Data Sciences Institute Catalyst Grants support transformative data science research

Data Science word cloud.

The Data Sciences Institute (DSI) at the University of Toronto is funding seventeen cross-disciplinary research teams focused on using the transformative nature of data sciences to solve complex and pressing problems.

“The global and research challenges we face today are increasingly complex. The DSI Catalyst Grant projects bring together collaborative research teams focused on the development of new data science methodology or the application of existing tools in innovative ways to address these challenges,” says Lisa Strug, director of the DSI. “We were floored by the cutting-edge advances proposed in the applications we received for our inaugural competition.”

Here we highlight a few of the inspiring funded proposals and research teams. The full list of recipients can be found below.

Using data science to rethink water practices and equity in India

The United Nations states that water scarcity affects more than 40 per cent of the global population. India is working hard to expand access to water pipe networks. However, because of rapid urbanization and inadequate infrastructure, most Indian pipe networks provide water for less than four hours per day, impacting 390 million people. To cope, residents invest in water storage infrastructure and seek alternative water sources, imposing significant financial, environmental, educational, health, and time costs, especially on women and girls.

Professors David Meyer (Civil & Industrial Engineering, Faculty of Applied Science & Engineering), Nidhi Subramanyam (Geography & Planning, Faculty of Arts & Science), and Carmen Logie (Factor Inwentash Faculty of Social Work) are developing tools and metrics that harness water data and empower water planners, communities, and activists to help achieve water equity in India. With their project Harnessing Data to Visualize and Mitigate Urban Water Inequities within the Cauvery River Basin, India, their team brings together diverse disciplinary perspectives on water and data – including a deep understanding of water engineering, water governance, and equity. Once they have collected the data, they will combine it to create novel insight-generating metrics and visualizations for planners regarding the equity and equality of water availability.

“We are delighted to receive this award,” says Nidhi Subramanyam. “The DSI provides an exciting platform for those of us interested in using data for justice to come together, discuss and reflect on how new technologies and streams of data can help us rethink pedagogy and practices within our respective fields.”

Improving data derived from single-cell sequencing

Single-cell sequencing, the ability to look at cells at the individual level, has been revolutionary. However, the technology also poses challenges. For example, different types of sequencing approaches produce distinct data sets that don’t integrate with each other.

Professors Zhaolei Zhang (Donnelly Centre/Molecular Genetics, Temerty Faculty of Medicine), Dehan Kong (Statistical Sciences, Faculty of Arts & Science, UofT), and Dennis Kim (Princess Margaret Cancer Centre, UHN) received a Catalyst Grant for their project, Developing rigorous statistical methods for multimodal single-cell sequencing data analysis, which aims to tackle this problem. Their research is co-funded by Medicine by Design.

“We need robust and effective statistical tools to handle the data being measured from the thousands of cells and tens of thousands of genes in one experiment. Our framework will be able to integrate that data generated from different approaches in a very efficient and accurate way,” says Zhaolei Zhang.

Using datasets collected primarily from brain or blood cells, this multi-disciplinary research team aims to refine a method that can give researchers a more complete picture of single-cell data.

Data science to support policies for gender equity

Early evidence indicates that the pandemic has profoundly and disproportionately impacted women. Many predict that the social and economic burden of the pandemic will be shouldered by women and girls worldwide. To help policymakers mitigate the damage, it is important to have up-to-date accurate information and data.

“The COVID pandemic has had differential impact on many communities and these impacts are not yet fully documented, and it is not clear yet what this means for these communities going forward. Our research will attempt to quantify the pandemic’s impacts on researchers and inventors across gender, location, and discipline by creating yearly measures of their productivity and research team diversity pre- and post-COVID,” say Professors Michelle Alexopoulos (Department of Economics, Faculty of Arts &Science) and Kelly Lyons (Faculty of Information, UofT). They are recipients of a Catalyst Grant for their project Using Data Science Methods to Understand the Differential Impact of COVID on Researchers and Inventors by Gender.

The DSI Catalyst Grant will support their collaborative research team to apply data mining and natural language processing techniques to data on publications, grant applications and patents. The resulting metrics, and extracted location and gender identifiers, will be combined with socio-economic information on outbreaks, government interventions across jurisdictions (such as lockdowns and school closures), locations of researcher’s team members, and measures of gender diversity within research teams to explore how the magnitudes of the pandemic’s impacts are influenced by these factors.

Building a community of data scientists   

“The Data Sciences Institute is committed to fostering new opportunities to cultivate multi-disciplinary collaborations between data science methodologists and researchers in various application domains. This is just the beginning,” says Timothy Chan, DSI associate director of research and thematic programming. “With this inaugural round, we received 70 highly competitive proposals which were carefully assessed by a multidisciplinary Review Panel.”

The DSI Catalyst Grants are supported by the University of Toronto Institutional Strategic Initiatives and external funding partners, the University Health Network, the Hospital for Sick Children and the Lunenfeld-Tanenbaum Research Institute. The grants are designed to fund multidisciplinary research teams focused on the development of new data science methodology or the innovative use of data science to address questions of major societal importance. Each grant is valued at up to $100,000 for one to two years.

Two of this year’s Catalyst Grants are co-funded by Medicine by Design, one of these projects is described above. Medicine by Design awards funding to multi-disciplinary, multi-institutional research teams that are finding solutions to key challenges in regenerative medicine. Medicine by Design receives funding from the Canada First Research Excellence Fund.

Congratulations to the 2022 DSI Catalyst Grant collaborative research teams! 

Using Data Science Methods to Understand the Differential Impact of COVID on Researchers and Inventors by Gender

  • Michelle Alexopoulos (Department of Economics, Faculty of Arts & Science, UofT); Kelly Lyons (Faculty of Information, UofT)

Stellar Flares in Hiding: Discovering Flares in Stellar Time-Series Data with Hidden Markov Models 

  • Gwendolyn Eadie (Astronomy & Astrophysics, Faculty of Arts & Science, UofT); Radu Craiu (Statistical Sciences, Arts & Science, UofT)
  • Read the announcement from the Department of Statistical Sciences.

Attention-based coupling, or learning how to swim, thousands of neurons at a time 

  • Guillaume Filion (Biological Sciences, UTSC); Minoru Koyama (Biological Sciences, UTSC)

50 years of spatial-explicit environmental data to examine changes in northern Canada

  • Yuhong He (Geography, Geomatics & Environment, UTM); Kent Moore (Chemical & Physical Science, UTM)
  • Read the story highlighting UTM Scholars.

MIRA Clinical Learning Environment (MIRA-CLE) for Lung 

  • Andrew Hope, Tony Tadic and Chris McIntosh (Radiation Medicine Program, UHN)

Preventing a Reproducibility Crisis in Quantum Computing: Benchmarking Quantum Computing Against Classical Algorithms for Molecular Property Predictions

  • Hans-Arno Jacobsen (Electrical & Computer Engineering, Faculty of Applied Science & Engineering, UofT); Ulrich Fekl (Chemical and Physical Sciences, UTM)
  • Read the story from the Faculty of Applied Science and Engineering.
  • Read the story highlighting UTM Scholars.

Using Geometric Data to Construct More Equitable Living Spaces 

  • Alec Jacobson (Computer Science, Arts & Science, UofT); Maria Yablonina (Daniels Faculty of Architecture, Landscape, and Design); Brady Peters (Daniels Faculty of Architecture, Landscape, and Design)
  • Read the full story from the John H. Daniels Faculty of Architecture, Landscape and Design.

Robust Risk-Aware Reinforcement Learning for Financial Modeling 

  • Sebastian Jaimungal (Statistical Sciences, Faculty of Arts & Science, UofT); John Hull (Joseph L. Rotman School of Management)
  • Read the announcement from the Department of Statistical Sciences.

Harnessing Data to Visualize and Mitigate Urban Water Inequities within the Cauvery River Basin, India

  • David Meyer (Faculty of Applied Science and Engineering); Nidhi Subramanyam (Geography & Planning, Faculty of Arts & Science); Carmen Logie (Factor-Inwentash Faculty of Social Work)
  • Read the story from the Faculty of Applied Science and Engineering.

Bioimage Informatics for Exploring Heterogeneous Cell Communities and Accelerating the Development of Effective Cancer Treatments

  • Project co-funded by Medicine by Design. Read the full story by Medicine by Design.
  • Joshua Milstein (Chemical and Physical Sciences, UTM); Alison McGuigan (Chemical Engineering & Applied Chemistry & Biomedical Engineering, UofT); Rodrigo Fernandez-Gonzalez (Chemical Engineering & Applied Chemistry &Biomedical Engineering, UofT)
  • Read the story from the Faculty of Applied Science and Engineering.
  • Read the story highlighting UTM Scholars.

Removing unwanted variations from heterogeneous neuroimaging and genomic data

  • Jun Young Park (Statistical Sciences, Faculty of Arts & Science, UofT); Laurent Briollais (Lunenfeld-Tanenbaum Research Institute); Michael Wilson (The Hospital for Sick Children)
  • Read the announcement from the Department of Statistical Sciences.

Predicting And Preventing Chronic Disease burden in populations (PREPARED): Deploying decision-support tools for the prevention of chronic diseases 

  • Laura Rosella (Dalla Lana School of Public Health); Birsen Donmez (Faculty of Applied Science & Engineering, UofT); Myrtede Alfred (Mechanical & Industrial Engineering); Hailey Banack (Dalla Lana School of Public Health); Greg A. Jamieson (Mechanical & Industrial Engineering)
  • Read the story from the Faculty of Applied Science and Engineering.

Informatics platform for a pan-Canadian drug discovery chemical library 

  • Matthieu Schapira (Pharmacology & Toxicology, Temerty Faculty of Medicine UofT); Robert Batey (Chemistry, Arts & Science, UofT)
  • Read the story from the Department of Pharmacology & Toxicology.

Methods for genome-wide studies of variants with sex differences in genetic effect 

  • Lei Sun (Statistical Sciences, Arts & Science, UofT); Andrew Paterson (The Hospital for Sick Children)
  • Read the announcement from the Department of Statistical Sciences.

Machine Learning for Dynamic and Short-term Fall Risk Assessment in People with Dementia 

  • Babak Taati (Kite Research Institute, Toronto Rehab, UHN); Andrea Iaboni (Department of Psychiatry, Temerty Faculty of Medicine)

Developing rigorous statistical methods for multimodal single-cell sequencing data analysis

  • Project co-funded by Medicine by Design. Read the full story by Medicine by Design.
  • Zhaolei Zhang (Donnelly Centre/ Molecular Genetics, Temerty Faculty of Medicine); Dehan Kong (Statistical Sciences, Faculty of Arts & Science, UofT); Dennis Kim (Princess Margaret Cancer Centre, UHN)
  • Read the announcement from the Department of Statistical Sciences.

Reduce Early Revisions of Joint Replacements through Data Science Strategies

  • Yu Zou (Faculty of Applied Science & Engineering, UofT); Qiang Sun (Computer & Mathematical Sciences, UTSC); Adele Changoor (Lunenfeld-Tanenbaum Research Institute)
  • Read the story from the Faculty of Applied Science and Engineering.

By Faculty of Arts & Science Staff

Upcoming Events