The man behind Bezos’ next lunar guidance system talks future tech

Draper, the MIT spin-off engineering lab, is famed for developing the Apollo 11 Guidance Computer (not Draper Esprit, I hasten to add). Ken Gabriel, President and CEO, also recently made a major announcement. Blue Origin has now partnered with Lockheed Martin and Northrop Grumman to build elements of the company’s human-rated lunar lander, and Draper will lead the development of the lander’s avionics and guidance systems, with an aim to be ready to land a crew on the moon by 2024.

“While Blue Origin is the prime contractor, Lockheed Martin is building the ascent stage, Northrop Grumman is building the transfer element and Draper is doing the GNC (guidance, navigation and control),” Blue Origin CEO and founder Jeff Bezos said, announcing the move at the International Astronautical Congress in Washington. Blue Origin is competing for a NASA contract to develop a crewed lunar lander, or Human Landing System, for the Artemis program, which aims to return astronauts to the surface of the moon by the end of 2024.

TechCrunch sat down to chat with Gabriel, who previously he co-founded Google’s Advanced Technology and Projects (ATAP) group, to tlak about what he sees coming up in the future for the most advanced technologies. Prior to this, he was Deputy and Acting Director of the famed DARPA in the U.S. Department of Defense. During his tenure, DARPA advanced capabilities in hypersonics, offensive and defensive cyber, and big data analytics for intelligence and national security.

You’ve heard of CRISPR, now meet its newer, savvier cousin CRISPR Prime

CRISPR, the revolutionary ability to snip out and alter genes with scissor-like precision, has exploded in popularity over the last few years and is generally seen as the standalone wizard of modern gene-editing. However, it’s not a perfect system, sometimes cutting at the wrong place, not working as intended and leaving scientists scratching their heads. Well, now there’s a new, more exacting upgrade to CRISPR called Prime, with the ability to, in theory, snip out more than 90% of all genetic diseases.

Just what is this new method and how does it work? We turned to IEEE fellow, biomedical researcher and dean of graduate education at Tuft University’s school of engineering Karen Panetta for an explanation.

How does CRISPR Prime editing work?

CRISPR is a powerful genome editor. It utilizes an enzyme called Cas9 that uses an RNA molecule as a guide to navigate to its target DNA. It then edits or modifies the DNA, which can deactivate genes or insert a desired sequence to achieve a behavior. Currently, we are most familiar with the application of genetically modified crops that are resistant to disease.

However, its most promising application is to genetically modify cells to overcome genetic defects or its potential to conquer diseases like cancer.

Some applications of genome editing technology include:

  • Genetically modified mosquitos that can’t carry malaria.
  • In humans, “turning on” a gene that can create fetal type behaving cells that can overcome sickle-cell anemia.

Of course, as with every technology, CRISPR isn’t perfect. It works by cutting the double-stranded DNA at precise locations in the genome. When the cell’s natural repair process takes over, it can cause damage or, in the case where the modified DNA is inserted at the cut site, it can create unwanted off-target mutations.

Some genetic disorders are known to mutate specific DNA bases, so having the ability to edit these bases would be enormously beneficial in terms of overcoming many genetic disorders. However, CRISPR is not well suited for intentionally introducing specific DNA bases, the As, Cs, Ts and Gs that make up the double helix.

Prime editing was intended to overcome this disadvantage, as well as other limitations of CRISPR.

Prime editing can do multi-letter base-editing, which could tackle fatal genetic disorders such as Tay-Sachs, which is caused by a mutation of four DNA letters.

It’s also more precise. I view this as analogous to the precision lasers brought to surgery versus using a hand-held scalpel. It minimized damage, so the healing process was more efficient.

Prime editing can insert, modify or delete individual DNA letters; it also can insert a sequence of multiple letters into a genome with minimal damage to DNA strands.

How effective might Prime editing be?

Imagine being able to prevent cancer and/or hereditary diseases, like breast cancer, from ever occurring by editing out the genes that are makers for cancer. Cancer treatments are usually long, debilitating processes that physically and emotionally drain patients. It also devastates patients’ loved ones who must endure watching helpless on the sidelines as the patient battles to survive.

“Editing out” genetic disorders and/or hereditary diseases to prevent them from ever coming to fruition could also have an enormous impact on reducing the costs of healthcare, effectively helping redefine methods of medical treatment.

It could change lives so that long-term disability care for diseases like Alzheimer’s and special needs education costs could be significantly reduced or never needed.

How did the scientific community get to this point — where did CRISPR/prime editing “come from?”

Scientists recognized CRISPR’s ability to prevent bacteria from infecting more cells and the natural repair mechanism that it initiates after damage occurs, thus having the capacity to halt bacterial infections via genome editing. Essentially, it showed adaptive immunity capabilities.

When might we see CRISPR Prime editing “out in the wild?”

It’s already out there! It has been used for treating sickle-cell anemia and in human embryos to prevent HIV infections from being transmitted to offspring of HIV parents.

So, what’s next?

IEEE engineers, like myself, are always seeking to take the fundamental science and expand it beyond the petri dish to benefit humanity.

In the short term, I think that Prime editing will help generate the type of fetal like cells that are needed to help patients recover and heal as well as developing new vaccines against deadly diseases. It will also allow researchers new, lower cost alternatives and access to Alzheimer’s like cells without obtaining them post-mortem.

Also, AI and deep learning is modeled after human neural networks, so the process of genome editing could potentially help inform and influence new computer algorithms for self-diagnosis and repair, which will become an important aspect of future autonomous systems.

A chat about UK deep tech and spin-out success with Octopus Ventures

New research commissioned by UK VC firm Octopus Ventures has put a spotlight on which of the country’s higher education institutions are doing the most to support spin outs. The report compiles a ranking of universities, foregrounding those with a record of producing what partner Simon King dubs “quality spin outs”.

The research combines and weights five data points — looking at university spinouts’ relative total funding as a means of quantifying exit success, for example. The idea for the Enterpreneurial Impact Ranking, as it’s been called, is to identify not just those higher education institutions with a track record of encouraging academics to set up a business off the back of a piece of novel work but those best at identifying the most promising commercialization opportunities — ultimately leading to spinout success (such as an exit where the company was sold for more than it raised).

Hence the report looking at data over almost a ten year period (2009-2018) to track spin-outs as they progress from an idea in the lab through prototyping to getting a product to market.

The ranking looks at five factors in all: Total funding per university; total spinouts created per university; total disclosures per university; total patents per university; and total sales from spinouts per university.

Topping the ranking is Queen’s University Belfast which the report notes has had a number of notable successes via its commercialization arm, Qubis, name checking the likes of Kainos (digital services), Andor Technology (scientific imaging) and Fusion Antibodies (therapeutics & diagnostics), all of whom have been listed on the London Stock Exchange.

The index ranks the top 100 UK universities on this entrepreneurial impact benchmark — but the rest of the top ten are as follows:

2) University of Cambridge
3) Cardiff University
4) Queen Mary University of London
5) University of Leeds
6) University of Dundee
7) University of Nottingham
8) King’s College London
9) University of Oxford
10) Imperial College London

Octopus Ventures says the ranking will help it to get a better handle on which universities to spend more time with as it searches for its next deep tech investment.

It also wants to increase visibility into how the UK is doing when it comes to commercializing academic research to feed further growth of the ecosystem by sharing best practice, per King.

“We are looking at a number of data points which are all self-reported by the universities themselves to the Higher Education Statistics Agency. And then we combine those in the way that we think brings out at a higher level which universities are doing a good job of spinning out companies,” he says.

“It means that you take into consideration which university is producing quality spin-outs. So it’s not just spray and pray and get lots of stuff out there. But actually which universities are creating spin-outs that then go on to return value back to them.”

Microsoft uses AI to diagnose cervical cancer faster in India

More women in India die from cervical cancer than in any other country. This preventable disease kills around 67,000 women in India every year, more than 25% of the 260,000 deaths worldwide.

Effective screening and early detection can help reduce its incidence, but part of the challenge — and there are several parts — today is that the testing process to detect the onset of the disease is unbearably time-consuming.

This is because the existing methodology that cytopathologists use is time consuming to begin with, but also because there are very few of them in the nation. Could AI speed this up?

At SRL Diagnostics, the largest chain to offer diagnostic services in pathology and radiology in India, we are getting an early look of this. Last year, Microsoft partnered with SRL Diagnostics to co-create an AI Network for Pathology to ease the burden of cytopathologists and histopathologists.

SRL Diagnostics receives more than 100,000 Pap smear samples every year. About 98% of these samples are typically normal and only the remaining 2% samples require intervention. “We were looking for ways to ensure our cytopathologists were able to find those 2% abnormal samples faster,” explained Dr. Arnab Roy, Technical Lead for New Initiatives & Knowledge Management at SRL Diagnostics.

Cytopathologists at SRL Diagnostics studied digitally scanned versions of Whole Slide Imaging (WSI) slides, each comprising about 300-400 cells, manually and marked their observations, which were used as training data for Cervical Cancer Image Detection API.

A digitally scanned version of a Whole Slide Imaging (WSI) slide, which is used to train the AI model

Then there was the challenge of subjectivity. “Different cytopathologists examine different elements in a smear slide in a unique manner even if the overall diagnosis is the same. This is the subjectivity element in the whole process, which many a time is linked to the experience of the expert,” reveals Dr. Roy.

Manish Gupta, Principal Applied Researcher at Microsoft Azure Global Engineering, who worked closely with the team at SRL Diagnostics, said the idea was to create an AI algorithm that could identify areas that everybody was looking at and “create a consensus on the areas assessed.”

Cytopathologists across multiple labs and locations annotated thousands of tile images of cervical smear. They created discordant and concordant notes on each sample image.

“The images for which annotations were found to be discordant — that is if they were viewed differently by three team members — were sent to senior cytopathologists for final analysis,” Microsoft wrote in a blog post.

This week, the two revealed that their collaboration has started to show results. SRL Diagnostics has started an internal preview to use Cervical Cancer Image Detection API. The Cervical Cancer Image Detection API, which runs on Microsoft’s Azure, can quickly screen liquid-based cytology slide images for detection of cervical cancer in the early stages and return insights to pathologists in labs, the two said.

The AI model can now differentiate between normal and abnormal smear slides with accuracy and is currently under validation in labs for a period of three to six months. It can also classify smear slides based on the seven-subtypes of cervical cytopathological scale, the two wrote in a blog post.

During the internal preview period, the exercise will use more than half-a-million anonymized digital tile images. Following internal validation, the API will be previewed in external cervical cancer diagnostic workflows, including hospitals and other diagnostic centers.

“Cytopathologists now have to review fewer areas, 20 as of now, on a whole slide liquid-based cytology image and validate the positive cases thus bringing in greater efficiency and speeding up the initial screening process,” Microsoft wrote.

“The API has the potential of increasing the productivity of a cytopathology section by about four times. In a future scenario of automated slide preparation with assistance from AI, cytopathologists can do a job in two hours what would earlier take about eight hours!” Dr. Roy said.

SRL Diagnostics-Microsoft consortium said they are hopeful their APIs could find application in other fields of pathology such as diagnosis of kidney pathologies and in oral, pancreatic and liver cancers. The consortium also aims to expand its reach with tie-ups with private players and governments and expand the reach of the model even in remote geographies where the availability of histopathologists is a challenge.

The announcement this week is the latest example of Microsoft’s ongoing research work in India. The world’s second most populous nation has become a test bed for many American technology companies to build new products and services that solve local challenges as they look for their next billion users worldwide.

Last week, Microsoft announced its AI project was helping improve the way driving tests are conducted in India. The company has unveiled a score of tools for the Indian market in the last two years. Microsoft has previously developed tools to help farmers in India increase their crop yields and worked with hospitals to prevent avoidable blindness. Last year, the company partnered with Apollo Hospitals to create an AI-powered API customized to predict risk of heart diseases in India.

Also last year, the company also worked with cricket legend Anil Kumble to develop a tracking device that helps youngsters analyze their batting performance. Microsoft has also tied up with insurance firm ICICI Lombard to help it process customers’ repair claims and renew lapsed policies using an AI system.

Medopad raises $25M led by Bayer to develop biomarkers tracked via apps and wearables

Medopad, the UK startup that has been working with Tencent to develop AI-based methods for building and tracking “digital” biomarkers — measurable indicators of the progression of illnesses and diseases that are picked up not with blood samples or in-doctor visits but using apps and wearables, has announced another round of funding to expand the scope of its developments. It has picked up $25 million led by pharmaceuticals giant Bayer, which will be working together with Medopad to build digital biomarkers and therapeutics related to heart health. Medopad said it is also working on separate biomarkers related to Parkinson’s, Alzheimer’s and Diabetes.

The Series B is being made at a post-money valuation of between $200 million and $300 million. In addition to Bayer, Hong Kong firm NWS Holdings and Chicago VC Healthbox also participated. All three are previous investors, with NWS leading its $28 million Series A in 2018, bringing the total raised by Medopad to over $50 million. It also comes on the heels of the company signing a high-profile deals totalling some $140 million with a string of firms in China, including Tencent, Ping An, and the Chinese divisions of GSK, Johnson & Johnson and more.

The world where medicine mixes with tech in the name of doing things faster, better and with less expense had a big knock with the rise and calamitous fall of Theranos, the blood-testing startup that claimed to have developed technology to perform a multitude of tests tracking biomarkers using only a few drops of blood — tests that used to require significantly more blood (and expense) to run accurately. Great concept, if only it weren’t a scam.

While Medopad also tracks biomarkers, it’s taking a very different, non-invasive route to building its solutions. The company constructs its algorithms and tracking working with pharmaceutical and tech partners to build the solution end-to-end, leaning on advances in software and hardware to fulfil ideas that have been unattainable goals for a long time.

“For the past 25 years, we have been talking about this connected healthcare, but no one has doe it,” CEO Dan Vahdat, who co-founded the company with Rich Khatib, said in an interview. “The nature of the concept has just been too challenging. The approach is established but the computing and device technology wasn’t able to detect and read these things outside of hospital settings.”

In one example, a classic Parkinson’s test would have required a patient to go to into a doctor’s office for a 30-minute assessment to determine how a patient is walking. In recent times, however, with the advent of advanced computer vision and far better sensors on devices, a new category of digital biomarkers, as Vahdat calls them, are being created — for example, by tracking how a person is walking — her/his gait and other metrics — to provide similar guidance to a clinician on the patient’s progress. “These can be collected, for example, based on how you walk and talk, along with other vital signs,” he said.

The startup is also working with teaching hospitals to build other clinical trials. For example it has a partnership with the Royal Wolverhampton to better track Aortic Stenosis, when heart valves narrow and restrict blood flow.

“This is a very exciting project and fits with our ethos of ‘proactive’ and ‘one to many care’ which, we think, will benefit patients and release valuable clinical time,” said Professor James Cotton at The Royal Wolverhampton NHS Trust, in a statement.

Longer term, it’s also working with Janssen (a division of Johnson & Johnson) a possible way of tracking early signs and progress of Alzheimers by way of cognitive tests that someone can take at home.

Medopad has a healthy approach to the work it is doing reminiscent of the kind of collaboration that is typical in the world of science, which perhaps is the aspect that sets it apart best from the vapourware of the world. “We won’t claim that we can do what others can’t, but we are using foundations that were built years ago, to discover and commercially deploy solutions via our channel.” He added that Babylon in the UK and Collective Health in the UK are two companies he admires for taking a similar approach in their respective fields of doctor/patient care and health insurance.

The fact that the company works so closely with Tencent and other Chinese companies is notable at a time when there is a lot of scrutiny of China and how its companies may be using or working with personal data in countries like the US and UK. Vahdat said that all patient data is only collected with consent, and if any data from Medopad is passed to its partners, it’s anonymised. A patient’s data, furthermore, does not leave the country in which it is collected.

The Tencent partnership, he added, was largely to help build the company’s AI engine, with China’s massive population providing a ripe background to train machine learning algorithms.

Medopad’s main asset, in any case, is not data, but the algorithms and methods it uses to collect and process digital biomarkers.

“We are a big believer in the fact that data is not our product,” he said. “That is something we are really proud of.”

Will unreliable research bury your healthcare startup?

For healthtech founders and funders, scientific claims and conclusions are more than policy — business models depend upon the lucid appraisal of clinical problems, evaluating inadequacies in current standards of care, a clear understanding of disease pathways, and designing superior interventions. 

At each step along this value chain, founders stand on the shoulders of the scientists that preceded them to obtain reliable evidence. When they promote their own innovations, credibility is a critical prerequisite. But where does credibility come from?

A 2012 study selecting 50 common cookbook ingredients found that 80% had publications linking their consumption to cancer risk; according to some reports, tomatoes, lemons, and celery all cause cancer. The to-and-fro of nutrition science is emblematic of a larger dynamic related to fickle research findings across disciplines. Because investigators seeking to build upon seminal studies struggle to reproduce the original findings, researchers have deemed the problem a reproducibility crisis

Simulations have found that up to 85% of published findings could not be replicated. In turn, tens of billions of dollars are wasted and countless patient lives are adversely impacted annually due to unreliable research. 

Historically, academic research and healthcare VC have had considerable overlap, but in recent years, this co-dependence has increased as researchers are looking more and more for financial support. Government research funding has seen a steady decline, with private sources now supporting almost 60% of the spend. Biomedical VC has been portrayed as a critical source of risk capital for early-stage research and a key engine for its translation at later stages.

UK biotech startup Mogrify injects $16M to get novel cell therapies to market soon

Cambridge, UK-based biotech startup Mogrify, which is working on systematizing the development of novel cell therapies in areas such as regenerative medicine, has closed an initial $16 million Series A.

The raise from investors Ahren Innovation CapitalParkwalk and 24Haymarket follows a $4M seed in February — taking its total raised to date to $20M.

Put simply, Mogrify’s approach entails analysis of vast amounts of genomic data in order to identify the specific energetic changes needed to flip an adult cell from one type to another without having to reset it to a stem cell state — with huge potential utility for a wide variety of therapeutic use-cases.

“What we’re trying to do with Mogrify is systematize that process where you can say here’s my source cell, here’s my target cell, here are the differences between the networks… and here are the most likely points of intervention that we’re going to have to make to drive the fate of an adult cell to another adult cell without going through a stem cell stage,” says CEO and investor Dr Darrin Disley.

So far he says it’s successfully converted 15 cells out of 15 tries.

“We’re now rapidly moving those on through our own programs and partnership programs,” he adds.

Mogrify’s business has three main components: Internal program development of cell therapies (current cell therapies it’s developing include enhancing augmented cartilage implantation; non-invasive treatment of ocular damage; and for blood disorders). It’s also developing a universal source of cells for use in immunotherapy — to act as “disease-eaters”, as Disley puts it.

Speculative IP development is another focus. “Because of the systematic nature of the technology we’re in a position very rapidly to identify areas of therapy that have particular cell conversions at their essence — and then drive that IP generation around those cells very quickly and create an IP footprint,” he says.

Partnering deals is the third piece. Mogrify is also working with others to co-develop and bring targeted cell therapies to market. Disley says it’s already closed some partnerships, though it’s not announcing any names yet.

The startup is drawing on around a decade’s worth of recent work genomics science. And specifically on a data-set generated by an international research effort, called Fantom 5, which its founders had early access to.

“We started with that massive Fantom data-set. That’s the baseline, the background if you like. Think of it like two cities in America: Chicago and New York. There’s your source cell, there’s your target cell. And because you have all the background data of every piece of the network — every building, every skyscraper — if you look at the two you can identify the difference in the gene expression, therefore you can identify which factors will regulate a wide array of those genes. So you can start identifying the differences between the two,” explains Disley.

“We’ve then added to that massive data sets in DNA-protein and protein-protein interactions… so you start to now overlay all of that data. And then we’ve added on top of that new next-gen sequencing data and epigenetic data. So you’ve now got this massive data-set. It’s like having a network map between all the different cell types. So you’re therefore then able to make predictions on how many interventions, what interventions are needed to drive that change of state — and it’s systematic. It doesn’t just recommend one set. There’s a ranking. It can go down to hundreds. And there is some overlap and redundancies, so for example if one — you’re preferred thing — doesn’t work the way you wanted it to you can go back and select another.

“Or if there’s an IP issue around that factor you can ignore that piece of the network and use an alternative route. And once you’ve got to your target cell, if it needs to some tweaking you can actually re-sequence it and take that back and that’s your starting cell again. And you can go through this optimization process. So what comes out at the other end… you’ve got a patent that it like a small molecule composition of matter patent; it’s the therapeutic. So you’re not coming out with the target, you’re actually coming out with here is the composition of matter on the cell.”

In terms of timeframe for getting novel cell therapies from concept to market Disley suggests a range of between four and seven years.

“Once you’ve identified the cell type that can be be the basis of your GMP manufacturable process and then you can tweak that to take it to the therapeutic indication you can develop a cell therapy and bring that to market in five years,” he says. “It’s not like the old days with small molecules where it can take ten, 15, 20 years to get a serious therapy on the market.

“When you’re treating patients… is because there are no other treatments for them, when you go into phase two and do your safety study [and] efficacy study you’re actually treating patients already in terms of their disease. And if you get it right you can get a fast track approval. Or a conditional approval… so that you may not even have to do a phase 3 [testing].”

“We’re not using any artificial intelligence here,” he also emphasizes, pointing to his experience investing in companies in the “big extreme data space” which he argues do best by using “unbiased approaches”.

“AI I think is still trying to find its way,” he continues. “Because in its essence it will be able to get to answers with smaller amounts of data but it’s only as good as the data you train it on. And the danger with AI… it just learns to recognize what you want it to recognize. It doesn’t know what it doesn’t know.

“In combination, once you continue to generate this massive cell network data etc you can start applying aspects of machine learning and AI. But you couldn’t do Mogrify with AI without the data. You have to do it that way. And the data is so complex and combinatorial — 2,000 transcription factors, in terms of regulation of those genes, they then interact in network to do the protein-protein interactions, you’ve got epigenetic aspects of that, you could even start adding cell microbiome effects to that later — so you’ve got a lot of factors that could influence the phenotype of the cell that’s coming out the other end.

“So I think with AI you have to be a little careful. I think it will be a more optimizing tool once you’ve got sufficient confidence in your system.”

The plan for the Series A funding is to ramp up Mogrify’s corporate operations and headcount — including bringing in senior executives and expertise from industry — as well as spending to fund its therapy development programs.

Disley notes its recent appointment of Dr Jane Osbourn as chair as one example.

“We’re bringing in more people with a lot of cell therapy experience from big pharma, around then more on the manufacturing and delivery of that — so really building so that we’re not just a tech company,” he says. “We’ve very strong already, we’re already 35 people on the tech and early stage drug discovery side — we’re going to add another 30 to that. But that’s going to be increasingly more people with big pharma, cell therapy development, manufacturing experience to get products on to market.”

Partner search is another focus for the Series A. “We’re trying to find the right strategy partners. We’re not doing services, we’re not doing products — so we want to find the right strategic partners in terms of doing multi-programs in a partnership,” he adds. “And then a series of more tactical deals where people have got a specific problem with a cell conversion. These more turnkey deals, if you like. We still get up-fronts, milestones and royalties but they’re smaller.”

Despite now having enough money for the next two to two and half years it’s also leaving the Series A open to continue expanding the round over the next 12 months — up to a maximum of another $16M.

“We have so many interested investors,” Disley tells us. “This round we didn’t actually open our round. We did it with internal investors and people we’re very close to who we’ve worked with before, and there were investors lining up… [so] we are leaving it open so that in these next 12 months we may choose to increase the amount we bring in.

“It would be a maximum of another $16M if it was an A round but we may decide just to go straight forward if we progress very fast to a much bigger B round.” uses machine learning to make synthesizing new drugs a snap

Say you’re a pharmaceutical company. You’ve figured out that a novel molecule could be effective in treating an illness — but that molecule only exists in a simulation. How do you actually make it, and enough of it, to test in the real world? is a computational chemistry platform that helps bring theoretical substances to life, and it is debuting its product onstage at Disrupt SF Startup Battlefield.

Computational chemistry is, believe it or not, something of a hot ticket right now. The explosion in computing resources over the last decade has made it possible for the extremely complex systems of molecular biology to be simulated in high enough fidelity to produce new drugs and other important substances.

For example, say a company knows that a condition is caused by overproduction of a given protein. By simulating that protein in the soup of the cell environment, computational chemists can also introduce and virtually observe the behavior of thousands or millions of molecules that don’t occur naturally but might, say, lock down those excess proteins and tag them for removal by the cell.

This process of drug discovery has been productive, but unlike in the real world, in a simulation you don’t actually have to make that magical molecule. It’s just a bunch of numbers interacting with other numbers. How can a pharmaceutical company, which may have paid a lot of money for those numbers, turn them into actual molecules? That’s where steps in.

1.4.0 Molecule Dashboard Reaction tree

Essentially, the company has created a software platform that automates the process of getting from chemicals A, B, and C to chemical Z, with the many steps in between accounted for and documented. It’s based on a machine learning system that has ingested millions of patents and known chemical processes, allowing it to connect the dots and propose a method for creating pretty much any complex organic molecule. In other words, once a drug company has the “what” — a molecule or compound that may fight Alzheimer’s — provides the “how.”

Piotr Byrski met co-founder Paweł Włodarczyk-Pruszyński (who goes by Maxus to avoid confusion with COO Paweł Łaskarzewski) while in college, where they studied and did research together, eventually both earning MDs. They discovered a shared aversion to the grunt work of chemistry — beakers, distillates, titration, and so on.

molecule one header


“We found out we shared a similar analytical approach to chemistry. A lot of chemists really like the cooking process involved with organic synthesis,” Byrski told me. “I have to say… I never liked it very much. That made me think that there are many things in the everyday life of a chemist that can be automated, and need to be automated.”

“Automating organic synthesis seems like just another difficult automation problem, but it’s one with real effects. Real people are suffering because drugs are coming to the market,” he said. “We thought we could help. So we did some research, and we found that the field is so under-developed —  the direction research is going is completely unsatisfactory. We began market research — we were both first timers so it was pretty new to us at the time — and we found out there was a big market need for this. It wasn’t a scientific discovery that would sit on a shelf, it could be applied today to help multiple industries.”

By the time they were working on this, companies were already applying simulation, and statistical techniques (machine learning is essentially weapon-grade statistical analysis) were already popping up. BenevolentAI started in 2013, Recursion in 2014, Atomwise in 2015; clearly the field was growing, and is still adding new companies, like ReviveMed. But these are mainly focused on the question of new drugs based on simulations.

“They provide a list of maybe tens of thousands of structures to a pharmaceutical company, but the company then needs to actually verify whether the predictions have any real-life backing. For that you need physical access to these molecules — just knowing the structure doesn’t cut it,” said Byrski.’s system tells them how to manifest these structures.

1.1.1 Molecule Dashboard Compounds

“We are making the whole synthesis pathway, so going from compounds that are available to ones that you want,” said Włodarczyk-Pruszyński. “Along the way we need to solve many problems — there are many reasons why a reaction could fail. We want to tell users how to make compounds with the process with the highest chance of success.”

And succeed they have: “Our system works for structures that have never been seen before by any chemist,” Byrski said.

The obvious question is why these huge pharma companies, with their bottomless pockets and technical expertise, don’t put together their own synthesis platforms. It comes down to people.

“The most important factor is that it’s hard for a pharmaceutical company to hire machine learning specialists who have a deep background in chemistry. Over 90 percent of the people I know that work on this in the pharmaceutical business are chemists who have some training in machine learning. This is a difficult problem that requires coming at it from the opposite direction,” Byrski explained. “Our head of machine learning [Stanislaw Jastrzębski] is a PhD from the computational side, who would normally go to Google, Facebook or Microsoft. We’ve built a team that is unique in how it bridges the computational technology and chemistry.”

The databases used by’s systems, surprisingly, are mostly public. The U.S. Patent office has tons of patents involving chemical processes — some important, some small, some obscure, some obvious, but all verified and presented formally. This was a gold mine sitting in plain sight, Byrski said. Or perhaps a box full of Lego pieces just waiting to be assembled into the right machine.

The main “proprietary” information they used was a private listing of commercially available chemicals and their prices. A molecule may have more than one pathway to reach it, after all, or perhaps thousands, and one might be cheaper than the others or involve fewer toxic reagents.

With strong results from public databases, they have a better chance of getting pharma companies to share their internal databases when signing up for the service.

The actual business is conducted SaaS-wise, naturally, and all the work takes place in the cloud. There’s also an enterprise tier that allows for on-premises operation, for companies that would rather not have their trade secrets anywhere but on company-owned infrastructure.

So far the company has bootstrapped, and currently has about $400K in the bank, which Byrski said should last them well into next year. “The biggest cost is people,” he said. “Developers, designers, chemists. We’re a software business so we don’t have a lot of other costs — we don’t have to hire a lab, for example.” So they are looking for funding to help hire and scale.

It’s not common in Poland to segue directly from medical school into a startup, Byrski admitted. But he and Włodarczyk-Pruszyński felt that this was too significant an opportunity to do good to pass up. With luck their platform will prove as popular as the drug discovery startups that helped make it necessary to invent.

Biology as technology will reinvent trillion-dollar industries

We face two major threats today: one to the health of our planet and the other to our own. The U.N. says the global population will hit 9.7 billion by 2050, meaning more people consuming more natural resources than at any point in human history. Consumption is already doubling every 10-12 years. Add to that the challenges of a warming planet. On the human health front, some 30% of young people under age 20 are obese, 31% of deaths are from cardiovascular disease, and cancer cases are growing at a rate twice as fast as the population.

Fortunately, biology and technology are creating fixes for the planet as well as for the human body. As they do so, they are poised to reinvent countless industries, giving rise to what I believe is a golden age for biology as technology. As Arvind Gupta, the founder of health-science accelerator IndieBio, argued in one recent Medium post, “the twin catastrophes of planetary and human health” will create a $100 trillion opportunity.

Before I tell you how, here is an extremely brief history of the field. Biology, of course, is the original technology. Our tinkering with life’s building blocks, and our ancestor’s manipulation of plants and herbs as medicines and their use of neem branches as toothpaste or the cultivation of plants like corn has been going on for millennia. It wasn’t until the 1970s and 1980s that we saw the first flowering of today’s modern biotech industry.

In 1972, Robert A. Swanson helped launch the birth of biotech when he co-founded Genentech, which became a pioneer in the field of recombinant DNA technology. By creating novel DNA sequences in the lab, Genentech was able to synthesize human insulin for diabetics (1982), and create growth hormones for kids who suffered from a hormone deficiency (1985).

Among the other early leaders in the field was Applied Molecular Genetics (today known as Amgen). In 1989, it won approval for the first recombinant human erythropoietin drugs to treat anemia in people with chronic kidney failure, and later to treat anemia in HIV patients. Last year, the $23.75 billion company’s best-selling drugs were Neulasta, used to prevent infections in cancer patients undergoing chemotherapy, and Enbrel, to treat some autoimmune diseases.

Startups working in these fields are creating entirely new industries, disrupting others and bringing us into what I believe is a golden era of biology as technology.

Today, innovative researchers are building on those early technologies. Among the most promising is the discovery of the CRISPR-Cas9 gene-editing technique. Using what they refer to as molecular scissors, scientists can use CRISPR to edit a living person’s DNA, deleting or repairing damaged sections. Because the changes are made at the genome, the DNA fix is hereditary, unlike previous fixes that affect only the individual patient. The technique promises to slow if not eradicate cancer. It could also prevent sickle cell disease, cystic fibrosis, hemophilia and heart disease.

Notwithstanding the concern over creating designer babies (and the recent controversial creation of the first gene-edited babies in China), it promises to fortify our bodies for us, those of our kids and all succeeding generations. Co-founded by Jennifer Doudna, a leader in the CRISPR field, Mammoth Biosciences is on a mission to leverage the power of CRISPR to democratize disease detection by bringing accurate and affordable testing out of the laboratory and into the point-of-care.

Other technologies, like DNA sequencing, cell engineering and bioprinting, have led to the creation of animal-free protein products, bio fuels for jet engines, lightweight materials stronger than steel and even memory for computer storage. As a result, startups working in these fields are creating entirely new industries, disrupting others and bringing us into what I believe is a golden era of biology as technology.

One successful company is Beyond Meat, which bills itself as the future of protein. With its plant-based meat product, it is trying to address our global population’s need for protein while also tackling the cow problem (they consume land and water and destroy the ozone with their flatulence, not to mention some people think eating them is wrong). The company’s work promises to disrupt the $270 billion global meat industry.

The entrepreneurs at New Culture are also tackling the cow issue. They are using an engineered version of baker’s yeast to make cheese without milk. Unlike other vegan cheeses, made from soy or nuts, this one has been praised as tasting like the real thing.


Another area ripe for disruption is our home. The startup Lingrove is trying to lessen our reliance on trees, and the deforestation that comes with it, by creating wood products with flax fiber and bio-epoxy resin. With its Ekoa TP product, Lingrove is targeting the $80 billion interior market, with an eye toward using its products in the construction industry. Another player in this field is bioMASON. The making of concrete contributes massive amounts of carbon to the air. But this company has shown it can “grow” bricks and masonry from sand without using a traditional heating-blasting-process, by infusing the sand with microorganisms that initiates a process like the one that creates coral.

There’s no telling where this golden age of biology as technology will lead.

And then there’s transportation, the No. 1 global contributor of greenhouse gasses. Companies like Amyris are trying to do away with fossil fuels by turning genetically engineered yeast (i.e. sugar) into environmentally friendly gas and jet fuel.

And that’s not all. There are many more biology as technology stories, with innovative companies doing things like turning mushrooms into leather (MycoWorks), molecules into whiskey (Endless West) and bacteria into silk (Bolt Threads). Biology might even reinvent information technology. Scientists have shown how a few grams of DNA can store as much information as an entire data center (Microsoft is working on this). Another company is building computers from neurons (Airbus is a partner).

There’s no telling where this golden age of biology as technology will lead, how many products it will come up with and how many industries it will end up disrupting, or creating. But it seems destined to reinvent trillion-dollar industries and create a healthier planet where we can live longer, healthier lives.

Disclosure: Genentech and Amgen are Mayfield investments from the 1970s and 1980s. Mammoth Biosciences is a current investment.

At-home blood testing startup Baze rakes in $6 million from Nature’s Way

By now, the venture world is wary of blood testing startups offering health data from just a few drops of blood. However, Baze, a Swiss-based personal nutrition startup providing blood tests you can do in the convenience of your own home, collects just a smidgen of your sanguine fluid through an MIT manufactured device, which, according to the company, is in accordance with FDA regulations.

The idea is to find out (via your blood sample) which vitamins you’re missing out on and are keeping you from living your best life. That seems to resonate with folks who don’t want to go into the doctor’s office and separately head to their nearest lab for testing.

And it’s important to know if you are getting the right amount of nutrition — Vitamin D deficiency is a worldwide epidemic affecting calcium absorption, hormone regulation, energy levels and muscle weakness. An estimated 74% of the U.S. population does not get the required daily levels of Vitamin D.

“There are definitely widespread deficiencies across the population,” Baze CEO and founder Philipp Schulte tells TechCrunch. “[With the blood test] we see that we can actually close those gaps for the first time ever in the supplement industry.”

While we don’t know exactly how many people have tried out Baze just yet, Schulte says the company has seen 40% month-over-month new subscriber growth.

That has garnered the attention of supplement company Nature’s Way, which has partnered with the company and just added $6 million to the coffers to help Baze ramp up marketing efforts in the U.S.

Screen Shot 2019 08 30 at 2.27.12 PMI had the opportunity to try out the test myself. It’s pretty simple to do. You just open up a little pear-shaped device, pop it on your arm and then press it to engage and get it to start collecting your blood. After it’s done, plop it in the provided medical packaging and ship it off to a Baze-contracted lab.

I will say it is certainly more convenient to just pop on a little device myself — although it might be tricky if you’re at all squeamish, as you’ll see a little bubble where the blood is being sucked from your arm. For anyone who hesitates, it might be easier to just head to a lab and have another human do this for you.

The price is also nice, compared to going to a Quest Diagnostics or LabCorp, which can vary depending on which vitamins you need to test for individually. With Baze it’s just $100 a pop, plus any additional supplements you might want to buy via monthly subscription after you get your results.

Baze’s website will show your results within about 12 days (though Schulte tells TechCrunch the company is working on getting your results faster). It does so with a score and then displays a range of various vitamins tested.

I was told that, overall, I was getting the nutrients I require with a score of 74 out of 100. But I’m already pretty good at taking high-quality vitamins. The only thing that really stuck out was my zinc levels, which I was told was way off the charts high after running the test through twice. Though I suspect, as I am not displaying any symptoms of zinc poisoning, this was likely the result of not wiping off my zinc-based sunscreen well enough before the test began.

For those interested in conducting their own at-home test and not afraid to prick themselves in the arm with something that looks like you might have it on hand in the kitchen, you can do so by heading over to Baze and signing up.