Grant: Engage Grants Program
Dalhousie University
$25,000.00
Machine-learning classification of genomic polymorphism data relating to fertility and reproductive longevity
EF 2012-13
Résumé
Dairy cattle have been successfully bred to increase milk production, but optimizing this trait has lead to a
decline in fertility and reproductive longevity, which impacts negatively on the productivity of the industry as
later milk-producing periods are lost. To remedy this, Performance Genomics Inc. has identified a series of
polymorphic sites in the mouse genome that influence the desired reproduction traits. When these sites were
tested in cattle, a significant association was found but the sensitivity of the test was too low for commercial
deployment. Since the traits of interest are complex and potentially involve a multitude of subtle interactions,
the statistical techniques initially used to discover predictive sites may have missed some due to low
independent predictive value.
The goal of the proposed project is to reanalyze the 8000 polymorphic mouse sites assessed in the initial mouse
study using machine-learning approaches that can discover interactions between sites, in order to boost the
signal and identify new candidate genes that may influence fertility and reproductive longevity. This will serve
as the basis for identifying a new set of sites in cattle that may yield better predictive power, especially when
new prediction techniques are employed at that level of testing. Increasing the effectiveness of the cattle test
will allow selective breeding to increase reproductive longevity, with economic benefits as cows produce milk
for longer periods.
Programme
Engage Grants Program
Bénéficiaire
Emplacement
Nova Scotia, Canada
Type de bénéficiaire
Academia
Type
Grant
Source
NSERC's Awards Data
Tel que publié
Application id
430139-2012
Name nom
Beiko, Robert
Department département
Computer Science, Faculty of
Organization id
79
Institution établissement
Dalhousie University
Province en
Nova Scotia
Province fr
Nouvelle-Écosse
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2012
Competition year année de concours
2012
Award amount
25000
Program id
EGP
Program name en
Engage Grants Program
Program name fr
Programme de subventions d'engagement partenariat
Group en
Research partnerships programs
Group fr
Programmes de partenariat
Committee code
1551
Committee name en
Atlantic Internal Decision Committee
Committee name fr
Comité de décision interne pour l'Atlantique
Area of application code
102
Area of application group en
Agriculture and primary food production
Area of application group fr
Agriculture et produits alimentaires primaires
Area of application en
Animal management (animal diseases, breeding)
Area of application fr
Gestion des animaux (maladies animales, reproduction)
Research subject code
5004
Research subject group en
Genetics
Research subject group fr
Génétique
Research subject en
Genome analysis
Research subject fr
Analyse du génome
Partie
1
Nb partie
1
Application title
Machine-learning classification of genomic polymorphism data relating to fertility and reproductive longevity
Keyword
NSERC
Application summary
Dairy cattle have been successfully bred to increase milk production, but optimizing this trait has lead to a
decline in fertility and reproductive longevity, which impacts negatively on the productivity of the industry as
later milk-producing periods are lost. To remedy this, Performance Genomics Inc. has identified a series of
polymorphic sites in the mouse genome that influence the desired reproduction traits. When these sites were
tested in cattle, a significant association was found but the sensitivity of the test was too low for commercial
deployment. Since the traits of interest are complex and potentially involve a multitude of subtle interactions,
the statistical techniques initially used to discover predictive sites may have missed some due to low
independent predictive value.
The goal of the proposed project is to reanalyze the 8000 polymorphic mouse sites assessed in the initial mouse
study using machine-learning approaches that can discover interactions between sites, in order to boost the
signal and identify new candidate genes that may influence fertility and reproductive longevity. This will serve
as the basis for identifying a new set of sites in cattle that may yield better predictive power, especially when
new prediction techniques are employed at that level of testing. Increasing the effectiveness of the cattle test
will allow selective breeding to increase reproductive longevity, with economic benefits as cows produce milk
for longer periods.