All News

University of Maryland computing experts are partnering with a consortium of scientists from across the U.S. to deploy the latest advances in artificial intelligence, machine learning, supercomputing and social science data against epidemic outbreaks.

Funded by a $10 million grant from the National Science Foundation (NSF), the researchers are using these powerful technologies and tools to explore trends in globalization, anti-microbial resistance, urbanization and ecological pressures—factors that have converged to increase the risk of global pandemics like the COVID-19 crisis now wreaking havoc on populations and economies worldwide.

Professor Aravind Srinivasan, Distinguished University Professor Rita Colwell and Assistant Professor Abhinav Bhatele join faculty from 10 other universities on the Global Pervasive Computational Epidemiology project, which includes researchers from Princeton University, Yale University, Stanford University, the Massachusetts Institute of Technology and the University of Virginia, which is leading the multidisciplinary effort.

All three Maryland faculty have appointments in the University of Maryland Institute for Advanced Computer Studies.

While the concept of using modern technology to address the spread of global disease is not new, NSF officials said the launch last month of this project could not have come at a more opportune time.

“We are currently experiencing unprecedented access to massive data, powerful advanced computing capabilities, and models and simulations that can capture the complexity of viruses and associated diseases in ways that weren’t possible as recently as a decade ago,” said Mitra Basu, who leads the NSF’s Expeditions in Computing Program that provided funding for the five-year project. “Together with the incredible number of researchers who have turned their attention to COVID-19 and pandemics more generally, we are likely witnessing transformational efforts that can help with the current crisis, and allow us to be much better equipped for the next pandemic.”

Srinivasan is leading the computational foundations part of the project. Key to this work, he said, is the development of new machine learning algorithms that can interpret large amounts of data from multiple sources over multiple networks. This could include climate data interspersed with disease vector factors—how a virus spreads over time and distance—which is then compiled with the demographics of people who have tested positive for the virus.

The technology can also be used for interpreting dense social-contact networks—a complex “who knows who” pyramid that often determines how far and fast a virus will spread.

“Artificial intelligence and machine learning can play a role when we’re only able to collect fairly sparse real-time data,” Srinivasan said. “Using this limited data, we can build models of where and when we see infections spreading the most, allowing public health experts to make intelligent predictions of what to do tomorrow and the day after.”

These machine learning models can be especially important for policymakers, Srinivasan added, who will need to separate valid information from misinformation regarding the size and scope of a pandemic.

Colwell, who has spent much of her career using technology to combat waterborne diseases like cholera, is expected to work closely with other scientists on the effects that climate may have on the spread of viruses. She will also offer public policy advice, working with researchers at the Center for Disease Dynamics, Economics and Policy, a public health organization located in Washington, D.C.

Srinivasan said that both he and Bhatele will collaborate with other scientists on tasks that require high-performance computing for large-scale simulations. This could include “percolation properties” of how a disease might spread through the air, taking into account multiple factors like climate, urban environments and social demographics.

Government supercomputers located at the Lawrence Livermore National Laboratory in California and the Oak Ridge National Laboratory in Tennessee will assist with these simulations, Srinivasan said.

He said he was “humbled” to be one of the thousands of scientists worldwide thrust into the fight against a gobal pandemic just as the NSF project—under development well before COVID-19 was identified—was getting started.

“We expect that our work can have an immediate impact, but are also aware that the computational tools and policies we develop now can have an effect on future events like this,” he said. “That’s what's driving much of our efforts now—preparing for the future.”

—Story by Tom Ventsias

Mihai Pop, a professor of computer science and director of the University of Maryland Institute for Advanced Computer Studies (UMIACS), was recently awarded a $2.6 million federal grant to develop a suite of computational tools for reconstructing DNA segments.

The four-year award comes from the National Institute of Allergy and Infectious Diseases, which is part of the National Institutes of Health. The money supports efforts to build software and develop algorithms that can reconstruct nearly-complete microbial genomes from complex mixtures found in environments like the human gut. Ultimately, researchers say, this will help scientists better understand the role that certain microbes have in human health and disease.

Pop (left in photo) is principal investigator of the project, and will be assisted by postdocs and graduate students in the Center for Bioinformatics and Computational Biology (CBCB), as well as software experts in the Fraunhofer USA Center for Experimental Software Engineering.

“We want our software to be well-written and usable by biologists across many different computing platforms, so Fraunhofer will help us greatly with that software engineering aspect,” Pop says.

Recent years have seen a “metagenomic revolution” made possible by rapid advances in sequencing technologies, explains Pop. Metagenomics involves the application of bioinformatics tools to study the genetic material from environmental, uncultured microorganisms.

To date, hundreds and possibly thousands of microbial communities have been characterized through deep sequencing, complementing the wealth of data that has already been generated through the targeted sequencing of individual genes.

These studies have started to shed light on the broad functional potential of microbial communities, Pop adds, even though the individual microbes cannot be easily isolated and analyzed in the laboratory.

But despite these advances, relatively few genome sequences have been generated through metagenomic methods. Even those sequences have had a limited impact on the scientific community due to concerns about the quality of reconstruction and inability to assign taxonomic labels to sequences not derived from isolated genomes.

“We want to better understand processes that usually can’t be seen until the bacteria is isolated,” Pop says. For example, he asks, “What if you have two different strains of E.coli in your gut, what is the difference between them, and why does that variance matter?”

In some of the samples his group has been looking at, certain bacteria have acquired antibiotic-resistance genes. This can turn some bacteria into harmful entities, even though they normally wouldn’t be. The software suite Pop’s team is developing will hopefully offer insight into this phenomenon.

“Just being able to generate more data to better understand how bacteria react to each other is a large part of the project,” says Jaquelyn Meisel (right in photo), a postdoctoral associate in CBCB.

“We might be able to identify that this patient has a resistant bacterium that came from some other bacteria that the patient has, or maybe it’s environmental,” Meisel explains. “Once you’re able to track variance, you might be able to say, ‘well I saw this variance somewhere else and now I see it here.’”

Looking ahead, Pop and his team see their work as an important step in helping other scientists and clinicians determine how both good and bad bacteria move through environments, inside and outside of the human body.

“In a cultural context, we want to know when antibiotic-resistant genes get into the food stream,” Pop says. “We know that if you feed animals antibiotics, eventually you see the same bacterium in humans with that resistance. But we don’t have a very clear path of transmission. These tools will hopefully start developing that chain of transmission.”

—Story by Maria Herd

Rita Colwell, a Distinguished University Professor in the University of Maryland Institute for Advanced Computer Studies, recently gave the keynote address at a campus forum discussing the health of the Chesapeake Bay.

“Ensuring a Clean and Healthy Chesapeake Bay” featured experts on storm water management, water use and reuse, the bay’s aquatic life, and more.

Before speaking at the forum, Colwell sat for an interview with Samantha Watters, assistant director of communications for the College of Agriculture & Natural Resources.

Q: What do you see as the biggest challenges facing humanity today and how have they helped advance your thinking and professional pursuits?

A: The biggest challenge is water, it really is. Right now, we are fighting over oil, but we’ve already got fights going on over water, who gets to use it, and this clearly is an agricultural problem. It’s a negotiation that has to be done between community use, agricultural use, and water recycling that is necessary for sustainability. It’s a tradeoff between water for drinking, domestic use, agricultural application, industry, recreation, you name it. And the assumption is that since 70 percent of the earth is covered with oceans, we must have plenty of water, but that water isn’t really available. Also, the tragedy of dealing with climate change means the glaciers are melting, and it’s a real problem because these glaciers feed freshwater drinking systems. We are going to be seeing huge climate change migrations away from areas drastically affected, and exacerbation of political problems that are all intertwined and connected by water.

Q: How does interdisciplinary science enter into solving these global issues?

A: Science has done a great job over the years tackling issues of reductionism—reducing problems to the molecular level, the galaxy level, and so on. But now, to solve the issues our planet is facing, we will need to be thinking at a much more holistic level. And agriculture is a prime example of the necessity of integration—it is a very complex system. The issues are complex, but they are solvable, and collaboration and machine learning can help us get there. It will be interesting to see what can come out of the analysis of interdisciplinary work across all these systems with the rise of big data approaches. Agriculture has the challenge of maintaining the small farm while figuring out how to feed the expanding population. It’s a problem that is an aspect of the global world and crossing disciplines and data integration is the only way.

Q: In what ways do you feel that current and future water scientists can make an impact in a changing world, with a changing climate and changing priorities?

A: It’s not how or when, they just have to. It’s a sheer necessity. It’s not just knowing how much and where, but it’s how to allocate usage of water and how to share with competing priorities. The focus should really be on recycling processes to protect and reuse our water. We can apply biotechnology to our sewage treatment systems to not only clean the water but produce enough power through bioreactors to heat and light cities. We have to go forward to figure out how to apply the sciences of computation agriculture, water reuse, recycling, and engineering to integrate these systems in daily life. Ensuring water systems and a clean and healthy Chesapeake Bay is far more complicated than just making sure you can see the bottom. It’s understanding that the Chesapeake Bay is a prime example of a resource that has to be protected and used in a sustainable way. It’s the only one we’ve got, and the history of the Bay and the resources are well worth protecting.

Q: What advice would you give the next generation of young scientists, policy makers, economists, and leaders hoping to make a difference in water quality and environmental stewardship?

A: The career you’ve planned is going to change many times, and you will have to constantly be relearning. You have to follow your interests—if you don’t really like what you’re doing, you won’t persevere. Also, it’s kind of a shame to be totally focused as a freshman and not sample other disciplines. Literature and art are sources of creativity as well as sources of satisfaction and stress release, and it makes you a stronger scientist. It’s a huge richness of the human spirit and human knowledge. For me, it gets a bit worrisome when a university experience becomes a training center rather than a learning center. You really have to develop the skills to be innovative and flexible in your studies and to keep an open mind in your career. The nature of life is change and thinking broadly keeps you receptive as a scientist and human being to new ideas.

Q: When you look back on such a decorated career, what have been your proudest moments and why?

A: My proudest moments are my two children and my grandchildren. I’ve been very fortunate that I was married to my husband, who was a physicist, for 62 years. And my two daughters are scientists, a botanist and a pediatrician. And the University of Maryland has been very good to me. I’ve loved being here. It’s a very progressive state and university. I’ve been able to do a lot of things here that I wouldn’t have necessarily been able to do in another institution.

A group of six students are spending much of this summer in the Center for Bioinformatics and Computational Biology (CBCB), collaborating with University of Maryland faculty and graduate students on projects ranging from identifying novel viruses to utilizing synthetic lethality to improve cancer treatments.

The students—who range from a rising college senior to a rising high school junior—are part of a 10-week long internship run by faculty in CBCB, with additional support coming from Illumina, a U.S. company focused on developing genomic analysis tools.

“We’ve been doing this for several years and find it valuable for our faculty and the students involved—both the visiting students and our own graduate students,” says Michael Cummings, a professor of biology and the director of CBCB.

The goal of the program, Cummings says, is to give young scientists a hands-on research experience in bioinformatics, letting them work side-by-side with faculty on complex research problems being investigated in CBCB.

Tracy Chen, a second-year UMD computer science doctoral student who is leading the interns, says she enjoys working with the “incredibly talented” group of students.

“I enjoy having one-on-one meetings with the interns every week to learn their research status and also what’s going on in their life, as well as organizing weekly internship seminars,” she says. “When the program finishes next month, I hope our interns will have learned more aspects of bioinformatics through our seminars in addition to their focused research areas. And since our interns come from different schools, I also hope they are making friends from across the country.”

Marie Crane, a rising senior majoring in biology at Macalester College in St. Paul, Minnesota, says CBCB’s program was a perfect fit since she was searching for an internship in computational biology or bioinformatics.

Crane is working with Mihai Pop, a professor of computer science and director of the University of Maryland Institute for Advanced Computer Studies (UMIACS), to develop a method to identify novel viruses. Specifically, she is working with metagenomic data from the hot springs at Yellowstone National Park.

“Participating in this program has been challenging in a good way for me,” Crane says. “I’ve been able to use more computational methods and learn more about coding than previous internships I’ve had. The resources I have had access to at CBCB have also been really helpful in completing my research.”

She adds that she feels lucky to be collaborating with Pop.

“Working with Mihai is great,” Crane says. “He is a very big figure in the field, so it is definitely a privilege to be able to work with him this summer.”

Jessica Pan, an incoming freshman at Yale University, says she felt compelled to apply for the program because of how CBCB is combining classical biology with new technologies. She is specifically interested in how these new advances are impacting the medical field.

“They’re really pioneering the way here,” Pan says. “I love the professors and my co-workers—it’s just a really incredible place to work.”

Pan is working on a project involving a gene-pair relationship called synthetic lethality, in which inactivation of both genes is lethal to a cell, but inactivation of one gene by itself is not. In cancer cells where mutations inactivate one gene, drugs inhibiting the partner gene would be lethal to cancer cells but have minimal or no effect on healthy tissue in which the first gene is expressed normally.

“That’s really important because with things like chemotherapy and typical radioactive treatments, you’re harming a lot of the patient’s healthy cells while you’re trying to kill the cancerous cells,” Pan says. “So this is a really great way to minimize the side effects and the adverse impact of cancer therapy. It’s a pretty new field, but it’s one that I find really interesting.”

Her mentor is Sridhar Hannenhalli, a professor of cell biology and molecular genetics.

“Dr. Hannenhalli is really engaged and involved,” she says. “Whenever we have any issues, he is always available to talk. In previous internships I’ve had, that has not really been the case. It’s nice that we are getting so much guidance from the people running this program.”

Other students participating in the CBCB program this summer are: Camilo Calvo-Alcaniz, a rising senior double majoring in computer science and pre-medicine at UMD; Kassie Wang, an incoming freshman at Cornell University; Hyeyun Chae, a rising junior double majoring in biology and computer science at Swarthmore College; and Rajit Mukhopadhyay, a rising junior at Montgomery Blair High School.

At the end of the summer, the six interns will put together a report outlining the results of their research and give a short presentation about their projects.

—Story by Melissa Brachfeld

From left in photo: Kassie Wang, Rajit Mukhopadhyay, Jessica Pan, Tracy Chen, Marie Crane and Camilo Calvo-Alcaniz. Not pictured: Hyeyun Chae.