The initial data set contains more than 22 million protein-ligand pairs.,To ensure that the sequence similarity between the training set and the test set is less than 40%, the researchers screened and obtained about 100,000 protein-small molecule pairs, and the test set contained 100 protein pockets. This dataset can be used for protein-small molecule interaction studies, especially for evaluating the binding ability of molecules to protein pockets.

Citation

@misc{haotian_zhang_2023_7759114, author = {Haotian Zhang}, title = {ResGen processed data}, month = mar, year = 2023, publisher = {Zenodo}, doi = {10.5281/zenodo.7759114}, url = {https://doi.org/10.5281/zenodo.7759114}, }