SUDS project

Oct 02 2026

Using advanced machine learning approaches to optimize psychological test efficiency interview

Research description:

This project will involve students to use advanced machine learning approaches to analyze large scale datasets of psychological tests with responses collected from participants all over the world. The goal of this project is to analyze response patterns from participants, train computational models to optimize the assessment of participants’ psychological traits (e.g., personality) and abilities (e.g., IQ) in an effective and efficient manner, and implement computational models in an app for use by real-world users.

The student will be responsible for data cleaning, data analysis, using machine learning techniques to optimize the models, implementing the models on a website for use by users, and writing a paper for publication.

Year: 2024

Researcher:
Kang Lee, Department of Applied Psychology and Human Development, Ontario Institute for Studies in Education, University of Toronto

Student:
Rogers Yang, University of Toronto

Through SUDS, undergraduate students engage in hands-on research focused on data sciences and AI methodology applications.

Learn more

Oct 02 2026

Using Natural Language Processing to Understand Naturalistic Speech Perception Herrman

Research description:

Many adults over 60 years live with some form of hearing impairment that makes speech comprehension difficulty. However, progress in predicting speech-comprehension difficulties in everyday life has been limited, in part, because hearing-science research has mainly focused on speech comprehension of short, disconnected sentences that lack a topical thread and are not relevant to the listener. New approaches to understanding naturalistic speech listening are thus critical to gaining insight into impaired speech processing.

The student will be involved in research that leverages novel natural language processing (NLP) approaches (e.g., sentence embeddings) with graph theoretic approaches (e.g., network centrality) to better understand how individuals listen to naturalistic speech. The student will analyze transcripts of spoken stories and transcripts of individuals recalling these stories after listening to them (using NLP), and will integrate relevant information from these analyses to capture the structure in which individuals comprehend speech (using graph theory). The student will program the analyses and visualize the results using Python/MATLAB. The student will work with the supervisor and a graduate student with biophysics and psychology background. The lab provides ample opportunities to learn how sophisticated data-analysis tools can be used to facilitate research in basic science with clinical applicability.

Year: 2024

Researcher:
Bjorn Herrmann, Baycrest

Students:
Nicholas Wong, University of Toronto Mississauga

Through SUDS, undergraduate students engage in hands-on research focused on data sciences and AI methodology applications.

Learn more

Oct 02 2026

Using single-cell data analysis approaches to inform the design of iNKT-targeted cancer immunotherapies

Research description:

Invariant natural killer T (iNKT) cells are unconventional T-cells that are ubiquitously found in mammals and provide immunity to pathogens and against tumours. Through their T-cell receptor (TCR), iNKT cells respond to glycolipid antigens, a class of antigens that is invisible to conventional CD4 or CD8 T-cells. Furthermore, these cells are heterogenous and can differentiate into discrete effector subsets. Using advanced functional genomics, we identified a bona fide cytotoxic iNKT cell subset, which is functionally equivalent to cytotoxic CD8 T-cells. These cytotoxic iNKT cells efficiently kill tumour cells in vitro/in vivo and provide several advantages over their CD8 T-cell counterparts. Interestingly, cytotoxic iNKT cells recognize and kill tumour cells through several modalities that are both TCR-dependent and TCR-independent. Together, our findings indicate that cytotoxic iNKT cells could be used to develop novel cancer immunotherapies with a lower risk of tumour evasion, although a mechanistic understanding of their function remains to be understood. The goal of this project is to leverage available single cell RNA sequencing datasets to identify immune receptors expressed by cytotoxic iNKT cells that may be involved in recognition of or response against tumour cells. Results from this work will inform the rational design of iNKT-targeted cancer immunotherapies. This project is co-supervised with Dr. Thierry Mallevaey (Department of Immunology, Temerty Faculty of Medicine, University of Toronto).

The responsibilities of the student will include, although are not limited to:

Review the primary literature to find important immune receptors expressed by cytotoxic iNKT cells
Assess the quality of available scRNA seq datasets, with consideration of experimental design/statistics
Establish a scRNA seq data processing workflow
Perform data reduction and clustering of available scRNA seq datasets using R software
Identify genes driving cluster formation from scRNA seq data and extract biological knowledge from cluster-specific biomarkers
Attend weekly lab meetings (~1 hour/week) and present research updates biweekly
If time: validate identified biomarkers on iNKT cell subsets in the laboratory setting via flow cytometry or through performing gene expression analyses using qRT-PCR

Year: 2024

Researcher:
Jastara Singh, Department of Immunology, Temerty Faculty of Medicine, University of Toronto

Students:
Jahin Kabir, University of Toronto

Through SUDS, undergraduate students engage in hands-on research focused on data sciences and AI methodology applications.

Learn more

Oct 02 2026

Mass extinctions and nocturnal behaviour: an analysis of the cryptic activity patterns of arthropods

Research description:

Animal species exhibit characteristic diurnal or nocturnal activity patterns, as a result of adaptations to the daily light cycle. However, we do not fully understand the evolutionary causes or consequences of these activity patterns. We have previously investigated temporal activity patterns across ~4000 species of fish through meta-analysis of the literature, and compared these to the activity patterns of ~5000 species of tetrapods. We demonstrated that nocturnality conferred an evolutionary advantage during mass extinctions, and that frequent nocturnal-to-diurnal transitions facilitated post-extinction diversification across vertebrates (Shafer et al, biorXiv, 2023). However, almost nothing is known about the evolution of this behaviour across the most diverse animal phyla, invertebrates (insects, mollusks, and cnidaria) of which there may be as many as 10 million species worldwide.

The SUDS scholar will extend our macro-analyses, and reconstruct the tempo and evolution of nocturnality and diurnality across invertebrates. Using machine learning assisted text mining, they will perform a systematic literature survey to identify the temporal activity patterns for thousands of species, and use statistical phylogenetic modeling and ancestral reconstruction to compare the evolution of nocturnality and diurnality across the vertebrate and invertebrate animal kingdoms.

Year: 2024

Researcher:
Maxwell Shafer, Department of Cell and Systems Biology, Faculty of Arts & Science, University of Toronto

Student:
David Carter, University of Toronto

Through SUDS, undergraduate students engage in hands-on research focused on data sciences and AI methodology applications.

Learn more

Oct 02 2026

Machine Learning to Uncover the Oldest Light in the Universe

Research description:

The Simons Observatory (SO) is a new, multi-telescope experiment to study the origin and evolution of the cosmos by measuring the cosmic microwave background (CMB), the oldest light in the Universe. Raw data consist of TBs of timestreams of measured sky brightness recorded each day—adding up to several PB over several years—that need to be reconstructed into 2D maps. However, before this can happen, the timestreams need to be automatically processed to remove noise contaminants and foreground galaxies/stars that block the main signal. In this project, you will work with a small team of researchers in Toronto that is developing machine learning methods to identify and classify these objects. Some development may use existing data from the Atacama Cosmology Telescope (ACT), a precursor to SO. Possible avenues of research include developing ways of retraining our classification algorithms on-the-fly and figuring out how to propagate uncertainties in classification into errors in the final maps. An exciting aspect of this project is that our classification will help enable the search for astrophysical transients, such as flaring stars and gamma ray bursts. The successful candidate will:

Write and document code in coordination with the research team led by Profs. Hincks & Hložek. This may include researching suitable methods/algorithms for the code.
Participate in regular meetings (~weekly) with team members, with flexibility regarding in-person or remote attendance.
Possibly participate in ~weekly telecons with other SO researchers.
Optionally attend training sessions and seminars for undergraduate researchers offered in the department of Astronomy & Astrophysics.
This is a full time position, but apart from meetings (schedules TBD), work hours are flexible.

Year: 2024

Researcher:
Adam Hincks, David A. Dunlap Department of Astronomy and Astrophysics, Faculty of Arts & Science, University of Toronto

Student:
Maxwell Bridgewater, University of Toronto

Through SUDS, undergraduate students engage in hands-on research focused on data sciences and AI methodology applications.

Learn more