SARS-CoV-2 RBD data along with ESM embeddings

This data is published along with the paper "Biophysical principles predict fitness of SARS-CoV-2 variants" and the code. Description: rbd_df.csv : RBD sequences filtered from GISAID data, along with occurence time, up untill May 2023. unique_mutant_sequence_emb_esm1v_650m.pkl : esm1v embeddings for unqiue RBDs in rbd_df.csv df_Desai_15loci_complete.csv: esm1v embeddings for the Desai combinatoric dataset If you use the code or predictions please consider citing: @article{ doi:10.1073/pnas.2314518121, author = {Dianzhuo Wang and Marian Huot and Vaibhav Mohanty and Eugene I. Shakhnovich }, title = {Biophysical principles predict fitness of SARS-CoV-2 variants}, journal = {Proceedings of the National Academy of Sciences}, volume = {121}, number = {23}, pages = {e2314518121}, year = {2024}, doi = {10.1073/pnas.2314518121}, URL = {https://www.pnas.org/doi/abs/10.1073/pnas.2314518121}, eprint = {https://www.pnas.org/doi/pdf/10.1073/pnas.2314518121}, }