Machine Learning Approaches in Complex Trait to Bridge Genome-to-Phenome – BridGe-Ph.
BridGe-Ph project aims to enhance animal breeding by integrating genomic and phenotypic data using machine learning algorithms.
Traditional breeding has relied on phenotypic evaluation and pedigree information, but genomic selection, using SNP markers, has revolutionized this process, accelerating genetic improvement in livestock.
Complex traits, such as polygenic productive traits and multifactorial genetic disorders, arise from interactions between multiple genes and environmental factors.
To address the complexity and high dimensionality of such data, BridGe-Ph aims to leverage machine learning to improve the accuracy and efficiency of genetic predictions.
The project will utilize genomic data from initiatives like GENORIP, GENOVAL, and CapraGEN, along with innovative phenotypic data from various instruments (e.g., temperature sensors, AMS data), to create a comprehensive and cost-effective genome-to-phenome prediction model.
Additionally, phenotypic (e.g., disease diagnoses) and genotypic data from pets will be analyzed with a similar approach.
This initiative aims to improve animal health and welfare, reduce breeding costs, and refine breeding strategies through advanced machine learning techniques.
MSc in Molecular and Medical Biotechnology at University of Verona.
Second-level master’s degree in Bioeconomy for the circular economy (BIOCIRCE).
Research Fellow of the CapraGEN Project.
Deep interest in bioinformatics.
Supervisor Prof. Alessandro Bagnato
Co-supervisor Prof. Guillherme J.M. Rosa
