Deep learning for large scale genomic prediction
| Title: |
Deep learning for large scale genomic prediction |
| DNr: |
SNIC 2019/7-1 |
| Project Type: |
SNIC Small Compute |
| Principal Investigator: |
Patrik Waldmann <Patrik.Waldmann@slu.se> |
| Affiliation: |
Sveriges lantbruksuniversitet |
| Duration: |
2019-01-08 – 2020-02-01 |
| Classification: |
40201 |
| Keywords: |
|
Abstract
Genome-wide marker data is used both in phenotypic association (GWAS) and prediction (GWP). A typical study includes high dimensional data with thousands to millions of genomic markers (SNPs) recorded in a number of individuals that is on the order of some hundreds to a few thousands. Different machine learning approaches have been used in GWAS and GWP effectively, but the use of neural networks (NN) and deep learning is still scarce. This goal of this project is to develop a flexible NN model for genomic SNP data that can be extended easily in different directions.
