Overview
This course was intended for research scientists from the private sector and public institutions interested in learning the foundations of different prediction frameworks considering the integration of multiple omics of information (or layers) with applications in plant and animal breeding. The course demonstrated the development and utilization of prediction models in plant breeding programs and how to implement these at different stages of the breeding pipeline. The focus of the course was to facilitate to attendees the foundations of the different paradigms (parametric, non-parametric AI) in which these implementations are based. Participants learned the basis for modeling trait performance of genotypes assisted by the integration of multiple data types ‘omics’ considering different approaches (parametric, non-parametric/Artificial Intelligence (AI), AI crop growth models, etc.)
Short Course Topics
Some of the most relevant and novel topics of interest for the private industry and research institutions were covered such as:
- Genomic Selection GS aided by Genomic Prediction GP models
- Artificial Intelligence Methods Implemented for GP
- GP aided by high-throughput phenotyping platforms
- Multi-Omics Integration for Continuous and Categorical Data
- Estimation and Prediction of Genotype-by-Environment (G×E) Interactions
- Multi-Trait Prediction
- Sparse Testing Designs
- Prediction of Time-Related Traits
- Crop Growth Models (CGM) for Integrating the Genotype-by-Environment-by-Management (G×E×M) Interaction in Whole Genome Prediction (WGP
- Modeling of the Host/Pathogen Interaction Using Dual Genome Approach with Potential Applications in Intercropping Systems, etc
In addition, attendees learned about the experiences and vision of implementing genomic selection (GS) approaches in different crop species (fruits, forages, grains, etc.) from world known experts in the field.
For the latest updates on the Multi-Omic Integration for AI Genomic Prediction Breeding Short Course, subcribe to our mailing list.
