arabidopsis

GPN application to Arabidopsis thaliana

Model usage

Loading the model:

import gpn.model
from transformers import AutoModelForMaskedLM

model = AutoModelForMaskedLM.from_pretrained("songlab/gpn-brassicales")

Additional resources

• GPN logo track at UCSC Genome Browser
• Training dataset on Hugging Face Hub
• Intermediate files necessary for running notebooks, such as embeddings and variant scores

Reproducing the analysis

General dependencies:

conda env create -f envs/general.yaml
conda activate gpn-arabidopsis

Analysis code is contained in both Snakefile and *.ipynb.