Hassaan Maan

Hassaan Maan

PhD Candidate at The University of Toronto

University of Toronto

Vector Institute

I’m a fourth year PhD candidate in the Bo Wang Lab, Department of Medical Biophysics, at the University of Toronto and Vector Institute. I’m also co-supervised by Kieran Campbell and Michael D. Taylor.

My research involves the development and application of machine learning and computational biology methods for genome sequencing data. During my PhD, I have worked on representation learning for single-cell sequencing data, for tasks such as integration and dynamic modeling. I have also worked with various groups performing single-cell analysis in development and cancer biology settings. More broadly, I am interested in advancing our understanding of human disease through the lens of genome sequencing, computational biology, and machine learning.

I’ve previously interned at Microsoft Research (x2), where I worked on the Antigen Map Project, and The Vector Insitute’s AI Engineering Team where I extended a COVID-19 genome analysis tool that I developed.

Download my CV to see full details of my academic and industry experience.

See my Google Scholar for a complete list of publications.

Please get in touch if you’d like to chat about research and/or collaboration!

Interests
  • Computational biology
  • Single-cell genomics
  • Representation learning
Education
  • PhD in Medical Biophysics, 2020-

    University of Toronto

  • Master of Bioinformatics (M.Binf), 2019

    University of Guelph

  • Bachelor of Science (BSc.), 2017

    University of Waterloo

Experience

 
 
 
 
 
Microsoft Research
Graduate Research Intern - Immunomics
Jun 2023 – Sep 2023 Redmond, Washington, United States (In-person)
Generative modelling for disentangling factors of variation in T-cell receptor repertoire data.
 
 
 
 
 
Microsoft Research
Graduate Research Intern - Immunomics
May 2022 – Aug 2022 Redmond, Washington, United States (Virtual)
Analyzing and incorporating HLA-interactions in machine-learning models for T-cell receptor repertoire-based disease prediction.
 
 
 
 
 
Vector Institute
Applied Machine Learning Intern
Sep 2021 – Dec 2021 Toronto, Ontario, Canada
Implementing a framework and projection methods for analyzing COVID-19 genome sequencing data.
 
 
 
 
 
University Health Network
Machine Learning Research Intern
Jan 2020 – Sep 2020 Toronto, Ontario, Canada
Various projects on utilizing single-cell sequencing data in clinically relevant settings and analysis of SARS-CoV-2 viral genomes.
 
 
 
 
 
Ontario Institute for Cancer Research
Computational Biology Intern
Apr 2019 – Dec 2019 Toronto, Ontario, Canada
Developed a framework for assessing impacts of non-coding RNA interactions with regulatory elements through RNA-sequencing data of cancer genomes.

Presentations & Talks

Characterizing the impacts of dataset imbalance on single-cell data integration
Single-cell transcriptomic data measured across multiple samples and conditions has led to a surge in computational methods for data …
Characterizing the impacts of dataset imbalance on single-cell data integration
A Deep Learning Framework for Estimating Cell-specific Kinetic Rates of RNA Velocity
Existing RNA velocity estimation methods rely on strong assumptions of predefined dynamics and cell-agnostic constant transcriptional …
A Deep Learning Framework for Estimating Cell-specific Kinetic Rates of RNA Velocity

Selected Publications

(2024). Characterizing the impacts of dataset imbalance on single-cell data integration. Nature Biotechnology.

Cite Source Document DOI

(2024). scGPT: toward building a foundation model for single-cell multi-omics using generative AI. Nature Methods.

Cite Source Document

(2024). DeepVelo: deep learning extends RNA velocity to multi-lineage systems with cell-specific kinetics. Genome Biology.

Cite Source Document

(2022). Colony stimulating factor-1 producing endothelial cells and mesenchymal stromal cells maintain monocytes within a perivascular bone marrow niche. Cell - Immunity.

PDF Cite

(2020). Genotyping SARS-CoV-2 through an interactive web application. The Lancet Digital Health.

PDF Cite

Contact