Tyler O'Neal, Staff Editor ASTRONOMY

Finnish re­search­ers develop AI model that pre­dicts which key of the im­mune sys­tem opens the locks of coronavirus

With the artificial intelligence (AI) method developed by researchers at Aalto University and the University of Helsinki, researchers can now link immune cells to their targets and for example, uncouple which white blood cells recognize SARS-CoV-2. The developed tool has broad applications in understanding the function of the immune system in infections, autoimmune disorders, and cancer.

The human immune defense is based on the ability of white blood cells to accurately identify disease-causing pathogens and to initiate a defense reaction against them. The immune defense is able to recall the pathogens it has encountered previously, on which, for example, the effectiveness of vaccines is based. Thus, the immune defense the most accurate patient record system that carries a history of all pathogens an individual has faced. This information however has previously been difficult to obtain from patient samples. coronavirus immune system zipper

The learning immune system can be roughly divided into two parts, of which B cells are responsible for producing antibodies against pathogens, while T cells are responsible for destroying their targets. The measurement of antibodies by traditional laboratory methods is relatively simple, which is why antibodies already have several uses in healthcare.

”Although it is known that the role of T cells in the defense response against for example viruses and cancer is essential, identifying the targets of T cells has been difficult despite extensive research,” says Satu Mustjoki, Professor of Translational Hematology.

AI helps to identify new key-lock pairs

T cells identify their targets in a key and a lock principle, where the key is the T cell receptor on the surface of the T cell and the key is the protein presented on the surface of an infected cell. An individual is estimated to carry more different T cell keys than there are stars in the Milky Way, making the mapping of T cell targets with laboratory techniques cumbersome.

Researchers at Aalto University and the University of Helsinki have therefore studied previously profiled key-lock pairs and were able to create an AI model that can predict targets for previously unmapped T cells.

”The AI model we created is flexible and is applicable to every possible pathogen - as long as we have enough experimentally produced key-lock pairs. For example, we were quickly able to apply our model to coronavirus SARS-CoV-2 when a sufficient number of such pairs were available,” explains, M.Sc. and a Ph.D. student at Aalto University.

The results of the study help us to understand how a T cell applies different parts of its key to identify its locks. The researchers studied which T cells recognize common viruses such as influenza-, HI-, and hepatitis B -virus. The researchers also used their tool to analyze the role of T-cells recognizing hepatitis B, which had lost their killing ability after the progression of hepatitis to hepatic cell cancer.

The study has been published in the scientific journal PLOS Computational Biology.  JANI HUUHTANEN (BIORENDER.COM)

A new life for pub­lished data with novel AI mod­els

Tools generated by AI are cost-effective research topics.

“With the help of these tools, we are able to make better use of the already published vast patient cohorts and gain additional understanding of them,” points out Harri Lähdesmäki, Professor of Computational Biology and Machine Learning at Aalto University.

Using the artificial intelligence tool, the researchers have figured out, among other things, how the intensity of the defense reaction relates to its target in different disease states, which would not have been possible without this study.

”For example, in addition to COVID19 infection, we have investigated the role of the defense system in the development of various autoimmune disorders and explained why some cancer patients benefit from new drugs and some do not”, reveals M.D. Jani Huuhtanen, a Ph.D. student at the University of Helsinki, about the upcoming work with the new model.

California's worst wildfires help improve air quality prediction

Tyler O'Neal, Staff Editor ASTRONOMY

New method measures and predicts air quality in areas with insufficient monitoring

UC Riverside engineers are developing methods to estimate the impact of California's destructive wildfires on air quality in neighborhoods affected by the smoke from these fires. Their research, funded by NASA and the results published in Atmospheric Pollution Research, fills in the gaps in current methods by providing air quality information at the neighborhood scales required by public health officials to make health assessments and evacuation recommendations.

Measurements of air quality depend largely on ground-based sensors that are typically spaced many miles apart. Determining how healthy it is to breathe air is straightforward in the vicinity of the sensors but becomes unreliable in areas in between sensors.

Akula Venkatram, a professor of mechanical engineering in UC Riverside's Marlan and Rosemary Bourns College of Engineering, directed a group that developed a method to interpret fine particulate matter concentrations observed by ground-based sensors during the 2017 fire complex that included the Atlas, Nuns, Tubbs, Pocket, and Redwood Valley fires, and the 2018 Camp Fire.

Their method fills in the gaps in air quality information obtained from ground-level monitors and satellite images using a mathematical model that simulates the transport of smoke from the fires. This approach provides estimates of particulate emissions from wildfires, which is the most uncertain of the inputs of other methods of interpreting the same data. These emissions combined with the physics embodied in the smoke transport model allowed the group to estimate the variation of particulate concentrations over distances as small as one kilometer.

"We need better ways to measure air quality so we can let people know when and where it's safe to go out and exercise or go stay somewhere else, for example," Venkatram said. "In addition to filling in the gaps in the data from monitoring stations and satellite images, our method can also be used to predict the next day's air quality by estimating wildfire emissions for tomorrow based on today's observations."

While any smoke can make air unpleasant to breathe, it is the tiniest particles, called PM2.5, that can penetrate lung tissue and cause the most health problems. The UC Riverside model is specifically designed to predict PM2.5 concentrations in areas with insufficient coverage by air quality monitoring stations.

The authors hope their work will help efforts to protect public health during California's inevitable annual wildfires.

Canada's Acceleration Consortium applies artificial intelligence to discovery of advanced materials

Tyler O'Neal, Staff Editor ASTRONOMY

New collaboration on self-driving laboratories to focus on materials design in the areas of energy, the environment, structural and biomedical applications

The Acceleration Consortium, a new global collaboration between academia, industry, and government, based at the University of Toronto (U of T) Canada, will use artificial intelligence (AI) and robotics to accelerate the design and discovery of materials that don't yet exist. These advanced materials will make technologies more affordable and eco-friendlier with applications ranging from renewable energy and consumer electronics to drugs.

A New Paradigm in Materials Discovery

By leveraging the power of AI, robotics, engineering, and chemistry, the AC will make U of T a global center for materials science innovation. Using materials acceleration platforms (MAPs), also known as self-driving laboratories, the AC will rapidly design and discover the materials needed to build a more sustainable, prosperous, and healthy future. The AC is led by Alán Aspuru-Guzik with support from the Faculty of Arts & Science in partnership with the Faculty of Applied Science & Engineering and the Division of the Vice-President, Research and Innovation.

"AI is changing the way we do science," said Alán Aspuru-Guzik, Director of the Acceleration Consortium, Canada 150 Research Chair in Theoretical Chemistry in the Departments of Chemistry and Computer Science at U of T and Canada CIFAR AI Chair at the Vector Institute. "The Acceleration Consortium's self-driving laboratories will revolutionize advanced materials innovation by reducing the time and cost to develop new materials from an average of 20 years and $100 million to as little as 1 year and $1 million." 262739 web Alán Aspuru-Guzik, director of the Acceleration Consortium, Canada 150 Research Chair in Theoretical Chemistry in the Departments of Chemistry and Computer Science at U of T, and Canada CIFAR AI Chair at the Vector Institute. CREDIT Johnny Guatto/University of Toronto

The AC's launch coincides with a recent announcement by the Government of Canada to provide $58.9 million in investments to the National Research Council of Canada and Natural Resources Canada to support new laboratory space for advanced materials and the collaborative deployment of MAPs in Mississauga and Hamilton.

A Wide Range of Applications

New advanced materials with superior performance characteristics are required for renewable and clean energy storage, sustainable polymers and packaging for consumer products, biomedical applications, drugs and therapeutics, lighter and stronger building materials, quantum supercomputing, communication technology, eco-friendly transportation, and a host of other applications.

"By creating these new materials, the Acceleration Consortium will help improve the lives of Canadians by addressing challenges in health, climate change, urbanization, and economic development," said Ed Clark, Board Chair, Vector Institute, and former President and CEO of TD Bank Group. "The AC's efforts will also directly support our country's post-COVID-19 economic recovery by generating commercialization opportunities, onshoring manufacturing, increasing productivity, and even sparking the creation of companies and industries that do not yet exist."

An Interdisciplinary Approach

"We take pride in a legacy of innovation and discovery that has changed the way we think about the world and respond to society's most pressing social, economic, and environmental questions," said Melanie Woodin, dean of the Faculty of Arts & Science at U of T. "I am excited to participate in this enterprise that will advance us in new areas of scientific inquiry."

"With a primary focus on materials design in the areas of energy, the environment, structural and biomedical applications, this cross-disciplinary partnership epitomizes knowledge transfer and collaboration across scholarly expertise at U of T," said Chris Yip, dean of the Faculty of Applied Science & Engineering.

The Acceleration Consortium, U of T's latest Institutional Strategic Initiative (ISI), embodies the University's ability to bring together talented faculty members and students spanning fields and faculties to tackle key world issues.

"Global issues require a global response. U of T is proud to launch the Acceleration Consortium to drive materials innovation through collaboration between experts across the University and around the world, including government, industry and emerging companies, and our academic peers," said Christine Allen, associate vice-president and vice provost Strategic Initiatives.

An Innovation Ecosystem

The Acceleration Consortium has 3 interconnected objectives: 1) Transform materials discovery: Drive the design of MAPs to accelerate the discovery of new materials and make fundamental breakthroughs in AI, robotics, computational, and materials science; 2) Build an ecosystem: Establish a global network of academic institutions, tech companies, and entrepreneurs dedicated to materials innovation; and 3) Train a highly skilled workforce: Create a nationwide training program for the next generation of researchers.

Together, these activities will help foster a robust and agile innovation ecosystem. This will allow AC members to capitalize on shared knowledge, more easily commercialize technological breakthroughs to address real market needs and create a talent pipeline that drives industry, launches start-ups, and attracts venture capital. AC initiatives will include workshops, conferences, hackathons, postdoctoral fellowships, a master's program, and a laboratory facility to provide training and access to self-driving laboratories for all AC members.

Current AC partners include Chemspeed, CIFAR, Creative Destruction Lab, National Research Council of Canada, Natural Resources Canada, SLAS, and Vector Institute, among many others. The AC boasts over 50 top researchers from the University of Toronto and across the world.

"CIFAR congratulates Professor Alán Aspuru-Guzik and the University of Toronto for the creation of the AC. The AC will catalyze advanced materials discovery for many applications, from renewable energy to new drugs. As a CIFAR Canada AI Chair and a Fellow in CIFAR's Bio-Inspired Energy program, Alán combines his leading-edge science with CIFAR's global interdisciplinary networks. CIFAR's partnership with the AC continues our longstanding contributions to the development and application of AI and to elucidating the mechanisms that will drive the green energy revolution," said Dr. Alan Bernstein, President & CEO of CIFAR.

"The launch of the Acceleration Consortium demonstrates what is possible when world-class scientists and practitioners converge and work across disciplines like chemistry and AI. We congratulate our colleagues and look forward to continued collaboration on this exemplary work as we progress towards our mission to use AI to foster economic growth and improve lives," said Garth Gibson, President & CEO, Vector Institute.

"The Acceleration Consortium is critical for advancing materials research. The adoption of high throughput parallelized experimentation enabled by automation is a key element of this endeavor. Chemspeed is thrilled that our automation solutions are one of the innovative technologies leveraged as part of this collaboration," said Diana Curran, Head Operations Americas, Chemspeed Technologies, Inc.

Within the ecosystem, the AC is also part of a Global Acceleration Network that includes A3MD, Air Force Research Laboratory (AFRL) - Materials and Manufacturing Directorate, Centre for Computer-Assisted Synthesis, Institute for Digital Molecular Design and Fabrication (DigiFAB), Materials Innovation Factory, Molecular Maker Lab Institute, Open Reaction Database and more.