Canada Spends Logo

Explorez notre analyse du budget 2026

Grant: Doctoral Research Award: Canada Graduate Scholarships

McGill University

$120,000.00

Leveraging cohort-scale single-cell RNA sequencing analysis of stem cell-derived dopaminergic neurons to identify genetic determinants of Parkinson's disease using an interpretable machine learning classification framework.

EF 2024-25

Résumé
Parkinson's Disease (PD) is the second most common neurodegenerative disease characterized by motor symptoms resulting from a loss of neurons. Despite a growing knowledge of the genetic risk factors of PD, the disease remains fatal as treatments cannot reverse disease progression. One way to nominate possible therapeutics is by sequencing individual cells to reveal how gene expression contribute to neurodegeneration. However, sequencing costs are prohibitively high for analyzing large cohorts of patients and the analytic methods remain challenging. I am developing and employing a novel methodology to analyze single-cell gene expression data from large cohorts to identify genetic determinants in PD. First, I developed a computational framework that allows for cells from distinct individuals to be sequenced together, greatly reducing costs for cohort-scale analyses, which I have made publicly available to other researchers. Next, I will develop a machine learning model using publicly available gene expression data to classify individual cells as diseased or healthy, which will concurrently reveal the gene expression changes that are most relevant in PD. Finally, I will use my computational framework and machine learning model to analyze in-house stem cell-derived neurons from individuals with PD and healthy controls to identify genetic mechanisms contributing to neurodegeneration and elucidate prospective therapeutic targets. In addition to identifying new insights into the underlying genetic mechanisms contributing to PD, my publicly available computational tools and experimental protocols for cohort-scale single-cell sequencing analyses will serve as a model for future work and help advance discovery across diseases. Finally, my novel approach to use machine learning to identify the most important gene expression patterns that characterize diseased cells will be broadly applicable across biomedical disciplines.
Programme
Doctoral Research Award: Canada Graduate Scholarships
Bénéficiaire
Emplacement
Quebec, Canada
Type de bénéficiaire
Academia
Type
Grant
Source
CIHR Funding Decisions Database

Tel que publié

Id
518892
Name
Fiorini Michael R
Region
Québec
Country
Canada
Orgtype
Institution Paid; Research Institution
Instname2
Genetics
Theme2
Biomedical
Prcname2
Doctoral Research Awards - A
Projecttitle
Leveraging cohort-scale single-cell RNA sequencing analysis of stem cell-derived dopaminergic neurons to identify genetic determinants of Parkinson's disease using an interpretable machine learning classification framework.
Programtype2
Studentship Programs
Orgnameinp2
McGill University
Cihramount2
$120,000
Cihrequipment2
$0
Programname2
Doctoral Research Award: Canada Graduate Scholarships
Keyworddelim
Bioinformatics; Differential Gene Expression; Genetic Demultiplexing; Genetics; Induced Pluripotent Stem Cell Disease Models; Machine Learning; Parkinson'S Disease; Single-Cell Rna Sequencing; Stem Cell Multiplexing; Transcriptomics
Abstract
Parkinson's Disease (PD) is the second most common neurodegenerative disease characterized by motor symptoms resulting from a loss of neurons. Despite a growing knowledge of the genetic risk factors of PD, the disease remains fatal as treatments cannot reverse disease progression. One way to nominate possible therapeutics is by sequencing individual cells to reveal how gene expression contribute to neurodegeneration. However, sequencing costs are prohibitively high for analyzing large cohorts of patients and the analytic methods remain challenging. I am developing and employing a novel methodology to analyze single-cell gene expression data from large cohorts to identify genetic determinants in PD. First, I developed a computational framework that allows for cells from distinct individuals to be sequenced together, greatly reducing costs for cohort-scale analyses, which I have made publicly available to other researchers. Next, I will develop a machine learning model using publicly available gene expression data to classify individual cells as diseased or healthy, which will concurrently reveal the gene expression changes that are most relevant in PD. Finally, I will use my computational framework and machine learning model to analyze in-house stem cell-derived neurons from individuals with PD and healthy controls to identify genetic mechanisms contributing to neurodegeneration and elucidate prospective therapeutic targets. In addition to identifying new insights into the underlying genetic mechanisms contributing to PD, my publicly available computational tools and experimental protocols for cohort-scale single-cell sequencing analyses will serve as a model for future work and help advance discovery across diseases. Finally, my novel approach to use machine learning to identify the most important gene expression patterns that characterize diseased cells will be broadly applicable across biomedical disciplines.
Competitiondate
202411
Approvedterm2
3 yrs 0 mth
Pinamesdelim
Fiorini, Michael R
Approvedterm
3 ans 0 mois
Cihrcontribution2
~ $120,000~ $0~