’re using AI to data-mine the quality parameters of crops.
“These quality parameters are very critical to these seed companies,” says Gupta. “Plant breeding is a very costly and very complex process… in terms of human resource and time these seed companies need to deploy.
“The research [on the kind of rice you are eating now] has been done in the previous seven to eight years. It’s a complete cycle… chain of continuous development to finally come up with a variety which is appropriate to launch in the market.”
But there’s more. The overarching vision is not only that AI will help seed companies make key decisions to select for higher-quality seed that can deliver higher-yielding crops, while also speeding up that (slow) process. Ultimately their hope is that the data generated by applying AI to automate phenotypic measurements of crops will also be able to yield highly valuable predictive insights.
Here, if they can establish a correlation between geotagged phenotypic measurements and the plants’ genotypic data (data which the seed giants they’re targeting would already hold), the AI-enabled data-capture method could also steer farmers toward the best crop variety to use in a particular location and climate condition — purely based on insights triangulated and unlocked from the data they’re capturing.
One current approach in agriculture to selecting the best crop for a particular location/environment can involve using genetic engineering. Though the technology has attracted major controversy when applied to foodstuffs.
Imago AI hopes to arrive at a similar outcome via an entirely different technology route, based on data and seed selection. And, well, AI’s uniform eye informing key agriculture decisions.
“Once we are able to establish this sort of relation this is very helpful for these companies and this can further reduce their total seed production time from six to eight years to very less number of years,” says Goyal. “So this sort of correlation we are trying to establish. But for that initially we need to complete very accurate phenotypic data.”
“Once we have enough data we will establish the correlation between phenotypic data and genotypic data and what will happen after establishing this correlation we’ll be able to predict for these companies that, with your genomics data, and with the environmental conditions, and we’ll predict phenotypic data for you,” adds Gupta.
“That will be highly, highly valuable to them because this will help them in reducing their time resources in terms of this breeding and phenotyping process.”
“Maybe then they won’t really have to actually do a field trial,” suggests Goyal. “For some of the traits they don’t really need to do a field trial and then check what is going to be that particular trait if we are able to predict with a very high accuracy if this is the genomics and this is the environment, then this is going to be the phenotype.”
So — in plainer language — the technology could suggest the best seed variety for a particular place and climate, based on a finer-grained understanding of the underlying traits.
In the case of disease-resistant plant strains it could potentially even help reduce the amount of pesticides farmers use, say, if the the selected crops are naturally more resilient to disease.
While, on the seed generation front, Gupta suggests their approach could shrink the production time frame — from up to eight years to “maybe three or four.”
“That’s the amount of time-saving we are talking about,” she adds, emphasizing the really big promise of AI-enabled phenotyping is a higher amount of food production in significantly less time.
As well as measuring crop traits, they’re also using computer vision and machine learning algorithms to identify crop diseases and measure with greater precision how extensively a particular plant has been affected.
This is another key data point if your goal is to help select for phenotypic traits associated with better natural resistance to disease, with the founders noting that around 40 percent of the world’s crop load is lost (and so wasted) as a result of disease.
And, again, measuring how diseased a plant is can be a judgement call for the human eye — resulting in data of varying accuracy. So by automating disease capture using AI-based image analysis the recorded data becomes more uniformly consistent, thereby allowing for better quality benchmarking to feed into seed selection decisions, boosting the entire hybrid production cycle.
Sample image processed by Imago AI showing the proportion of a crop affected by disease
In terms of where they are now, the bootstrapping, nearly year-old startup is working off data from a number of trials with seed companies — including a recurring paying client they can name (DuPont Pioneer); and several paid trials with other seed firms they can’t (because they remain under NDA).
Trials have taken place in India and the U.S. so far, they tell TechCrunch.
“We don’t really need to pilot our tech everywhere. And these are global [seed] companies, present in 30, 40 countries,” adds Goyal, arguing their approach naturally scales. “They test our technology at a single country and then it’s very easy to implement it at other locations.”
Their imaging software does not depend on any proprietary camera hardware. Data can be captured with tablets or smartphones, or even from a camera on a drone or using satellite imagery, depending on the sought for application.
Although for measuring crop traits like length they do need some reference point to be associated with the image.
“That can be achieved by either fixing the distance of object from the camera or by placing a reference object in the image. We use both the methods, as per convenience of the user,” they note on that.
While some current phenotyping methods are very manual, there are also other image-processing applications in the market targeting the agriculture sector.
But Imago AI’s founders argue these rival software products are only partially automated — “so a lot of manual input is required,” whereas they couch their approach as fully automated, with just one initial manual step of selecting the crop to be quantified by their AI’s eye.
Another advantage they flag up versus other players is that their approach is entirely non-destructive. This means crop samples do not need to be plucked and taken away to be photographed in a lab, for example. Rather, pictures of crops can be snapped in situ in the field, with measurements and assessments still — they claim — accurately extracted by algorithms which intelligently filter out background noise.
“In the pilots that we have done with companies, they compared our results with the manual measuring results and we have achieved more than 99 percent accuracy,” is Goyal’s claim.
While, for quantifying disease spread, he points out it’s just not manually possible to make exact measurements. “In manual measurement, an expert is only able to provide a certain percentage range of disease severity for an image example; (25-40 percent) but using our software they can accurately pin point the exact percentage (e.g. 32.23 percent),” he adds.
They are also providing additional support for seed researchers — by offering a range of mathematical tools with their software to support analysis of the phenotypic data, with results that can be easily exported as an Excel file.
“Initially we also didn’t have this much knowledge about phenotyping, so we interviewed around 50 researchers from technical universities, from these seed input companies and interacted with farmers — then we understood what exactly is the pain-point and from there these use cases came up,” they add, noting that they used WhatsApp groups to gather intel from local farmers.
While seed companies are the initial target customers, they see applications for their visual approach for optimizing quality assessment in the food industry too — saying they are looking into using computer vision and hyper-spectral imaging data to do things like identify foreign material or adulteration in production line foodstuffs.
“Because in food companies a lot of food is wasted on their production lines,” explains Gupta. “So that is where we see our technology really helps — reducing that sort of wastage.”
“Basically any visual parameter which needs to be measured that can be done through our technology,” adds Goyal.
They plan to explore potential applications in the food industry over the next 12 months, while focusing on building out their trials and implementations with seed giants. Their target is to have between 40 to 50 companies using their AI system globally within a year’s time, they add.
While the business is revenue-generating now — and “fully self-enabled” as they put it — they are also looking to take in some strategic investment.
“Right now we are in touch with a few investors,” confirms Goyal. “We are looking for strategic investors who have access to agriculture industry or maybe food industry… but at present haven’t raised any amount.”
Powered by WPeMatico
Human sequencing pioneer George Church wants to give you the power to sell your DNA on the blockchain
The blockchain is the buzziest thing on the internet these days and now MIT professor and godfather of the Human Genome Project George Church wants to put your genes on it. His new startup Nebula Genomics plans to sequence your genome for less than $1,000 and then add your data to the blockchain through the purchase of a “Nebula Token.” Read More
Powered by WPeMatico
Rex Animal Health is using genomics to keep livestock healthy
A startup called Rex Animal Health wants to protect livestock from illnesses that can quickly turn into epidemics, and help farmers breed animals with the healthiest and most attractive traits. Today at Disrupt SF, Rex unveiled technology to help veterinarians provide clinical support at the point on the farm, and predict the genetic causes of problematic traits in their herds, and in the… Read More
Powered by WPeMatico