{ "data_id": "35704", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL2581", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL2581", "version": 10, "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: CHEMBL2581 (TID: 10003), and it has 1187 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 18:45:57", "update_comment": null, "last_update": "2016-07-15 18:45:57", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3565781\/data_53563.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL2581", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL2581 (TID: 10003), and it has 1187 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": 1187, "NumberOfFeatures": 71, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 70, "NumberOfSymbolicFeatures": 1, "ClassEntropy": null, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "Dimensionality": 0.05981465880370682, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": 0.17104684296988304, "EquivalentNumberOfAtts": null, "MeanSkewnessOfNumericAtts": 0.5114656906062678, "Quartile2MeansOfNumericAtts": 3.3835627632687446, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 3.585303238572098, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": 0.3425016460825461, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -0.9678960786290829, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.4171602599591559, "MaxKurtosisOfNumericAtts": 20.54253095919424, "MinMeansOfNumericAtts": 0.03314574557708509, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 85.3647851727043, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 0.8754117344757504, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.59154929577466, "Quartile3MeansOfNumericAtts": 7.4801350042123, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -1.414718552034508, "PercentageOfSymbolicFeatures": 1.4084507042253522, "Quartile3MutualInformation": null, "MaxSkewnessOfNumericAtts": 3.326716712183978, "MinStdDevOfNumericAtts": 0.009298306524773097, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 0.965014014669061, "MaxStdDevOfNumericAtts": 89.20836518079189, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": -0.6559901681496023, "Quartile3StdDevOfNumericAtts": 2.0293282469992806, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 0.5557051390058976, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": 0.9472228816358411, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 8.575742748826574, "Quartile1SkewnessOfNumericAtts": 0.12730666114813008, "AutoCorrelation": 0.16158853288364308, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.2219900367645063 }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "70", "type": "numeric", "distinct": "646", "missing": "0", "target": "1", "min": "4", "max": "10", "mean": "6", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "1187", "missing": "0", "identifier": "1", "distr": [] }, { "name": "PW5", "index": "1", "type": "numeric", "distinct": "56", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Eig04_EA.ri.", "index": "2", "type": "numeric", "distinct": "480", "missing": "0", "min": "2", "max": "3", "mean": "3", "stdev": "0" }, { "name": "CATS2D_03_DD", "index": "3", "type": "numeric", "distinct": "8", "missing": "0", "min": "0", "max": "7", "mean": "2", "stdev": "1" }, { "name": "SpMax8_Bh.s.", "index": "4", "type": "numeric", "distinct": "563", "missing": "0", "min": "4", "max": "8", "mean": "5", "stdev": "1" }, { "name": "ATSC1i", "index": "5", "type": "numeric", "distinct": "651", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "ATSC1s", "index": "6", "type": "numeric", "distinct": "1048", "missing": "0", "min": "4", "max": "180", "mean": "23", "stdev": "15" }, { "name": "Eig04_EA", "index": "7", "type": "numeric", "distinct": "451", "missing": "0", "min": "2", "max": "3", "mean": "3", "stdev": "0" }, { "name": "SM12_AEA.bo.", "index": "8", "type": "numeric", "distinct": "451", "missing": "0", "min": "2", "max": "3", "mean": "3", "stdev": "0" }, { "name": "Eig04_AEA.dm.", "index": "9", "type": "numeric", "distinct": "479", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "C.001", "index": "10", "type": "numeric", "distinct": "13", "missing": "0", "min": "0", "max": "12", "mean": "2", "stdev": "2" }, { "name": "SsCH3", "index": "11", "type": "numeric", "distinct": "933", "missing": "0", "min": "0", "max": "26", "mean": "5", "stdev": "4" }, { "name": "nCp", "index": "12", "type": "numeric", "distinct": "13", "missing": "0", "min": "0", "max": "12", "mean": "2", "stdev": "2" }, { "name": "X4A", "index": "13", "type": "numeric", "distinct": "49", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "CATS2D_06_DL", "index": "14", "type": "numeric", "distinct": "24", "missing": "0", "min": "0", "max": "23", "mean": "8", "stdev": "4" }, { "name": "Eig02_AEA.dm.", "index": "15", "type": "numeric", "distinct": "378", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "Eig08_EA.bo.", "index": "16", "type": "numeric", "distinct": "547", "missing": "0", "min": "0", "max": "4", "mean": "2", "stdev": "0" }, { "name": "CATS2D_02_DL", "index": "17", "type": "numeric", "distinct": "14", "missing": "0", "min": "0", "max": "13", "mean": "4", "stdev": "3" }, { "name": "SpMax2_Bh.s.", "index": "18", "type": "numeric", "distinct": "109", "missing": "0", "min": "5", "max": "9", "mean": "7", "stdev": "1" }, { "name": "Eig01_AEA.ri.", "index": "19", "type": "numeric", "distinct": "359", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SpMax_AEA.ri.", "index": "20", "type": "numeric", "distinct": "359", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "DLS_05", "index": "21", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "P_VSA_LogP_1", "index": "22", "type": "numeric", "distinct": "95", "missing": "0", "min": "0", "max": "142", "mean": "26", "stdev": "19" }, { "name": "SpDiam_EA.ed.", "index": "23", "type": "numeric", "distinct": "450", "missing": "0", "min": "15", "max": "28", "mean": "20", "stdev": "3" }, { "name": "Eig01_EA.ed.", "index": "24", "type": "numeric", "distinct": "379", "missing": "0", "min": "9", "max": "18", "mean": "13", "stdev": "2" }, { "name": "SM10_AEA.dm.", "index": "25", "type": "numeric", "distinct": "379", "missing": "0", "min": "9", "max": "18", "mean": "13", "stdev": "2" }, { "name": "SpMax_EA.ed.", "index": "26", "type": "numeric", "distinct": "379", "missing": "0", "min": "9", "max": "18", "mean": "13", "stdev": "2" }, { "name": "X3A", "index": "27", "type": "numeric", "distinct": "62", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Eig01_EA", "index": "28", "type": "numeric", "distinct": "317", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SM09_AEA.bo.", "index": "29", "type": "numeric", "distinct": "317", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SpDiam_EA", "index": "30", "type": "numeric", "distinct": "324", "missing": "0", "min": "5", "max": "6", "mean": "5", "stdev": "0" }, { "name": "SpMax_EA", "index": "31", "type": "numeric", "distinct": "317", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "N.", "index": "32", "type": "numeric", "distinct": "102", "missing": "0", "min": "0", "max": "16", "mean": "5", "stdev": "2" }, { "name": "X2Av", "index": "33", "type": "numeric", "distinct": "135", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Eig09_EA.bo.", "index": "34", "type": "numeric", "distinct": "510", "missing": "0", "min": "0", "max": "3", "mean": "2", "stdev": "0" }, { "name": "MCD", "index": "35", "type": "numeric", "distinct": "293", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SM14_EA.ed.", "index": "36", "type": "numeric", "distinct": "642", "missing": "0", "min": "31", "max": "41", "mean": "35", "stdev": "2" }, { "name": "N.074", "index": "37", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "SM13_EA.ed.", "index": "38", "type": "numeric", "distinct": "637", "missing": "0", "min": "29", "max": "38", "mean": "33", "stdev": "2" }, { "name": "SM12_EA.ed.", "index": "39", "type": "numeric", "distinct": "663", "missing": "0", "min": "27", "max": "35", "mean": "30", "stdev": "2" }, { "name": "SM11_EA.ed.", "index": "40", "type": "numeric", "distinct": "667", "missing": "0", "min": "25", "max": "32", "mean": "28", "stdev": "2" }, { "name": "SM10_EA.ed.", "index": "41", "type": "numeric", "distinct": "671", "missing": "0", "min": "22", "max": "29", "mean": "26", "stdev": "2" }, { "name": "X3Av", "index": "42", "type": "numeric", "distinct": "93", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Infective.80", "index": "43", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "BAC", "index": "44", "type": "numeric", "distinct": "217", "missing": "0", "min": "2", "max": "1032", "mean": "85", "stdev": "89" }, { "name": "NdsN", "index": "45", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "Eig06_AEA.bo.", "index": "46", "type": "numeric", "distinct": "514", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "CATS2D_08_DL", "index": "47", "type": "numeric", "distinct": "24", "missing": "0", "min": "0", "max": "24", "mean": "6", "stdev": "5" }, { "name": "N.066", "index": "48", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "nRNH2", "index": "49", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "X5Av", "index": "50", "type": "numeric", "distinct": "49", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SM03_EA.ri.", "index": "51", "type": "numeric", "distinct": "514", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "X4Av", "index": "52", "type": "numeric", "distinct": "69", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SpMax1_Bh.v.", "index": "53", "type": "numeric", "distinct": "246", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "Eig03_AEA.dm.", "index": "54", "type": "numeric", "distinct": "462", "missing": "0", "min": "3", "max": "5", "mean": "3", "stdev": "0" }, { "name": "PW4", "index": "55", "type": "numeric", "distinct": "83", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "ATSC2s", "index": "56", "type": "numeric", "distinct": "1094", "missing": "0", "min": "10", "max": "522", "mean": "74", "stdev": "57" }, { "name": "SpMin3_Bh.v.", "index": "57", "type": "numeric", "distinct": "272", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "SM14_EA.ri.", "index": "58", "type": "numeric", "distinct": "845", "missing": "0", "min": "15", "max": "19", "mean": "17", "stdev": "1" }, { "name": "SM15_EA.ri.", "index": "59", "type": "numeric", "distinct": "822", "missing": "0", "min": "16", "max": "21", "mean": "18", "stdev": "1" }, { "name": "CATS2D_02_AP", "index": "60", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "CATS2D_04_PL", "index": "61", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "SpMin3_Bh.p.", "index": "62", "type": "numeric", "distinct": "230", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "IDE", "index": "63", "type": "numeric", "distinct": "603", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "H.046", "index": "64", "type": "numeric", "distinct": "32", "missing": "0", "min": "0", "max": "33", "mean": "7", "stdev": "7" }, { "name": "nCsp3", "index": "65", "type": "numeric", "distinct": "34", "missing": "0", "min": "0", "max": "41", "mean": "12", "stdev": "6" }, { "name": "Eig09_AEA.dm.", "index": "66", "type": "numeric", "distinct": "651", "missing": "0", "min": "1", "max": "4", "mean": "2", "stdev": "0" }, { "name": "Mv", "index": "67", "type": "numeric", "distinct": "193", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "LLS_01", "index": "68", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "CATS2D_07_PL", "index": "69", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "5", "mean": "1", "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 }