Citizen science, which asks the public to help out science projects, has produced somespectacularsuccesses. But finding a way to grab and maintain hold of the public’s attention can be a challenge. That’s led to a number of projects that turn the science challenge into a game, finding ways of making a “win” into scientific progress.
But scientists have also figured out ways of hijacking existing games, including using pre-existing fan bases that recruits players through in-game rewards. Now, there’s a progress report on an effort to turn EVE Online players into cell biology experts. Thanks to some in-game rewards, over 300,000 players contributed roughly 33 million calls on where in a cell a protein was located. This not only greatly expanded a public database of information on proteins, but it enabled the researchers to better train a neural network to do the same thing.
While in many cases, it’s been possible to determine or infer what a protein does, that only gives us a partial idea of its actual function. That’s because many proteins are shipped to specific locations in cells. So while two proteins may look similar in terms of the order and identity of their amino acids, one may be shipped to the nucleus, where it interacts with DNA, while its relative gets sent to the cell’s surface, where it does acts on proteins in; the surroundings. So figuring out where a protein normally resides within cells can go a long way toward helping us figure out its normal functions.
For the last year or so, Stratolaunch has conducted a number of ground-based tests on the world’s largest aircraft, both inside its gargantuan hangar and on a runway in Mojave, California. If all goes well, the company plans for the aircraft with a 117-meter wingspan to make its maiden flight by the end of this year.
But the aircraft is only a means to an end—sustainably launching rockets into space. Although Stratolaunch appears to have built a fine airplane, questions have lingered for years regarding exactly which rockets will be flown to a cruising altitude, and then released by the airplane. And when you’ve built an aircraft the likes of which have never been seen before, such curiosity is understandable.
On Monday, the company finally provided some additional clarity. Previously, Stratolaunch announced an agreement to launch small Pegasus rockets from the aircraft, but these boosters can only deliver up to 370kg into low-Earth orbit. (And they are so small, their use could not possibly justify the scale of the Stratolaunch plane, with a wingspan 20 meters greater than even the Spruce Goose).
Magnetic resonance imaging is an invaluable tool in the medical field, but it’s also a slow and cumbersome process. It may take fifteen minutes or an hour to complete a scan, during which time the patient, perhaps a child or someone in serious pain, must sit perfectly still. NYU has been working on a way to accelerate this process, and is now collaborating with Facebook with the goal of cutting down MRI durations by 90 percent by applying AI-based imaging tools.
It’s important at the outset to distinguish this effort from other common uses of AI in the medical imaging field. An X-ray, or indeed an MRI scan, once completed, could be inspected by an object recognition system watching for abnormalities, saving time for doctors and maybe even catching something they might have missed. This project isn’t about analyzing imagery that’s already been created, but rather expediting its creation in the first place.
The reason MRIs take so long is because the machine must create a series of 2D images or slices, many of which must be stacked up to make a 3D image. Sometimes only a handful are needed, but for full fidelity and depth — for something like a scan for a brain tumor — lots of slices are required.
The FastMRI project, begun in 2015 by NYU researchers, investigates the possibility of creating imagery of a similar quality to a traditional scan, but by collecting only a fraction of the data normally needed.
Think of it like scanning an ordinary photo. You could scan the whole thing… but if you only scanned every other line (this is called “undersampling”) and then intelligently filled in the missing pixels, it would take half as long. And machine learning systems are getting quite good at tasks like that. Our own brains do it all the time: you have blind spots with stuff in them right now that you don’t notice because your vision system is filling in the gaps — intelligently.
The data collected at left could be “undersampled” as at right, with the missing data filled in later
If an AI system could be trained to fill in the gaps from MRI scans where only the most critical data is collected, the actual time during which a patient would have to sit in the imaging tube could be reduced considerably. It’s easier on the patient, and one machine could handle far more people than it does doing a full scan every time, making scans cheaper and more easily obtainable.
The NYU School of Medicine researchers began work on this three years ago and published some early results showing that the approach was at least feasible. But like an MRI scan, this kind of work takes time.
“We and other institutions have taken some baby steps in using AI for this type of problem,” explained NYU’s Dan Sodickson, director of the Center of Advanced Imaging Innovation and Research there. “The sense is that already in the first attempts, with relatively simple methods, we can do better than other current acceleration techniques — get better image quality and maybe accelerate further by some percentage, but not by large multiples yet.”
So to give the project a boost, Sodickson and the radiologists at NYU are combining forces with the AI wonks at Facebook and its Artificial Intelligence Research group (FAIR).
NYU School of Medicine’s Department of Radiology chair Michael Recht, MD, Daniel Sodickson, MD, vice chair for research and director of the Center for Advanced Imaging Innovation and Yvonne Lui, MD, director of artificial intelligence, examine an MRI
“We have some great physicists here and even some hot-stuff mathematicians, but Facebook and FAIR have some of the leading AI scientists in the world. So it’s complementary expertise,” Sodickson said.
And while Facebook isn’t planning on starting a medical imaging arm, FAIR has a pretty broad mandate.
“We’re looking for impactful but also scientifically interesting problems,” said FAIR’s Larry Zitnick. AI-based creation or re-creation of realistic imagery (often called “hallucination”) is a major area of research, but this would be a unique application of it — not to mention one that could help some people.
With a patient’s MRI data, he explained, the generated imagery “doesn’t need to be just plausible, but it needs to retain the same flaws.” So the computer vision agent that fills in the gaps needs to be able to recognize more than just overall patterns and structure, and to be able to retain and even intelligently extend abnormalities within the image. To not do so would be a massive modification of the original data.
Fortunately it turns out that MRI machines are pretty flexible when it comes to how they produce images. If you would normally take scans from 200 different positions, for instance, it’s not hard to tell the machine to do half that, but with a higher density in one area or another. Other imagers like CT and PET scanners aren’t so docile.
Even after a couple years of work the research is still at an early stage. These things can’t be rushed, after all, and with medical data there are ethical considerations and a difficulty in procuring enough data. But the NYU researchers’ ground work has paid off with initial results and a powerful data set.
Zitnick noted that because AI agents require lots of data to train up to effective levels, it’s a major change going from a set of, say, 500 MRI scans to a set of 10,000. With the former data set you might be able to do a proof of concept, but with the latter you can make something accurate enough to actually use.
The partnership announced today is between NYU and Facebook, but both hope that others will join up.
“We’re working on this out in the open. We’re going to be open-sourcing it all,” said Zitnick. One might expect no less of academic research, but of course a great deal of AI work in particular goes on behind closed doors these days.
So the first steps as a joint venture will be to define the problem, document the data set and release it, create baselines and metrics by which to measure their success, and so on. Meanwhile, the two organizations will be meeting and swapping data regularly and running results past actual clinicians.
“We don’t know how to solve this problem,” Zitnick said. “We don’t know if we’ll succeed or not. But that’s kind of the fun of it.”
You wouldn’t expect a medical app to get its start as a Snapchat competitor. Neither did video chat startup TapTalk’s founder Onno Faber. But four years ago he was diagnosed with a rare disease called Neurofibromatosis Type 2 that caused tumors leading Onno to lose hearing in one ear. He’s amongst the one in ten people with an uncommon health condition suffering from the lack of data designed to invent treatments for their ails. And he’s now the co-founder of RDMD.
Emerging from stealth today, RDMD aggregates and analyzes medical records and sells the de-identified data to pharmaceutical companies to help them develop medicines. In exchange for access to the data, patients gets their fragmented medical records organized into an app they can use to track their treatment and get second opinions. It’s like Flatiron Health, the Google-backed cancer data startup that just got bought for $2.1 billion, but for rare diseases.
Now RDMD is announcing it’s raised a $3 million seed round led by Lux Capital and joined by Village Global, Shasta, Garuda, First Round’s Healthcare Coop, and a ton of top healthtech angels including Flatiron investors and board members. The cash will help RDMD expand to build out its product and address more rare diseases.
RDMD founders (from left): Nancy Yu and Onno Faber
“We believe that the traditional way rare disease R&D is done needs to change” RDMD CEO Nancy Yu tells TechCrunch. The former head of corp dev at 23andme explains that, “There are over 7,000 rare diseases and growing, yet <5% of them have an FDA-approved therapy . . . it’s a massive problem.”
While data infrastructure supports development of treatments for more common diseases like cancer and diabetes, rare diseases have been ignored because it’s wildly expensive and difficult to collect the high-quality data required to invent new medicines. But “RDMD generates research-grade, regulatory-grade data from patient medical records for use in rare disease drug R&D” says Yu. The more data it can collect, the more pharma companies can do to help patients.
Trading Utility For Patient Data
With RDMD’s app, a patient’s medical data that’s strewn across hospitals and health facilities can be compiled, organized and synthesized. Handwritten physicians’ notes and faxes are digitized with optical character recognition, structuring the data for scientific research. RDMD lays out a patients’ records in a disease-specific timeline that summarizes their data that can be kept updated, delivered to specialists for consultations, or shared with their family and caregivers.
If users opt in, that data can be anonymized and provided to research organizations, hospitals, and pharma companies that pay RDMD, though these patients can delete their accounts at any time. Since it’s straight from the medical records, the data is reliable enough to be regulation-compliant and research-ready. That allows it to accelerate the drug development process that’s both lucrative and life-saving. “It normally takes millions of dollars over several years to gather this type of data in rare diseases” Yu notes. “For the first time, we have a centralized and consented set of data for use in translational research, in a fraction of the time and cost.”
So far, RDMD has enrolled 150 patients with neurofibromatosis. But the potential to expand to other rare diseases attracted a previous pre-seed round from Village Global and new funding from angels like Clover Health CEO and Flatiron board member Vivek Garipalli, Flatiron investor and GV (Google Ventures) partner Vineeta Agarwala, Twitter CTO Parag Agrawal, former 23andme president Andy Page, and the husband and wife duo of former Instagram VP of product Kevin Weil and 137 Ventures managing director Elizabeth Weil.
“Onno and Nancy realized there’s an opportunity to do in rare diseases what Flatiron has done in oncology — to aggregate clinical data from patients, and to leverage that data in clinical trials and other use cases for biotech and pharma” says Shasta partner Nikhil Basu Trivedi. RDMD will be competing against pharma contract research organizations that incur high costs for collecting data the startup gets for free from patients in exchange for its product. Luckily, Flatiron’s exit paved the way for industry acceptance of RDMD’s model.
“The biggest risk for our company is if we lose our focus on providing real, immediate value to rare disease patients and families. Patients are the reason we are all here, and only with their trust can we fundamentally change how rare disease drug research is done” says Yu. RDMD will have to ensure it can protect the privacy of patients, the security of data, and the efficacy of its application to drug development.
Hindering this process is just one more consequence of our fractured medical records. Hopefully if startups like RDMD and Flatiron can demonstrate the massive value created by unifying medical data, it will pressure the healthcare power players to cooperate on a true industry standard.
The rancid refuse was chipped off an infamous sewer clog discovered in London late last year called the Whitechapel “Fatberg”—the preferred term for such muck monsters. The complete clog clocked in as an epic 250-meter-long, 130-metric ton mass of congealed excrement and waste, thought to be one of the largest—if not the largest—fatbergs ever identified. Authorities found it blocking a Victorian-era sewer line in the eastern Whitechapel area of the city. They spent nine long weeks in a subterranean war, hacking and blasting away the hardened blob of feces, fats, wet wipes, and various other detritus.
The Russian space program gets a lot of credit for flying the first woman in space. In fact, the Soviet Union flew the first two women: Valentina Tereshkova in 1963 and Svetlana Savitskaya in 1982. NASA waited until the space shuttle era before selecting female astronauts, and Sally Ride did not become the first American woman in space until 1983.
However, since Ride broke the US space gender barrier 35 years ago, 50 other American women have flown into space. By contrast, just two other women from Russia have flown into space since then, Yelena Kondakova (1994 and 1997) and Yelena Serova (2014). Two women from China, Japan, and Canada have also flown into space, as well as one woman each from the countries France, India, Italy, South Korea, and the United Kingdom.
This disparity seems likely to only widen in the future. Of NASA’s last two astronaut classes, in 2013 and 2017, nine of the 20 chosen candidates were women. Of Russia’s last two classes in 2012 and 2018, just a single woman, Anna Kikina, was picked. Selected in 2012, Kikina was subsequently expelled from the cosmonaut corps in 2014 for unspecified reasons. After a public outcry, Kikina was reinstated, but it is not clear whether she will ever fly.
Palm oil is ubiquitous and is set to become more so over the next few decades. The oil is used in food, cleaning, and beauty products and as biofuel, so demand is set to grow rapidly. With this skyrocketing demand comes a need for the land on which to grow more oil palms—and a threat to the ecosystems currently using that land.
Currently, Southeast Asia is the oil palm hotspot, and the deforestation and ensuing damage in the region have been well publicized. But much of the future expansion may happen in Africa, introducing the likelihood of new conservation problems. A paper published in this week’s PNAS argues that there’s a huge overlap between the land where oil palms could be grown and the land that houses the continent’s primates. “Large-scale expansion of oil palm cultivation in Africa will have unavoidable, negative effects on primates,” write Giovanni Strona and his colleagues.
Growth in demand, loss in habitat
The tree that provides us with palm oil (which is pressed from its fruit) is a tropical species. Currently, palm oil agriculture uses approximately 20 million hectares. One million hectares (or 10,000 km2) is about half the area of New Jersey; 20 million is about the area of Nebraska. Most of these plantations are in Indonesia and Malaysia.
One of the least fun jobs when writing a scientific paper is coming up with a motivation. It should be easy and fun: look at this awesomely cool thing we did—aren’t the results interesting? Instead, we typically have to claim to reveal the secrets of the Universe, cure cancer, or protect the public. Preferably all three at the same time.
A recent paper (PDF) on using Wi-Fi as an environmental sensor has some really exciting results. But my heart shrank three sizes after reading the following: “Traditional baggage check involves either high manpower for manual examinations or expensive and specialized instruments, such as X-ray and CT. As such, many public places (i.e., museums and schools) that lack of strict security check are exposed to high risk.”
As I said, the research is totally cool. It’s just not likely to ever help with security unless molesting people with hip replacements is your version of improved security.