The COVID-19 pandemic seemed like a never-ending parade of SARS-CoV-2 variants, each equipped with new ways to evade the immune system, leaving the world bracing for what would come next.

But what if there were a way to make predictions about new viral variants before they actually emerge?

A new artificial intelligence tool namedEVEscape,developed by researchers at Harvard Medical School and the University of Oxford, can do just that.

The tool has two elements: A model of evolutionary sequences that predicts changes that can occur to a virus, and detailed biological and structural information about the virus. Together, they allow EVEscape to make predictions about the variants most likely to occur as the virus evolves.

In a studypublished Wednesday inNature, the researchers show that had it been deployed at the start of the COVID-19 pandemic, EVEscape would have predicted the most frequent mutations and identified the most concerning variants for SARS-CoV-2. The tool also made accurate predictions about other viruses, including HIV and influenza.

The researchers are now using EVEscape to look ahead at SARS-CoV-2 and predict future variants of concern; every two weeks, they release a ranking of new variants. Eventually, this information could help scientists develop more effective vaccines and therapies. The team is also broadening the work to include more viruses.

We want to know if we can anticipate the variation in viruses and forecast new variants because if we can, thats going to be extremely important for designing vaccines and therapies, said senior author Debora Marks, associate professor of systems biology in the Blavatnik Institute at HMS.

The researchers first developedEVE, short for evolutionary model of variant effect, in a different context: gene mutations that cause human diseases. The core of EVE is a generative model that learns to predict the functionality of proteins based on large-scale evolutionary data across species.

In a previous study, EVE allowed researchers todiscern disease-causing from benign mutations in genes implicated in various conditions, including cancers and heart rhythm disorders.

Viruses are flexible its almost like theyve evolved to evolve.

Debora Marks, Blavatnik Institute at Harvard Medical School

You can use these generative models to learn amazing things from evolutionary information the data have hidden secrets that you can reveal, Marks said.

As the COVID-19 pandemic hit and progressed, the world was caught off guard by SARS-CoV-2s impressive ability to evolve. The virus kept morphing, changing its structure in ways subtle and substantial to slip past vaccines and therapies designed to defeat it.

We underestimate the ability of things to mutate when theyre under pressure and have a large population in which to do so, Marks said. Viruses are flexible its almost like theyve evolved to evolve.

Watching the pandemic unfold, Marks and her team saw an opportunity to help: TheyrebuiltEVE into a new tool called EVEscape for the purpose of predicting viral variants.

They took the generative model from EVE which can predict mutations in viral proteins that wont interfere with the viruss function and added biological and structural details about the virus, including information about regions most easily targeted by the immune system.

Were taking biological information about how the immune system works and layering it on our learnings from the broader evolutionary history of the virus, explained co-lead author Nicole Thadani,a former research fellow in the Marks lab.

Such an approach, Marks emphasized, means that EVEscape has a flexible framework that can be easily adapted to any virus.

In the new study, the team turned the clock back to January 2020, just before the COVID-19 pandemic started. Then they asked EVEscape to predict what would happen with SARS-CoV-2.

Its as if you have a time machine. You go back to day one, and you say, I only have that data, what am I going to say is happening? Marks said.

The tool was able to sift through the tens of thousands of new SARS-CoV-2 variants produced each week and identify the ones most likely to become problematic.

EVEscape predicted which SARS-CoV-2 mutations would occur during the pandemic with accuracy similar to this of experimental approaches that test the virus ability to bind to antibodies made by the immune system. EVEscape outperformed experimental approaches in predicting which of those mutations would be most prevalent. More importantly, EVEscape could make its predictions more quickly and efficiently than lab-based testing since it didnt need to wait for relevant antibodies to arise in the population and become available for testing.

Additionally, EVEscape predicted which antibody-based therapies would lose their efficacy as the pandemic progressed and the virus developed mutations to escape these treatments.

The tool was also able to sift through the tens of thousands of new SARS-CoV-2 variants produced each week and identify the ones most likely to become problematic.

By rapidly determining the threat level of new variants, we can help inform earlier public health decisions, said co-lead author Sarah Gurev, a graduate student in the Marks lab from the Electrical Engineering and Computer Science program at MIT.

In a final step, the team demonstrated that EVEscape could be generalized to other common viruses, including HIV and influenza.

The team is now applying EVEscape to SARS-CoV-2 in real time, using all of the information available to make predictions about how it might evolve next.

The researchers publish a biweeklyranking of new SARS-CoV-2 variantson their website and share this information with entities such as the World Health Organization. Thecomplete code for EVEscapeis also freely available online.

They are also testing EVEscape on understudied viruses such as Lassa and Nipah, two pathogens of pandemic potential for which relatively little information exists.

We want to figure out how we can actually design vaccines and therapies that are future-proof.

Noor Youssef, research fellow in the Marks lab

Such less-studied viruses can have a huge impact on human health across the globe, the researchers noted.

Another important application of EVEscape would be to evaluate vaccines and therapies against current and future viral variants. The ability to do so can help scientists design treatments that are able to withstand the escape mechanisms a virus acquires.

Historically, vaccine and therapeutic design has been retrospective, slow, and tied to the exact sequences known about a given virus, Thadani said.

Noor Youssef, a research fellow in the Marks lab, added, We want to figure out how we can actually design vaccines and therapies that are future-proof.

Additional authors: Pascal Notin, Nathan Rollins, Daniel Ritter, Chris Sander, and Yarin Gal.

Disclosures: Marks is an adviser for Dyno Therapeutics, Octant, Jura Bio, Tectonic Therapeutic, and Genentech, and is a co-founder of Seismic Therapeutic. Sander is an adviser for CytoReason Ltd.

Funding for the research was provided by the National Institutes of Health (GM141007-01A1), the Coalition for Epidemic Preparedness Innovations, the Chan Zuckerberg Initiative, GSK, the UK Engineering and Physical Sciences Research Council, and the Alan Turing Institute.

Sign up for daily emails to get the latest Harvardnews.

See the rest here:

Scientists develop AI tool that predicts virus mutations - Harvard Gazette

When Heather Cox Richardson was an undergraduate at Harvard, she took a course on the Civil War. Research for a final paper took her to the basement of the Division of Government Documents, known as Gov Docs, where she spent long hours reading articles on microfilm. The room was dark, cold and mostly empty, except for one professor and an unexpected visitor: John Updike. Richardson never spoke to him and she still doesnt know why he was there. But, in a phone interview, she recalled the chance encounter one of those things a student is popeyed over with fondness and reverence. Maybe it was the silence of the library; maybe it was the significance of her subject or the illustriousness of Updikes company; but by the time she completed her paper, a historian was born.

Richardsons latest project is Democracy Awakening, an examination of American history through the lens of authoritarianism, which debuted at No. 4 on the hardcover nonfiction list. Shes also known for Letters From an American, a wildly popular newsletter that presents the days political news in simple, streamlined terms.

When she sits down to compose her daily dispatch, Richardson tends to picture her college roommates as her audience. Theyre going to give me grief if I say something stupid, but they dont wish me ill, she said. Its much harder to write for an audience that you believe is eager to tear you down.

Not surprisingly, this Boston College professor is bullish on the importance of studying history. But what does she have to say to current undergraduates who feel pressured to focus on practical subjects like finance, law and computer science?

Anybody who studies history learns two things: They learn to do research and they learn to write, Richardson said. The reason that matters now is that most people who are in college now are going to end up switching jobs a number of times in their careers. She pointed out that some of these jobs may not even exist yet. So, Richardson continued, What history will give you is the ability to pivot into the different ideas, the different fields, the different careers as they arise.

A historian will also know how to metabolize confounding situations, distill them to their essence and communicate that information to others as Richardson does with current events in her newsletter. She said, It makes sense to recognize that these skills provide a tool kit for moving into the future in a way that Im not entirely sure we always recognize. Plus, you never know who youll meet along the way.

Elisabeth Egan is an editor at the Book Review and the author of A Window Opens.

More:

Heather Cox Richardson Wants You to Study History - The New York Times

Weve reached that lull in the school year when the excitement of Back to School has worn off and the reality of spending long stretches staring into the laptop and Smart Board has set in. Sitting still, glued to screens, for hours.

Pandemic-era remote learning is well over, but for middle and high school students, school can still seem like an endless Zoom in the dullest sense of the word. Many schools have schedules loaded with classwork, and with early starts and less frequent physical education classes, and have curtailed lunch and recess seemingly in an effort to improve Americas woeful standing in student performance.

The kind of classes that used to cut into desk time have largely been squeezed out of the schedule. No more woodworking or shop, automotive arts, typing or home economics classes that taught skills better learned through active doing rather than passive learning.

Instead, after decades of decline, Career Technical Education, as its now known, has focused on upgrading itself academically. C.T.E. is now likely to consist of digital design, 3-D printing, communications and computer science; in New York State, for example, what was once known as industrial arts has evolved into technology education. And forget altogether about home economics; student enrollment in the full category of Family and Consumer Sciences courses declined by nearly 40 percent between 2003 and 2012.

But theres an argument for bringing back home ec and shop, not only for students who may be better served by opting out of college, but also for those students bent on white-collar life. These are the kinds of adulting skills many kids no longer learn at home, whether its because their working parents are too busy or their extracurriculars too onerous. And the benefits of these classes using ones hands, working with real-world materials, collaborating offscreen, taking risks extend well beyond the classroom.

First, to state the obvious: Kids need a break. The advantages of getting up from ones desk standing, walking around, going outside, taking 15-minute breaks are well known to adults, especially for people who spend much of their days on screens. Yet we dont extend the same courtesy to schoolchildren. An hour or two each week grappling with wood planks or mixing batter can leaven a long and monotonous school day.

Second, kids learn from physical work just as they do from mental labor, and when the two are interwoven, academic learning can also improve. Moving our bodies and letting our minds wander bring renewed focus. According to popular educational theory, some kids are what educators call tactile learners they do especially well with a kinesthetic instruction that involves actively doing over passively absorbing. Schools apply these ideas to early childhood education, with its emphasis on sand tables and hands-on learning. But older students, particularly boys and kids with attention difficulties, also benefit.

Home ec and shop skills especially make sense in light of current environmental and health challenges. For kids who wear fast fashion but care about climate and overconsumption, its worth knowing how to darn a sock or patch a hole. Likewise, in a country with skyrocketing obesity and high consumption of processed foods, learning how to make healthy, inexpensive meals is important.

The more both sexes can handle kitchen and household skills, the better. In his book Shop Class as Soulcraft, Matthew Crawford lamented a world without shop class the experience of making things and fixing things as one that encourages us to be more passive and more dependent.

But shop class and home ec also teach a broader range of skills. Educators may extol the value of collaboration and its desirability in todays workplace, but in school, those lessons rarely extend beyond the confines of a Google Doc. Whereas in home economics, collaboration means taking turns cleaning up and requires social skills to determine who does what and how.

Working with ones hands also rewards patience. Kids accustomed to immediate results and instant gratification must grapple with the tedium and rewards of slower processes; even the best math and chemistry students dont automatically bake a bread that rises.

In Building: A Carpenters Notes on Life & the Art of Good Work, which came out earlier this year, Mark Ellison writes: I firmly believe that most of life passes us by when we avoid mucking about in dirt, or dough, or dark thoughts. Doing anything from beginning to end brings understanding that no finished product can provide.

Personally, I found shop class scary. It was unnerving to sink a saw into a block of hardwood, to be surrounded by hormonal youths wielding hammers and hot metal. (Relatedly, these classes can be expensive for schools to fund; whenever sharp objects or power tools are involved, insurance rates go up. My junior high school, which once required shop, has since replaced it with Tech.)

But in a culture that has stripped children of all possible hazards, kids could use a few more risk-taking opportunities, a sense of danger, even.

These are exactly the kind of life skills educators, parents and administrators say current students desperately need and sorely lack. At a time when kids themselves seem just as concerned with adulting as grown-ups are, maybe we ought to give them more opportunities to learn what are as much 21st century skills as any other.

Original post:

Opinion | To Prepare Kids for the Future, Bring Back Shop and ... - The New York Times

AUSTIN, Texas The University of Texas at Austin raised its ranking among the best universities in the country, according to the most recent undergraduate rankings from U.S. News & World Report. UT Austin climbed to No. 9 among national public universities and remains the No. 1 public university in Texas. Among both public and private universities, UT rose six places to No. 32.

UTs continued upward rankings trajectory is a reflection of the exceptional talent we continue to attract; our commitment to unmatched academic, research and campus experiences that are life-changing and affordable; and the opportunities that exist in Austin as an innovation and cultural hub, said President Jay Hartzell. Many of our top-ranked programs in computer science, artificial intelligence, engineering, design, business and psychology are major contributors to the U.S. economy and position our graduates for tremendous career opportunities, where they can have significant impact and change the world.

The McCombs School of Business rose two places this year to No. 5 in the country, and 12 of the schools specialties ranked in the top 10, with accounting maintaining its No. 1 ranking. The Cockrell School of Engineering placed No. 11 in the country, with six specialties ranking in the top 10. The computer science program ranked No. 11, with five specialties landing in the top 10, including a newly added category for artificial intelligence. Undergraduate research rose four places to No. 15. UT continues to be the best university in Texas for veterans and increased its national standing to No. 16. The University also ranked No. 16 among the countrys Most Innovative Schools.

U.S. News reviewed several undergraduate disciplines this year, and UT earned top-10 rankings in many of them. Twelve of the McCombs specialties earned top-10 status:

The Cockrell School of Engineering earned top-10 specialty rankings in six categories:

The Computer Science program earned top-10 specialty rankings in five categories:

Other top rankings in areas of interest include:

The U.S. News ranking is one of the most widely referenced measurements of undergraduate programs nationally and is based on 19 key measures, such as graduation rates and student outcomes, faculty resources, expert opinions, financial resources and student excellence.

Originally posted here:

UT Continues Upward Climb in Latest U.S. News Undergraduate ... - The University of Texas at Austin

Willie Neiswanger | Assistant Professor of Computer Science (Starting Jan. 2024) | Ph.D. in Computer Science, Carnegie Mellon University. Postdoctoral scholar, Stanford University.

Research focus: developing machine learning methods to perform efficient optimization and experimental design in costly real-world settings, where resources are limited.

Neiswanger applies these methods to solve problems in science and engineering, for example in the physical sciences and machine learning systems. In 2021, he won the Jay Lepreau Best Paper Award at OSDI.

What attracted you to computer science at USC? The strength of AI at USC and the emphasis on interdisciplinary research. This meshed well with my focus on machine learning as well as its application to solving problems in science and engineering.

If your research could solve any problem immediately, which one would it be and why? I would love for the machine learning techniques that I research to be used for efficient discovery of new materials, tools, and methods for improvements in sustainable energy.

Any interesting hobbies? I love to read, ride my bike, and take walks. In the past I've been very interested in movie making, rock climbing, and soccer.

Read any good books lately? Yes "Under the Frog", by Tibor Fischer, and "The Soul of a New Machine", by Tracy Kidder

See original here:

Ten New Faculty Members Join the Thomas Lord Department of ... - USC Viterbi School of Engineering