Supplementary Data:
收藏资源简介:
All data necessary to reproduce our result including molecular structure files, molecular property files, docking output files, and protein-ligand interaction analysis output files (ZIP) See readme.txt for a description of the data: Description of directory structure and files contained in this archive. data/ readme.txt gen/ - generated compound data diffsbdd/ drughive/ pocket2mol/ zinc_random_50k/ search/ - search results data mols_best/ - data for the set of top-10 generated compounds per model and target mols_gen_data.csv - compound metadata diffsbdd/ drughive/ pocket2mol/ mols_best_sws/ - data for the similarity search results and compounds sws_search_results.csv - similarity search results for all compounds from the top-10 set sws_search_results_toembed.csv - metadata for the similarity search compounds selected to be embedded and docked diffsbdd/ drughive/ pocket2mol/ All directories for comparator groups diffsbdd/, drughive/, pocket2mol/, and zinc_random_50k/ contain compounds, docking results, and plip calculations following the pattern: <comparator>/ <target>/ <prefix>.sdf - compound structure file <prefix>_opt.sdf - force field optimized compound structures <prefix>_qvina.sdf - docked compound structures <prefix>_qvina.pdbqt - docked compound structures <prefix>_qvina.csv - docking results data <prefix>_data.csv - compound metadata plip/report_xml_data_all.csv - PLIP protein-ligand interaction data



