Identification of gut microbial bile acid metabolic enzymes via an Al-assisted pipeline

This record deposits necessary data for the Bile acid Enzyme Announcer Unit Tool (BEAUT) developed in the paper "Identification of gut microbial bile acid metabolic enzymes via an Al-assisted pipeline". After downloaded and decompressed the BEAUT_release_data.tar.gz file, 

• Place the data/ directory under the root directory of BEAUT. It contains data necessary for developing the BEAUT model as well as screening the PRJNA28331 data set.
• Place the data_augmentation_data/ under the BEAUT/data_augmentation/ folder and rename the data_augmentation_data/ directory to data/. It contains data for selection of augmentation samples based on substrate binding pocket similarity comparisons.  

The results.tar.gz file contains the results of pocket similarity calculations needed for reproducing the data augmentation workflow. Place the file under directory BEAUT/data_augmentation/PocketMatch and decompress the file. 

Reference to the original article:

Ding, Y.; Luo, X.; Guo, J.; Xing, B.; Lin, H.; Ma, H.; Li, M.; Ye, C.; Yan, S.; Lin, K.; Zhang, J.; Wang, Y.; Zhuo, Y.; Nie, Q.; Yang, D.; Zhang Z.; Pang Y.; Wang, K.; Pang, Y.; Ma, M.; Lai, L.; Jiang, C. Identification of gut microbial bile acid metabolic enzymes via an Al-assisted pipeline. DOI: 10.1016/j.cell.2025.07.017