Tyler O'Neal, Staff Editor

Sweden's University of Gothenburg prof builds AI model that helps understand virus spread from animals to humans

A new model that applies artificial intelligence to carbohydrates improves the understanding of the infection process and could help predict which viruses are likely to spread from animals to humans. This is reported in a recent study led by researchers at the University of Gothenburg.

Carbohydrates participate in nearly all biological processes - yet they are still not well understood. Referred to as glycans, these carbohydrates are crucial to making our body work the way it is supposed to. However, with a frightening frequency, they are also involved when our body does not work as intended. Nearly all viruses use glycans as their first contact with our cells in the process of infection, including our current menace SARS-CoV-2, causing the COVID-19 pandemic. Glycan diversity. The image shows a glimpse of glycan diversity, showcasing several classes of glycans from various kingdoms of life.

A research group led by Daniel Bojar, assistant professor at the University of Gothenburg, has now developed an artificial intelligence-based model to analyze glycans with an unprecedented level of accuracy. The model improves the understanding of the infection process by making it possible to predict new virus-glycan interactions, for example between glycans and influenza viruses or rotaviruses: a common cause for viral infections in infants.

As a result, the model can also lead to a better understanding of zoonotic diseases, where viruses spread from animals to humans.

"With the emergence of SARS-CoV-2, we have seen the potentially devastating consequences of viruses jumping from animals to humans. Our model can now be used to predict which viruses are particularly close to "jumping over". We can analyze this by seeing how many mutations would be necessary for the viruses to recognize human glycans, which increases the risk of human infection. Also, the model helps us predict which parts of the human body are likely targeted by a potentially zoonotic virus, such as the respiratory system or the gastrointestinal tract", says Daniel Bojar, who is the main author of the study.

In addition, the research group hopes to leverage the improved understanding of the infection process to prevent viral infection. The aim is to use the model to develop glycan-based antivirals, medicines that suppress the ability of viruses to replicate.

"Predicting virus-glycan interactions means we can now search for glycans that bind viruses better than our own glycans do, and use these "decoy" glycans as antivirals to prevent viral infection. However, further advances in glycan manufacturing are necessary, as potential antiviral glycans might include diverse sequences that are currently difficult to produce", Daniel Bojar says.

He hopes the model will constitute a step towards including glycans in approaches to prevent and combat future pandemics, as they are currently neglected in favor of molecules that are simpler to analyze, such as DNA.

"The work of many groups in recent years has really revolutionized glycobiology and I think we are finally at the cusp of using these complex biomolecules for medical purposes. Exciting times are ahead," says Daniel Bojar.

Kyndi's Neuro-symbolic AI recognized by the World Economic Forum

Tyler O'Neal, Staff Editor

Kyndi was selected among hundreds of candidates as one of the World Economic Forum’s “Technology Pioneers.” Kyndi pioneered the development and application of Neuro-Symbolic AI, a field of AI that aims to overcome the limitations of traditional machine learning systems. Put into practice, the result is a Natural Language Technology (NLT) platform that eliminates the need for large volumes of training data, reduces the requirement for skilled AI engineers, all while accelerating time-to-value. Boosting the success rate and ROI of Cognitive Search solutions, Kyndi accelerates the building, deployment, and maintenance of AI-driven enterprise applications at scale. Kyndi aims to amplify the productivity of all 230 million workers globally that spend 25% of their time looking for answers locked up in large repositories of unstructured business documents.

The World Economic Forum’s Technology Pioneers are early to growth-stage companies from around the world that are involved in the use of new technologies and innovation that are poised to have a significant impact on business and society.

With their selection as Technology Pioneer, CEO Ryan Welsh of Kyndi will be invited to participate in World Economic Forum activities, events, and discussions throughout the year. Kyndi will also contribute to Forum initiatives over the next two years, working with global leaders to help address key industry and societal issues.

“We’re excited to welcome Kyndi to our 2021 cohort of Technology Pioneers,” says Susan Nesbitt, Head of the Global Innovators Community, World Economic Forum. “Kyndi and its fellow pioneers are developing technologies that can help society solve some of its most pressing issues. We look forward to their contribution to the World Economic Forum in its commitment to improving the state of the world.”

“It’s great to be acknowledged as a pioneer by the World Economic Forum,” said Kyndi’s Ryan Welsh. “It is confirmation that our technology is among the most unique in the world and our products have significantly improved enterprise productivity. If the 2000s were about becoming a Big Data-enabled enterprise, and the 2010s were about becoming a Data Science-enabled enterprise, then the 2020s are about becoming a Natural Language-enabled enterprise. Kyndi’s platform is the leading NLT platform enabling this transformation.”

For the first time in the community’s history, over 30% of the cohort are led by women. The firms also come from regions all around the world, extending their community far beyond Silicon Valley. This year’s cohort includes start-ups from 26 countries, with UAE, El Salvador, Ethiopia and Zimbabwe represented for the first time.

The diversity of these companies extends to their innovations as well. 2021 Tech Pioneer firms are shaping the future by advancing technologies such as AI, IoT, robotics, blockchain, biotechnology, and many more. The full list of Technology Pioneers can be found here. Technology Pioneers have been selected based on the community’s selection criteria, which includes innovation, impact, and leadership as well as the company’s relevance with the World Economic Forum’s Platforms.

NASA's SnowEx data collection campaign wraps up for 2021

Tyler O'Neal, Staff Editor

As the last snow melts, NASA's SnowEx teams are packing up the snowshoes, skis, and scientific instruments they've used all winter to study snow in mountains and prairies. Now, they're turning their attention to a different kind of mountain - all of the data they collected.

This year, SnowEx teams took snow measurements at six sites across the Western United States, on the ground and with drones and airplanes flying overhead. This information will help scientists determine how much water the winter snowpack holds, which is crucial for managing water resources for drinking, agriculture, hydropower, flood forecasting, drought and wildfire management, and more. Randall Bonnell (left), PhD student at Colorado State University, and Lucas Zeller (right), Master's student at Colorado State University, pull the GPR sled at Cameron Pass, Colorado. CREDIT Courtesy of Alex Olsen Mikitowicz.

In addition to studying snow, SnowEx researchers are also evaluating how accurately various techniques can measure snow in different environments. In the future, NASA hopes to launch a satellite dedicated to studying snow - and the water it stores - from space, in order to understand how changes in the snowpack affect droughts, wildfires, and more. One of the main goals of the multi-year SnowEx campaign is figuring out which instruments may be best suited for the job.

"We're not going to solve the snow monitoring problem from space with one technology," said HP Marshall, an associate professor at Boise State University and SnowEx 2021's co-project scientist. "A big part of SnowEx is figuring out the best way to combine fieldwork, remote sensing, and modeling into one framework."

In 2020, the SnowEx campaign was cut short due to the COVID-19 pandemic and the team couldn't finish their airborne experiments. For 2021, the science team had three major goals: conduct a time series of L-band Interferometric Synthetic Aperture Radar (InSAR) observations in diverse snow conditions, measure the reflectivity of the snow surface, and study snow distribution in a prairie landscape.

A Gulf Stream 3 aircraft, carrying the Uninhabited Aerial Vehicle Synthetic Aperture Radar (UAVSAR) instrument from NASA's Jet Propulsion Laboratory, flew over seven sites in Colorado, Utah, Idaho, and Montana from mid-January until the end of March. UAVSAR is an L-band InSAR, a special kind of radar, that SnowEx is using to measure changes in the mass of the snowpack.

The snowpack's mass can change drastically from one UAVSAR flight to the next. For example, a large snowstorm may dump massive amounts of snow in one area over a short period of time. Some of the snow may melt or sublimate - skipping the liquid phase and going straight from solid to gas. It may also get redistributed by high winds.

The SnowEx team is testing how well the UAVSAR sensor can detect these different changes in the snow's mass. Summing up the changes in snow mass over the winter season will help the team calculate how much water is stored in the seasonal snowpack, or snow-water equivalent (SWE). "With UAVSAR, what we're looking at is a change in SWE from one flight to the next," said Carrie Vuyovich, lead snow scientist for NASA's Terrestrial Hydrology Program, at NASA's Goddard Space Flight Center in Greenbelt, Maryland. Randall Bonnell and Lucas Zeller, graduate students at Colorado State University, collect a snow-water equivalent core sample at the site in Cameron Pass, Colorado. CREDIT Courtesy of Dan McGrath, Colorado State University

Scheduled for 2022, NASA and the Indian Space Research Organization (ISRO) plan to launch the NISAR satellite to study changes in Earth's surface from space. NISAR will carry an L-band radar instrument similar to UAVSAR, and the SnowEx team is testing how they may use NISAR observations to study snow.

As the planes flew overhead, scientists collected data on the ground below. They measured snow characteristics such as snow depth and density, the size of individual snow grains, temperature, how reflective the snow surface is, and how much of the snowpack is ice, snow, or liquid water. The team collected these measurements from snow pits - car-sized holes dug in the snow. From inside the pits, scientists took samples at different depths to see how the characteristics of the snowpack varied from layer to layer.

The SnowEx observers also measured the snowpack using ground-based remote sensing tools similar to those used from the air and space. The data collected during SnowEx is publicly available from the National Snow and Ice Data Center; more datasets are published every month as scientists from across the country complete processing each of the raw datasets and carefully checking them for errors.

Scientists on snowshoes or skis also used handheld spectrometers to measure albedo, or how bright and reflective the snow surface is. Albedo plays a huge role in how fast the snow melts. It depends on a range of factors, such as the size and shape of individual snow crystals, how much of the snow has melted already, and impurities like dust on top of the snow.

From the air, researchers measured albedo using the Airborne Visible / Infrared Imaging Spectrometer (AVIRIS) Next Generation instrument from NASA's Jet Propulsion Laboratory. Comparing the airborne and ground measurements will help the scientists identify how different factors contribute to the snow albedo.

This year, SnowEx added a site in a prairie, which is an important but under-studied landscape when it comes to snow science. While the amount of snow in prairies is much less than what falls in the mountains, "a large percentage of the snow-covered Earth is considered prairie. Snow in those areas is important for agriculture and contributes to flooding," said Vuyovich.

These exposed landscapes often have high winds that move snow from one area to another, forming deep snowdrifts in some areas and leaving only a light dusting of snow in others. Because of these variations, the SnowEx team wanted to see how well remote sensing can detect these large changes in snow cover over short distances.

All of the experiments went smoothly despite the pandemic, said, Marshall. "There are always challenges," he said, citing risks of hypothermia, avalanches, and dangerous roadway conditions. "But COVID was a big additional challenge that we weren't used to dealing with." To ensure that everyone was safe, the team implemented routine COVID-19 testing, masks, social distancing protocols, and limited passengers in vehicles.

SnowEx teams also recruited local snow scientists to help collect data in the field. "These teams were completely instrumental in making this campaign a success," said Vuyovich. "That was the only way we were able to continue SnowEx this winter."

After a successful winter in the field, the SnowEx team is changing its focus from snowshoes and spectrometers to high-performance laptop computers and supercomputers. In mid-July, 90 members of the community will participate in a week-long hackathon, which will provide tutorials for working with SnowEx data and group projects to build software for analysis of the large datasets. Next winter, the SnowEx team plans to conduct experiments in the Alaskan tundra and boreal forest. Full data analysis involving broader community participation will continue into the future.