Grant: Master's Award: Canada Graduate Scholarships
University of Toronto
$17,500.00
Machine learning-guided design of bio-orthogonal metallic nanoparticles for biosensing of urinary tract infection-causing bacteria
FY 2020-21
Summary
Urinary tract infections (UTIs) are a highly prevalent communicable infectious disease caused predominantly by bacteria, with a higher incidence in women, children and the elderly. Due to the large variety of UTI-causing bacteria, the gold standard for diagnosis, urine culture and inspection, is a laborious and time-consuming procedure that can only be performed in equipped clinical laboratories. As a result, physicians often prescribe drugs based on clinical observations and error-prone screening tests, which can result in incorrect treatment, contribute to antibiotic resistance, and increase a patient's risk of developing health complications. Diagnostic platforms commonly use specific probes for each bacterial species being detected, where every probe can detect only one specific species. This requires multiple tests to be run, either in parallel or sequentially, to identify the disease-causing bacterial species – an inefficient approach for use at the point of care. Using machine learning, my project develops novel, ""bio-orthogonal"" metal nanoparticle probes for bacterial identification: an efficient diagnostic strategy relying on generalized sensing mechanisms. I will study how metal nanoparticles of different compositions, structures, and surface chemistries interact with bacteria through generalized mechanisms. All bacteria have similar features on their surface; however, the properties and arrangements of these features are unique to each species. By using machine learning, I will model the patterns of interaction between unique bacterial species and a given nanoparticle design. This model will then be used to select a single, optimal set of ""bio-orthogonal"" metal nanoparticle probes capable of identifying every UTI-causing bacterial species with a single test.
Department
Program
Master's Award: Canada Graduate Scholarships
Recipient
Location
Ontario, Canada
Recipient Type
Academia
Type
Grant
Source
CIHR Funding Decisions Database
As published
Id
449344
Name
Prakash Gayatri
Region
Ontario
Country
Canada
Orgtype
Institution Paid; Research Institution
Prcname2
Special Cases - Awards Programs
Projecttitle
Machine learning-guided design of bio-orthogonal metallic nanoparticles for biosensing of urinary tract infection-causing bacteria
Programtype2
Studentship Programs
Orgnameinp2
University of Toronto
Cihramount2
$17,500
Cihrequipment2
$0
Programname2
Master's Award: Canada Graduate Scholarships
Keyworddelim
Biosensing; Diagnostics; Machine Learning; Metallic Nanoparticles; Nanoparticle Synthesis
Abstract
Urinary tract infections (UTIs) are a highly prevalent communicable infectious disease caused predominantly by bacteria, with a higher incidence in women, children and the elderly. Due to the large variety of UTI-causing bacteria, the gold standard for diagnosis, urine culture and inspection, is a laborious and time-consuming procedure that can only be performed in equipped clinical laboratories. As a result, physicians often prescribe drugs based on clinical observations and error-prone screening tests, which can result in incorrect treatment, contribute to antibiotic resistance, and increase a patient's risk of developing health complications. Diagnostic platforms commonly use specific probes for each bacterial species being detected, where every probe can detect only one specific species. This requires multiple tests to be run, either in parallel or sequentially, to identify the disease-causing bacterial species – an inefficient approach for use at the point of care. Using machine learning, my project develops novel, ""bio-orthogonal"" metal nanoparticle probes for bacterial identification: an efficient diagnostic strategy relying on generalized sensing mechanisms. I will study how metal nanoparticles of different compositions, structures, and surface chemistries interact with bacteria through generalized mechanisms. All bacteria have similar features on their surface; however, the properties and arrangements of these features are unique to each species. By using machine learning, I will model the patterns of interaction between unique bacterial species and a given nanoparticle design. This model will then be used to select a single, optimal set of ""bio-orthogonal"" metal nanoparticle probes capable of identifying every UTI-causing bacterial species with a single test.
Competitiondate
202012
Approvedterm2
1 yr 0 mth
Pinamesdelim
Prakash, Gayatri
Approvedterm
1 an 0 mois
Cihrcontribution2
~ $17,500~ $0~