{ "data_id": "31854", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3831", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3831", "version": 9, "version_label": null, "description": "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL3831 (TID: 30001), and it has 717 rows and 69 features (not including molecule IDs and class feature: molecule_id and pXC50). The features represent Molecular Descriptors which were generated from SMILES strings. Missing value imputation was applied to this dataset (By choosing the Median). Feature selection was also applied.", "format": "ARFF", "uploader": "Noureddin Sadawi", "uploader_id": 62, "visibility": "public", "creator": "\"Dr Jeremy Besnard, Dr Ivan Olier, Dr Noureddin Sadawi, Dr Larisa Soldatova, Dr Crina Grosan, Prof Ross King, Dr Richard Bickerton, Prof Andrew Hopkins and Dr Willem van Hoorn\"", "contributor": null, "date": "2016-07-15 08:40:53", "update_comment": null, "last_update": "2016-07-15 08:40:53", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3462624\/data_53528.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3831", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL3831 (TID: 30001), and it has 717 rows and 69 features (not including molecule IDs and class feature: molecule_id and pXC50). The features represent Molecular Descriptors which were generated from SMILES strings. Missing value imputation was applied to this dataset (By choosing the Median). Feature selection was also applied. " ], "weight": 5 }, "qualities": { "NumberOfInstances": 717, "NumberOfFeatures": 71, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 70, "NumberOfSymbolicFeatures": 1, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.7916785298116636, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -0.7736725315279891, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxKurtosisOfNumericAtts": 73.43334524533626, "MinMeansOfNumericAtts": -0.02120781032078099, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 3.2873175876787597, "MaxMeansOfNumericAtts": 10821.644351464434, "MinMutualInformation": null, "PercentageOfNumericFeatures": 98.59154929577466, "Quartile3MeansOfNumericAtts": 17.85621269177127, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfSymbolicFeatures": 1.4084507042253522, "Quartile3MutualInformation": null, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -1.8156887170276987, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 0.7760911702148818, "MaxSkewnessOfNumericAtts": 7.470347445163074, "MinStdDevOfNumericAtts": 0.0571863678324819, "Quartile1KurtosisOfNumericAtts": 0.5710531421159404, "Quartile3StdDevOfNumericAtts": 4.441148161407955, "MaxStdDevOfNumericAtts": 8270.441298804359, "MinorityClassPercentage": null, "Quartile1MeansOfNumericAtts": 1.6353427475592746, "StdvNominalAttDistinctValues": null, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MutualInformation": null, "MeanKurtosisOfNumericAtts": 5.384961753986339, "NumberOfBinaryFeatures": 0, "Quartile1SkewnessOfNumericAtts": -0.6850988462142243, "MeanMeansOfNumericAtts": 322.05465132496505, "Quartile1StdDevOfNumericAtts": 0.30575582742269347, "AutoCorrelation": 0.4868044692737423, "MeanMutualInformation": null, "Quartile2AttributeEntropy": null, "ClassEntropy": null, "MeanNoiseToSignalRatio": null, "Quartile2KurtosisOfNumericAtts": 1.1826042670750887, "Dimensionality": 0.09902370990237098, "MeanNominalAttDistinctValues": null, "Quartile2MeansOfNumericAtts": 3.49536889818689, "EquivalentNumberOfAtts": null, "MeanSkewnessOfNumericAtts": 0.45649589196514034, "Quartile2MutualInformation": null, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 236.3390887635782, "Quartile2SkewnessOfNumericAtts": 0.4702058652082374, "MajorityClassSize": null, "MinAttributeEntropy": null }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "70", "type": "numeric", "distinct": "59", "missing": "0", "target": "1", "min": "4", "max": "9", "mean": "5", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "717", "missing": "0", "identifier": "1", "distr": [] }, { "name": "D.Dtr09", "index": "1", "type": "numeric", "distinct": "398", "missing": "0", "min": "0", "max": "439", "mean": "77", "stdev": "76" }, { "name": "nPyrroles", "index": "2", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "SpMax2_Bh.i.", "index": "3", "type": "numeric", "distinct": "257", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "SsNH2", "index": "4", "type": "numeric", "distinct": "250", "missing": "0", "min": "0", "max": "43", "mean": "3", "stdev": "4" }, { "name": "Hy", "index": "5", "type": "numeric", "distinct": "380", "missing": "0", "min": "-1", "max": "15", "mean": "1", "stdev": "1" }, { "name": "SpMax2_Bh.e.", "index": "6", "type": "numeric", "distinct": "256", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "D.Dtr05", "index": "7", "type": "numeric", "distinct": "490", "missing": "0", "min": "0", "max": "472", "mean": "68", "stdev": "62" }, { "name": "Xindex", "index": "8", "type": "numeric", "distinct": "268", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "SpMax6_Bh.m.", "index": "9", "type": "numeric", "distinct": "464", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "H.050", "index": "10", "type": "numeric", "distinct": "10", "missing": "0", "min": "0", "max": "20", "mean": "3", "stdev": "2" }, { "name": "nHDon", "index": "11", "type": "numeric", "distinct": "10", "missing": "0", "min": "0", "max": "20", "mean": "3", "stdev": "2" }, { "name": "SpMax3_Bh.m.", "index": "12", "type": "numeric", "distinct": "367", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "GMTI", "index": "13", "type": "numeric", "distinct": "642", "missing": "0", "min": "603", "max": "73005", "mean": "10822", "stdev": "8270" }, { "name": "Eig09_EA.ed.", "index": "14", "type": "numeric", "distinct": "548", "missing": "0", "min": "-4", "max": "7", "mean": "3", "stdev": "2" }, { "name": "SM04_AEA.ri.", "index": "15", "type": "numeric", "distinct": "548", "missing": "0", "min": "-4", "max": "7", "mean": "3", "stdev": "2" }, { "name": "SpMax5_Bh.m.", "index": "16", "type": "numeric", "distinct": "456", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SpMax1_Bh.e.", "index": "17", "type": "numeric", "distinct": "227", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "Yindex", "index": "18", "type": "numeric", "distinct": "398", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Eig12_EA.bo.", "index": "19", "type": "numeric", "distinct": "491", "missing": "0", "min": "-3", "max": "3", "mean": "1", "stdev": "1" }, { "name": "CATS2D_08_DP", "index": "20", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "8", "mean": "0", "stdev": "1" }, { "name": "Eig09_EA", "index": "21", "type": "numeric", "distinct": "440", "missing": "0", "min": "-1", "max": "2", "mean": "1", "stdev": "1" }, { "name": "SM03_AEA.dm.", "index": "22", "type": "numeric", "distinct": "440", "missing": "0", "min": "-1", "max": "2", "mean": "1", "stdev": "1" }, { "name": "Eig09_EA.ri.", "index": "23", "type": "numeric", "distinct": "486", "missing": "0", "min": "-1", "max": "2", "mean": "1", "stdev": "1" }, { "name": "Vindex", "index": "24", "type": "numeric", "distinct": "212", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Eig07_AEA.ri.", "index": "25", "type": "numeric", "distinct": "521", "missing": "0", "min": "0", "max": "3", "mean": "3", "stdev": "0" }, { "name": "X1sol", "index": "26", "type": "numeric", "distinct": "570", "missing": "0", "min": "6", "max": "26", "mean": "13", "stdev": "3" }, { "name": "Eig09_AEA.dm.", "index": "27", "type": "numeric", "distinct": "501", "missing": "0", "min": "-1", "max": "3", "mean": "1", "stdev": "1" }, { "name": "X3sol", "index": "28", "type": "numeric", "distinct": "624", "missing": "0", "min": "4", "max": "20", "mean": "10", "stdev": "3" }, { "name": "SpMax3_Bh.i.", "index": "29", "type": "numeric", "distinct": "357", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "Eig09_AEA.ri.", "index": "30", "type": "numeric", "distinct": "495", "missing": "0", "min": "-1", "max": "3", "mean": "2", "stdev": "1" }, { "name": "Eig14_AEA.dm.", "index": "31", "type": "numeric", "distinct": "518", "missing": "0", "min": "-2", "max": "2", "mean": "0", "stdev": "1" }, { "name": "Eig15_AEA.dm.", "index": "32", "type": "numeric", "distinct": "522", "missing": "0", "min": "-2", "max": "2", "mean": "0", "stdev": "1" }, { "name": "SMTI", "index": "33", "type": "numeric", "distinct": "644", "missing": "0", "min": "652", "max": "73813", "mean": "10276", "stdev": "7762" }, { "name": "ATS2m", "index": "34", "type": "numeric", "distinct": "493", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SpMin4_Bh.v.", "index": "35", "type": "numeric", "distinct": "398", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "SpMin4_Bh.p.", "index": "36", "type": "numeric", "distinct": "416", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "CATS2D_06_DL", "index": "37", "type": "numeric", "distinct": "15", "missing": "0", "min": "0", "max": "20", "mean": "3", "stdev": "3" }, { "name": "VvdwMG", "index": "38", "type": "numeric", "distinct": "617", "missing": "0", "min": "79", "max": "416", "mean": "190", "stdev": "46" }, { "name": "Vx", "index": "39", "type": "numeric", "distinct": "617", "missing": "0", "min": "184", "max": "1008", "mean": "455", "stdev": "112" }, { "name": "Chi0_EA.dm.", "index": "40", "type": "numeric", "distinct": "619", "missing": "0", "min": "0", "max": "54", "mean": "18", "stdev": "8" }, { "name": "SpMin3_Bh.p.", "index": "41", "type": "numeric", "distinct": "333", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "SpMin3_Bh.v.", "index": "42", "type": "numeric", "distinct": "332", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "SpMax8_Bh.p.", "index": "43", "type": "numeric", "distinct": "392", "missing": "0", "min": "0", "max": "3", "mean": "3", "stdev": "0" }, { "name": "XMOD", "index": "44", "type": "numeric", "distinct": "685", "missing": "0", "min": "37", "max": "168", "mean": "86", "stdev": "20" }, { "name": "SpAD_EA.bo.", "index": "45", "type": "numeric", "distinct": "654", "missing": "0", "min": "26", "max": "113", "mean": "61", "stdev": "14" }, { "name": "Eig13_AEA.dm.", "index": "46", "type": "numeric", "distinct": "502", "missing": "0", "min": "-2", "max": "2", "mean": "0", "stdev": "1" }, { "name": "Chi0_EA.bo.", "index": "47", "type": "numeric", "distinct": "605", "missing": "0", "min": "6", "max": "32", "mean": "16", "stdev": "4" }, { "name": "UNIP", "index": "48", "type": "numeric", "distinct": "194", "missing": "0", "min": "21", "max": "497", "mean": "112", "stdev": "54" }, { "name": "X2sol", "index": "49", "type": "numeric", "distinct": "615", "missing": "0", "min": "5", "max": "24", "mean": "12", "stdev": "3" }, { "name": "SAdon", "index": "50", "type": "numeric", "distinct": "92", "missing": "0", "min": "0", "max": "335", "mean": "52", "stdev": "33" }, { "name": "IC5", "index": "51", "type": "numeric", "distinct": "440", "missing": "0", "min": "3", "max": "6", "mean": "5", "stdev": "0" }, { "name": "Eta_beta", "index": "52", "type": "numeric", "distinct": "149", "missing": "0", "min": "15", "max": "69", "mean": "38", "stdev": "9" }, { "name": "Eig15_AEA.bo.", "index": "53", "type": "numeric", "distinct": "467", "missing": "0", "min": "-1", "max": "3", "mean": "1", "stdev": "1" }, { "name": "Psi_i_0", "index": "54", "type": "numeric", "distinct": "667", "missing": "0", "min": "7", "max": "38", "mean": "19", "stdev": "5" }, { "name": "SpMax1_Bh.p.", "index": "55", "type": "numeric", "distinct": "253", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "Eig07_AEA.bo.", "index": "56", "type": "numeric", "distinct": "466", "missing": "0", "min": "1", "max": "4", "mean": "3", "stdev": "0" }, { "name": "ICR", "index": "57", "type": "numeric", "distinct": "413", "missing": "0", "min": "1", "max": "4", "mean": "3", "stdev": "0" }, { "name": "MSD", "index": "58", "type": "numeric", "distinct": "610", "missing": "0", "min": "3", "max": "14", "mean": "6", "stdev": "2" }, { "name": "Chi1_EA.ed.", "index": "59", "type": "numeric", "distinct": "613", "missing": "0", "min": "2", "max": "10", "mean": "5", "stdev": "1" }, { "name": "AECC", "index": "60", "type": "numeric", "distinct": "533", "missing": "0", "min": "4", "max": "23", "mean": "11", "stdev": "3" }, { "name": "Chi0_AEA.bo.", "index": "61", "type": "numeric", "distinct": "515", "missing": "0", "min": "7", "max": "36", "mean": "18", "stdev": "4" }, { "name": "Chi0_AEA.dm.", "index": "62", "type": "numeric", "distinct": "515", "missing": "0", "min": "7", "max": "36", "mean": "18", "stdev": "4" }, { "name": "Chi0_AEA.ed.", "index": "63", "type": "numeric", "distinct": "515", "missing": "0", "min": "7", "max": "36", "mean": "18", "stdev": "4" }, { "name": "Chi0_AEA.ri.", "index": "64", "type": "numeric", "distinct": "515", "missing": "0", "min": "7", "max": "36", "mean": "18", "stdev": "4" }, { "name": "Chi0_EA", "index": "65", "type": "numeric", "distinct": "515", "missing": "0", "min": "7", "max": "36", "mean": "18", "stdev": "4" }, { "name": "X1v", "index": "66", "type": "numeric", "distinct": "670", "missing": "0", "min": "4", "max": "17", "mean": "9", "stdev": "2" }, { "name": "SpMax5_Bh.e.", "index": "67", "type": "numeric", "distinct": "443", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "Eig11_AEA.ri.", "index": "68", "type": "numeric", "distinct": "487", "missing": "0", "min": "-1", "max": "3", "mean": "2", "stdev": "1" }, { "name": "Eig07_EA", "index": "69", "type": "numeric", "distinct": "460", "missing": "0", "min": "-1", "max": "2", "mean": "2", "stdev": "0" } ], "nr_of_issues": 0, "nr_of_downvotes": 0, "nr_of_likes": 0, "nr_of_downloads": 0, "total_downloads": 0, "reach": 0, "reuse": 0, "impact_of_reuse": 0, "reach_of_reuse": 0, "impact": 0 }