filename,rows,columns,column_names,missing_cells,bytes,sha256
tables/applicability_metrics.csv,42,11,scheme | stratum | metric | estimate | ci_low | ci_high | n | active | n_scaffolds | bootstrap_valid | bootstrap_invalid,6,4769,2f5906b400106368d6c7499fe319b2438b1ede56cbb47d975ca74e4b7b90fde1
tables/applicability_summary.csv,6,15,scheme | stratum | n | active | inactive | n_scaffolds | test_fraction | ranking_estimates_reportable | average_precision | roc_auc | brier | log_loss | ECE_10_fixed_bins | mean_probability | observed_prevalence,2,1346,a53caf5714c949cbafc02a3ecd43ec918c34fe9f20c8e3f393b762498246ec16
tables/bootstrap_applicability.csv,6000,10,replicate | scheme | stratum | average_precision | roc_auc | brier | log_loss | ECE_10_fixed_bins | mean_probability | observed_prevalence,2002,945713,ad79759429ea35f61279f1c4cc2c469cbf9f42d231de7cc475f938c9832220c1
tables/bootstrap_metrics.csv,3000,11,replicate | model | n | active | average_precision | roc_auc | brier | log_loss | ECE_10_fixed_bins | mean_probability | observed_prevalence,0,460918,85adc1764c29b8d65ad8996d293db3712f3aa24bb6cf980d8dba5fd2bb1fc3cc
tables/bootstrap_operating_points.csv,3000,13,replicate | model | threshold_label | tn | fp | fn | tp | precision | recall | specificity | F1 | balanced_accuracy | predicted_positive_fraction,0,443867,a02761d1322efa29b82d4c9fd6627f64853ae9a3e5c5c003356338ed988ce94a
tables/calibration_bins.csv,30,12,model | bin | lower | upper | n | active | n_scaffolds | mean_probability | observed_fraction | ci_low | ci_high | bootstrap_valid,36,2817,210c7f777897b28d0dd07919f25b9b3d79aeecbb4d35e2de74316883719cd3ee
tables/calibration_diagnostics.csv,2,4,model | intercept_joint | slope_joint | note,0,308,5e24b7ad83801ce1a7191de0145df6fa26a6ec2d888315c316c29ad3b17457ff
tables/calibration_paired_differences.csv,6,6,metric | comparison | estimate | ci_low | ci_high | bootstrap_valid,0,686,86b702aac3f012c675d02ae27ed56a66c472e2cc85e355b088631f8390b792fa
tables/calibration_predictions.csv,942,7,compound_id | identity | scaffold_group | y | decision_score | p_raw | p_calibrated,0,138369,ca071eaf59bbb48c9c75e40165956e120372b5ab76feca858281264fd6cf7b90
tables/calibration_threshold_selection.csv,939,4,threshold | precision | recall | F1,0,71142,741138f0c94c8ba78f7773b0aceef12438ebb9dc1adce2bde111a12dce938fe5
tables/conflicting_labels.csv,21,13,source_row | mol_id | original_smiles | label | structure_status | standardized_smiles | identity | scaffold_group | removed_fragments | error | disposition | retained_identity_id | identity_split,64,4018,57404ba272bf19c3d0e2e49f82cf5e70f4398527b8d5ac99f0949bd90a3e2162
tables/coverage_annotations.csv,1887,11,compound_id | split | max_training_tanimoto | nearest_training_compound_id | nearest_training_identity | nearest_training_label | training_neighbors_at_least_0_5 | within_all_training_descriptor_bounds | outside_descriptors | supported_by_screen | similarity_band,1721,236428,7b9891e414e1a3e375f3a344a71a7022b9117b9337af461fbc8ffaf836a53a8b
tables/cross_split_identical_fingerprints.csv,6,30,compound_id | source_rows | mol_ids | identity | scaffold_group | y | decision_score | p_raw | p_calibrated | p_prevalence | predicted_at_0_5 | predicted_at_development_threshold | max_training_tanimoto | nearest_training_compound_id | nearest_training_identity | nearest_training_label | training_neighbors_at_least_0_5 | within_all_training_descriptor_bounds | outside_descriptors | supported_by_screen | similarity_band | molecular_weight | cLogP | TPSA | HBD | HBA | rotatable_bonds | ring_count | heavy_atoms | error_category,6,2309,f771c14750086beee774565b80c6d1e5643e1a33e5d23363d420ae54e5b40084
tables/descriptor_summary.csv,5,81,Unnamed: 0 | molecular_weight | molecular_weight.1 | molecular_weight.2 | molecular_weight.3 | molecular_weight.4 | molecular_weight.5 | molecular_weight.6 | molecular_weight.7 | molecular_weight.8 | molecular_weight.9 | cLogP | cLogP.1 | cLogP.2 | cLogP.3 | cLogP.4 | cLogP.5 | cLogP.6 | cLogP.7 | cLogP.8 | cLogP.9 | TPSA | TPSA.1 | TPSA.2 | TPSA.3 | TPSA.4 | TPSA.5 | TPSA.6 | TPSA.7 | TPSA.8 | TPSA.9 | HBD | HBD.1 | HBD.2 | HBD.3 | HBD.4 | HBD.5 | HBD.6 | HBD.7 | HBD.8 | HBD.9 | HBA | HBA.1 | HBA.2 | HBA.3 | HBA.4 | HBA.5 | HBA.6 | HBA.7 | HBA.8 | HBA.9 | rotatable_bonds | rotatable_bonds.1 | rotatable_bonds.2 | rotatable_bonds.3 | rotatable_bonds.4 | rotatable_bonds.5 | rotatable_bonds.6 | rotatable_bonds.7 | rotatable_bonds.8 | rotatable_bonds.9 | ring_count | ring_count.1 | ring_count.2 | ring_count.3 | ring_count.4 | ring_count.5 | ring_count.6 | ring_count.7 | ring_count.8 | ring_count.9 | heavy_atoms | heavy_atoms.1 | heavy_atoms.2 | heavy_atoms.3 | heavy_atoms.4 | heavy_atoms.5 | heavy_atoms.6 | heavy_atoms.7 | heavy_atoms.8 | heavy_atoms.9,81,3638,38fc3361e4d480e40be59559c0508975db780e02445a3e6bac798eef8b6ba388
tables/exclusion_counts.csv,12,3,disposition | structure_status | n,0,516,3426644f7fa3cbf2c098ef0e2c9eea7cb166b28c3437916987a1e51e7cba1542
tables/exclusion_counts_by_label.csv,14,3,disposition | label | n,1,469,0d6f313d4db350cbcecb1fcb8aa7e51dc2c460463e97b82f1cef6f38ffc15660
tables/fingerprint_alias_diagnostics.csv,6,8,compound_id | nearest_training_compound_id | test_smiles | training_smiles | unfolded_feature_presence_equal | unfolded_feature_counts_equal | test_heavy_atoms | training_heavy_atoms,0,841,98fe37ff9a51e8128955badcfab014f33754a8335a6de220611de784ed6c1f72
tables/fingerprint_overlap_sensitivity.csv,6,11,analysis | model | n | active | average_precision | roc_auc | brier | log_loss | ECE_10_fixed_bins | mean_probability | observed_prevalence,0,1167,7d58068d2744454c199c34e8032398e38993cd763f93f2457be3d157d4b0f56a
tables/held_out_predictions.csv,945,12,compound_id | source_rows | mol_ids | identity | scaffold_group | y | decision_score | p_raw | p_calibrated | p_prevalence | predicted_at_0_5 | predicted_at_development_threshold,0,169597,0cb873e7be5c4428d9cd82b58cf7858f76eab99ceb44cb1db149ec9ec11f100c
tables/held_out_predictions_annotated.csv,945,29,compound_id | source_rows | mol_ids | identity | scaffold_group | y | decision_score | p_raw | p_calibrated | p_prevalence | predicted_at_0_5 | predicted_at_development_threshold | max_training_tanimoto | nearest_training_compound_id | nearest_training_identity | nearest_training_label | training_neighbors_at_least_0_5 | within_all_training_descriptor_bounds | outside_descriptors | supported_by_screen | similarity_band | molecular_weight | cLogP | TPSA | HBD | HBA | rotatable_bonds | ring_count | heavy_atoms,873,319196,4fa95e3efc720200035d1dabb0a3e174dfcc8e4b8c1b9bc6227b9491e5c7cea1
tables/logistic_coefficients.csv,2048,2,fingerprint_bit | coefficient,0,52278,ad0adc1d8e04c04f2904f55b3619324cbe1889f28653871b74e9f7217558bc41
tables/model_selection_folds.csv,16,9,C | fold | n_train | n_validation | validation_active | average_precision | roc_auc | brier | n_iter,0,1382,62625a3d4a366dfd686849d70bf74673671f3548263e4e9cf3e8e79c01184d89
tables/model_selection_summary.csv,4,5,C | mean_AP | sd_AP | mean_ROC_AUC | mean_Brier,0,376,a8e3a98788a0d5e3d16cb1698da103edfd5669dae1668d3464dca7f6d648e862
tables/molecular_descriptors.csv,5395,11,compound_id | split | y | molecular_weight | cLogP | TPSA | HBD | HBA | rotatable_bonds | ring_count | heavy_atoms,0,483772,0ff21001423c80613337c562017943b2e2ffa86b0f5c3346f4474b898d20f278
tables/operating_points.csv,30,8,model | threshold_label | threshold | metric | estimate | ci_low | ci_high | bootstrap_valid,0,2552,0149a30d243c91eb01fa7347bf5412bf3cded4954b875715bfc5e6d0c4b4a91b
tables/pr_curve_calibrated.csv,934,3,precision | recall | threshold,1,54029,5ab67cc60ad236f295fd16b879a64785de2b73c652da6c327e315cd1ab274841
tables/pr_curve_prevalence.csv,2,3,precision | recall | threshold,1,82,7e433ec74c7594811cd4e2492bb8e51dca011f6bb4d75bbf5e48c1d5f7f78f12
tables/pr_curve_raw.csv,934,3,precision | recall | threshold,1,54381,99e1938a83924101abb1736adb618b8bc7a1c5e9a606ee4c34a910a2080209bd
tables/representative_predictions.csv,12,30,compound_id | source_rows | mol_ids | identity | scaffold_group | y | decision_score | p_raw | p_calibrated | p_prevalence | predicted_at_0_5 | predicted_at_development_threshold | max_training_tanimoto | nearest_training_compound_id | nearest_training_identity | nearest_training_label | training_neighbors_at_least_0_5 | within_all_training_descriptor_bounds | outside_descriptors | supported_by_screen | similarity_band | molecular_weight | cLogP | TPSA | HBD | HBA | rotatable_bonds | ring_count | heavy_atoms | error_category,9,5396,bad47d11022597a11aab0423f9af29f41d576808e902f049b73202b3a2f2c058
tables/roc_curve_calibrated.csv,228,3,false_positive_rate | true_positive_rate | threshold,0,13383,bdf5a4ba921c0cdf3eb91251dc0744fd23a923a3f3ecfad3d7b4f2ccaf0cfa5c
tables/roc_curve_prevalence.csv,2,3,false_positive_rate | true_positive_rate | threshold,0,91,7662d23d1978198f8c29f5f2deb11b72b55b60eceb47136be598578bbe11a27d
tables/roc_curve_raw.csv,228,3,false_positive_rate | true_positive_rate | threshold,0,13402,f4bdccd9906d56c7af64478c3bc02660b51585fe261c26f2887b1220aa88870f
tables/row_audit.csv,7831,13,source_row | mol_id | original_smiles | label | structure_status | standardized_smiles | identity | scaffold_group | removed_fragments | error | disposition | retained_identity_id | identity_split,15323,1474152,235c30f158887d15315af76281b604afae6d760946b3f3e39eec8cea877f5ca2
tables/split_assignments.csv,5395,18,source_row | mol_id | original_smiles | label | structure_status | standardized_smiles | identity | scaffold_group | removed_fragments | error | disposition | y | compound_id | source_rows | mol_ids | source_record_count | outer_fold | split,5395,1157936,fc61b12a2de25923c149da913a43728b6fbed077d73b7a77d4bee80b9c9ceaa8
tables/split_summary.csv,3,7,split | n | active | scaffolds | inactive | prevalence | fraction,0,245,08aac6b3cd07ac2fb0d31877bbfcfc6d9452ec57517b2fe44566bca73ec3ff48
tables/test_metrics.csv,21,10,model | metric | estimate | ci_low | ci_high | n_test | n_scaffolds | bootstrap_valid | bootstrap_invalid | CI_method,0,3243,7ca703fd6c3463a8796cdf8ef8f66ba655ff9a69b875f362d271ab1d2809cdb6
tables/training_cv_assignments.csv,3508,4,compound_id | scaffold_group | y | cv_validation_fold,0,138741,bf9c0020041edd0740359bfdd8f8f57cbe88550e84c536683453e6167bba407d
tables/training_descriptor_bounds.csv,8,5,descriptor | training_q01 | training_q99 | training_min | training_max,0,400,dd01c4a3d7a97bbd4682c9d8d9eb52e77deffcde5e244c507b5e5c2bf7f60d83
tables/training_oof_predictions.csv,14032,5,C | fold | compound_id | y | p_raw,0,679534,95f3870aea7725762dd8f2a3f7d58cb61d1c30d0f523b8df0c3da7673eef902a
