Author: Pae Wu

Canaery leverages the animal kingdom’s superior sense of smell to detect and digitize the world of scent.

---

A dog’s nose is a smelling machine. From cancer to covid to cocaine to citrus greening, no other chemical sensor on the planet can smell and sort through the billions of environmental compounds like an animal’s olfactory bulb.  Today the only way to know what a dog or rodent is smelling is to interpret its trained behavior.  Canaery has brought us a way to read what the animal is detecting in the world without pre-training it on those compounds.  Deciphering the cacophony of scents we encounter daily is a daunting task, but done right you can unlock industries like agriculture, global shipping, and medical diagnostics.  Below are excerpts from our conversation with CEO and co-founder, Gabriel Lavella, Ph.D.

---

Nobody has been close to reproducing an animal’s sense of smell in terms of range and sensitivity. Until now.

CEO, Gabriel Lavella

During IndieBio, Canaery designed and built a prototype neurotech device to digitize the sense of scent. What is so hard about digitizing olfaction and why you are different?

We have sensors that are spectacular at digitizing all human senses except scent. The reason for this is clear; it has been a daunting task to reproduce the animal sense of smell. In fact engineers and scientists have been working on it for decades.  It’s relatively easy to make a sensor that detects one type of molecule, for instance a CO2 detector.  However, scents are often complex mixtures. The nose detects billions of different scents and does this using a complex set of receptors and machinery for introducing and rapidly removing the scent molecules. Canaery didn’t recreate that feat of nature but instead we use it. That’s what makes us different, we use a sensor already perfected over millions of years of evolution. 

Canaery’s neural interface is smaller than a penny and thinner than tissue paper!

Tell us about your team and what led you to your major breakthrough? 

Back in 2019, I jumped on a plane and flew to Trieste, Italy from my home in Barcelona.  Dima [Rinberg, CSO and co-founder] was coming out from NYU to a conference on chemical senses, a couple years earlier he had made the first major breakthroughs on decoding scents using interfaces.  It didn’t take long for us to realize we were on the same page.  Those fascinating conversations centered on discussing how combining his theories with our efforts in high scale interfaces could produce the ultimate smell sensor. 

That combination was the key that unlocked Canaery’s capabilities today.  From there we knew the applications and impact were immense.

The world is awash in scents and smells. Can you describe how Canaery keeps us safe and open for business? 

Nearly all objects give off a unique scent profile that can be used to identify the underlying object or even the state of that object. Scents are essentially volatile compounds and there is a great diversity of them in air, trillions in fact. 

To humans these compounds are often invisible because our noses aren’t trained to smell them. It is unlike our eyes where we can easily recognize and categorize millions of objects. Nevertheless these scents are there and they identify things critical to human health and safety. We don’t want to shut down the economy again when the next pandemic hits, we want to be able to detect and contain it from day one, scent can do that.

Vertical Oceans is elevating shrimp through its advanced vertical aquaculture system integrating 83 different technologies to build a perfect ecosystem for the world’s cleanest, freshest, and most sustainably produced shrimp.  Below we caught up with John Diener and Enzo Acerbi, co-founders and CEO and CTO, respectively, of Vertical Oceans.  It was 3 AM in Singapore, but as usual, these two tech founders were game to talk seafood.  

---

PW: Singapore is filled with fresh seafood, how has Vertical Oceans’ product garnered so much attention from foodies there? You’ve got chefs from some of the finest restaurants in Singapore clamoring for more product.  That’s impressive! 

JD: Even though we’re in the heartland of shrimp aquaculture in Southeast Asia, customers love our shrimp because it’s unlike anything available in the market.  Over and over again, our customers say, “I’ve never had anything this good and fresh before”. So even though we’re in the middle of so much shrimp farming and even fresh wild caught shrimp in Singapore, our product is on a different level and that really stands out. 

PW: Your shrimp are on a “different level” you say.   It sounds like you’re really . . . elevating shrimp.

JD: Yes!

PW: Sustainability and resilience in the food system has a lot to do with food miles.  Going from farm to fork with the least amount of process in between.  How long does it take to get the shrimp from the Vertical Oceans farms to your customers’ hands? 

JD: A few hours.  We start harvesting around 6AM and they’re in the customer’s hands before 2PM.  That’s less than 8 hours. 

PW: Not bad for an 8 hour day. 

JD: It’s hard, but worth it.  Here in Singapore we think a lot about food security and the COVID experience of 2020 only accelerated the urgency of that trend. It was a wake up call. Vertical Oceans sits at the cross section of two key themes: aquaculture and vertical farming. And as we mentioned before, if we can make the commercial side work in Singapore, where we are surrounded by shrimp aquaculture, imagine what we could do in a market much further away. 

PW: Let’s talk technology.  One metric that always catches the eye is your target feed conversion ratio of less than one.  First, what is FCR?  And second, how could you possibly get to less than one? That seems impossible.   

JD: Feed conversion ratio, or FCR, is a great metric in many ways, but also a bit misleading. 

Typically feed conversion ratio measures “as-is” meaning that you do not adjust for moisture content. So the feed moisture content of 10% is not adjusted to the shrimp moisture content of 70%. That’s why it is biologically possible to have a feed conversion ratio less than 1. But critically, shrimp and other aquaculture species are poikilothermic which means they do not produce metabolic heat to maintain a designated body temperature unlike farmed livestock. That, in addition to the fact they don’t need a large skeletal structure to fight gravity, makes aquaculture a potentially very efficient model of food production when done right because so much more of what they eat goes into their biomass.  

PW: You frequently say you came at the problem using first principles thinking – where do you think was the biggest leap you had to take to come up with a solution within your system? Or was it the whole system itself? 

JD: The first principles question is a good one. 

PW: Thank you. 

JD: The biggest leap happened when we flipped our perspective to thinking from the customer experience and working back from there. People want fresh seafood that looks and tastes like something that just came out of the ocean. Fresh seafood needs to be produced where it is consumed because it goes off very quickly if it’s not fresh and handled properly. 

So, that meant we had to go urban. Urban meant vertical. Vertical meant we had to re-think the entire system and that cascaded into the 83 technologies we have now. It was clear from thinking about it from a customer perspective that we needed a completely different approach. 

PW: Your tech stack is remarkable – from where do you draw inspiration and solutions? 

JD: We were laughing about this the other day. We have a database which contains 1,432 entries of various references, technical data sheets and other information. We’ve been collecting ideas since we first came up with the idea for Vertical Oceans in 2016.  A big part of it also comes from keeping your eyes open for technologies that could be applied. 

Like the time I was sitting on a plane watching them refuel it from under the wing and wondering “How do they do that without spilling jet fuel all over the place?”.  After researching airplane fuel handling, it inspired some new thinking about the water handling in our system. 

Some of the solutions were serendipitous like that, others were deliberate searches for new solutions to specific challenges. Probably 2/3rds was serendipitous.

PW: Speaking of the serendipitous tech solutions, what’s up with the disco lights? 

JD: Tony Manero (Saturday Night Fever) was Italian-American, the running hypothesis is that Enzo may have felt some inter-generational connection to that character.

EA: I confirm my love for disco lights. But who likes them even more is our seaweed. They literally cannot survive without disco lights, so we created this party environment for them to foster and live happily. 

PW: John you come from a long history in aquaculture, was Vertical Oceans a sudden fit of inspiration or a slow burn? 

JD: Vertical Oceans was a slow burn for several years. Then one last piece of the puzzle fell into place and the slow burn exploded into a full-on orbital burn.   

PW: Now I must ask, what was the last piece of the puzzle? 

JD: The last piece of the puzzle was how to really go vertical, not just the same tanks on multiple levels, but something automated, dense and vertical. And then I had the breakthrough – move the tanks, not the people. Making the tanks mobile and self-contained changed everything. It was an example of our first principles reasoning – there was no reason you couldn’t make the tanks mobile, just no one did it that way before. The idea was totally nuts, but the more we looked into it, the more we realized, “this works!”. 

PW: Enzo, how did John convince you to join him? 

EA: John fished me with the ability of an experienced fisherman. In fact, he’s pulled this trick on me twice — once before for an insect protein company. 

With no background in aquaculture, I was not quick in deciding to join Vertical Oceans. But John was patient and determined. During our chat John transmitted to me the vision and a lot of enthusiasm.  He explained to me the problem and the concept of Vertical Oceans in a very simple yet compelling way, highlighting the importance of digital technologies for the overall solution. His enthusiasm and drive was contagious. I decided to join him once I realized that what he wanted to do was revolutionary, and that my contribution could help achieve that vision. 

JD: There’s an additional anecdote to this story. In the interview, I was explaining what I had in mind on the white board and as we were talking through it we ran out of white board space. And at the end of the interview it was something like: “Ok, so can you do this? Is that interesting for you?”.

EA: The reality is that John and I get excited and motivated by the same kind of things.  Creating new solutions, that involve intersecting many technologies, to solve challenging problems, so it is easy for us to make plans together.

PW: What was your greatest accomplishment during IndieBio’s program? 

JD: These four-plus months were transformative. I think the biggest accomplishment was our ability to produce multiple batches of our shrimp that we sold direct-to-consumers and received so much positive feedback and interest. We progressed a lot on our technology and funding and other aspects, but proving out the product-market fit over and over again was huge. 

PW:  Most importantly, a wise man once said that shrimp is the fruit of the sea.  What’s your favorite way to prepare shrimp? Popcorn shrimp, pineapple shrimp, grilled shrimp. . . ? 

JD: The Vertical Oceans shrimp taste great as sashimi, but probably my favorite is just a quick pan sear with olive oil, sea salt and a touch of cooking sake.  

EA: One funny aspect of this is that I am not a big lover of shrimps or seafood in general. I used to have one or two shrimps, then get bothered by their chewiness and stop eating. But the first time I tried our shrimps, I could not stop eating them. Their snappiness and freshness is addictive.  

I have this feeling, but limited means to confirm it, that deep in the archives of Russian scientific literature lies a treasure trove of valuable new technologies, just waiting to spring forth and solve big problems.

It turns out that secret treasure trove landed on our doorsteps a stone’s throw away in Nova Scotia, Canada.  Khorcheska Bhatyrova and Anna Khusnutdinova are two biochemistry Ph.D.s who are taking on greenhouse gas emissions and the petrochemical industry with their invention, the zombie cell.

OzoneBio is producing an emissions-free, low-cost adipic acid produced from waste feedstocks to make the world’s only bio-nylon 6, 6 that can compete in the open market. No green premiums needed here. The zombie cell technique invented by co-founders Khorcheska Batyrova and Anna Khusnutdinova eliminates the need for costly metal catalysts. This adipic acid is scalable, cost competitive with petroleum-derived products, and can be made from wood-derived aromatics.

---

How did you come up with the idea for the zombie cells?

Everyone knows that all living organisms consist of enzymes, biological molecules that perform all kinds of chemical reactions inside living cells.  We thought, what if we can make this enzyme work robustly in our target reactions. We were lucky to have great profs in Russia who passed to us their knowledge and skills. Back in Russia we discussed with our profs the idea of what will happen if we make enzymes so stable and active so they would perform like chemical catalysts in the reactions, that is how we invented zombie cells.

Why is it you’re taking on nylon 6, 6? What’s so special about it?

Nylon 6, 6 is used everywhere from car parts to running shoes, it is used also to make your favorite yoga pants.  

Our first product is adipic acid (one of two key building blocks of Nylon 6, 6).  Currently, adipic acid is made only from oil, and it is one of the most toxic production processes in the world.  It leads to at least 60 million tons per year of greenhouse gases.  Especially nitrous oxide, which should scare us all, a gas that is 300 times more toxic than CO2 and stays in the atmosphere for 115 years destroying our only protection from UV radiation — the ozone layer.  That is why we named our company Ozonebio.

Seems limited to only make nylon 6, 6.

Alone, the fact that we already can make the powder of emission-free adipic acid on the bench is super exciting.  Adding in the fact that at scale we can make it cost competitive with the petroleum-derived adipic acid is revolutionary. 

We have made a complex family of enzymes work in our zombie cells.  This makes us a platform company.  That family of enzymes can be used to produce plastic precursors, fragrances or drugs. 

Why is your process so much less expensive than other bio-processes for adipic acid?

Using our zombie cells there is no need to use expensive manipulations to purify enzymes and there is no enzyme degradation.  No need to express helper proteins to ensure your product comes out the cells, [and] we discover[ed] the way to make cells porous just enough.  In addition, zombie cells together with our cheap helper chemical allow us to replace the expensive protein cofactors and Pt/Pd catalysts with hydrogenation facilities. 

And we have no need to keep cells happy and in a comfortable environment to make them produce your product. 

Keeping cells happy, this is where the capex and opex in biofermentation drives up cost and energy requirements in traditional biomanufacturing?

Yes, exactly.  Plus, we can use challenging / toxic feed stocks that [would otherwise] simply kill alive cells. And our feedstocks are waste products.

Circular and emissions-free and cost-competitive!

Yes.

It seems like you want to save the world one yoga pant at a time.  Why the urgency?

For over a decade, industry was looking for the replacement of expensive NAD(P)H cofactors and Pt/Pd catalysts using a cheap, robust approach. We could stabilize enzymes inside the cells without degradation and found a replacement for expensive cofactors, that is when I realized it is the time for the fast actions.  Thankfully, IndieBio is the place where things get done super-fast and efficiently.  That awesome team took our company to the completely different level in just 4.5 month! [Editor’s note: your check’s in the mail.]

This is a very difficult problem that many before you have failed to solve in a way that can compete on cost.  What possessed you to go after such a hard problem?

Throughout our careers in academia we used to work on complex enzymes trying to make them work, either adjusting reaction conditions or engineering enzymes. Same happened in this case, it was one of the complex enzymes we were working on, and in that case an uncommon technique worked to solve the problem of this enzyme stability and function.  That’s how we invented the zombie cells approach.  We made one of the most complicated and sensitive families of enzymes in the world to work without any extra manipulations.

How did you meet?

We met in 2007 in the Institute of Basic Biological Problems, in Russia, where we both got our PhD. There we worked on another group of complex enzymes that are responsible for hydrogen production. 

How did you two decide to start this company?

We started our company because I realized that it is time for us to be independent and start our own journey.  Anna and I had become experienced enough to identify the direction of our research and decide how to proceed.

Nova Scotia isn’t the first place that comes to mind for building a start-up, tell us a little bit about your journey there.

In Canada, the pandemic made many [start-up spaces] disappear.  Nova Scotia responded quickly to our request and they had the facility we needed to succeed through the IndieBio program.  We moved here 2 months ago, and during these two months we were able to make our first batch of the first in the world emissions-free adipic acid.  We only regret we did not move here earlier, right away after we were accepted to IndieBio, I think now we would already have Nylon 6, 6 chips made. But we are working on it now!

How did you feel the first time you produced adipic acid using your process?

We felt immediately that there is so much more work we need to do, and we kept going!

Quick word association exercise, what is your first reaction to the following phrase: You can’t do that.

Anna: Why?

Khorcheska: I prefer to decide it on my own, whether I can or can’t do it 😊

OncoPrecision can predict a patient’s response to cancer therapies by replicating the tumor microenvironment ex vivo. Their unique, triple co-culture method increases patient-derived cancer cell viability 60x in a 2.5D format that has been validated using real patient data.  For patients in dire need of the right cancer treatment the first time, OncoPrecision offers doctors the assurance that decisions made today will make the difference tomorrow.  When time is of the essence, being able to screen potential therapies with your personalized cancer avatar in under 10 days is fast.  Doing so with more accuracy than today’s sequencing or organoid approaches is huge. Through their growing list of strategic partnerships, OncoPrecision is screening, selecting, and speeding up the delivery of precision oncology.

What inspired you to start OncoPrecision?

Fighting cancer is the life purpose of OncoPrecision’s founders. As an academic spin-off, OncoPrecision follows the scientific journey of its CSO. Gaston Soria started working in cancer genetics during his MSc, which continued during his PhD training. After realizing that genetics was not sufficient to explain the complex behavior of cancer cells, he decided  to focus his postdoctoral training in the epigenetic field. Disappointed, and with the increasing conviction that every -omic only explains a single dimension of cancer, he founded a drug-discovery lab asking questions directly to the cancer cells.

He figured that cancer cells are the minimal unit that will provide us with reliable outputs for multidimensional phenoma, such as the response to anticancer agents. OncoPrecision originated as the evolution of cell-based screening technologies developed at Gaston’s Lab, but with its own fingerprint: working with cancer cells that directly derive from patients before therapy prescription. 

Why AML/ALL and how does your approach differ?

OncoPrecision’s MVP focuses on acute leukemias, with particular focus on AML. AML is a devastating disease, with about 50% of patients not responding to standard of therapies and with very common multi-resistant phenotypes. OncoPrecision’s technology can work with minimal biopsies, even utilizing the remaining pathological cells that are leftover from leukemia diagnosis samples. 

In other words, we work with the patients’ cells and combine them with two cell lines we’ve selected that enable us to replicate what’s going on in the tumor, so we can then analyze the response to different therapies. We decided to initially focus on AML because of its extremely high relapse rates and the challenge of patients responding favorably to the first line of treatment. AML also has the advantage of enabling us to use the patients’ blood for our analysis, rather than requiring invasive biopsies as other types of cancers might.

In other words, we take patient-derived cancer cells, culture them to mimic the body’s environment, screen for the best treatment. AML is a difficult cancer to cure, with higher than average relapse rates, but easier for us to approach as our first target. 

What made you realize you could accelerate the screening and selection process for cancer therapeutics? 

There are ex-vivo functional tests, such as patient-derived xenograft in mice (growing a tumor in a lab mouse) and organoids, which have had remarkable success in pre-clinical settings. However, due to their high costs and extended length (up to several months), the translation of these technologies into clinical settings failed thus far.

Our approach uses patient-derived cancer cells that are immediately set for screening in a triple co-culture setup that we call 2.5D Micro Cancer Avatars. Our platform allows us to obtain actionable results within 7 to 10 days, which is remarkably faster than current approaches. This is possible due to our extreme miniaturization procedure, which does not require the amplification of cancer cells, yet retains the clonal heterogeneity found in all cancers.

You already have a 15-person team coming from Argentina, can you tell us more about the cast of characters at OncoPrecision?

One of our Team’s pillars is Candelaria (Cande pronounced “Candy”) who is our master of organization and perfectionism at the lab. She’s been recognized by the Ministry of Science and Technology as one of the emerging female leaders in science (she’s also a leader within our team). We also have Gerardo who has a network of clinicians in Argentina like no other. He’s been elemental in rapidly building our network of clinics that are participating in our studies. Gaston is another pillar of our Team who we like to call “The Professor” (he’s actually Tarek’s Oncology tutor) for his incredible mentorship to our senior and junior talent. We would be lost without his guidance. Finally, Tarek is our youngest founder and the CEO.  After selling his first company, this second-time founder has learned OncoPrecision’s science quickly and is great at communicating that science and the vision. 

We have a multidisciplinary team that includes biotechnologists, geneticists, immunologists, bioengineers, biochemists and medical scientific liaisons. Moreover, it is remarkable that a big part of our team had a shared scientific history. Our team leaders and medical scientific liaison manager have worked together in academia for more than 5 years, developing strong professional and personal bonds that set the ground of OncoPrecision’s culture. 

We’re thrilled by the scientific progress we’ve made in such a short time since we founded the company in September 2020. The truth is that we couldn’t have come this far without the deep scientific talent that’s available in Argentina, combined with the unbeatable cost advantages (the ratio of scientists we could hire with the same seniority there vs. the US is about 7:1).

What are your plans for clinical studies? 

We’re now raising our Seed Round to move rapidly towards proving out the predictive power of our platform in clinical studies for AML patients, as well as beginning proof-of-concept for adapting our technology to be able to work with solid tumors. We’re also in the process of taking our first steps towards building our New York Hub, which will be the core of our US operations.

Precision oncology is a tough space to break into, tell us a bit about your advisors. 

We’re very excited about the advisors who have joined our journey over the past few months, both on the Business and Clinical sides. As our Business Advisor, we have Darrin Crisitello who has a wealth of experience building and scaling precision medicine businesses. He’s currently the Chief Commercial Officer of Mission Bio, a leading Single-Cell Sequencing startup and previously held leadership roles building the businesses of Color Genomics as well as Natera. As our Medical Advisor, we have Jorge Solimano, MD who leads Hematology at CEMIC, one of Latin America’s top cancer centers. Dr. Solimano has been elemental in designing our clinical validation milestones, as well as bringing his collaboration expertise with pharmaceutical companies to some key conversations. We actually are in the process of adding our third advisor who we’re thrilled about. We can’t say too much about her yet, but she’s a world-leading expert in heme malignancies and has done a tremendous amount of work to advance research in the field, as well as practiced as a leading clinician. 

What’s your vision for OncoPrecision in the future? 

Our mission is to dramatically improve cancer patient outcomes and ensure that each patient receives the best possible therapy. We envision a world where NO patient is prescribed therapy before understanding how the patient will respond to therapy.

Making plant-based foods without compromise. Lypid’s secret sauce: a sustainable, healthy and tastier fat alternative.

We’ve had an on again, off again relationship with fats.  One crucial challenge for plant-based foods is that they’re missing the fat.  Most of the time, they incorporate coconut oil as an ersatz lard or butter, and it’s simply not hitting the spot. As a B2B company, Lypid is putting a new spin on fats to bring lip-smacking goodness to the exploding plant-based meat category.  

Who is Lypid and what was its genesis?

I’m Jen-Yu, the co-founder and CEO of Lypid. I did my PhD in chemical engineering at Cornell where I actually did a lot of research on carbon capture. And I interviewed more than a hundred companies in 3 months to figure out whether there’s a way to commercialize the technology I was building in the lab. And what I figured out is that why not just eat less animal meat, then we don’t need to worry about capturing those carbon dioxide. Then that’s how I started my journey in the food space. And that I did try a lot of  alternative protein and plant-based meat on the market. But as a meat eater myself, I have to be honest, that current product is not there yet to totally change my diet and I happen to be a scientist. So I decided to do more research and study in this space and to figure out why plant-based meat doesn’t taste like real meat.

I’m also pretty lucky to have met my co-founder and Michelle at Cornell. We found out that fat is the key missing part to elevate the taste, texture and appearance of plant-based products. So that’s how we started our journey.

What is the fat you are making? 

We enable a tech that allows vegan oils to perform like animal fat. We take liquid vegan oils, and with our special processing technology and formulation strategy, it can perform like animal fat which stands above cooking temperature. The new vegan fat can cook above 165 degrees Celsius and it will still stay on the pan. No matter how you cook our new vegan fat, it behaves like real bacon fat.

How is Lypid’s technology going to deploy into the market? 

Currently, almost all of the alternative protein products on the market need improvements, especially in terms of tastes and textures. We think fat is the key missing part for such improvements. That’s why we decided that we would go with a B2B business model to elevate the entire alternative protein industry. We position ourselves as an upstream technology provider for other companies. Not only do we want to sell fat, but in the long term we also want to provide a high-tech full solution to the industry.

What has been the biggest thing you’ve learned during the IndieBio program?

I will say it’s getting connected to partners and talking to a lot of customers. Since Michelle and I are both scientists, both of us spent most of our time in the lab. So talking to people is very challenging in the beginning. At IndieBio, we learn to discover customers’ needs by utilizing our entrepreneurship and scientist mindset. In the past four months, we have talked with more than fifteen customers and are designing solutions for them.

“This is bone black” she said as she handed me a sample of jet black hair.  Silky smooth, shiny, and knottable — the bundle of plant-based hair extensions was, unmistakably, hair.

Aja Labs’ biodegradable, plant-based hair samples on display at IndieBio Batch 11’s Expo on 12 July 2021

Co-founded by Osahon Ojeaga and Suna Lumeh, Aja Labs is a direct-to-consumer company premiering at IndieBio San Francisco’s Demo Day on July 15th.  Their mission is to make superhuman hair, from plants, for healthier hair, healthier people, and a healthier planet.

Ojeaga’s vision sprang from her experiences using and selling hair extensions and braids.  During her travels through Asia, she grew disillusioned with the hair industry’s toll on the environment, users’ health, and the human exploitation powering human hair products.

After recruiting Chief Scientific Officer Dr. Mary Moore, a polymer engineer who had pivoted from R&D in the Department of Defense and Raytheon to starting her own natural products line to solve her daughter’s hair product allergies – the Aja Labs team developed two product-line prototypes for plant-based hairs.  They boast a growing following of users, stylists, and distributors alike. 

Aja Labs’ co-founder, Suna Lumeh, models their caramel-colored, plant-based hair at IndieBio Batch 11’s Expo

By some estimates, hair extension and braid users spend between $2000 and $5000 per year on hair extensions alone and no products exist that address the comfort and safety of the users while simultaneously creating minimal environmental or human cost in the production process.  Combining their vision, biotech and chemistry backgrounds, and extensive experience in the market the Aja team executed a two-pronged development plan — first a nourishing, biodegradable, biopolymer to improve the user experience and second a low energy, green chemistry approach directly transforming agricultural waste into supple, beautiful hair that rivals the natural products “donated” from India.  Seeing their technical development paths unfold, there is no question the team is committed to the overall vision for Aja Labs to give the consumer what she wants, ethically, sustainably, and healthfully.  

If you’re interested in learning more about Aja Labs, come to IndieBio SF’s Batch 11 Demo Day on July 15th and book your time with Osahon and Suna!

Eliminating excessive false positives is the holy grail in gene discovery – it saves money and time. Its Gene Discovery by Informationless Perturbation (GDIP) method has reduced false positive rates by 10-100x (depending on the trait and the organism) and they are bringing the power of GDIP to breeding climate-resilience traits into crops ranging from rice to rubber-producing plants. Avalo.ai is the seed company where sustainability and crop science are converging.

With a pinkish glow, the silvery door opened to reveal trays of dirt and seedlings.  Held at a cool 54°F, Avalo CEO Brendan Collins gingerly removes the trays and proceeds to count with surgical concentration. Two new seedlings had popped and, notably, one their algorithm predicted would be the highest performing knock-out.  

Based off a computational platform CSO Mariano Alvarez developed during his postdoctoral fellowship at Duke, Avalo’s ultra-fast, high sensitivity, and high accuracy gene discovery platform is being used to generate cold tolerant rice strains that can stave off the harvest shattering effects of weedy rice and late frosts. 

Gene discovery itself isn’t new, but the gold standard, Genome Wide Association Studies or GWAS, is fraught with a major problem: too many false positives.  A plant breeder who wants to target a specific trait is left with hundreds of gene targets to address, the vast majority of which are a waste of time (read: $20M dollars worth of time and effort wasted for each wrong gene target). 

We’ve seen how this type of baked-in R&D cost is passed down to the payers in pharmaceuticals. Outside of major row crops, the agriculture industry simply cannot bear these types of excessive development costs.  Enter Avalo’s Gene Discovery by Informationless Perturbation approach (GDIP, for short).  Powered by Prof. Cynthia Rudin’s pioneering work in interpretable artificial intelligence, Avalo is using GDIP to solve the urgent problem of developing climate-resilient crops to feed the next billion people.

The excitement around Avalo’s early data is palatable.  The 5 month old company has initiated four new academic and industry partnerships during IndieBio and last month it raised its Seed round.  Brendan and Mariano are building their team and churning out new performance data every week.

We are creating the genetic blueprints for the fastest sustainable transformation in agricultural history. 

Brendan Collins, CEO of Avalo

Yeah, totally!

Mariano Alvarez, CSO of Avalo

During SOSV’s IndieBio program we asked you prove your next generation gene discovery for the future of plants works. What did you discover? 

We needed to show one major thing: that GDIP–Gene Discovery via Informationless Perturbation–finds usable gene targets the first time. We decided to take some publicly-available data on cold tolerance in rice (a major problem for California growers) and try to find a target that we could break quickly and inexpensively. At the Phytotron in Duke University, we were able to validate four genes for cold tolerance over a three month experiment for about $15,000. Pretty good compared to the alternative!

Can you explain a little bit about how your predictive algorithm actually works relative to current approaches?

We know that biology is inherently complex. However, to interpret biology, we have to simplify the model and that is what we are doing every time we run a genome wide association study. This allows scientists to bring some interpretability to biology, but the downside is that it lets in hundreds of false positives. By employing interpretable machine learning we can create a much more realistic model of biology that doesn’t compromise on complexity and using our informationless perturbations (our proprietary technique to explain black box models) we can probe that model and make discoveries.

Why does predicting crop or plant phenotype matter?

Plant products are all around us – not just as food, but as cosmetics, perfumes, and industrial feedstocks. The phenotypes of the plants – from the color of an aesthetically pleasing flower to the ability of a crop to shrug off infection – usually have some genetic component that we can amplify to make the plant more useful.

The problem is that most traits are the result of complex architectures, many genes interacting with each other and the environment to produce the observable outcome. This makes both gene discovery and trait prediction… well, hard! Current genetic tools cannot accommodate this complexity. We make it easy.

Who is Avalo?

When we started this whole thing, we were just two scientists from North Carolina with a good idea. Mariano was a postdoctoral researcher at Duke University with a background in plant evolutionary and computational biology. Brendan has a background in cell and clinical biology and has spent the last seven years doing software development for startups around Durham. 

IndieBio really believed in us from a very early stage. Now, we’re growing to a team of 7 by the end of the year, with a team of superstar scientific advisors including Cynthia Rudin (head of the Prediction Analysis Lab at Duke) and Daniel Pomp (Professor Emeritus of Genetics at UNC Chapel Hill and co-founder of GeneSeek) as well as an amazing group of investors and supporters behind us. We feel pretty lucky.

We often joke that Avalo will develop partnerships on all 7 continents — from rice to wheat to dandelion to corals — do you think you will develop something for Antarctica?

That’s funny — our first in planta trial was cold tolerance in rice, so maybe we’ll just ratchet that up a bit. There are some cold tolerant varieties in Japan, so… maybe? In all seriousness, I think there are some really interesting opportunities to work on marine organisms in Antarctica – reefs, microbes, and even fish. We’d love to find a partner for those projects in the future!