science
Auto Added by WPeMatico
Decades-old ASCII adventure NetHack may hint at the future of AI
Machine learning models have already mastered Chess, Go, Atari games and more, but in order for it to ascend to the next level, researchers at Facebook intend for AI to take on a different kind of game: the notoriously difficult and infinitely complex NetHack.
“We wanted to construct what we think is the most accessible ‘grand challenge’ with this game. It won’t solve AI, but it will unlock pathways towards better AI,” said Facebook AI Research’s Edward Grefenstette. “Games are a good domain to find our assumptions about what makes machines intelligent and break them.”
You may not be familiar with NetHack, but it’s one of the most influential games of all time. You’re an adventurer in a fantasy world, delving through the increasingly dangerous depths of a dungeon that’s different every time. You must battle monsters, navigate traps and other hazards, and meanwhile stay on good terms with your god. It’s the first “roguelike” (after Rogue, its immediate and much simpler predecessor) and arguably still the best — almost certainly the hardest.
(It’s free, by the way, and you can download and play it on nearly any platform.)
Its simple ASCII graphics, using a g for a goblin, an @ for the player, lines and dots for the level’s architecture, and so on, belie its incredible complexity. Because Nethack, which made its debut in 1987, has been under active development ever since, with its shifting team of developers expanding its roster of objects and creatures, rules, and the countless, countless interactions between them all.
And this is part of what makes NetHack such a difficult and interesting challenge for AI: It’s so open-ended. Not only is the world different every time, but every object and creature can interact in new ways, most of them hand-coded over decades to cover every possible player choice.
NetHack with a tile-based graphics update – all the information is still available via text.
“Atari, Dota 2, StarCraft 2… the solutions we’ve had to make progress there are very interesting. NetHack just presents different challenges. You have to rely on human knowledge to play the game as a human,” said Grefenstette.
In these other games, there’s a more or less obvious strategy to winning. Of course it’s more complex in a game like Dota 2 than in an Atari 800 game, but the idea is the same — there are pieces the player controls, a game board of environment, and win conditions to pursue. That’s kind of the case in NetHack, but it’s weirder than that. For one thing, the game is different every time, and not just in the details.
“New dungeon, new world, new monsters and items, you don’t have a save point. If you make a mistake and die you don’t get a second shot. It’s a bit like real life,” said Grefenstette. “You have to learn from mistakes and come to new situations armed with that knowledge.”
Drinking a corrosive potion is a bad idea, of course, but what about throwing it at a monster? Coating your weapon with it? Pouring it on the lock of a treasure chest? Diluting it with water? We have intuitive ideas about these actions, but a game-playing AI doesn’t think the way we do.
The depth and complexity of the systems in NetHack are difficult to explain, but that diversity and difficulty make the game a perfect candidate for a competition, according to Grefenstette. “You have to rely on human knowledge to play the game,” he said.
People have been designing bots to play NetHack for many years that rely not on neural networks but decision trees as complex as the game itself. The team at Facebook Research hopes to engender a new approach by building a training environment that people can test machine learning-based game-playing algorithms on.
NetHack screens with labels showing what the AI is aware of.
The NetHack Learning Environment was actually put together last year, but the NetHack Challenge is only just now getting started. The NLE is basically a version of the game embedded in a dedicated computing environment that lets an AI interact with it through text commands (directions, actions like attack or quaff)
It’s a tempting target for ambitious AI designers. While games like StarCraft 2 may enjoy a higher profile in some ways, NetHack is legendary and the idea of building a model on completely different lines from those used to dominate other games is an interesting challenge.
It’s also, as Grefenstette explained, a more accessible one than many in the past. If you wanted to build an AI for StarCraft 2, you needed a lot of computing power available to run visual recognition engines on the imagery from the game. But in this case the entire game is transmitted via text, making it extremely efficient to work with. It can be played thousands of times faster than any human could with even the most basic computing setup. That leaves the challenge wide open to individuals and groups who don’t have access to the kind of high-power setups necessary to power other machine learning methods.
“We wanted to create a research environment that had a lot of challenges for the AI community, but not restrict it to only large academic labs,” he said.
For the next few months, NLE will be available for people to test on, and competitors can basically build their bot or AI by whatever means they choose. But when the competition itself starts in earnest on October 15, they’ll be limited to interacting with the game in its controlled environment through standard commands — no special access, no inspecting RAM, etc.
The goal of the competition will be to complete the game, and the Facebook team will track how many times the agent “ascends,” as it’s called in NetHack, in a set amount of time. But “we’re assuming this is going to be zero for everyone,” Grefenstette admitted. After all, this is one of the hardest games ever made, and even humans who have played it for years have trouble winning even once in a lifetime, let alone several times in a row. There will be other scoring metrics to judge winners in a number of categories.
The hope is that this challenge provides the seed of a new approach to AI, one that more fundamentally resembles actual human thinking. Shortcuts, trial and error, score-hacking, and zerging won’t work here — the agent needs to learn systems of logic and apply them flexibly and intelligently, or die horribly at the hands of an enraged centaur or owlbear.
You can check out the rules and other specifics of the NetHack Challenge here. Results will be announced at the NeurIPS conference later this year.
Powered by WPeMatico
OroraTech’s space-based early wildfire warnings spark $7M investment
With wildfires becoming an ever more devastating annual phenomenon, it is in the whole planet’s interest to spot them and respond as early as possible — and the best vantage point for that is space. OroraTech is a German startup building a constellation of small satellites to power a global wildfire warning system, and will be using a freshly raised €5.8 million (~$7 million) A round to kick things off.
Wildfires destroy tens of millions of acres of forest every year, causing immense harm to people and the planet in countless ways. Once they’ve grown to a certain size, they’re near impossible to stop, so the earlier they can be located and worked against, the better.
But these fires can start just about anywhere in a dried out forest hundreds of miles wide, and literally every minute and hour counts — watch towers, helicopter flights and other frequently used methods may not be fast or exact enough to effectively counteract this increasingly serious threat. Not to mention they’re expensive and often dangerous jobs for those who perform them.
OroraTech’s plan is to use a constellation of about 100 satellites equipped with custom infrared cameras to watch the entire globe (or at least the parts most likely to burst into flame) at once, reporting any fire bigger than 10 meters across within half an hour.
Image Credits: OroraTech
To start out with, the Bavarian company has used data from over a dozen satellites already in space, in order to prove out the service on the ground. But with this funding round they are set to put their own bird in the air, a shoebox-sized satellite with a custom infrared sensor that will be launched by Spire later this year. Onboard machine learning processing of this imagery simplifies the downstream process.
Fourteen more satellites are planned for launch by 2023, presumably once they’ve kicked the proverbial tires on the first one and come up with the inevitable improvements.
“In order to cover even more regions in the future and to be able to give warning earlier, we aim to launch our own specialized satellite constellation into orbit,” said CEO and co-founder Thomas Grübler in a press release. “We are therefore delighted to have renowned investors on board to support us with capital and technological know-how in implementing our plans.”
Image Credits: OroraTech
Those renowned investors consist of Findus Venture and Ananda Impact Ventures, which led the round, followed by APEX Ventures, BayernKapital, Clemens Kaiser, SpaceTec Capital and Ingo Baumann. The company was spun out of research done by the founders at TUM, which maintains an interest.
“It is absolutely remarkable what they have built up and achieved so far despite limited financial resources and we feel very proud that we are allowed to be part of this inspiring and ambitious NewSpace project,” APEX’s Wolfgang Neubert said, and indeed it’s impressive to have a leading space-based data service with little cash (it raised an undisclosed seed about a year ago) and no satellites.
It’s not the only company doing infrared imagery of the Earth’s surface; SatelliteVu recently raised money to launch its own, much smaller constellation, though it’s focused on monitoring cities and other high-interest areas, not the vast expanse of forests. And ConstellR is aimed (literally) at the farming world, monitoring fields for precision crop management.
With money in its pocket Orora can expand and start providing its improved detection services, though sadly, it likely won’t be upgrading before wildfire season hits the northern hemisphere this year.
Powered by WPeMatico
Anthropic is the new AI research outfit from OpenAI’s Dario Amodei, and it has $124M to burn
As AI has grown from a menagerie of research projects to include a handful of titanic, industry-powering models like GPT-3, there is a need for the sector to evolve — or so thinks Dario Amodei, former VP of research at OpenAI, who struck out on his own to create a new company a few months ago. Anthropic, as it’s called, was founded with his sister Daniela and its goal is to create “large-scale AI systems that are steerable, interpretable, and robust.”
The challenge the siblings Amodei are tackling is simply that these AI models, while incredibly powerful, are not well understood. GPT-3, which they worked on, is an astonishingly versatile language system that can produce extremely convincing text in practically any style, and on any topic.
But say you had it generate rhyming couplets with Shakespeare and Pope as examples. How does it do it? What is it “thinking”? Which knob would you tweak, which dial would you turn, to make it more melancholy, less romantic, or limit its diction and lexicon in specific ways? Certainly there are parameters to change here and there, but really no one knows exactly how this extremely convincing language sausage is being made.
It’s one thing to not know when an AI model is generating poetry, quite another when the model is watching a department store for suspicious behavior, or fetching legal precedents for a judge about to pass down a sentence. Today the general rule is: the more powerful the system, the harder it is to explain its actions. That’s not exactly a good trend.
“Large, general systems of today can have significant benefits, but can also be unpredictable, unreliable, and opaque: our goal is to make progress on these issues,” reads the company’s self-description. “For now, we’re primarily focused on research towards these goals; down the road, we foresee many opportunities for our work to create value commercially and for public benefit.”
The goal seems to be to integrate safety principles into the existing priority system of AI development that generally favors efficiency and power. Like any other industry, it’s easier and more effective to incorporate something from the beginning than to bolt it on at the end. Attempting to make some of the biggest models out there able to be picked apart and understood may be more work than building them in the first place. Anthropic seems to be starting fresh.
“Anthropic’s goal is to make the fundamental research advances that will let us build more capable, general, and reliable AI systems, then deploy these systems in a way that benefits people,” said Dario Amodei, CEO of the new venture, in a short post announcing the company and its $124 million in funding.
That funding, by the way, is as star-studded as you might expect. It was led by Skype co-founder Jaan Tallinn, and included James McClave, Dustin Moskovitz, Eric Schmidt and the Center for Emerging Risk Research, among others.
The company is a public benefit corporation, and the plan for now, as the limited information on the site suggests, is to remain heads-down on researching these fundamental questions of how to make large models more tractable and interpretable. We can expect more information later this year, perhaps, as the mission and team coalesces and initial results pan out.
The name, incidentally, is adjacent to anthropocentric, and concerns relevancy to human experience or existence. Perhaps it derives from the “Anthropic principle,” the notion that intelligent life is possible in the universe because… well, we’re here. If intelligence is inevitable under the right conditions, the company just has to create those conditions.
Powered by WPeMatico
Engine Biosciences expands its digital drug discovery pipeline with $43M round
Drug discovery is a large and growing field, encompassing both ambitious startups and billion-dollar Big Pharma incumbents. Engine Biosciences is one of the former, a Singaporean outfit with an expert founding crew and a different approach to the business of finding new therapeutics, and it just raised $43 million to keep growing.
Digital drug discovery in general means large-scale analysis of biological data like genes, gene expression, protein structures, binding sites, things like that. Where it has hit a wall in the past is not on the digital side, where any number of likely molecules or processes can be generated, but on the next step, when those notions need to be tested in vitro. So a new crop of biotech companies have worked to integrate these aspects.
Engine does so with a pair of tools it has dubbed NetMAPPR and CombiGEM. NetMAPPR is a huge sort of search engine for genes and gene interactions, taking special note of “errors” that could provide a foothold for a molecule or treatment. CombiGEM is like a mass genetic testing process that can look into thousands of gene combinations and edits on diseased cells simultaneously, providing quick experimental confirmation of the targets and effects proposed by the digital side. The company is focused on anti-cancer drugs but is looking into other fields as they become viable.
Image Credits: Engine Biosciences
The focus on gene interactions sets their approach apart, said co-founder and CEO Jeffrey Lu.
“Gene interactions are relevant to all diseases, and in cancers, where we focus, a proven approach for effective precision medicines,” he explained. “For example, there are four approved drugs targeting the PARP enzyme in the context of mutation in the BRCA gene that is changing cancer treatment for millions of people. The fundamental principle of this precision medicine is based on understanding the gene interaction between BRCA and PARP.”
The company raised a $10 million seed in 2018 and has been doing its thing ever since — but it needs more money if it’s going to bring some of these things to market.
“We already have chemical compounds directed toward the novel biology we have uncovered,” said Lu. “These are effectively prototype drugs, which are showing anti-cancer effects in diseased cells. We need to refine and optimize these prototypes to a suitable candidate to enter the clinic for testing in humans.”
Right now they’re working with other companies to do the next step up from automated testing, which is to say animal testing, to clear the way for human trials.
The CombiGEM experiments — hundreds of thousands of them — produce a large amount of data as well, and they’re sharing and collaborating on that front with several medical centers throughout Asia. “We have built what we believe to be the largest data compendium related to gene interactions in the context of cancer disease relevance,” said Lu, adding that this is crucial to the success of the machine learning algorithms they employ to predict biological processes.
The $43 million round was led by Polaris Partners, with participation by newcomers Invus and a long list of existing investors. The money will go toward the requisite testing and paperwork involved in bringing a new drug to market based on promising leads.
“We have small molecule compounds for our lead cancer programs with data from in vitro (in cancer cells) experiments. We are refining the chemistry and expanding studies this year,” said Lu. “Next year, we anticipate having our first drug candidate enter the late preclinical phase of development and regulatory work for an IND (investigational new drug) filing with the FDA, and starting the clinical trials in 2023.”
It’s a long road to human trials, let alone widespread use, but that’s the risk any drug discovery startup takes. The carrot dangling in front of them is not just the possibility of a product that could generate billions in income, but perhaps save the lives of countless cancer patients awaiting novel therapies.
Powered by WPeMatico
Liquid Instruments raises $13.7M to bring its education-focused 8-in-1 engineering gadget to market
Part of learning to be an engineer is understanding the tools you’ll have to work with — voltmeters, spectrum analyzers, things like that. But why use two, or eight for that matter, where one will do? The Moku:Go combines several commonly used tools into one compact package, saving room on your workbench or classroom while also providing a modern, software-configurable interface. Creator Liquid Instruments has just raised $13.7 million to bring this gadget to students and engineers everywhere.
Image Credits: Liquid Instruments
The idea behind Moku:Go is largely the same as the company’s previous product, the Moku:Lab. Using a standard input port, a set of FPGA-based tools perform the same kind of breakdowns and analyses of electrical signals as you would get in a larger or analog device. But being digital saves a lot of space that would normally go toward bulky analog components.
The Go takes this miniaturization further than the Lab, doing many of the same tasks at half the weight and with a few useful extra features. It’s intended for use in education or smaller engineering shops where space is at a premium. Combining eight tools into one is a major coup when your bench is also your desk and your file cabinet.
Those eight tools, by the way, are: waveform generator, arbitrary waveform generator, frequency response analyzer, logic analyzer/pattern generator, oscilloscope/voltmeter, PID controller, spectrum analyzer and data logger. It’s hard to say whether that really adds up to more or less than eight, but it’s definitely a lot to have in a package the size of a hardback book.
You access and configure them using a software interface rather than a bunch of knobs and dials — though let’s be clear, there are good arguments for both. When you’re teaching a bunch of young digital natives, however, a clean point-and-click interface is probably a plus. The UI is actually very attractive; you can see several examples by clicking the instruments on this page, but here’s an example of the waveform generator:
Image Credits: Liquid Instruments
Love those pastels.
The Moku:Go currently works with Macs and Windows but doesn’t have a mobile app yet. It integrates with Python, MATLAB and LabVIEW. Data goes over Wi-Fi.
Compared with the Moku:Lab, it has a few perks. A USB-C port instead of a mini, a magnetic power port, a 16-channel digital I/O, optional power supply of up to four channels and of course it’s half the size and weight. It compromises on a few things — no SD card slot and less bandwidth for its outputs, but if you need the range and precision of the more expensive tool, you probably need a lot of other stuff too.
Image Credits: Liquid Instruments
Since the smaller option also costs $500 to start (“a price comparable to a textbook”… yikes) compared with the big one’s $3,500, there’s major savings involved. And it’s definitely cheaper than buying all those instruments individually.
The Moku:Go is “targeted squarely at university education,” said Liquid Instruments VP of marketing Doug Phillips. “Professors are able to employ the device in the classroom and individuals, such as students and electronic engineering hobbyists, can experiment with it on their own time. Since its launch in March, the most common customer profile has been students purchasing the device at the direction of their university.”
About a hundred professors have signed on to use the device as part of their fall classes, and the company is working with other partners in universities around the world. “There is a real demand for portable, flexible systems that can handle the breadth of four years of curriculum,” Phillips said.
Production starts in June (samples are out to testers), the rigors and costs of which likely prompted the recent round of funding. The $13.7 million comes from existing investors Anzu Partners and ANU Connect Ventures, and new investors F1 Solutions and Moelis Australia’s Growth Capital Fund. It’s a convertible note “in advance of an anticipated Series B round in 2022,” Phillips said. It’s a larger amount than they intended to raise at first, and the note nature of the round is also not standard, but given the difficulties faced by hardware companies over the last year, some irregularities are probably to be expected.
No doubt the expected B round will depend considerably on the success of the Moku:Go’s launch and adoption. But this promising product looks as if it might be a commonplace item in thousands of classrooms a couple years from now.
Powered by WPeMatico
Artificial raises $21M led by Microsoft’s M12 for a lab automation platform aimed at life sciences R&D
Automation is extending into every aspect of how organizations get work done, and today comes news of a startup that is building tools for one industry in particular: life sciences. Artificial, which has built a software platform for laboratories to assist with, or in some cases fully automate, research and development work, has raised $21.5 million.
It plans to use the funding to continue building out its software and its capabilities, to hire more people, and for business development, according to Artificial’s CEO and co-founder David Fuller. The company already has a number of customers including Thermo Fisher and Beam Therapeutics using its software directly and in partnership for their own customers. Sold as aLab Suite, Artificial’s technology can both orchestrate and manage robotic machines that labs might be using to handle some work; and help assist scientists when they are carrying out the work themselves.
“The basic premise of what we’re trying to do is accelerate the rate of discovery in labs,” Fuller said in an interview. He believes the process of bringing in more AI into labs to improve how they work is long overdue. “We need to have a digital revolution to change the way that labs have been operating for the last 20 years.”
The Series A is being led by Microsoft’s venture fund M12 — a financial and strategic investor — with Playground Global and AME Cloud Ventures also participating. Playground Global, the VC firm co-founded by ex-Google exec and Android co-creator Andy Rubin (who is no longer with the firm), has been focusing on robotics and life sciences and it led Artificial’s first and only other round. Artificial is not disclosing its valuation with this round.
Fuller hails from a background in robotics, specifically industrial robots and automation. Before founding Artificial in 2019, he was at Kuka, the German robotics maker, for a number of years, culminating in the role of CTO; prior to that, Fuller spent 20 years at National Instruments, the instrumentation, test equipment and industrial software giant. Meanwhile, Artificial’s co-founder, Nikhita Singh, has insight into how to bring the advances of robotics into environments that are quite analogue in culture. She previously worked on human-robot interaction research at the MIT Media Lab, and before that spent years at Palantir and working on robotics at Berkeley.
As Fuller describes it, he saw an interesting gap (and opportunity) in the market to apply automation, which he had seen help advance work in industrial settings, to the world of life sciences, both to help scientists track what they are doing better, and help them carry out some of the more repetitive work that they have to do day in, day out.
This gap is perhaps more in the spotlight today than ever before, given the fact that we are in the middle of a global health pandemic. This has hindered a lot of labs from being able to operate full in-person teams, and increased the reliance on systems that can crunch numbers and carry out work without as many people present. And, of course, the need for that work (whether it’s related directly to Covid-19 or not) has perhaps never appeared as urgent as it does right now.
There have been a lot of advances in robotics — specifically around hardware like robotic arms — to manage some of the precision needed to carry out some work, but up to now no real efforts made at building platforms to bring all of the work done by that hardware together (or in the words of automation specialists, “orchestrate” that work and data); nor link up the data from those robot-led efforts, with the work that human scientists still carry out. Artificial estimates that some $10 billion is spent annually on lab informatics and automation software, yet data models to unify that work, and platforms to reach across it all, remain absent. That has, in effect, served as a barrier to labs modernising as much as they could.
A lab, as he describes it, is essentially composed of high-end instrumentation for analytics, alongside then robotic systems for liquid handling. “You can really think of a lab, frankly, as a kitchen,” he said, “and the primary operation in that lab is mixing liquids.”
But it is also not unlike a factory, too. As those liquids are mixed, a robotic system typically moves around pipettes, liquids, in and out of plates and mixes. “There’s a key aspect of material flow through the lab, and the material flow part of it is much more like classic robotics,” he said. In other words, there is, as he says, “a combination of bespoke scientific equipment that includes automation, and then classic material flow, which is much more standard robotics,” and is what makes the lab ripe as an applied environment for automation software.
To note: the idea is not to remove humans altogether, but to provide assistance so that they can do their jobs better. He points out that even the automotive industry, which has been automated for 50 years, still has about 6% of all work done by humans. If that is a watermark, it sounds like there is a lot of movement left in labs: Fuller estimates that some 60% of all work in the lab is done by humans. And part of the reason for that is simply because it’s just too complex to replace scientists — who he described as “artists” — altogether (for now at least).
“Our solution augments the human activity and automates the standard activity,” he said. “We view that as a central thesis that differentiates us from classic automation.”
There have been a number of other startups emerging that are applying some of the learnings of artificial intelligence and big data analytics for enterprises to the world of science. They include the likes of Turing, which is applying this to helping automate lab work for CPG companies; and Paige, which is focusing on AI to help better understand cancer and other pathology.
The Microsoft connection is one that could well play out in how Artificial’s platform develops going forward, not just in how data is perhaps handled in the cloud, but also on the ground, specifically with augmented reality.
“We see massive technical synergy,” Fuller said. “When you are in a lab you already have to wear glasses… and we think this has the earmarks of a long-term use case.”
Fuller mentioned that one area it’s looking at would involve equipping scientists and other technicians with Microsoft’s HoloLens to help direct them around the labs, and to make sure people are carrying out work consistently by comparing what is happening in the physical world to a “digital twin” of a lab containing data about supplies, where they are located, and what needs to happen next.
It’s this and all of the other areas that have yet to be brought into our very AI-led enterprise future that interested Microsoft.
“Biology labs today are light- to semi-automated—the same state they were in when I started my academic research and biopharmaceutical career over 20 years ago. Most labs operate more like test kitchens rather than factories,” said Dr. Kouki Harasaki, an investor at M12, in a statement. “Artificial’s aLab Suite is especially exciting to us because it is uniquely positioned to automate the masses: it’s accessible, low code, easy to use, highly configurable, and interoperable with common lab hardware and software. Most importantly, it enables Biopharma and SynBio labs to achieve the crowning glory of workflow automation: flexibility at scale.”
Harasaki is joining Peter Barratt, a founder and general partner at Playground Global, on Artificial’s board with this round.
“It’s become even more clear as we continue to battle the pandemic that we need to take a scalable, reproducible approach to running our labs, rather than the artisanal, error-prone methods we employ today,” Barrett said in a statement. “The aLab Suite that Artificial has pioneered will allow us to accelerate the breakthrough treatments of tomorrow and ensure our best and brightest scientists are working on challenging problems, not manual labor.”
Powered by WPeMatico
With $21M in funding, Code Ocean aims to help researchers replicate data-heavy science
Every branch of science is increasingly reliant on big data sets and analysis, which means a growing confusion of formats and platforms — more than inconvenient, this can hinder the process of peer review and replication of research. Code Ocean hopes to make it easier for scientists to collaborate by making a flexible, shareable format and platform for any and all data sets and methods, and it has raised a total of $21 million to build it out.
Certainly there’s an air of “Too many options? Try this one!” to this (and here’s the requisite relevant XKCD). But Code Ocean isn’t creating a competitor to successful tools like Jupyter or GitLab or Docker — it’s more of a small-scale container platform that lets you wrap up all the necessary components of your data and analysis in an easily shared format, whatever platform they live on natively.
The trouble appears when you need to share what you’re doing with another researcher, whether they’re on the bench next to you or at a university across the country. It’s important for replication purposes that data analysis — just like any other scientific technique — be done exactly the same way. But there’s no guarantee that your colleague will use the same structures, formats, notation, labels and so on.
That doesn’t mean it’s impossible to share your work, but it does add a lot of extra steps as would-be replicators or iterators check and double check that all the methods are the same, that the same versions of the same tools are being used in the same order, with the same settings, and so on. A tiny inconsistency can have major repercussions down the road.
Turns out this problem is similar in a way to how many cloud services are spun up. Software deployments can be as finicky as scientific experiments, and one solution to this is containers, which like tiny virtual machines include everything needed to accomplish a computing task, in a portable format compatible with many different setups. The idea is a natural one to transfer to the research world, where you can tie up all in one tidy package the data, the software used and the specific techniques and processes used to reach a given result. That, at least, is the pitch Code Ocean offers for its platform and “Compute Capsules.”
Image Credits: Code Ocean
Say you’re a microbiologist looking at the effectiveness of a promising compound on certain muscle cells. You’re working in R, writing in RStudio on an Ubuntu machine, and your data are such and such collected during an in vitro observation. While you would naturally declare all this when you publish, there’s no guarantee anyone has an Ubuntu laptop with a working RStudio setup around, so even if you provide all the code, it might be for nothing.
If, however, you put it on Code Ocean, like this, it makes all the relevant code available, and capable of being inspected and run unmodified with a click, or being fiddled with if a colleague is wondering about a certain piece. It works through a single link and web app, cross platform, and can even be embedded on a webpage like a document or video. (I’m going to try to do that below, but our backend is a little finicky. The capsule itself is here.)
More than that, though, the Compute Capsule can be repurposed by others with new data and modifications. Maybe the technique you put online is a general purpose RNA sequence analysis tool that works as long as you feed it properly formatted data, and that’s something others would have had to code from scratch in order to take advantage of some platforms.
Well, they can just clone your capsule, run it with their own data and get their own results in addition to verifying your own. This can be done via the Code Ocean website or just by downloading a zip file of the whole thing and getting it running on their own computer, if they happen to have a compatible setup. A few more example capsules can be found here.
Image Credits: Code Ocean
This sort of cross-pollination of research techniques is as old as science, but modern data-heavy experimentation often ends up siloed because it can’t easily be shared and verified even though the code is technically available. That means other researchers move on, build their own thing and further reinforce the silo system.
Right now there are about 2,000 public compute capsules on Code Ocean, most of which are associated with a published paper. Most have also been used by others, either to replicate or try something new, and some, like ultra-specific open source code libraries, have been used by thousands.
Naturally there are security concerns when working with proprietary or medically sensitive data, and the enterprise product allows the whole system to run on a private cloud platform. That way it would be more of an internal tool, and at major research institutions that in itself could be quite useful.
Code Ocean hopes that by being as inclusive as possible in terms of codebases, platforms, compute services and so on will make for a more collaborative environment at the cutting edge.
Clearly that ambition is shared by others, as the the company has raised $21 million so far, $6 million of which was in previously undisclosed investments and $15 million in an A round announced today. The A round was led by Battery Ventures, with Digitalis Ventures, EBSCO and Vaal Partners participating as well as numerous others.
The money will allow the company to further develop, scale and promote its platform. With luck they’ll soon find themselves among the rarefied air often breathed by this sort of savvy SaaS — necessary, deeply integrated and profitable.
Powered by WPeMatico
Longevity startup Gero AI has a mobile API for quantifying health changes
Sensor data from smartphones and wearables can meaningfully predict an individual’s ‘biological age’ and resilience to stress, according to Gero AI.
The ‘longevity’ startup — which condenses its mission to the pithy goal of “hacking complex diseases and aging with Gero AI” — has developed an AI model to predict morbidity risk using ‘digital biomarkers’ that are based on identifying patterns in step-counter sensor data which tracks mobile users’ physical activity.
A simple measure of ‘steps’ isn’t nuanced enough on its own to predict individual health, is the contention. Gero’s AI has been trained on large amounts of biological data to spots patterns that can be linked to morbidity risk. It also measures how quickly a personal recovers from a biological stress — another biomarker that’s been linked to lifespan; i.e. the faster the body recovers from stress, the better the individual’s overall health prognosis.
A research paper Gero has had published in the peer-reviewed biomedical journal Aging explains how it trained deep neural networks to predict morbidity risk from mobile device sensor data — and was able to demonstrate that its biological age acceleration model was comparable to models based on blood test results.
Another paper, due to be published in the journal Nature Communications later this month, will go into detail on its device-derived measurement of biological resilience.
The Singapore-based startup, which has research roots in Russia — founded back in 2015 by a Russian scientist with a background in theoretical physics — has raised a total of $5 million in seed funding to date (in two tranches).
Backers come from both the biotech and the AI fields, per co-founder Peter Fedichev. Its investors include Belarus-based AI-focused early stage fund, Bulba Ventures (Yury Melnichek). On the pharma side, it has backing from some (unnamed) private individuals with links to Russian drug development firm, Valenta. (The pharma company itself is not an investor).
Fedichev is a theoretical physicist by training who, after his PhD and some ten years in academia, moved into biotech to work on molecular modelling and machine learning for drug discovery — where he got interested in the problem of ageing and decided to start the company.
As well as conducting its own biological research into longevity (studying mice and nematodes), it’s focused on developing an AI model for predicting the biological age and resilience to stress of humans — via sensor data captured by mobile devices.
“Health of course is much more than one number,” emphasizes Fedichev. “We should not have illusions about that. But if you are going to condense human health to one number then, for a lot of people, the biological age is the best number. It tells you — essentially — how toxic is your lifestyle… The more biological age you have relative to your chronological age years — that’s called biological acceleration — the more are your chances to get chronic disease, to get seasonal infectious diseases or also develop complications from those seasonal diseases.”
Gero has recently launched a (paid, for now) API, called GeroSense, that’s aimed at health and fitness apps so they can tap up its AI modelling to offer their users an individual assessment of biological age and resilience (aka recovery rate from stress back to that individual’s baseline).
Early partners are other longevity-focused companies, AgelessRx and Humanity Inc. But the idea is to get the model widely embedded into fitness apps where it will be able to send a steady stream of longitudinal activity data back to Gero, to further feed its AI’s predictive capabilities and support the wider research mission — where it hopes to progress anti-ageing drug discovery, working in partnerships with pharmaceutical companies.
The carrot for the fitness providers to embed the API is to offer their users a fun and potentially valuable feature: A personalized health measurement so they can track positive (or negative) biological changes — helping them quantify the value of whatever fitness service they’re using.
“Every health and wellness provider — maybe even a gym — can put into their app for example… and this thing can rank all their classes in the gym, all their systems in the gym, for their value for different kinds of users,” explains Fedichev.
“We developed these capabilities because we need to understand how ageing works in humans, not in mice. Once we developed it we’re using it in our sophisticated genetic research in order to find genes — we are testing them in the laboratory — but, this technology, the measurement of ageing from continuous signals like wearable devices, is a good trick on its own. So that’s why we announced this GeroSense project,” he goes on.
“Ageing is this gradual decline of your functional abilities which is bad but you can go to the gym and potentially improve them. But the problem is you’re losing this resilience. Which means that when you’re [biologically] stressed you cannot get back to the norm as quickly as possible. So we report this resilience. So when people start losing this resilience it means that they’re not robust anymore and the same level of stress as in their 20s would get them [knocked off] the rails.
“We believe this loss of resilience is one of the key ageing phenotypes because it tells you that you’re vulnerable for future diseases even before those diseases set in.”
“In-house everything is ageing. We are totally committed to ageing: Measurement and intervention,” adds Fedichev. “We want to building something like an operating system for longevity and wellness.”
Gero is also generating some revenue from two pilots with “top range” insurance companies — which Fedichev says it’s essentially running as a proof of business model at this stage. He also mentions an early pilot with Pepsi Co.
He sketches a link between how it hopes to work with insurance companies in the area of health outcomes with how Elon Musk is offering insurance products to owners of its sensor-laden Teslas, based on what it knows about how they drive — because both are putting sensor data in the driving seat, if you’ll pardon the pun. (“Essentially we are trying to do to humans what Elon Musk is trying to do to cars,” is how he puts it.)
But the nearer term plan is to raise more funding — and potentially switch to offering the API for free to really scale up the data capture potential.
Zooming out for a little context, it’s been almost a decade since Google-backed Calico launched with the moonshot mission of ‘fixing death’. Since then a small but growing field of ‘longevity’ startups has sprung up, conducting research into extending (in the first instance) human lifespan. (Ending death is, clearly, the moonshot atop the moonshot.)
Death is still with us, of course, but the business of identifying possible drugs and therapeutics to stave off the grim reaper’s knock continues picking up pace — attracting a growing volume of investor dollars.
The trend is being fuelled by health and biological data becoming ever more plentiful and accessible, thanks to open research data initiatives and the proliferation of digital devices and services for tracking health, set alongside promising developments in the fast-evolving field of machine learning in areas like predictive healthcare and drug discovery.
Longevity has also seen a bit of an upsurge in interest in recent times as the coronavirus pandemic has concentrated minds on health and wellness, generally — and, well, mortality specifically.
Nonetheless, it remains a complex, multi-disciplinary business. Some of these biotech moonshots are focused on bioengineering and gene-editing — pushing for disease diagnosis and/or drug discovery.
Plenty are also — like Gero — trying to use AI and big data analysis to better understand and counteract biological ageing, bringing together experts in physics, maths and biological science to hunt for biomarkers to further research aimed at combating age-related disease and deterioration.
Another recent example is AI startup Deep Longevity, which came out of stealth last summer — as a spinout from AI drug discovery startup Insilico Medicine — touting an AI ‘longevity as a service’ system which it claims can predict an individual’s biological age “significantly more accurately than conventional methods” (and which it also hopes will help scientists to unpick which “biological culprits drive aging-related diseases”, as it put it).
Gero AI is taking a different tack toward the same overarching goal — by honing in on data generated by activity sensors embedded into the everyday mobile devices people carry with them (or wear) as a proxy signal for studying their biology.
The advantage being that it doesn’t require a person to undergo regular (invasive) blood tests to get an ongoing measure of their own health. Instead our personal device can generate proxy signals for biological study passively — at vast scale and low cost. So the promise of Gero’s ‘digital biomarkers’ is they could democratize access to individual health prediction.
And while billionaires like Peter Thiel can afford to shell out for bespoke medical monitoring and interventions to try to stay one step ahead of death, such high end services simply won’t scale to the rest of us.
If its digital biomarkers live up to Gero’s claims, its approach could, at the least, help steer millions towards healthier lifestyles, while also generating rich data for longevity R&D — and to support the development of drugs that could extend human lifespan (albeit what such life-extending pills might cost is a whole other matter).
The insurance industry is naturally interested — with the potential for such tools to be used to nudge individuals towards healthier lifestyles and thereby reduce payout costs.
For individuals who are motivated to improve their health themselves, Fedichev says the issue now is it’s extremely hard for people to know exactly which lifestyle changes or interventions are best suited to their particular biology.
For example fasting has been shown in some studies to help combat biological ageing. But he notes that the approach may not be effective for everyone. The same may be true of other activities that are accepted to be generally beneficial for health (like exercise or eating or avoiding certain foods).
Again those rules of thumb may have a lot of nuance, depending on an individual’s particular biology. And scientific research is, inevitably, limited by access to funding. (Research can thus tend to focus on certain groups to the exclusion of others — e.g. men rather than women; or the young rather than middle aged.)
This is why Fedichev believes there’s a lot of value in creating a measure than can address health-related knowledge gaps at essentially no individual cost.
Gero has used longitudinal data from the UK’s biobank, one of its research partners, to verify its model’s measurements of biological age and resilience. But of course it hopes to go further — as it ingests more data.
“Technically it’s not properly different what we are doing — it just happens that we can do it now because there are such efforts like UK biobank. Government money and also some industry sponsors money, maybe for the first time in the history of humanity, we have this situation where we have electronic medical records, genetics, wearable devices from hundreds of thousands of people, so it just became possible. It’s the convergence of several developments — technological but also what I would call ‘social technologies’ [like the UK biobank],” he tells TechCrunch.
“Imagine that for every diet, for every training routine, meditation… in order to make sure that we can actually optimize lifestyles — understand which things work, which do not [for each person] or maybe some experimental drugs which are already proved [to] extend lifespan in animals are working, maybe we can do something different.”
“When we will have 1M tracks [half a year’s worth of data on 1M individuals] we will combine that with genetics and solve ageing,” he adds, with entrepreneurial flourish. “The ambitious version of this plan is we’ll get this million tracks by the end of the year.”
Fitness and health apps are an obvious target partner for data-loving longevity researchers — but you can imagine it’ll be a mutual attraction. One side can bring the users, the other a halo of credibility comprised of deep tech and hard science.
“We expect that these [apps] will get lots of people and we will be able to analyze those people for them as a fun feature first, for their users. But in the background we will build the best model of human ageing,” Fedichev continues, predicting that scoring the effect of different fitness and wellness treatments will be “the next frontier” for wellness and health (Or, more pithily: “Wellness and health has to become digital and quantitive.”)
“What we are doing is we are bringing physicists into the analysis of human data. Since recently we have lots of biobanks, we have lots of signals — including from available devices which produce something like a few years’ long windows on the human ageing process. So it’s a dynamical system — like weather prediction or financial market predictions,” he also tells us.
“We cannot own the treatments because we cannot patent them but maybe we can own the personalization — the AI that personalized those treatments for you.”
From a startup perspective, one thing looks crystal clear: Personalization is here for the long haul.
Powered by WPeMatico
Cognixion’s brain-monitoring headset enables fluid communication for people with severe disabilities
Of the many frustrations of having a severe motor impairment, the difficulty of communicating must surely be among the worst. The tech world has not offered much succor to those affected by things like locked-in syndrome, ALS and severe strokes, but startup Cognixion aims to with a novel form of brain monitoring that, combined with a modern interface, could make speaking and interaction far simpler and faster.
The company’s One headset tracks brain activity closely in such a way that the wearer can direct a cursor — reflected on a visor like a heads-up display — in multiple directions, or select from various menus and options. No physical movement is needed, and with the help of modern voice interfaces like Alexa, the user can not only communicate efficiently but freely access all kinds of information and content most people take for granted.
But it’s not a miracle machine, and it isn’t a silver bullet. Here’s how it got started.
Overhauling decades-old brain tech
Everyone with a motor impairment has different needs and capabilities, and there are a variety of assistive technologies that cater to many of these needs. But many of these techs and interfaces are years or decades old — medical equipment that hasn’t been updated for an era of smartphones and high-speed mobile connections.
Some of the most dated interfaces, unfortunately, are those used by people with the most serious limitations: those whose movements are limited to their heads, faces, eyes — or even a single eyelid, like Jean-Dominique Bauby, the famous author of “The Diving Bell and the Butterfly.”
One of the tools in the toolbox is the electroencephalogram, or EEG, which involves detecting activity in the brain via patches on the scalp that record electrical signals. But while they’re useful in medicine and research in many ways, EEGs are noisy and imprecise — more for finding which areas of the brain are active than, say, which sub-region of the sensory cortex or the like. And of course you have to wear a shower cap wired with electrodes (often greasy with conductive gel) — it’s not the kind of thing anyone wants to do for more than an hour, let alone all day every day.
Yet even among those with the most profound physical disabilities, cognition is often unimpaired — as indeed EEG studies have helped demonstrate. It made Andreas Forsland, co-founder and CEO of Cognixion, curious about further possibilities for the venerable technology: “Could a brain-computer interface using EEG be a viable communication system?”
He first used EEG for assistive purposes in a research study some five years ago. They were looking into alternative methods of letting a person control an on-screen cursor, among them an accelerometer for detecting head movements, and tried integrating EEG readings as another signal. But it was far from a breakthrough.
A modern lab with an EEG cap wired to a receiver and laptop — this is an example of how EEG is commonly used. Image Credits: BSIP/Universal Images Group via Getty Images
He ran down the difficulties: “With a read-only system, the way EEG is used today is no good; other headsets have slow sample rates and they’re not accurate enough for a real-time interface. The best BCIs are in a lab, connected to wet electrodes — it’s messy, it’s really a non-starter. So how do we replicate that with dry, passive electrodes? We’re trying to solve some very hard engineering problems here.”
The limitations, Forsland and his colleagues found, were not so much with the EEG itself as with the way it was carried out. This type of brain monitoring is meant for diagnosis and study, not real-time feedback. It would be like taking a tractor to a drag race. Not only do EEGs often work with a slow, thorough check of multiple regions of the brain that may last several seconds, but the signal it produces is analyzed by dated statistical methods. So Cognixion started by questioning both practices.
Improving the speed of the scan is more complicated than overclocking the sensors or something. Activity in the brain must be inferred by collecting a certain amount of data. But that data is collected passively, so Forsland tried bringing an active element into it: a rhythmic electric stimulation that is in a way reflected by the brain region, but changed slightly depending on its state — almost like echolocation.
The Cognixion One headset with its dry EEG terminals visible. Image Credits: Cognixion
They detect these signals with a custom set of six EEG channels in the visual cortex area (up and around the back of your head), and use a machine learning model to interpret the incoming data. Running a convolutional neural network locally on an iPhone — something that wasn’t really possible a couple years ago — the system can not only tease out a signal in short order but make accurate predictions, making for faster and smoother interactions.
The result is sub-second latency with 95-100% accuracy in a wireless headset powered by a mobile phone. “The speed, accuracy and reliability are getting to commercial levels — we can match the best in class of the current paradigm of EEGs,” said Forsland.
Dr. William Goldie, a clinical neurologist who has used and studied EEGs and other brain monitoring techniques for decades (and who has been voluntarily helping Cognixion develop and test the headset), offered a positive evaluation of the technology.
“There’s absolutely evidence that brainwave activity responds to thinking patterns in predictable ways,” he noted. This type of stimulation and response was studied years ago. “It was fascinating, but back then it was sort of in the mystery magic world. Now it’s resurfacing with these special techniques and the computerization we have these days. To me it’s an area that’s opening up in a manner that I think clinically could be dramatically effective.”
BCI, meet UI
The first thing Forsland told me was “We’re a UI company.” And indeed even such a step forward in neural interfaces as he later described means little if it can’t be applied to the problem at hand: helping people with severe motor impairment to express themselves quickly and easily.
Sad to say, it’s not hard to imagine improving on the “competition,” things like puff-and-blow tubes and switches that let users laboriously move a cursor right, right a little more, up, up a little more, then click: a letter! Gaze detection is of course a big improvement over this, but it’s not always an option (eyes don’t always work as well as one would like) and the best eye-tracking solutions (like a Tobii Dynavox tablet) aren’t portable.
Why shouldn’t these interfaces be as modern and fluid as any other? The team set about making a UI with this and the capabilities of their next-generation EEG in mind.
Image Credits: Cognixion
Their solution takes bits from the old paradigm and combines them with modern virtual assistants and a radial design that prioritizes quick responses and common needs. It all runs in an app on an iPhone, the display of which is reflected in a visor, acting as a HUD and outward-facing display.
In easy reach of, not to say a single thought but at least a moment’s concentration or a tilt of the head, are everyday questions and responses — yes, no, thank you, etc. Then there are slots to put prepared speech into — names, menu orders and so on. And then there’s a keyboard with word- and sentence-level prediction that allows common words to be popped in without spelling them out.
“We’ve tested the system with people who rely on switches, who might take 30 minutes to make 2 selections. We put the headset on a person with cerebral palsy, and she typed our her name and hit play in 2 minutes,” Forsland said. “It was ridiculous, everyone was crying.”
Goldie noted that there’s something of a learning curve. “When I put it on, I found that it would recognize patterns and follow through on them, but it also sort of taught patterns to me. You’re training the system, and it’s training you — it’s a feedback loop.”
“I can be the loudest person in the room”
One person who has found it extremely useful is Chris Benedict, a DJ, public speaker and disability advocate who himself has Dyskinetic Cerebral Palsy. It limits his movements and ability to speak, but doesn’t stop him from spinning (digital) records at various engagements, however, or from explaining his experience with Cognixion’s One headset over email. (And you can see him demonstrating it in person in the video above.)
Image Credits: Cognixion
“Even though it’s not a tool that I’d need all the time it’s definitely helpful in aiding my communication,” he told me. “Especially when I need to respond quickly or am somewhere that is noisy, which happens often when you are a DJ. If I wear it with a Bluetooth speaker I can be the loudest person in the room.” (He always has a speaker on hand, since “you never know when you might need some music.”)
The benefits offered by the headset give some idea of what is lacking from existing assistive technology (and what many people take for granted).
“I can use it to communicate, but at the same time I can make eye contact with the person I’m talking to, because of the visor. I don’t have to stare at a screen between me and someone else. This really helps me connect with people,” Benedict explained.
“Because it’s a headset I don’t have to worry about getting in and out of places, there is no extra bulk added to my chair that I have to worry about getting damaged in a doorway. The headset is balanced too, so it doesn’t make my head lean back or forward or weigh my neck down,” he continued. “When I set it up to use the first time it had me calibrate, and it measured my personal range of motion so the keyboard and choices fit on the screen specifically for me. It can also be recalibrated at any time, which is important because not every day is my range of motion the same.”
Alexa, which has been extremely helpful to people with a variety of disabilities due to its low cost and wide range of compatible devices, is also part of the Cognixion interface, something Benedict appreciates, having himself adopted the system for smart home and other purposes. “With other systems this isn’t something you can do, or if it is an option, it’s really complicated,” he said.
Next steps
As Benedict demonstrates, there are people for whom a device like Cognixion’s makes a lot of sense, and the hope is it will be embraced as part of the necessarily diverse ecosystem of assistive technology.
Forsland said that the company is working closely with the community, from users to clinical advisors like Goldie and other specialists, like speech therapists, to make the One headset as good as it can be. But the hurdle, as with so many devices in this class, is how to actually put it on people’s heads — financially and logistically speaking.
Cognixion is applying for FDA clearance to get the cost of the headset — which, being powered by a phone, is not as high as it would be with an integrated screen and processor — covered by insurance. But in the meantime the company is working with clinical and corporate labs that are doing neurological and psychological research. Places where you might find an ordinary, cumbersome EEG setup, in other words.
The company has raised funding and is looking for more (hardware development and medical pursuits don’t come cheap), and has also collected a number of grants.
The One headset may still be some years away from wider use (the FDA is never in a hurry), but that allows the company time to refine the device and include new advances. Unlike many other assistive devices, for example a switch or joystick, this one is largely software-limited, meaning better algorithms and UI work will significantly improve it. While many wait for companies like Neuralink to create a brain-computer interface for the modern era, Cognixion has already done so for a group of people who have much more to gain from it.
You can learn more about the Cognixion One headset and sign up to receive the latest at its site here.
Powered by WPeMatico
Serimmune launches new immune response mapping service for COVID-19
Immune intelligence startup Serimmune hopes to better understand the relationship between antibody epitopes (the parts of antigen molecules that bind to antibodies) and the SARS-CoV-2 virus.
The company’s proprietary technology, originally developed at UC Santa Barbara, provides a new and specific way of mapping the entire array of an individual’s antibodies through a small blood sample. They do this through the use of a bacterial peptide display — a sort of screening mechanism that can isolate plasmid DNA from antibody-bound bacteria in the sample. This DNA can then be sequenced to identify epitopes, which provide information about which antigens someone may have been exposed to, as well as how their immune system responded to them.
“It’s a very highly multiplexed and exquisitely specific way of looking at the epitopes found by antibodies in a specimen,” said Serimmune CEO Noah Nasser, who has a degree in molecular biology from UC San Diego and has previously worked for several diagnostics companies.
This week, Serimmune announced the launch of a new application of their core technology to help understand the disease states of and immune responses to SARS-CoV-2, the virus that causes COVID-19.
“So what we do is we take these antibody profiles we build, and we’re able to then map those back with about a 12 amino acid specificity to the SARS-CoV-2 proteome,” said Nasser. “And what we find is that antibody expression is highly correlated to disease state, so we can distinguish mild, moderate, severe and asymptomatic disease on the basis of antibodies that are present in the specimen.”
The more patient data Serimmune can collect, the better its core technology becomes at finding patterns across different antigen exposure and disease severity. Noticing those patterns sooner won’t only help physicians and researchers to better understand how the SARS-CoV-2 virus operates, but can also inform new approaches to diagnostics, treatments and vaccines for any antigen.
Serimmune’s launch of its new COVID antibody epitope mapping service is a way of making this data more accessible to customers like vaccine companies, government agencies and academic labs that have shown interest in better understanding the immune response to SARS-CoV-2.
“The key was to zero in on the information that researchers wanted to know and standardize that,” said Nasser. “We can actually now provide these results back in as few as two days from sample receipt.”
Beyond this new service, Serimmune also has plans to launch a longitudinal clinical study on immunity to SARS-CoV-2. Using a painless at-home collection kit, study participants send in small blood samples to Serimmune, which then uses its core technology to outline an individual immunity map.
“We provide their results back to them in the form of a personal immune landscape to COVID,” said Nasser. “And what we’re trying to do is to understand over time how that immune response changes, and what happens to that immune response on repeated exposure to COVID.”
The mapping technology is now so specific that it can tell whether a patient has antibodies from natural exposure to the SARS-CoV-2 virus or from a vaccine, he added.
While the primary focus for Serimmune remains these applications to the COVID-19 pandemic for now, Nasser also mentioned that the company has plans to move into personalized medicine, potentially offering their mapping service directly to interested patients.
“We believe that this has value to individual patients in understanding their immune status and what antigens they’ve been exposed to,” he said. Until then, Serimmune plans to continue growing its database with more patient samples.
Powered by WPeMatico