Grant: Master's Award: Canada Graduate Scholarships
McMaster University
$17,500.00
Drug discovery guided by artificial intelligence
EF 2018-19
Résumé
The increasing prevalence of antibiotic resistant pathogens demands the discovery of biologically active compounds. Nature has provided molecules with chemical structures that have evolved to provide microbes with competitive advantages. Currently, new compounds are found through bioactivity-guided screening. Mixtures of organic compounds are extracted from microbial cultures and screened for biological activities of interest. However, this method progressively meets with failure due to high rediscovery rates. The objective of my research is to propose an alternative approach by using machine learning algorithms to analyze genomic and chemical information of microbes. Machine learning algorithms learn patterns in data to produce reliable and repeatable predictions. Since the genome encodes the blueprints for natural products, algorithms can analyze DNA sequences to make predictions of the chemical structures. Next, the algorithm uses these predictions to survey compounds produced by microbes, identifying the target of interest. By creating technologies connecting genomic and chemical information, my research hopes to lower rediscovery rates and accelerate the discovery of new therapeutics.
Programme
Master's Award: Canada Graduate Scholarships
Bénéficiaire
Emplacement
Ontario, Canada
Type de bénéficiaire
Academia
Type
Grant
Source
CIHR Funding Decisions Database
Tel que publié
Id
411242
Name
Gunabalasingam Mathusan
Region
Ontario
Country
Canada
Orgtype
Institution Paid; Research Institution
Prcname2
Special Cases - Awards Programs
Projecttitle
Drug discovery guided by artificial intelligence
Programtype2
Studentship Programs
Orgnameinp2
McMaster University
Cihramount2
$17,500
Cihrequipment2
$0
Programname2
Master's Award: Canada Graduate Scholarships
Keyworddelim
Antibiotics; Artificial Intelligence; Bioinformatics; Chromatography; Deep Learning; Drug Discovery; Genomics; Machine Learning; Natural Products
Abstract
The increasing prevalence of antibiotic resistant pathogens demands the discovery of biologically active compounds. Nature has provided molecules with chemical structures that have evolved to provide microbes with competitive advantages. Currently, new compounds are found through bioactivity-guided screening. Mixtures of organic compounds are extracted from microbial cultures and screened for biological activities of interest. However, this method progressively meets with failure due to high rediscovery rates. The objective of my research is to propose an alternative approach by using machine learning algorithms to analyze genomic and chemical information of microbes. Machine learning algorithms learn patterns in data to produce reliable and repeatable predictions. Since the genome encodes the blueprints for natural products, algorithms can analyze DNA sequences to make predictions of the chemical structures. Next, the algorithm uses these predictions to survey compounds produced by microbes, identifying the target of interest. By creating technologies connecting genomic and chemical information, my research hopes to lower rediscovery rates and accelerate the discovery of new therapeutics.
Competitiondate
201812
Approvedterm2
1 yr 0 mth
Pinamesdelim
Gunabalasingam, Mathusan
Approvedterm
1 an 0 mois
Cihrcontribution2
~ $17,500~ $0~