Published September 9, 2025
| Version v1
Dataset
Open
ESM2 15B parameter embeddings for GFP deep mutational scan dataset
Description
This release accompanies the pub, "Efficient GFP variant design with a simple neural network ensemble"
This dataset contains the file "esm2_15b_embeddings_and_meta.csv" which contains the embeddings for the sequences from the amino_acid_genotypes_to_brightness.tsv file available at https://figshare.com/articles/dataset/Local_fitness_landscape_of_the_green_fluorescent_protein/3102154.
Files
esm2_15b_embeddings_and_meta.csv
Files
(3.7 GB)
| Name | Size | Download all |
|---|---|---|
|
md5:113b521541109024bb7550ef9b486b89
|
3.7 GB | Preview Download |
Additional details
Software
- Repository URL
- https://github.com/Arcadia-Science/2025-GFP-variant-design