Additional file 2 of SIMPD: an algorithm for generating simulated time splits for validating machine learning approaches

Additional file 2. project_data_summary.txt: Summary statistics – e.g. size, active/inactive counts, spatial statistics values, median descriptor values, etc. – calculated for the various splits of the NIBR project data sets. project_data_ML_summary.txt: Summary statistics for ML performance across the various splits of the NIBR project data sets. project_data_baselineML_summary.txt: Summary statistics for the baseline ML performance across the various splits of the NIBR project data sets. full_chembl_assay_list.csv: Details of the 99 ChEMBL32 data sets.