SARS-CoV-2 RBD data along with ESM embeddings + Active learning results

Code: https://github.com/m-huot/VIRAL.git Download the following folders and place them in the root directory of the github repository: data_bloom/ – contains ESM embeddings and experimental log₁₀(Kd) values from Bloom lab. data_desai/ – contains ESM embeddings and log₁₀(Kd) values for variant libraries from Desai lab. script_results/ – stores active-learning outputs, including the variants selected by the model at each acquisition round. Licence: see github repository Citation: If you use this toolkit in published work, please cite: @article{doi:10.1073/pnas.2503742122,author = {Marian Huot and Dianzhuo Wang and Jiacheng Liu and Eugene I. Shakhnovich },title = {Predicting high-fitness viral protein variants with Bayesian active learning and biophysics},journal = {Proceedings of the National Academy of Sciences},volume = {122},number = {24},pages = {e2503742122},year = {2025},doi = {10.1073/pnas.2503742122},URL = {https://www.pnas.org/doi/abs/10.1073/pnas.2503742122},eprint = {https://www.pnas.org/doi/pdf/10.1073/pnas.2503742122},}