Tag Archives: lab
#437171 Scientists Tap the World’s Most ...
In The Hitchhiker’s Guide to the Galaxy by Douglas Adams, the haughty supercomputer Deep Thought is asked whether it can find the answer to the ultimate question concerning life, the universe, and everything. It replies that, yes, it can do it, but it’s tricky and it’ll have to think about it. When asked how long it will take it replies, “Seven-and-a-half million years. I told you I’d have to think about it.”
Real-life supercomputers are being asked somewhat less expansive questions but tricky ones nonetheless: how to tackle the Covid-19 pandemic. They’re being used in many facets of responding to the disease, including to predict the spread of the virus, to optimize contact tracing, to allocate resources and provide decisions for physicians, to design vaccines and rapid testing tools, and to understand sneezes. And the answers are needed in a rather shorter time frame than Deep Thought was proposing.
The largest number of Covid-19 supercomputing projects involves designing drugs. It’s likely to take several effective drugs to treat the disease. Supercomputers allow researchers to take a rational approach and aim to selectively muzzle proteins that SARS-CoV-2, the virus that causes Covid-19, needs for its life cycle.
The viral genome encodes proteins needed by the virus to infect humans and to replicate. Among these are the infamous spike protein that sniffs out and penetrates its human cellular target, but there are also enzymes and molecular machines that the virus forces its human subjects to produce for it. Finding drugs that can bind to these proteins and stop them from working is a logical way to go.
The Summit supercomputer at Oak Ridge National Laboratory has a peak performance of 200,000 trillion calculations per second—equivalent to about a million laptops. Image credit: Oak Ridge National Laboratory, U.S. Dept. of Energy, CC BY
I am a molecular biophysicist. My lab, at the Center for Molecular Biophysics at the University of Tennessee and Oak Ridge National Laboratory, uses a supercomputer to discover drugs. We build three-dimensional virtual models of biological molecules like the proteins used by cells and viruses, and simulate how various chemical compounds interact with those proteins. We test thousands of compounds to find the ones that “dock” with a target protein. Those compounds that fit, lock-and-key style, with the protein are potential therapies.
The top-ranked candidates are then tested experimentally to see if they indeed do bind to their targets and, in the case of Covid-19, stop the virus from infecting human cells. The compounds are first tested in cells, then animals, and finally humans. Computational drug discovery with high-performance computing has been important in finding antiviral drugs in the past, such as the anti-HIV drugs that revolutionized AIDS treatment in the 1990s.
World’s Most Powerful Computer
Since the 1990s the power of supercomputers has increased by a factor of a million or so. Summit at Oak Ridge National Laboratory is presently the world’s most powerful supercomputer, and has the combined power of roughly a million laptops. A laptop today has roughly the same power as a supercomputer had 20-30 years ago.
However, in order to gin up speed, supercomputer architectures have become more complicated. They used to consist of single, very powerful chips on which programs would simply run faster. Now they consist of thousands of processors performing massively parallel processing in which many calculations, such as testing the potential of drugs to dock with a pathogen or cell’s proteins, are performed at the same time. Persuading those processors to work together harmoniously is a pain in the neck but means we can quickly try out a lot of chemicals virtually.
Further, researchers use supercomputers to figure out by simulation the different shapes formed by the target binding sites and then virtually dock compounds to each shape. In my lab, that procedure has produced experimentally validated hits—chemicals that work—for each of 16 protein targets that physician-scientists and biochemists have discovered over the past few years. These targets were selected because finding compounds that dock with them could result in drugs for treating different diseases, including chronic kidney disease, prostate cancer, osteoporosis, diabetes, thrombosis and bacterial infections.
Scientists are using supercomputers to find ways to disable the various proteins—including the infamous spike protein (green protrusions)—produced by SARS-CoV-2, the virus responsible for Covid-19. Image credit: Thomas Splettstoesser scistyle.com, CC BY-ND
Billions of Possibilities
So which chemicals are being tested for Covid-19? A first approach is trying out drugs that already exist for other indications and that we have a pretty good idea are reasonably safe. That’s called “repurposing,” and if it works, regulatory approval will be quick.
But repurposing isn’t necessarily being done in the most rational way. One idea researchers are considering is that drugs that work against protein targets of some other virus, such as the flu, hepatitis or Ebola, will automatically work against Covid-19, even when the SARS-CoV-2 protein targets don’t have the same shape.
Our own work has now expanded to about 10 targets on SARS-CoV-2, and we’re also looking at human protein targets for disrupting the virus’s attack on human cells. Top-ranked compounds from our calculations are being tested experimentally for activity against the live virus. Several of these have already been found to be active.The best approach is to check if repurposed compounds will actually bind to their intended target. To that end, my lab published a preliminary report of a supercomputer-driven docking study of a repurposing compound database in mid-February. The study ranked 8,000 compounds in order of how well they bind to the viral spike protein. This paper triggered the establishment of a high-performance computing consortium against our viral enemy, announced by President Trump in March. Several of our top-ranked compounds are now in clinical trials.
Also, we and others are venturing out into the wild world of new drug discovery for Covid-19—looking for compounds that have never been tried as drugs before. Databases of billions of these compounds exist, all of which could probably be synthesized in principle but most of which have never been made. Billion-compound docking is a tailor-made task for massively parallel supercomputing.
Dawn of the Exascale Era
Work will be helped by the arrival of the next big machine at Oak Ridge, called Frontier, planned for next year. Frontier should be about 10 times more powerful than Summit. Frontier will herald the “exascale” supercomputing era, meaning machines capable of 1,000,000,000,000,000,000 calculations per second.
Although some fear supercomputers will take over the world, for the time being, at least, they are humanity’s servants, which means that they do what we tell them to. Different scientists have different ideas about how to calculate which drugs work best—some prefer artificial intelligence, for example—so there’s quite a lot of arguing going on.
Hopefully, scientists armed with the most powerful computers in the world will, sooner rather than later, find the drugs needed to tackle Covid-19. If they do, then their answers will be of more immediate benefit, if less philosophically tantalizing, than the answer to the ultimate question provided by Deep Thought, which was, maddeningly, simply 42.
This article is republished from The Conversation under a Creative Commons license. Read the original article.
Image credit: NIH/NIAID Continue reading
Posted in Human Robots
#436774 AI Is an Energy-Guzzler. We Need to ...
There is a saying that has emerged among the tech set in recent years: AI is the new electricity. The platitude refers to the disruptive power of artificial intelligence for driving advances in everything from transportation to predicting the weather.
Of course, the computers and data centers that support AI’s complex algorithms are very much dependent on electricity. While that may seem pretty obvious, it may be surprising to learn that AI can be extremely power-hungry, especially when it comes to training the models that enable machines to recognize your face in a photo or for Alexa to understand a voice command.
The scale of the problem is difficult to measure, but there have been some attempts to put hard numbers on the environmental cost.
For instance, one paper published on the open-access repository arXiv claimed that the carbon emissions for training a basic natural language processing (NLP) model—algorithms that process and understand language-based data—are equal to the CO2 produced by the average American lifestyle over two years. A more robust model required the equivalent of about 17 years’ worth of emissions.
The authors noted that about a decade ago, NLP models could do the job on a regular commercial laptop. Today, much more sophisticated AI models use specialized hardware like graphics processing units, or GPUs, a chip technology popularized by Nvidia for gaming that also proved capable of supporting computing tasks for AI.
OpenAI, a nonprofit research organization co-founded by tech prophet and profiteer Elon Musk, said that the computing power “used in the largest AI training runs has been increasing exponentially with a 3.4-month doubling time” since 2012. That’s about the time that GPUs started making their way into AI computing systems.
Getting Smarter About AI Chip Design
While GPUs from Nvidia remain the gold standard in AI hardware today, a number of startups have emerged to challenge the company’s industry dominance. Many are building chipsets designed to work more like the human brain, an area that’s been dubbed neuromorphic computing.
One of the leading companies in this arena is Graphcore, a UK startup that has raised more than $450 million and boasts a valuation of $1.95 billion. The company’s version of the GPU is an IPU, which stands for intelligence processing unit.
To build a computer brain more akin to a human one, the big brains at Graphcore are bypassing the precise but time-consuming number-crunching typical of a conventional microprocessor with one that’s content to get by on less precise arithmetic.
The results are essentially the same, but IPUs get the job done much quicker. Graphcore claimed it was able to train the popular BERT NLP model in just 56 hours, while tripling throughput and reducing latency by 20 percent.
An article in Bloomberg compared the approach to the “human brain shifting from calculating the exact GPS coordinates of a restaurant to just remembering its name and neighborhood.”
Graphcore’s hardware architecture also features more built-in memory processing, boosting efficiency because there’s less need to send as much data back and forth between chips. That’s similar to an approach adopted by a team of researchers in Italy that recently published a paper about a new computing circuit.
The novel circuit uses a device called a memristor that can execute a mathematical function known as a regression in just one operation. The approach attempts to mimic the human brain by processing data directly within the memory.
Daniele Ielmini at Politecnico di Milano, co-author of the Science Advances paper, told Singularity Hub that the main advantage of in-memory computing is the lack of any data movement, which is the main bottleneck of conventional digital computers, as well as the parallel processing of data that enables the intimate interactions among various currents and voltages within the memory array.
Ielmini explained that in-memory computing can have a “tremendous impact on energy efficiency of AI, as it can accelerate very advanced tasks by physical computation within the memory circuit.” He added that such “radical ideas” in hardware design will be needed in order to make a quantum leap in energy efficiency and time.
It’s Not Just a Hardware Problem
The emphasis on designing more efficient chip architecture might suggest that AI’s power hunger is essentially a hardware problem. That’s not the case, Ielmini noted.
“We believe that significant progress could be made by similar breakthroughs at the algorithm and dataset levels,” he said.
He’s not the only one.
One of the key research areas at Qualcomm’s AI research lab is energy efficiency. Max Welling, vice president of Qualcomm Technology R&D division, has written about the need for more power-efficient algorithms. He has gone so far as to suggest that AI algorithms will be measured by the amount of intelligence they provide per joule.
One emerging area being studied, Welling wrote, is the use of Bayesian deep learning for deep neural networks.
It’s all pretty heady stuff and easily the subject of a PhD thesis. The main thing to understand in this context is that Bayesian deep learning is another attempt to mimic how the brain processes information by introducing random values into the neural network. A benefit of Bayesian deep learning is that it compresses and quantifies data in order to reduce the complexity of a neural network. In turn, that reduces the number of “steps” required to recognize a dog as a dog—and the energy required to get the right result.
A team at Oak Ridge National Laboratory has previously demonstrated another way to improve AI energy efficiency by converting deep learning neural networks into what’s called a spiking neural network. The researchers spiked their deep spiking neural network (DSNN) by introducing a stochastic process that adds random values like Bayesian deep learning.
The DSNN actually imitates the way neurons interact with synapses, which send signals between brain cells. Individual “spikes” in the network indicate where to perform computations, lowering energy consumption because it disregards unnecessary computations.
The system is being used by cancer researchers to scan millions of clinical reports to unearth insights on causes and treatments of the disease.
Helping battle cancer is only one of many rewards we may reap from artificial intelligence in the future, as long as the benefits of those algorithms outweigh the costs of using them.
“Making AI more energy-efficient is an overarching objective that spans the fields of algorithms, systems, architecture, circuits, and devices,” Ielmini said.
Image Credit: analogicus from Pixabay Continue reading
Posted in Human Robots
#436578 AI Just Discovered a New Antibiotic to ...
Penicillin, one of the greatest discoveries in the history of medicine, was a product of chance.
After returning from summer vacation in September 1928, bacteriologist Alexander Fleming found a colony of bacteria he’d left in his London lab had sprouted a fungus. Curiously, wherever the bacteria contacted the fungus, their cell walls broke down and they died. Fleming guessed the fungus was secreting something lethal to the bacteria—and the rest is history.
Fleming’s discovery of penicillin and its later isolation, synthesis, and scaling in the 1940s released a flood of antibiotic discoveries in the next few decades. Bacteria and fungi had been waging an ancient war against each other, and the weapons they’d evolved over eons turned out to be humanity’s best defense against bacterial infection and disease.
In recent decades, however, the flood of new antibiotics has slowed to a trickle.
Their development is uneconomical for drug companies, and the low-hanging fruit has long been picked. We’re now facing the emergence of strains of super bacteria resistant to one or more antibiotics and an aging arsenal to fight them with. Gone unchallenged, an estimated 700,000 deaths worldwide due to drug resistance could rise to as many as 10 million in 2050.
Increasingly, scientists warn the tide is turning, and we need a new strategy to keep pace with the remarkably quick and boundlessly creative tactics of bacterial evolution.
But where the golden age of antibiotics was sparked by serendipity, human intelligence, and natural molecular weapons, its sequel may lean on the uncanny eye of artificial intelligence to screen millions of compounds—and even design new ones—in search of the next penicillin.
Hal Discovers a Powerful Antibiotic
In a paper published this week in the journal, Cell, MIT researchers took a step in this direction. The team says their machine learning algorithm discovered a powerful new antibiotic.
Named for the AI in 2001: A Space Odyssey, the antibiotic, halicin, successfully wiped out dozens of bacterial strains, including some of the most dangerous drug-resistant bacteria on the World Health Organization’s most wanted list. The bacteria also failed to develop resistance to E. coli during a month of observation, in stark contrast to existing antibiotic ciprofloxacin.
“In terms of antibiotic discovery, this is absolutely a first,” Regina Barzilay, a senior author on the study and computer science professor at MIT, told The Guardian.
The algorithm that discovered halicin was trained on the molecular features of 2,500 compounds. Nearly half were FDA-approved drugs, and another 800 naturally occurring. The researchers specifically tuned the algorithm to look for molecules with antibiotic properties but whose structures would differ from existing antibiotics (as halicin’s does). Using another machine learning program, they screened the results for those likely to be safe for humans.
Early study suggests halicin attacks the bacteria’s cell membranes, disrupting their ability to produce energy. Protecting the cell membrane from halicin might take more than one or two genetic mutations, which could account for its impressive ability to prevent resistance.
“I think this is one of the more powerful antibiotics that has been discovered to date,” James Collins, an MIT professor of bioengineering and senior author told The Guardian. “It has remarkable activity against a broad range of antibiotic-resistant pathogens.”
Beyond tests in petri-dish bacterial colonies, the team also tested halicin in mice. The antibiotic cleared up infections of a strain of bacteria resistant to all known antibiotics in a day. The team plans further study in partnership with a pharmaceutical company or nonprofit, and they hope to eventually prove it safe and effective for use in humans.
This last bit remains the trickiest step, given the cost of getting a new drug approved. But Collins hopes algorithms like theirs will help. “We could dramatically reduce the cost required to get through clinical trials,” he told the Financial Times.
A Universe of Drugs Awaits
The bigger story may be what happens next.
How many novel antibiotics await discovery, and how far can AI screening take us? The initial 6,000 compounds scanned by Barzilay and Collins’s team is a drop in the bucket.
They’ve already begun digging deeper by setting the algorithm loose on 100 million molecules from an online library of 1.5 billion compounds called the ZINC15 database. This first search took three days and turned up 23 more candidates that, like halicin, differ structurally from existing antibiotics and may be safe for humans. Two of these—which the team will study further—appear to be especially powerful.
Even more ambitiously, Barzilay hopes the approach can find or even design novel antibiotics that kill bad bacteria with alacrity while sparing the good guys. In this way, a round of antibiotics would cure whatever ails you without taking out your whole gut microbiome in the process.
All this is part of a larger movement to use machine learning algorithms in the long, expensive process of drug discovery. Other players in the area are also training AI on the vast possibility space of drug-like compounds. Last fall, one of the leaders in the area, Insilico, was challenged by a partner to see just how fast their method could do the job. The company turned out a new a proof-of-concept drug candidate in only 46 days.
The field is still developing, however, and it has yet to be seen exactly how valuable these approaches will be in practice. Barzilay is optimistic though.
“There is still a question of whether machine-learning tools are really doing something intelligent in healthcare, and how we can develop them to be workhorses in the pharmaceuticals industry,” she said. “This shows how far you can adapt this tool.”
Image Credit: Halicin (top row) prevented the development of antibiotic resistance in E. coli, while ciprofloxacin (bottom row) did not. Collins Lab at MIT Continue reading
Posted in Human Robots