Each year, researchers around the world create thousands of new materials — but many of them never reach their full potential. A new AI tool from U of T Engineering could change that by predicting how a new material could best be used, right from the moment it’s made.
In a study published in Nature Communications, a team led by Professor Seyed Mohamad Moosavi (ChemE) introduces a multimodal AI tool that can predict how well a new material might perform in the real world.
The system focuses on a class of porous materials known as metal-organic frameworks (MOFs). Moosavi says that last year alone, materials scientists created more than 5,000 different types of MOFs, which have tunable properties that lead to a wide range of potential applications.
For example, MOFs can be used to separate CO2 from other gases in a waste stream, preventing the carbon from reaching the atmosphere and contributing to climate change. They can also be used to deliver drugs to particular areas of the body, or to add new functions to advanced electronic devices.
According to Moosavi, one major challenge facing the field is that a MOF created for one purpose often turns out to have the ideal properties for a completely different application.
For example, in one of their previous studies, it was found that a material originally synthesized for photocatalysis was instead very effective for carbon capture — but this discovery was only made seven years later.
“In materials discovery, the typical question is, ‘What is the best material for this application?’” says Moosavi.
“We flipped the question and asked, ‘What’s the best application for this new material?’ With so many materials made every day, we want to shift the focus from ‘what material do we make next’ to ‘what evaluation should we do next.’”
This approach aims to reduce the time lag between discovery and deployment of MOFs.
To help make this possible, ChemE PhD student Sartaaj Khan developed a multimodal machine learning system trained on various types of data typically available immediately after synthesis — specifically, the precursor chemicals used to make the material, and its powder X-ray diffraction (PXRD) pattern.
“Multimodality matters,” says Khan. “Just as humans use different senses — such as vision and language — to understand the world, combining different types of material data gives our model a more complete picture.”
The AI system uses a multimodal pretraining strategy to gain insights into a material’s geometry and chemical environment, enabling it to make accurate property predictions without needing post-synthesis structural characterization.
This can speed up the discovery process and help researchers recognize promising materials before they’re overlooked or shelved.
To test the model, the team conducted a ‘time-travel’ experiment. They trained the AI on material data available before 2017 and asked it to evaluate materials synthesized after that date.
The system successfully flagged several materials — originally developed for other purposes — as strong candidates for carbon capture. Some of those are now undergoing experimental validation in collaboration with the National Research Council of Canada.
Looking ahead, Moosavi plans to integrate the AI into the self-driving laboratories (SDLs) at U of T’s Acceleration Consortium, a global hub for automated materials discovery.
“SDLs automate the process of designing, synthesizing and testing new materials,” he says.
“When one lab creates a new material, our system could evaluate it — and potentially reroute it to another lab better equipped to assess its full potential. That kind of seamless inter-lab coordination could accelerate materials discovery.”
A new paper by Professor Isabelle Rao in the Department of Mechanical & Industrial Engineering (MIE) uses mathematical modelling to show the impact of providing stable housing to people experiencing homelessness and opioid addiction.
The paper published in JAMA Network Open shows that a ‘housing first’ approach to treating homelessness and addiction can minimize the likelihood of fatal overdoses and decrease healthcare costs.
“Homelessness, substance abuse disorders and a disconnect from healthcare services are all intertwined,” says Rao, who joined MIE in 2024. “For example, homelessness increases the likelihood of developing an addiction, while addiction increases the likelihood of losing housing options.”
Approaches to treating these interrelated issues typically fall into two general categories: housing first and treatment first. Housing first emphasizes providing permanent housing as quickly as possible, with other supportive services following afterward, while treatment first advocates for the opposite.
During the COVID-19 pandemic, opioid use spiked and fentanyl became a leading cause of overdose deaths. This motivated Rao and her former advisor, Professor Margaret Brandeau of the Management Science and Engineering Department at Stanford University, to create a dynamic mathematical model that incorporated housing, a key social determinant of health, into the analysis of the opioid epidemic.
The model simulated treatment and health outcomes for 1,000 unhoused people with opioid addiction, with and without the provision of stable housing. The model encompassed men and women over a range of ages, projected overdoses and deaths over five years, as well as lifetime healthcare and housing costs, and quality-adjusted life years (QALYs).
The results of their simulations demonstrated that investing in stable housing for marginalized populations was cost-effective, improved health outcomes, increased entry into and retention in addiction treatment, and saved lives.
“The most successful outcome in our analysis came when stable housing was provided,” says Rao. “This improved addiction treatment success and reduced mortality rates among individuals who had experienced homelessness.”
The team found that implementing the housing intervention reduced total overdoses and fatal overdoses over the five years by 11% and 9% respectively. The housing intervention costs $96,000 USD per person and increases QALYs by 3.59, leading to an incremental cost of $26,800 USD per QALY gained compared to the scenario with no housing. Accounting for savings in criminal justice system costs that accrue when individuals are no longer homeless, such housing programs may even be cost-saving.
“The results from the mathematical modelling demonstrate that providing stable housing is both life-saving and cost-effective,” says Rao. “This study has the potential to help inform local policies for funding and demonstrate the cost-effectiveness of Housing First programs.”
Rao and Brandeau have engaged with officials in California’s Santa Clara County, where Stanford University is located, to inform policies around homelessness.
They are also looking to do outreach with other local health communities, and expand into Toronto, and are currently seeking funding opportunities from the US National Institutes of Health (NIH).
“I have always been invested in having an impact on policies to improve the lives of marginalized communities,” says Rao. “My engineering and mathematical background allows me to use modelling to inform critical decisions in public health. It’s very motivating to see the positive and long-term healthcare and personal care impacts that stable housing can provide to people experiencing homelessness.”
Professors Craig Simmons (MIE, BME) and Julie Audet (BME), in collaboration with boutIQ solutions Inc., a University of Toronto spinout company specializing in AI-driven media optimization, has been awarded a $421,000 research grant through the Stem Cell Network’s 2025 Research Funding Competition. The award will support a collaborative initiative with the Acceleration Consortium and University Health Network to enhance stem cell-derived therapies for heart repair, with boutIQ contributing its proprietary AI-powered platform to improve the maturation and function of therapeutic cells.
Founded by professors Simmons and Audet, with clinician-scientist Neal Callaghan (BME PhD 2T1) and researchers Heta Lad (BME PhD 2T4), Doris Adao (BME PhD student), and Alice Feng (BME MASc student), boutIQ solutions aims to transform the way cell culture media is developed. The company uses artificial intelligence and machine learning to design complex, chemically-defined media that accelerates cell growth and boosts physiological performance. This is an essential step for making cell-based therapies more effective and clinically viable.
“We wanted to start this company because our platform can dramatically reduce the time and cost associated with the development of cell manufacturing processes,” says Audet.
“This is often a critical bottleneck not only for cardiac cell therapy but for many other cell-based biotechnologies as they are often struggling to address stringent and extremely complex cell culture requirements.”
With support from the Stem Cell Network, boutIQ will partner with Professors Milica Radisic (BME), Michael Laflamme of the University Health Network, and Yimu Zhao (BME PhD 1T6) at the Acceleration Consortium, to apply its technology to cardiac regenerative medicine. The goal is to develop optimized media that improves the function and maturity of heart cells derived from stem cells, helping them integrate more effectively into damaged heart tissue.
The company’s recent success builds on its growing reputation in Canada’s biotechnology sector. Earlier this year, boutIQ solutions was named the 2025 BBTV Grand Prize Winner at the Building a Biotech Venture Pitch Competition, for its AI/ML-powered approach to media development for regenerative medicine, biotechnology and cellular agriculture. The award included $25,000 in research funding from PRiME and Medicine by Design, a $5,000 BioHubNet VentureConnect Travel Award, a prize package from STEMCELL Technologies, including product support and training, and a one-on-one mentorship session with the Creative Destruction Lab.
“The U of T partnership allows us to apply our media optimization tools to cutting-edge stem cell research,” says Lad.
“It’s an important milestone for boutIQ as we grow our portfolio and continue refining our platform to support more predictive, scalable cell manufacturing.”
Professor Caitlin Maikawa of the University of Toronto’s Institute of Biomedical Engineering (BME) has been awarded the 2024 John Charles Polanyi Prize in Chemistry, recognizing her innovative research into biomaterials that could transform the way chronic diseases, such as inflammatory bowel disease (IBD), are monitored and managed.
Maikawa is one of five early-career researchers across Ontario to receive the award, which honours outstanding researchers who are building on the work of Nobel laureate John C. Polanyi. The recipients were recognized during a ceremony held at Queen’s Park on June 10, 2025.
An alumna of U of T’s Chemical Engineering program, Maikawa earned her PhD at Stanford University under Professor Eric Appel, where she developed advanced insulin formulations aimed at achieving autonomous insulin delivery. Her work sought to improve global access to insulin therapies, particularly in resource-limited regions. She later completed postdoctoral training at Brigham and Women’s Hospital in Boston, where she collaborated with Professors Jeffrey Karp and Yuhan Lee on biologically derived materials for inflammation tracking technologies.
Since joining BME in July 2023, Maikawa has launched an independent research program focused on developing next-generation biomaterials for personalized, at-home health monitoring. Her team is exploring ways to use responsive polymers that interact with inflammation-related molecules to signal changes in disease activity.
Current IBD monitoring often relies on stool-based tests, which are inconvenient and lead to low patient compliance. Maikawa’s research proposes an alternative: swallowable or orally administered devices containing polymer materials that dissolve in the presence of inflammation biomarkers, releasing a visible signal such as a colour change. These systems could offer a user-friendly and non-invasive way for patients and clinicians to catch flare-ups early and adjust treatment accordingly.
Her work has been published in leading scientific journals, including Science Translational Medicine, Nature Biomedical Engineering and Advanced Science. In addition to the Polanyi Prize, Maikawa has received a string of competitive research grants over the past year, including an NSERC Discovery Grant, the Connaught New Researcher Fund, the Canadian Foundation for Innovation’s John R. Evans Leaders Fund, and the 2024–2026 XSeed Grant.
The John Charles Polanyi Prizes are awarded annually by the Government of Ontario to support outstanding researchers in the early stages of their careers in the fields of chemistry, physics, physiology or medicine, literature and economic science.
From multilingual models for edge AI to new prognostics models for cancer patients, an international collaboration at U of T Engineering is developing innovative solutions to complex problems.
Two of the initiative’s key partners are U of T’s Centre for Analytics & Artificial Intelligence Engineering (CARTE) and the Institute of Information & Communications Technology Planning & Evaluation (IITP), South Korea.
For the last six months, 34 graduate students from across South Korea, sponsored by IITP, have been in Toronto, working with mentors at CARTE and U of T’s Department of Mechanical & Industrial Engineering (MIE) on challenges brought forward by partners from several different sectors.
All teams used AI and machine learning (ML) in their projects and presented their findings at The Hall at the Engineering Partnership Office on June 18. In the audience were U of T Engineering faculty members and representatives from all project partners — including Lorex Technology Inc., Kijiji Canada Ltd. and Guhuza, among many others.
“Our team developed an AI model for predicting mortality in prostate cancer patients. We took a multi-modal approach to integrate time-series data and textual records from patient visits, while accounting for the irregular visit intervals,” says Eunseon Seong, one of the students who worked on a project with Sunnybrook Health Sciences Centre.
“The project provided us with invaluable insights into building AI systems in real-world clinical settings”.
Dr. Kevin Ferreira, Senior Director of Artificial Intelligence and Head of LG Electronics Toronto AI Lab, was at the ceremony.
“This is the second year that we have partnered with this program, and we continue to be impressed by the caliber and creativity of the participating students,” says Ferreira.
“This year’s projects tackled some of the most exciting frontiers in AI research — from building efficient multilingual language models for edge deployment, to advancing knowledge distillation techniques that make large models faster, more efficient and environmentally sustainable, to designing robust evaluation frameworks for agentic AI systems.”
“Each project reflects our commitment to developing AI that is not only powerful, but practical and scalable. The student teams, mentored by our Toronto AI Lab researchers, brought fresh perspectives and technical excellence, delivering contributions that aid in advancing our research initiatives.”
In addition to working on the projects, all students took three graduate-level courses offered by MIE, and had access to customized AI drop-in clinics provided by CARTE.
They also attended a number of applied AI seminars offered at U of T, and used a dedicated workspace to facilitate collaborative opportunities and apply their knowledge and skills in the booming AI ecosystem in Toronto.
“Since 2024, MIE has hosted more than 30 grad students annually from South Korea through this program to take advantage of the variety of AI/ML courses that we offer,” says Professor Markus Bussmann, Chair of the Department of Mechanical & Industrial Engineering, who was also at the event.
“Through this engagement and other partnerships with South Korea, including hosting an international doctoral cluster with Korea Advanced Institute of Science and Technology (KAIST), and a new Global Industrial Technology Cooperation Center between South Korea and Canada on AI and Manufacturing, led by MIE Professor Chi-Guhn Lee, we are building an international community of researchers able to make real-world impact with AI.”
“This partnership between CARTE and IITP is a perfect example of how international collaboration can accelerate innovation and train the next generation of AI leaders,” says Professor Alex Mihailidis (BME), Associate Vice-President for International Partnerships at U of T.
“By bringing together talented students, world-class mentors and real-world challenges, we’re creating solutions that are not only technically advanced, but also socially meaningful. This is exactly the kind of initiative we need more of.”
The full list of projects and partner organizations in the latest round includes:
- Optimizing Real-Time Candidate Matching for Staffing Efficiency — Guhuza
- Comprehensive Quality Scoring for Marketplace Listings — Kijiji Canada Ltd.
- Efficient Multi-Lingual Language Models for Edge AI — LG Electronics Toronto AI Lab
- Knowledge Distillation for Edge AI Deployment — LG Electronics Toronto AI Lab
- Evaluation Frameworks for Agentic AI Systems — LG Electronics Toronto AI Lab
- Anomaly Detection for Security Camera Footage — Lorex Technology Inc.
- Realistic Hair Removal and Reconstruction in Images — ModiFace Inc.
- Enhancing Robustness and Transparency in Conversational AI Scoring — Nexxt Intelligence Inc.
- Prognostics for Musculoskeletal Health in Prostate Cancer Patients — Sunnybrook Health Sciences Centre
To learn more about partnership opportunities with CARTE on applied research or training programs in AI, please connect online.
For Allana Nakashook-Zettler (ChemE 2T4 + PEY), studying at the University of Toronto wasn’t just an investment in her future — it was an opportunity to make an impact today.
An urban Inuk who is passionate about science and engineering, Nakashook-Zettler worked with one of U of T’s leading researchers to investigate the health impacts of industrial chemicals on people in northern Ontario. Later, during a co-op program placement at Environment and Climate Change Canada, she helped refine criteria for an emissions grant program to improve benefits for Indigenous communities.
In her spare time, she fostered community among her peers as an intramural volleyball captain, campus tour guide and Indigenous peer mentor.
“I’ve gotten so many amazing opportunities … and to see that I can have really impactful and meaningful change is really encouraging,” says Nakashook-Zettler, who will graduate on June 17 with a bachelor of applied science degree in chemical engineering from the Faculty of Applied Science & Engineering, where she will begin graduate studies in the fall.
“U of T has really created a path for me in my life and allowed me to see where I can make a difference.”
Born in Iqaluit, Nakashook-Zettler has lived in British Columbia, Newfoundland, Ontario and the Northwest Territories. She studied at U of T with the support of an Engineering Entrance Scholarship for Indigenous Students.
A former Girl Guide, she credits the organization’s strong female role models with inspiring her passion for STEM subjects. “A lot of them were engineers… they were able to bring that out of me and encourage me to pursue engineering.”
At U of T, Nakashook-Zettler sought out opportunities that combined her interests in sustainability, engineering and Indigenous empowerment. In her second year, for example, she joined a research project, led by University Professor Cristina Amon (MIE), a former dean of the engineering faculty, exploring links between benzene exposure and development of acute myeloid leukemia in children.
“This is important because communities in northern Ontario have seen an increase of acute myeloid leukemia in children under five … so they’re investigating the link to it and surrounding factories and processing plants,” Nakashook-Zettler says.
For Nakashook-Zettler, the project was a chance to elevate Indigenous knowledge systems, which have often been overlooked in Western science.
“From my perspective, knowing and understanding Western perspectives on research has helped me convey the importance of Indigenous Knowledge and its integration into all research, particularly engineering.”
After her third year, she completed a Professional Experience Year Co-Op Program placement at Environment and Climate Change Canada’s climate change branch. While reviewing funding criteria for emissions reduction projects, she noticed that the department’s “Indigenous co-benefits” requirement allowed companies with only superficial ties to Indigenous communities to qualify for federal grants.
“As an Inuk, I didn’t really appreciate how it was written and could see there was vast room for improvement,” she says, adding that she shared her concern with her manager who sought her input on revising the requirement.
“It was phenomenal for my confidence,” she says. “It really pushed me to see the contributions I can make, especially as I’m still only a student.”
Back on campus, Nakashook-Zettler continued to build community through co-curricular activities.
As captain of two intramural volleyball teams, she prioritized connection as much as competition. “A lot of the time, you show up, play volleyball, don’t talk to each other and leave — but I intentionally fostered a sense of community and caring,” she says. “It not only made everyone happier — I feel like I created friendships that will last a lifetime — but it also helped us play better.”
She also became involved with First Nations House, mentoring first-year engineering students through the Indigenous Peer Group Mentorship initiative.
As a St. George campus tour guide, she emphasized the importance of community to incoming students.
“One thing I always tell them is that you have to be really intentional … my advice is to put yourself out there, talk to your professors and classmates, say ‘Yes,’ to go hang out or get lunch. Those are the important moments,” she says.
“Nobody’s going to remember what you got in your quiz on Oct. 12 in your second year, but you’re going to remember the fun times and moments. Making room for that and creating a balance for yourself will ultimately make you happier, but also open you up to more opportunities.”
Nakashook-Zettler is set to continue her studies at U of T, where she has been accepted into the master of engineering program in chemical engineering. Long-term, she hopes to find a job where she can grow and continue making an impact.
For now, she’s focused on celebrating her achievement and sharing the moment with loved ones.
“My family’s so proud of me,” she says. “On my mom’s side, I’m the first to graduate university with a bachelor’s degree. There’s such a sense of pride — it’s hard to describe in words.”