{ "data_id": "35108", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL2334", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL2334", "version": 12, "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: CHEMBL2334 (TID: 10131), and it has 1979 rows and 70 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 17:09:14", "update_comment": null, "last_update": "2016-07-15 17:09:14", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3548320\/data_53715.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL2334", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL2334 (TID: 10131), and it has 1979 rows and 70 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": 1979, "NumberOfFeatures": 72, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 71, "NumberOfSymbolicFeatures": 1, "Quartile3AttributeEntropy": null, "MaxKurtosisOfNumericAtts": 77.42827159826349, "MinMeansOfNumericAtts": -0.9143597776654909, "PercentageOfInstancesWithMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 3.380749126798646, "MaxMeansOfNumericAtts": 480.19010914603336, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3MeansOfNumericAtts": 6.819605356240525, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.61111111111111, "Quartile3MutualInformation": null, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -1.8614519022126863, "PercentageOfSymbolicFeatures": 1.3888888888888888, "Quartile3SkewnessOfNumericAtts": 1.4704035054419458, "MaxSkewnessOfNumericAtts": 5.741571617003181, "MinStdDevOfNumericAtts": 0.1464850628871353, "Quartile1AttributeEntropy": null, "Quartile3StdDevOfNumericAtts": 3.2120409452175904, "MaxStdDevOfNumericAtts": 154.4334400054545, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": -0.7930951679660647, "StdvNominalAttDistinctValues": null, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 0.42496210207175145, "MeanKurtosisOfNumericAtts": 2.4274277252248098, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 19.453654797913302, "Quartile1SkewnessOfNumericAtts": 0.05303925354277568, "AutoCorrelation": 0.11971284125379132, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.4362361899311808, "ClassEntropy": null, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "Dimensionality": 0.03638201111672562, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": 0.37863010126626717, "EquivalentNumberOfAtts": null, "MeanSkewnessOfNumericAtts": 0.8155625438543761, "Quartile2MeansOfNumericAtts": 2.5831227892875352, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 8.918043751994722, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": 0.5399326165108668, "Quartile2StdDevOfNumericAtts": 0.5519020043797945, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.990267054675136, "PercentageOfBinaryFeatures": 0 }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "71", "type": "numeric", "distinct": "983", "missing": "0", "target": "1", "min": "4", "max": "11", "mean": "5", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "1979", "missing": "0", "identifier": "1", "distr": [] }, { "name": "Eta_C_A", "index": "1", "type": "numeric", "distinct": "662", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "DLS_03", "index": "2", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "nDB", "index": "3", "type": "numeric", "distinct": "13", "missing": "0", "min": "0", "max": "12", "mean": "3", "stdev": "2" }, { "name": "SddssS", "index": "4", "type": "numeric", "distinct": "327", "missing": "0", "min": "-9", "max": "0", "mean": "-1", "stdev": "2" }, { "name": "P_VSA_p_1", "index": "5", "type": "numeric", "distinct": "118", "missing": "0", "min": "35", "max": "1012", "mean": "210", "stdev": "88" }, { "name": "nSO2N", "index": "6", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "CATS2D_04_AN", "index": "7", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "0" }, { "name": "ATSC4e", "index": "8", "type": "numeric", "distinct": "1081", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "0" }, { "name": "LLS_02", "index": "9", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "ATS2s", "index": "10", "type": "numeric", "distinct": "1043", "missing": "0", "min": "5", "max": "7", "mean": "6", "stdev": "0" }, { "name": "ATSC2s", "index": "11", "type": "numeric", "distinct": "1927", "missing": "0", "min": "4", "max": "376", "mean": "54", "stdev": "44" }, { "name": "Eig01_AEA.dm.", "index": "12", "type": "numeric", "distinct": "675", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "1" }, { "name": "SpMax_AEA.dm.", "index": "13", "type": "numeric", "distinct": "675", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "1" }, { "name": "N.068", "index": "14", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "CMC.80", "index": "15", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "BAC", "index": "16", "type": "numeric", "distinct": "164", "missing": "0", "min": "0", "max": "1032", "mean": "39", "stdev": "51" }, { "name": "nRCOOH", "index": "17", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "0" }, { "name": "SpMax6_Bh.e.", "index": "18", "type": "numeric", "distinct": "741", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "CATS2D_03_DN", "index": "19", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "0" }, { "name": "NddssS", "index": "20", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "S.110", "index": "21", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "Eig07_AEA.ri.", "index": "22", "type": "numeric", "distinct": "904", "missing": "0", "min": "0", "max": "4", "mean": "3", "stdev": "0" }, { "name": "Eig07_EA.ri.", "index": "23", "type": "numeric", "distinct": "915", "missing": "0", "min": "-1", "max": "3", "mean": "1", "stdev": "0" }, { "name": "CATS2D_05_AN", "index": "24", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "5", "mean": "0", "stdev": "1" }, { "name": "Eig01_AEA.ed.", "index": "25", "type": "numeric", "distinct": "706", "missing": "0", "min": "5", "max": "9", "mean": "7", "stdev": "1" }, { "name": "SpMax_AEA.ed.", "index": "26", "type": "numeric", "distinct": "706", "missing": "0", "min": "5", "max": "9", "mean": "7", "stdev": "1" }, { "name": "SM11_EA.dm.", "index": "27", "type": "numeric", "distinct": "288", "missing": "0", "min": "0", "max": "19", "mean": "5", "stdev": "5" }, { "name": "S1K", "index": "28", "type": "numeric", "distinct": "1242", "missing": "0", "min": "7", "max": "74", "mean": "19", "stdev": "7" }, { "name": "nRCO", "index": "29", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "SpDiam_AEA.dm.", "index": "30", "type": "numeric", "distinct": "689", "missing": "0", "min": "5", "max": "7", "mean": "6", "stdev": "1" }, { "name": "SM13_EA.dm.", "index": "31", "type": "numeric", "distinct": "283", "missing": "0", "min": "0", "max": "22", "mean": "6", "stdev": "6" }, { "name": "SM05_EA.dm.", "index": "32", "type": "numeric", "distinct": "285", "missing": "0", "min": "0", "max": "8", "mean": "2", "stdev": "2" }, { "name": "CATS2D_08_AN", "index": "33", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "0", "stdev": "0" }, { "name": "P_VSA_MR_1", "index": "34", "type": "numeric", "distinct": "117", "missing": "0", "min": "24", "max": "789", "mean": "190", "stdev": "74" }, { "name": "Eig07_EA", "index": "35", "type": "numeric", "distinct": "853", "missing": "0", "min": "-1", "max": "3", "mean": "2", "stdev": "0" }, { "name": "SM15_AEA.bo.", "index": "36", "type": "numeric", "distinct": "853", "missing": "0", "min": "-1", "max": "3", "mean": "2", "stdev": "0" }, { "name": "SM05_EA.bo.", "index": "37", "type": "numeric", "distinct": "979", "missing": "0", "min": "5", "max": "9", "mean": "8", "stdev": "0" }, { "name": "Infective.80", "index": "38", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "O.058", "index": "39", "type": "numeric", "distinct": "12", "missing": "0", "min": "0", "max": "11", "mean": "2", "stdev": "2" }, { "name": "CATS2D_03_AA", "index": "40", "type": "numeric", "distinct": "9", "missing": "0", "min": "0", "max": "9", "mean": "1", "stdev": "1" }, { "name": "SM14_EA.dm.", "index": "41", "type": "numeric", "distinct": "468", "missing": "0", "min": "0", "max": "24", "mean": "9", "stdev": "6" }, { "name": "Eig03_EA.dm.", "index": "42", "type": "numeric", "distinct": "189", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "SM10_EA.dm.", "index": "43", "type": "numeric", "distinct": "542", "missing": "0", "min": "0", "max": "17", "mean": "6", "stdev": "4" }, { "name": "NsssN", "index": "44", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "SM09_EA.dm.", "index": "45", "type": "numeric", "distinct": "296", "missing": "0", "min": "0", "max": "15", "mean": "4", "stdev": "4" }, { "name": "Depressant.80", "index": "46", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "ATSC2e", "index": "47", "type": "numeric", "distinct": "812", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "Inflammat.80", "index": "48", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SM15_EA.dm.", "index": "49", "type": "numeric", "distinct": "272", "missing": "0", "min": "0", "max": "25", "mean": "7", "stdev": "7" }, { "name": "C.038", "index": "50", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "CATS2D_06_NL", "index": "51", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "5", "mean": "0", "stdev": "1" }, { "name": "SpMax6_Bh.m.", "index": "52", "type": "numeric", "distinct": "804", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SAtot", "index": "53", "type": "numeric", "distinct": "1778", "missing": "0", "min": "195", "max": "1811", "mean": "480", "stdev": "154" }, { "name": "NdO", "index": "54", "type": "numeric", "distinct": "12", "missing": "0", "min": "0", "max": "11", "mean": "3", "stdev": "2" }, { "name": "SM07_EA.dm.", "index": "55", "type": "numeric", "distinct": "301", "missing": "0", "min": "0", "max": "12", "mean": "3", "stdev": "3" }, { "name": "SM12_EA.dm.", "index": "56", "type": "numeric", "distinct": "501", "missing": "0", "min": "0", "max": "20", "mean": "7", "stdev": "5" }, { "name": "MAXDN", "index": "57", "type": "numeric", "distinct": "1384", "missing": "0", "min": "0", "max": "8", "mean": "3", "stdev": "1" }, { "name": "Eig01_EA.ed.", "index": "58", "type": "numeric", "distinct": "974", "missing": "0", "min": "7", "max": "18", "mean": "11", "stdev": "2" }, { "name": "SM10_AEA.dm.", "index": "59", "type": "numeric", "distinct": "974", "missing": "0", "min": "7", "max": "18", "mean": "11", "stdev": "2" }, { "name": "SpMax_EA.ed.", "index": "60", "type": "numeric", "distinct": "974", "missing": "0", "min": "7", "max": "18", "mean": "11", "stdev": "2" }, { "name": "CATS2D_07_NL", "index": "61", "type": "numeric", "distinct": "9", "missing": "0", "min": "0", "max": "8", "mean": "0", "stdev": "1" }, { "name": "CATS2D_03_AL", "index": "62", "type": "numeric", "distinct": "23", "missing": "0", "min": "0", "max": "23", "mean": "7", "stdev": "4" }, { "name": "SM04_EA.ri.", "index": "63", "type": "numeric", "distinct": "993", "missing": "0", "min": "4", "max": "7", "mean": "6", "stdev": "0" }, { "name": "CATS2D_01_AN", "index": "64", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "1" }, { "name": "CATS2D_01_DN", "index": "65", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "1" }, { "name": "Eig08_AEA.ed.", "index": "66", "type": "numeric", "distinct": "940", "missing": "0", "min": "1", "max": "6", "mean": "4", "stdev": "1" }, { "name": "P_VSA_s_6", "index": "67", "type": "numeric", "distinct": "835", "missing": "0", "min": "0", "max": "428", "mean": "125", "stdev": "67" }, { "name": "ATSC3s", "index": "68", "type": "numeric", "distinct": "1933", "missing": "0", "min": "6", "max": "444", "mean": "76", "stdev": "60" }, { "name": "SM08_EA.dm.", "index": "69", "type": "numeric", "distinct": "588", "missing": "0", "min": "0", "max": "14", "mean": "5", "stdev": "4" }, { "name": "CATS2D_01_NL", "index": "70", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "1" } ], "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 }