AI in Genomics

The goal of the event is to learn about the current research happening in our University of Toronto community, seed collaborations or larger initiatives, build a community and share experiences, as well as understand major research areas in genomics that could benefit from AI where we could grow.

Co-sponsored by

August 18, 2025
9:30-9:55
Registration
9:55-10:00
Welcome and Opening Remarks

Stephen W. Scherer, Chief of Research, Northbridge Chair in Paediatric Research, Senior Scientist, Genetics & Genome Biology program, The Hospital for Sick Children; Director, McLaughlin Centre, University of Toronto

Lisa Strug, Director, Data Sciences Institute, University of Toronto Professor, Departments of Statistical Sciences, Computer Science and cross-appointed in Biostatistics, University of Toronto; Senior Scientist in the Program in Genetics and Genome Biology, Hospital for Sick Children
10:00-10:30
Opportunities and pitfalls in using AI for integration of high-dimensional spatial genomics data
Kieran Campbell, Scientist, Lunenfeld-Tanenbaum Research Institute Assistant Professor, Departments of Molecular Genetics and Statistical Sciences, University of Toronto
10:30-11:00
Combining statistical machine learning with mechanistic modeling on multi-scale high-dimensional biological data
Shu Wang, Assistant Professor, Donnelly Centre for Cellular and Biomolecular Research & Department of Molecular Genetics, University of Toronto
11:00-11:20
Coffee break and discussion with speakers
11:20-11:35
GeneClinTransform: Pretraining a Genomic Foundation Model for Complex Disease Risk Prediction
Yu Shi, PhD Student, Dalla Lana School of Public Health, University of Toronto
11:35 -11:50
Enhancing Clinical Utility of Polygenic Scores with Small, Phenotypically Refined Cohorts: Application to Idiopathic Generalized Epilepsy
Yu-Chung (Jerry) Lin, PhD Student, Division of Biostatistics, Dalla Lana School of Public Health, University of Toronto
11:50-12:05
Cell type similarity score for predicting transcription factor binding with neural networks
Gergely Pap, Postdoctoral Fellow, Hoffman Lab, Princes Margaret Cancer Center, University Health Network
12:05-1:00
Lunch and networking
1:00-1:30
Machine learning methods for peptide, protein and antibody design
Philip M. Kim, Canada Research Chair Machine Learning in Protein and Peptide Science and Professor, Donnelly Centre for Cellular and Biomolecular Research Departments of Molecular Genetics and Computer Science, University of Toronto
1:30-2:00
Pass the baton: finding communication relay networks in tissue
Gregory Schwartz , 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
2:00-2:20
Coffee break and discussion with speakers
2:20-2:35
OmniPert: A Deep Learning Foundation Model for Predicting Responses to Genetic and Chemical Perturbations in Single Cancer Cells
Farzan Taj, PhD Student, Department of Molecular Genetics, University of Toronto
2:35-2:50
Integrating AI into Cancer Early Detection: Examples of Proteomics and Lung Cancer
Elham Moez, Data Sciences Institute Postdoctoral Fellow, Posserman Centre for Population Health Research, Lunenfeld-Tanenbaum Research Institute, Sinai Health
2:50-3:50
Open questions and opportunities for AI in Genomics
Panel discussion

Michael Brudno, Professor, Department of Computer Science, University of Toronto, Chief Data Scientist, University Health Network Senior Scientist, Princess Margaret Cancer Center

Michael Hoffman, Senior Scientist and Chair, Computational Biology Medicine Program, Princess Margaret Cancer Centre, University Health Network; Associate Professor, Department of Medical Biophysics, University of Toronto

Rayjean J. Hung, Senior Investigator and Associate Director of Population Health, Lunenfeld-Tanenbaum Research Institute, Sinai Health System

Lincoln Stein, Acting Scientific Director, and Head, Adaptive Oncology, Ontario Institute for Cancer Research and Professor, Department of Molecular Genomics, University of Toronto

Lisa Strug, Moderator, Director, Data Sciences Institute, University of Toronto Professor, Departments of Statistical Sciences, Computer Science and cross-appointed in Biostatistics, University of Toronto; Senior Scientist in the Program in Genetics and Genome Biology, Hospital for Sick Children.

Speakers

Michael Brudno, Professor, Department of Computer Science, University of Toronto,
Chief Data Scientist, University Health Network
Senior Scientist, Princess Margaret Cancer Center

Prof. Brudno’s research interest is the development of computational methods for the analysis of clinical and genomic datasets, especially the capture of precise clinical data from clinicians using effective user interfaces, and its utilization in the automated analysis of genomes. This work focuses on the capture of structured phenotypic data from clinical encounters, using both refined User Interfaces, and mining of unstructured data (based on Machine Learning methodology), and the analysis of omics data (genome, transcriptome, epigenome) in the context of the structured patient phenotypes, mostly for rare diseases. His overall research goal is to enable the seamless automated analysis of patient omics data based on automatically captured information from a clinical encounter, thus streamlining clinical workflows and enabling faster and better treatments. He received his PhD from the Computer Science Department of Stanford University, working on algorithms for whole genome alignments.

Kieran Campbell, Scientist, Lunenfeld-Tanenbaum Research Institute
Assistant Professor, Departments of Molecular Genetics and Statistical Sciences, University of Toronto
Canada Research Chair in Machine Learning for Translational Biomedicine

Dr. Campbell’s research focuses on Bayesian models and machine learning for high-dimensional biomedical data, including single-cell and cancer genomics. Recently, he has led efforts to develop statistical machine learning methodology to integrate single-cell RNA and DNA sequencing data to uncover the effects of tumour clonal identity on gene expression, as well as methods to automatically delineate the tumour microenvironment from single-cell RNA-sequencing data. Such findings can improve our understanding of cancer progression and of why certain tumours are resistant to therapies, leading to relapse. He obtained his D. Phil in computational and statistical genomics at the University of Oxford.

Michael Hoffman, Senior Scientist and Chair, Computational Biology Medicine Program, Princess Margaret Cancer Centre, University Health Network; Associate Professor, Department of Medical Biophysics, University of Toronto

Dr. Hoffman creates predictive computational models to understand interactions between genome, epigenome, and phenotype in human cancers. His influential machine learning approaches have reshaped researchers’ analysis of gene regulation. These approaches include the genome annotation method Segway, which enables simple interpretation of multivariate genomic data.

Rayjean J. Hung, Senior Investigator and Associate Director of Population Health, Lunenfeld-Tanenbaum Research Institute, Sinai Health System= Professor, Division of Epidemiology, Dalla Lana School of Public Health, University of Toronto.
Canada Research Chair in Integrative Molecular Epidemiology

Dr. Hung’s research focuses on molecular and genomic epidemiology of cancer with ultimate goals of understanding cancer etiology and mechanism, and contributing to primary and secondary prevention. The current research topics in Dr. Hung’s team include international studies of aerodigestive tract cancers and childhood cancers, as well as multi-omics integrative analysis for risk modeling. She has substantial experience and expertise in analyzing data with high-dimensionality and published several high-impact papers on lung cancer genetics and cross-cancer pleiotropy. She has also led several seminal and highly-cited papers that quantified the risk factors for lung cancer beyond tobacco smoking. In addition, she has several long-standing collaborative projects with the World Health Organization and National Institutes of Health, and has advisory roles for several national and international organizations.

Philip M. Kim, Canada Research Chair Machine Learning in Protein and Peptide Science and Professor, Donnelly Centre for Cellular and Biomolecular Research
Departments of Molecular Genetics and Computer Science, University of Toronto

Prof. Kim leads an integrated computational and experimental research laboratory that focuses on peptide and protein-based therapeutics. In particular, he is developing artificial intelligence as well as physics-based algorithms for peptide and protein design and is tightly integrating these with modern high-throughput wet-lab screening technologies. Before setting up his lab at the University of Toronto, he was a postdoctoral fellow at Yale University and an associate with McKinsey & Co. He holds a PhD from the Massachusetts Institute of Technology and a BS in Biochemistry and Physics from the University of Tuebingen.

Yu-Chung Lin, PhD Student, Division of Biostatistics, Dalla Lana School of Public Health, University of Toronto

Jerry Lin completed his B.ASc in Electrical Engineering and M.Sc in Statistics at the University of Toronto before enrolling in PhD program in Biostatistics at the Dalla Lana School of Public Health. Under the supervision of Dr. Lisa Strug, he is building predictive models for Cystic Fibrosis Related Diabetes (CFRD) and severity of CF. 

Elham Moez, Data Science Postdoctoral Fellow, Posserman Centre for Population Health Research, Lunenfeld-Tanenbaum Research Institute, Sinai Health

Dr. Elham is an interdisciplinary researcher specializing in molecular epidemiology and statistical genetics. She earned her PhD in Epidemiology from the University of Alberta and is currently completing a data science postdoctoral fellowship at the Lunenfeld-Tanenbaum Research Institute, Sinai Health. Her research focuses on integrating molecular, imaging, and clinical data using advanced machine learning (ML) and deep learning (DL) approaches to advance personalized medicine in oncology. Currently, her work is dedicated to developing innovative strategies for the early detection and screening of lung cancer.

Gergely Pap, Postdoctoral Fellow, Hoffman Lab, Princes Margaret Cancer Center, University Health Network

Dr. Pap’s interests include genomics and neural network architectures. He has been involved in implementing new model structures for novel DNA representations to classify binding sites of transcription factors. Recently, he has been researching and pursuing new machine learning techniques to answer questions in computational biology. He earned his PhD in Deep Learning from the University of Szeged.

Gregory Schwartz, 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

Dr. Schwartz is a Scientist at the Princess Margaret Cancer Centre and Assistant Professor in the Department of Medical Biophysics at the University of Toronto. He received his B.A. double majoring in biology and mathematics in 2011 from Franklin & Marshall College and his Ph.D. in the School of Biomedical Engineering, Science and Health Systems at Drexel University in 2016 where he studied the immune receptor repertoire. In 2021 he completed his postdoctoral fellowship in the Department of Pathology and Laboratory Medicine at the Perelman School of Medicine in the University of Pennsylvania, where he developed new computational methods and approaches to understand cancer heterogeneity and diverse responses to anti-cancer therapies. His current research explores the role of cellular diversity and evolution in response to treatment. As such, he has developed numerous methodologies including multi-omic integration of information, joint molecular and image based interrogation of single cells, and large data visualization.

Yu Shi, PhD Student, Division of Biostatistics, Dalla Lana School of Public Health, University of Toronto

Yu Shi is a doctoral student in Biostatistics at the University of Toronto. Her current research focuses on developing and applying advanced machine learning and statistical methods to address challenges related to out-of-distribution data, particularly in genomic contexts such as cross-biobank analysis. Under the supervision of Dr. Pingzhao Hu and Dr. Wei Xu, she is working on developing genomic foundation models using individual-level genomic data for disease risk prediction. She holds a Master’s degree in Biostatistics from Yale University, where she conducted research in statistical genetics, focusing on transethnic genetic correlation analysis using GWAS summary statistics. In 2022, she began her PhD at the University of Toronto.

Lincoln Stein, Acting Scientific Director, and Head, Adaptive Oncology, Ontario Institute for Cancer Research and Professor, Department of Molecular Genomics, University of Toronto

Dr. Stein’s research focuses on using network and pathway-based analysis to identify common mechanisms in multiple cancer types and to devise prognostic and predictive signatures to aid in patient management. He focuses on supporting biomedical research both in Ontario and around the world by making large and complex biological datasets findable, accessible and usable. Prior to joining OICR, he played an integral role in many large-scale data initiatives at Cold Spring Harbor Laboratory and at the Massachusetts Institute of Technology Genome Center. He led the development of the first physical clone map of the human genome, and ran the data coordinating centre and the data portal for the SNP Consortium and the HapMap Consortium. At OICR, Dr. Stein has led several international cancer data sharing and research initiatives, including the creation and development of the data coordination centre for the International Cancer Genome Consortium and other related projects.

Lisa Strug, Director, Data Sciences Institute, University of Toronto
Professor, Departments of Statistical Sciences, Computer Science and cross-appointed in Biostatistics, University of Toronto; Senior Scientist in the Program in Genetics and Genome Biology, Hospital for Sick Children. S

Prof. Strug holds several other leadership positions at the University of Toronto including the Director of the Canadian Statistical Sciences Institute Ontario Region (CANSSI Ontario), and at the Hospital for Sick Children as Associate Director of the Centre for Applied Genomics and the Lead of the Canadian Cystic Fibrosis Gene Modifier Consortium and the Biology of Juvenile Myoclonic Epilepsy International Consortium. She is a statistical geneticist and her research focuses on the development of novel statistical approaches to analyze and integrate multi-omics data to identify genetic contributors to complex human disease. She has received several honours including the Tier 1 Canada Research Chair in Genome Data Science. 

Farzan Taj, PhD Student, Department of Molecular Genetics, University of Toronto

Farzan Taj is a graduate researcher at the Ontario Institute for Cancer Research. His research focuses on modeling single-cell perturbation screens, such as Perturb-Seq, in-silico.
Farzan completed his MSc in the same lab, working on drug response prediction, which resulted in an open-access publication on multimodal drug response prediction.
During his undergraduate studies at UofT, he specialized in computational biology and bioinformatics, with a major in molecular genetics and a minor in computer sciences.

Shu Wang, Assistant Professor, Donnelly Centre for Cellular and Biomolecular Research & Department of Molecular Genetics, University of Toronto

Prof. Wang’s lab is broadly interested in mathematically understanding the multi-scale networks underlying biological systems (e.g. protein signaling, cell states, tissue organization), seeking the accuracy and precision that would be needed to reliably treat heterogeneous diseases such as cancer. He obtained a PhD in Biophysics at Harvard University, studying how the high-dimensional geometry of single-cell multiplex imaging data can be analyzed and interpreted with biochemical reactions and spatial processes, under the supervision of Peter Sorger and Eduardo Sontag. He then pursued postdoctoral research at the Massachusetts Institute of Technology on multi-modal data integration using probabilistic graphical models, supervised by Douglas Lauffenburger.

August 18, 2025

Schwartz-Reisman Innovation Campus
University of Toronto
2nd Floor, Multipurpose Room (W280)
108 College Street
Toronto

Register here