Enhanced Sequence-Activity Mapping and Evolution of Artificial Metalloenzymes by Active Learning

This entry contains data, pretrained models and supplementary files for our enzyme engineering study: Title: Enhanced Sequence-Activity Mapping and Evolution of Artificial Metalloenzymes by Active LearningJournal: ACS Central Science If you use any of the data or code in the repository, please cite the paper. The contents of this entry are: Sequence embeddings needed for reproducing the code are found in data.zip. Unzip the contents of the folder to /data in the code structure. NGS sequencing analysis and raw data in NGS analysis.zip 10% subset of structures generated with the Rosetta software in structures.zip Pretrained and saved models for plotting, clustering and further prediction are saved in models.zip Raw assay data including our designed libraries by active learning are found in assay_and_ML_data.zip