Deep learning models for modelling genetic variation
||Deep learning models for modelling genetic variation|
||Carl Nettelblad <email@example.com>|
||2022-09-01 – 2023-03-01|
We are developing deep learning models based on autoencoder architectures for modelling genetic variation, as well as predicting traits of economic importance in plant and animal breeding applications.
Our deep learning genetics model was recently accepted in the genetics journal G3. There are currently only a few successful models for full genome models, with ours being one.
Specifically, we aim to apply our models to the NIAB Magic Wheat population http://mtweb.cs.ucl.ac.uk/mus/www/MAGICdiverse/, with a significant scaling in the number of genotype variants. This necessitates multi-GPU training. We are also aiming to do general improvements of our models, with the specific aim to predict trait values (the NIAB public dataset is one of few public agricultural datasets with genotype as well as phenotype, trait, data).