{ "data_id": "31338", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4018", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4018", "version": 11, "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: CHEMBL4018 (TID: 10477), and it has 682 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 07:18:59", "update_comment": null, "last_update": "2016-07-15 07:18:59", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3445924\/data_53652.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4018", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL4018 (TID: 10477), and it has 682 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": 682, "NumberOfFeatures": 72, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 71, "NumberOfSymbolicFeatures": 1, "Quartile3AttributeEntropy": null, "MaxKurtosisOfNumericAtts": 13.215814622507754, "MinMeansOfNumericAtts": -6.098951612903232, "PercentageOfInstancesWithMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 5.21937215812434, "MaxMeansOfNumericAtts": 197.7957360703814, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3MeansOfNumericAtts": 4.7375366568914865, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.61111111111111, "Quartile3MutualInformation": null, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -2.82608574619433, "PercentageOfSymbolicFeatures": 1.3888888888888888, "Quartile3SkewnessOfNumericAtts": 2.286576861054471, "MaxSkewnessOfNumericAtts": 3.4039819255031527, "MinStdDevOfNumericAtts": 0.1295860651520595, "Quartile1AttributeEntropy": null, "Quartile3StdDevOfNumericAtts": 8.660021076795013, "MaxStdDevOfNumericAtts": 330.88114193224794, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": 1.3734645311801548, "StdvNominalAttDistinctValues": null, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 0.5703812316715563, "MeanKurtosisOfNumericAtts": 3.296960788054159, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 9.966497315269923, "Quartile1SkewnessOfNumericAtts": 1.6248946881411117, "AutoCorrelation": 0.21250513950073388, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.7640542562771031, "ClassEntropy": null, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "Dimensionality": 0.10557184750733138, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": 2.6266907153418706, "EquivalentNumberOfAtts": null, "MeanSkewnessOfNumericAtts": 1.7218431318898093, "Quartile2MeansOfNumericAtts": 1.6466275659824148, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 17.39755205068461, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": 1.8943466427519775, "Quartile2StdDevOfNumericAtts": 3.504944534094708, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -0.365413744048499, "PercentageOfBinaryFeatures": 0 }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "71", "type": "numeric", "distinct": "378", "missing": "0", "target": "1", "min": "4", "max": "10", "mean": "6", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "682", "missing": "0", "identifier": "1", "distr": [] }, { "name": "CATS2D_07_DA", "index": "1", "type": "numeric", "distinct": "18", "missing": "0", "min": "0", "max": "19", "mean": "2", "stdev": "3" }, { "name": "CATS2D_07_AP", "index": "2", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "6", "mean": "0", "stdev": "1" }, { "name": "CATS2D_05_DD", "index": "3", "type": "numeric", "distinct": "11", "missing": "0", "min": "0", "max": "12", "mean": "1", "stdev": "2" }, { "name": "CIC5", "index": "4", "type": "numeric", "distinct": "475", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "GATS2p", "index": "5", "type": "numeric", "distinct": "342", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "H.052", "index": "6", "type": "numeric", "distinct": "52", "missing": "0", "min": "0", "max": "83", "mean": "9", "stdev": "16" }, { "name": "GATS2i", "index": "7", "type": "numeric", "distinct": "366", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Eig08_EA.dm.", "index": "8", "type": "numeric", "distinct": "63", "missing": "0", "min": "-1", "max": "2", "mean": "0", "stdev": "1" }, { "name": "Eig09_EA.dm.", "index": "9", "type": "numeric", "distinct": "57", "missing": "0", "min": "-2", "max": "2", "mean": "0", "stdev": "1" }, { "name": "Eig11_EA.dm.", "index": "10", "type": "numeric", "distinct": "48", "missing": "0", "min": "-1", "max": "2", "mean": "0", "stdev": "1" }, { "name": "Eig12_EA.dm.", "index": "11", "type": "numeric", "distinct": "52", "missing": "0", "min": "-2", "max": "2", "mean": "0", "stdev": "1" }, { "name": "Eig13_EA.dm.", "index": "12", "type": "numeric", "distinct": "42", "missing": "0", "min": "-4", "max": "2", "mean": "0", "stdev": "1" }, { "name": "Eig14_EA.dm.", "index": "13", "type": "numeric", "distinct": "43", "missing": "0", "min": "-1", "max": "2", "mean": "0", "stdev": "1" }, { "name": "Eig15_EA.dm.", "index": "14", "type": "numeric", "distinct": "46", "missing": "0", "min": "-1", "max": "2", "mean": "0", "stdev": "1" }, { "name": "NdO", "index": "15", "type": "numeric", "distinct": "29", "missing": "0", "min": "0", "max": "44", "mean": "5", "stdev": "9" }, { "name": "CATS2D_08_AA", "index": "16", "type": "numeric", "distinct": "36", "missing": "0", "min": "0", "max": "47", "mean": "4", "stdev": "8" }, { "name": "CATS2D_09_DA", "index": "17", "type": "numeric", "distinct": "38", "missing": "0", "min": "0", "max": "64", "mean": "7", "stdev": "14" }, { "name": "CATS2D_09_PL", "index": "18", "type": "numeric", "distinct": "15", "missing": "0", "min": "0", "max": "15", "mean": "1", "stdev": "3" }, { "name": "CATS2D_04_AL", "index": "19", "type": "numeric", "distinct": "51", "missing": "0", "min": "0", "max": "65", "mean": "12", "stdev": "11" }, { "name": "CATS2D_04_DP", "index": "20", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "C.042", "index": "21", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "nRCONH2", "index": "22", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "6", "mean": "0", "stdev": "1" }, { "name": "C.002", "index": "23", "type": "numeric", "distinct": "33", "missing": "0", "min": "0", "max": "43", "mean": "6", "stdev": "9" }, { "name": "C.040", "index": "24", "type": "numeric", "distinct": "27", "missing": "0", "min": "0", "max": "44", "mean": "5", "stdev": "9" }, { "name": "CATS2D_00_DD", "index": "25", "type": "numeric", "distinct": "13", "missing": "0", "min": "0", "max": "15", "mean": "2", "stdev": "4" }, { "name": "CATS2D_00_DP", "index": "26", "type": "numeric", "distinct": "13", "missing": "0", "min": "0", "max": "15", "mean": "2", "stdev": "4" }, { "name": "CATS2D_00_PP", "index": "27", "type": "numeric", "distinct": "13", "missing": "0", "min": "0", "max": "15", "mean": "2", "stdev": "4" }, { "name": "CATS2D_02_AP", "index": "28", "type": "numeric", "distinct": "11", "missing": "0", "min": "0", "max": "13", "mean": "2", "stdev": "4" }, { "name": "CATS2D_02_DP", "index": "29", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "12", "mean": "1", "stdev": "3" }, { "name": "CATS2D_03_DD", "index": "30", "type": "numeric", "distinct": "25", "missing": "0", "min": "0", "max": "34", "mean": "3", "stdev": "7" }, { "name": "CATS2D_06_DA", "index": "31", "type": "numeric", "distinct": "35", "missing": "0", "min": "0", "max": "55", "mean": "5", "stdev": "11" }, { "name": "CATS2D_07_DD", "index": "32", "type": "numeric", "distinct": "18", "missing": "0", "min": "0", "max": "25", "mean": "2", "stdev": "5" }, { "name": "CATS2D_07_DP", "index": "33", "type": "numeric", "distinct": "10", "missing": "0", "min": "0", "max": "12", "mean": "2", "stdev": "3" }, { "name": "CATS2D_08_AP", "index": "34", "type": "numeric", "distinct": "14", "missing": "0", "min": "0", "max": "14", "mean": "2", "stdev": "4" }, { "name": "CATS2D_08_DD", "index": "35", "type": "numeric", "distinct": "20", "missing": "0", "min": "0", "max": "30", "mean": "2", "stdev": "5" }, { "name": "CATS2D_08_DL", "index": "36", "type": "numeric", "distinct": "51", "missing": "0", "min": "0", "max": "75", "mean": "8", "stdev": "16" }, { "name": "CATS2D_08_DP", "index": "37", "type": "numeric", "distinct": "12", "missing": "0", "min": "0", "max": "14", "mean": "2", "stdev": "4" }, { "name": "CATS2D_09_AL", "index": "38", "type": "numeric", "distinct": "58", "missing": "0", "min": "0", "max": "86", "mean": "12", "stdev": "16" }, { "name": "CATS2D_09_AP", "index": "39", "type": "numeric", "distinct": "14", "missing": "0", "min": "0", "max": "16", "mean": "2", "stdev": "4" }, { "name": "Eig06_EA.dm.", "index": "40", "type": "numeric", "distinct": "92", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "Eig10_EA.dm.", "index": "41", "type": "numeric", "distinct": "56", "missing": "0", "min": "-2", "max": "2", "mean": "0", "stdev": "1" }, { "name": "N.066", "index": "42", "type": "numeric", "distinct": "10", "missing": "0", "min": "0", "max": "11", "mean": "1", "stdev": "3" }, { "name": "nC..N.N2", "index": "43", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "6", "mean": "1", "stdev": "1" }, { "name": "nRNH2", "index": "44", "type": "numeric", "distinct": "10", "missing": "0", "min": "0", "max": "11", "mean": "1", "stdev": "3" }, { "name": "NsNH2", "index": "45", "type": "numeric", "distinct": "13", "missing": "0", "min": "0", "max": "15", "mean": "2", "stdev": "4" }, { "name": "P_VSA_e_3", "index": "46", "type": "numeric", "distinct": "248", "missing": "0", "min": "0", "max": "1300", "mean": "164", "stdev": "282" }, { "name": "P_VSA_i_4", "index": "47", "type": "numeric", "distinct": "271", "missing": "0", "min": "0", "max": "1300", "mean": "166", "stdev": "281" }, { "name": "P_VSA_LogP_4", "index": "48", "type": "numeric", "distinct": "300", "missing": "0", "min": "0", "max": "1797", "mean": "198", "stdev": "331" }, { "name": "SdssC", "index": "49", "type": "numeric", "distinct": "502", "missing": "0", "min": "-57", "max": "7", "mean": "-4", "stdev": "11" }, { "name": "SsNH2", "index": "50", "type": "numeric", "distinct": "146", "missing": "0", "min": "0", "max": "87", "mean": "11", "stdev": "23" }, { "name": "CATS2D_07_DL", "index": "51", "type": "numeric", "distinct": "46", "missing": "0", "min": "0", "max": "58", "mean": "7", "stdev": "13" }, { "name": "CATS2D_09_DD", "index": "52", "type": "numeric", "distinct": "33", "missing": "0", "min": "0", "max": "40", "mean": "4", "stdev": "8" }, { "name": "CATS2D_09_DP", "index": "53", "type": "numeric", "distinct": "8", "missing": "0", "min": "0", "max": "8", "mean": "1", "stdev": "1" }, { "name": "CATS2D_08_PL", "index": "54", "type": "numeric", "distinct": "8", "missing": "0", "min": "0", "max": "8", "mean": "1", "stdev": "2" }, { "name": "CATS2D_09_AA", "index": "55", "type": "numeric", "distinct": "19", "missing": "0", "min": "0", "max": "20", "mean": "2", "stdev": "4" }, { "name": "CATS2D_05_PL", "index": "56", "type": "numeric", "distinct": "17", "missing": "0", "min": "0", "max": "18", "mean": "2", "stdev": "4" }, { "name": "Eta_F_A", "index": "57", "type": "numeric", "distinct": "450", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "DLS_cons", "index": "58", "type": "numeric", "distinct": "44", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "C.008", "index": "59", "type": "numeric", "distinct": "27", "missing": "0", "min": "0", "max": "37", "mean": "4", "stdev": "8" }, { "name": "CATS2D_08_AL", "index": "60", "type": "numeric", "distinct": "53", "missing": "0", "min": "0", "max": "72", "mean": "11", "stdev": "14" }, { "name": "nCs", "index": "61", "type": "numeric", "distinct": "43", "missing": "0", "min": "0", "max": "78", "mean": "9", "stdev": "16" }, { "name": "nO", "index": "62", "type": "numeric", "distinct": "34", "missing": "0", "min": "0", "max": "58", "mean": "7", "stdev": "11" }, { "name": "NsssCH", "index": "63", "type": "numeric", "distinct": "30", "missing": "0", "min": "0", "max": "42", "mean": "5", "stdev": "9" }, { "name": "SsssCH", "index": "64", "type": "numeric", "distinct": "389", "missing": "0", "min": "-70", "max": "3", "mean": "-6", "stdev": "14" }, { "name": "CATS2D_02_PP", "index": "65", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "C.041", "index": "66", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "6", "mean": "1", "stdev": "1" }, { "name": "GATS2v", "index": "67", "type": "numeric", "distinct": "304", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "ATSC1e", "index": "68", "type": "numeric", "distinct": "275", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "Eig02_AEA.ri.", "index": "69", "type": "numeric", "distinct": "391", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "CATS2D_06_DP", "index": "70", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "6", "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 }