Linkedin

Become a Member >

Data Sciences Institute (DSI)

AI in Genomics: Building a Collaborative Future for Health Innovation

Genomics and data science researchers from across the University of Toronto (U of T) and affiliated research institutes recently gathered to explore a shared frontier: how artificial intelligence (AI) can accelerate discoveries in genomics and improve patient outcomes.

AI in Genomics – a community-building day of presentations and discussions designed to explore how AI can help unlock new insights across genomics and multi-omics research – was a collaborative event co-sponsored by the SickKids Research Institute, the McLaughlin Centre and the Data Sciences Institute.

“Our goal is to highlight the exciting work already happening across the U of T ecosystem and to create space for meaningful connections,” said Lisa Strug, Director, Data Sciences Institute and Professor in the Departments of Statistical Sciences and Computer Science (Faculty of Arts & Science) and the Division of Biostatistics (Dalla Lana School of Public Health) at the University of Toronto.

“We’re looking to seed new collaborations and larger initiatives that will push this field forward and we are pleased to work with SickKids and McLaughlin on the event.”

“Detecting cell-cell communication from transcriptomic data is by nature extremely difficult, as the actual binding occurs at the protein level. As such, we required the use of AI-powered models to learn patterns too complex for other traditional models. To meet this challenge, we developed a specialized model trained in an unsupervised way and, instead of using the direct output of the model, we opened up the machinery of the model to detect cellular communication in a new way,” said Gregory Schwartz, one of the presenters and Canada Research Chair in Bioinformatics and Computational Biology and Scientist, Princess Margaret Cancer Centre, University Health Network Assistant Professor, Department of Medical Biophysics, University of Toronto.

“We have all been using AI and machine learning for years but everyone in their own way. In some cases, we are world leaders,” explained Stephen W. Scherer (Chief of Research, Northbridge Chair in Paediatric Research, Senior Scientist, Genetics & Genome Biology program, The Hospital for Sick Children (SickKids); Director, McLaughlin Centre, University of Toronto).

“At the Future of Homo Sapiens event we hosted at SickKids last fall, there was a memorable moment when Craig Venter and Geoffrey Hinton clashed over the potential impact, and risks, of AI. That sparked the idea for AI in Genomics as an extended ‘lab meeting’… which quickly evolved into something much bigger.”

Aiming to spotlight emerging research, spark interdisciplinary partnerships, and shape a growing community dedicated to the responsible and impactful use of AI in genomic science, AI in Genomics served as a platform for faculty, trainees, students, and research staff to share their work, learn from one another, and identify key opportunities where AI can address pressing challenges in genomics.

AI in Genomics encouraged participants to map out areas within genomics – such as disease risk prediction, gene expression analysis, or precision medicine – that could benefit most from advanced computational tools like machine learning and deep learning. The research panel explored impacts of AI in genomics from getting AI tools into the hands of clinicians and uses for optimizing population health. Researchers highlighted the need for a continuous cycle of discovery and implementation, and the need to figure out where is the right place for structured and unstructured data that can be used for research or clinical care, as well as the importance of reproducibility for research in AI in genomics.

“The DSI brings communities together to help advance fields,” Strug added. “This was supposed to be a small intimate event to understand what’s happening on campus but the demand reflected that this is already a major area of interest and opportunity. We hope to better understand what is happening, how we can fill training gaps and how we can support the community to advance this area and realize the limitless opportunities.”

Data Sciences Institute hosts networking event with newly upskilled talent and top employers

by Andrea Smitko

The Data Sciences Institute (DSI) — a central hub and incubator for data science research, training and partnerships at U of T — hummed with excitement as participants from the first two cohorts of its new Data Science and Machine Learning Software Foundations Certificates met representatives from several organizations during an engaging in-person employer networking event.

Nearly 50 participants seized the opportunity to meet and mingle with their peers, as well as make connections with prospective employers.

With the financial support of Upskill Canada, powered by Palette Skills and the Government of Canada, the DSI Certificates are 16-week part-time intensive offerings. The Certificates are designed to train and upskill working professionals with three or more years of experience for careers in data analytics and applied machine learning.

“We just launched our Certificates a few months ago and we have had over 400 applications and over 200 participants and it is just growing — there is such a need in the community for this work,” said Lisa Strug, academic director of the DSI and professor in the Departments of Statistical Sciences and Computer Science and the Division of Biostatistics, in her opening remarks.

“These Certificates are very unique because we’ve developed them in concert with industry, so we’re making sure that the tools everybody receives are the tools that are actually needed to solve the problems that we’re seeing out there in the real world.”

Designed to be accessible and to build a more inclusive workforce, these Certificates aim to support diversifying the industry. From the first cohort, 90 per cent of participants belong to at least one underrepresented group.

The Certificates include job readiness training dedicated to career advancement and offer valuable coaching in job-seeking skills such as resume writing, interview preparation and networking.

“I really enjoyed the Certificate. Everything included in it was great. There was time to learn and to put that learning into practice,” said Certificate participant, Niyaz Nazari. “All of the associates were very professional, and I really enjoyed the job search courses. I needed to learn those soft skills. The theory is not enough, so that helped a lot.”

As part of its commitment to employment training, the DSI’s goal is for 75 per cent of participants to obtain a new role within six months of completing the Certificate.

“That’s why events like these are so important. To achieve this goal, we need to facilitate connections between organizations looking for talent with the in-demand skills we are teaching through these certificates,” said Strug.

The event welcomed nine organizations looking to hire new talent in the data sciences, including Accenture, Ontario Digital Services, Children’s Aid Society of Toronto, MPAC, Ontario Health, SOCAN, MunichRe, Norton Rose Fulbright, and Yorkville University. Employers were positioned in the DSI’s event space and attendees moved throughout asking questions, pitching their skills, and inquiring about the company and potential employment opportunities.

“Of all the talks I’ve given and events I’ve been a part of, I enjoy this audience the most,” said Tristan Walsh of MunichRe. “It’s all really positive. There’s such a strong level of engagement and great insight. It’s good to see people learning and growing, and it’s so great to meet people in person.”

“The Certificate was a great experience. I want to go back and do another course,” said program participant, Ahmed Alhuraibi Alamoudi. “It was very valuable, and now I can develop a roadmap so I can improve and transition into data science and hopefully do a co-op or an internship so I can practice what I’ve learned.”

 

To join our next event and meet accomplished professionals with data science and machine learning skills to grow your team, please contact dsi.partnerships@utoronto.ca

Data Sciences Institute conference explores the future of virtual reality

by Andrea Smitko

The Data Sciences Institute (DSI) — U of T’s multidisciplinary hub for data science innovation and collaboration — recently hosted “Questioning Reality: Explorations of Virtual Reality (VR) and our Social Future,” a three-day conference where leading scholars, industry professionals, and VR enthusiasts gathered to discuss the future of VR and its impact on social interactions.

The conference  — led by the DSI’s Bree McEwan, an associate professor in the Institute for Communication, Culture, and Information Technology (ICCIT) at the University of Toronto Mississauga and Sun Joo (Grace) Ahn, director of the Center for Advanced Computer-Human Ecosystems and professor at the University of Georgia — featured a series of engaging discussions, presentations and networking opportunities.

Programmed with the goal of shaping a social interaction-informed agenda for the next research cycle on VR, the event focused on exploring social interactions in mediated environments, including VR, augmented reality (AR), extended reality (XR), and mixed realities (MR).

“This event is an extension of the DSI’s mission to bring the data sciences across industries together to drive social change and work on a concept of social interaction across a variety of realities,” said McEwan. “We’ve brought together not only the academics but also industry professionals to hear their ideas about the potential future of this area of research.”

With the intention of sparking dialogue and fostering meaningful connections, the event was kept to 40 attendees, which allowed for an atmosphere that promoted relationship building, a free flow of ideas and many key opportunities for cross-collaboration.

“Everybody in attendance is interested in social interactions, but across a different range of media or technologies,” said Ahn at the event.

“Each attendee represents a piece of the question: how do people interact in virtual environments using different devices — it could be video games, virtual reality, social media, XR. All of the conversations over the next few days should reveal the kinds of questions we should be asking in the next phase of research: What are the important and critical questions that will push forward the research for the next five or 10 years as an output?”

The conference began on Thursday afternoon with introductions and a keynote presentation on communication in VR/AR by Professor Lynn Miller of the University of Southern California.

In a talk entitled Interpersonal Science in Space and Time: Advancing (and Learning from) Emerging Synchronous Virtual (and “Real”) Worlds, Miller spoke about the importance of understanding and improving social interactions in both virtual and real-world contexts.

On the second day, attendees participated in a series of collaborative exercises and lightning talks on cutting-edge research, brainstormed “blue sky” ideas, and explored forthcoming challenges from privacy concerns to the democratization of VR experiences.

In the afternoon, Shalini De Mello, director of research and distinguished research scientist at NVIDIA, delivered the keynote talk Democratizing Telepresence with AI-Mediated Photoreal Avatar Creation, where she spoke about the exciting field of AI-mediated reality and the intersection of technology with human communication and interaction.

The day also featured an industry panel discussion with leaders Reality Prime, Meta Reality Labs, Engage XR and JP Morgan Chase. Panelists spoke about the important relationship between business and research, and the challenges faced and opportunities available when partnering on future projects.

“I would really love to see, not just online schools but also in-person schools, create an ecosystem with social VR that allows students to feel more engaged with content socialization, because our world is shifting and changing,” said Maxwell McGee of Engage XR and Post University. “It’s not as easy as it once was to travel halfway across the world to your dream university or college. I would like to see more ecosystems created to increase those connections where they otherwise might not be available.” 

The last day included a session devoted to forecasting for the future and a final keynote presentation by Tony Liao, associate professor at the University of Houston, Moving Across and Between Realities: An Agenda for the Next Wave of Social XR Research, in which he emphasized the critical need for responsible and thoughtful development of artificial intelligence (AI) technologies as we navigate the intersection of virtual reality and our social future. Liao also noted that the Questioning Reality conference served as a potentially field-configuring event, and that the discussions that took place over its three days may shape the field and direction of research for years to come.

The Questioning Reality conference was supported by the Alfred P. Sloan Foundation, a not-for-profit, mission-driven grantmaking institution dedicated to improving the welfare of all through the advancement of scientific knowledge. The grant was awarded to the DSI to delve into VR technology and its profound implications for human interaction and communication.

“VR and AR technologies have the potential to reshape how we interact and collaborate as individuals, groups and as a society,” said Josh Greenberg, program director for the Sloan Foundation. “We’re very proud to fund this innovative work through the DSI and to support the advancement of this research that will help to inform the responsible development of this influential technology.”

Discussions from the conference will be reflected in a new edition of Debates in Digital Media focused on virtual reality. The Sloan Foundation will also fund five mini-grant research projects, each designed to propel the field forward through innovative research endeavors. The Questioning Reality conference and Sloan Foundation grant serve as a beacon of support and recognition for the DSI’s commitment to pushing the boundaries of knowledge and innovation in the data sciences. 

Polygenic Risk Score Grant Winners Announced: Advancing Genomic Medicine Through Innovative Research

by Sara Elhawash

The Data Sciences Institute (DSI) is pleased to announce the recipients of the DSI-McLaughlin Centre Polygenic Risk Score Grant competition. This grant, created in partnership with the University of Toronto’s McLaughlin Centre and the Dalla Lana School of Public Health, aims to support emerging research and build capacity in the field of polygenic risk score studies. Polygenic risk scores enable researchers to use multiple genetic factors to estimate an individual’s genetic risk for complex diseases, providing important information for predicting, preventing and treating diseases. 

Professor France Gagnon, Chair of the adjudication committee and Associate Dean Research at the Dalla Lana School of Public Health, expressed enthusiasm for the wide range of proposals received from researchers across the University and partner institutions. These proposals demonstrate the potential for innovative methodologies in polygenic risk scores to impact a wide range of fields. “We are thrilled to support this cutting-edge research and look forward to seeing its impact on the field of precision population health and medicine,” said Gagnon. 

Two of the grant recipients are Professors Frank Wendt and Esteban Parra, Department of Anthropology at the University of Toronto Mississauga. They are taking a new approach to the study of major depressive disorder (MDD) and hippocampus volume. Their research aims to improve the accuracy of polygenic risk score predictions for this disorder and expand our understanding of its biology. Wendt and Parra said, “By taking a tandem repeat aware approach to risk scores, we hope to uncover new insights into the biology of major depressive disorder, improve prediction accuracy, and develop scores that better translate across population groups. We are thrilled to contribute to this important area of research that takes an interdisciplinary approach to pressing matters in genomic medicine.” 

Grant recipients Lei Sun and Ziang Zhang from the Department of Statistical Sciences, Faculty of Arts & Science, are collaborating with Dr. Andrew Paterson from The Hospital for Sick Children on a project to develop polygenic risk scores for binary traits, which are traits that can only take on two possible outcomes, such as the presence or absence of a particular disease. Their research aims to investigate how the estimated effects of different genetic factors can be biased and propose a new way to adjust for this bias to improve the accuracy of the polygenic risk scores. “Because of DSI’s emphasis on interdisciplinary research, all team members with complementary expertise worked closely to define and develop a research project with statistical rigor and practical impact. This grant also provides graduate students in Statistical Sciences a unique opportunity to lead a grant application, which is rare in our discipline,” said Sun. These projects have the potential to improve our understanding of complex diseases and advance the fields of precision medicine and population health. 

Congratulations to all the DSI – McLaughlin Centre Polygenic Risk Score Grant collaborative research teams! 

A Multimodal AI Solution for Improved Outcome Prediction using Polygenic Scores and EHR  

  • Zahra Shakeri (Institute of Health Policy, Management, and Evaluation, Dalla Lana School of Public Health, U of T); Kuan Liu (Institute of Health Policy, Management, and Evaluation, Dalla Lana School of Public Health, U of T) 

Addressing non-collapsibility in logistic regression when constructing polygenic risk scores for binary traits 

  • Lei Sun (Department of Statistical Sciences, Faculty of Arts & Science, U of T), Andrew Paterson (Genetics and Genome Biology, The Hospital for Sick Children), and Ziang Zhang (Department of Statistical Sciences, Faculty of Arts & Science, U of T) 

Inclusive Trans-ancestry Polygenic Genetic Risk Scores (iPRS) via Robust Transfer Learning 

  • Jessica Gronsbell (Department of Statistical Sciences, Faculty of Arts & Science, U of T); Jianhui Gao (Department of Statistical Sciences, Faculty of Arts & Science, U of T)

Tandem repeat aware risk scores linking major depression and hippocampus volume 

  • Frank Wendt (Department of Anthropology, University of Toronto Mississauga); Esteban Parra (Department of Anthropology, University of Toronto Mississauga) 

Revolutionizing Neuroscience with DSI Catalyst Grant: UTSC Professors Harness the Power of Machine Learning

by Sara Elhawash

Professors Guillaume Filion and Minoru Koyama, DSI members from the University of Toronto Scarborough’s Department of Biological Sciences, are advancing neuroscience with an innovative approach through the help of the Data Sciences Institute Catalyst Grant. Their work repurposes technology found in Google Translate and DeepL to translate images of brain activity into movements, offering a powerful understanding of the relationship between the brain and behaviour. 

 

One main goal of neuroscience is to understand how complex connections between neurons lead to behaviour when reacting to stimuli. The researchers note that it is now possible to record the activity of tens of thousands of neurons simultaneously in behaving animals. However, there’s still a need for better analytical methods. Their project aims to develop a new approach to understanding the brain by exploring the relationship between neural activity and behaviour.  The team will record the brain activity and movements of zebrafish and use a cross-attention mechanism to interpret the data. The ultimate goal is to change experimental research by introducing a different approach that goes beyond solving short-term problems or answering specific questions related to fish behaviour. 

 

“As researchers, we are striving to use machine learning for scientific discovery by exploring how machines can teach us the things they figure out about nature. However, it is important to note that not all machine learning techniques are equally helpful in advancing our understanding of the brain. An AI that simply predicts behaviour from the activity of the brain may not give any insight into brain function “ explained Filion and Koyama. They emphasized that for an AI to help understand the brain, it must be programmed with explanation mechanisms from the start. This is crucial for advancing our understanding of the brain and ultimately developing treatments for brain-related disorders.

 

Interdisciplinary collaborations are key for advancing knowledge and discovery, according to the researchers. They emphasize the value of combining expertise from different disciplines to unlocking new insights. “The support from the DSI is making a significant difference by allowing us to invest in new research avenues,“ they noted. “The developments in this area could have revolutionary implications for experimental neuroscience.“

 

Gary Bader, DSI’s Associate Director, Research & Software, said, “This ground-breaking research is pushing the boundaries of interactions between machines and humans in the field of neuroscience. We are thrilled to support their innovative work and look forward to seeing its impact.“