{ "data_id": "34550", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL2007", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL2007", "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: CHEMBL2007 (TID: 12627), and it has 612 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 15:39:53", "update_comment": null, "last_update": "2016-07-15 15:39:53", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3532132\/data_53490.arff", "kaggle_url": null, "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL2007", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL2007 (TID: 12627), and it has 612 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": 612, "NumberOfFeatures": 71, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 70, "NumberOfSymbolicFeatures": 1, "MaxSkewnessOfNumericAtts": 1.962513464499294, "MinStdDevOfNumericAtts": 0.03287066458187007, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 0.2758066414180022, "MaxStdDevOfNumericAtts": 17064.022620508553, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": -0.37182612072708654, "Quartile3StdDevOfNumericAtts": 5.558367609570765, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 3.599184232026144, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": 1.2550885021524973, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 460.0928100373482, "Quartile1SkewnessOfNumericAtts": -0.8893352685209681, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.36753721243937876, "AutoCorrelation": -0.022384615384614674, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "ClassEntropy": null, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": -0.1190705824592162, "Dimensionality": 0.11601307189542484, "MeanSkewnessOfNumericAtts": -0.27550968038987944, "Quartile2MeansOfNumericAtts": 9.704352124183007, "EquivalentNumberOfAtts": null, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 287.6998254586639, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": -0.3162053788576069, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -0.6802017719012863, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 2.750289568430994, "MaxKurtosisOfNumericAtts": 10.7601164086971, "MinMeansOfNumericAtts": 0.10717320261437908, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 25423.66225980392, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 2.3574148111874242, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.59154929577466, "Quartile3MeansOfNumericAtts": 20.405617647058822, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -2.523578918834807, "PercentageOfSymbolicFeatures": 1.4084507042253522, "Quartile3MutualInformation": null }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "70", "type": "numeric", "distinct": "226", "missing": "0", "target": "1", "min": "4", "max": "10", "mean": "6", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "612", "missing": "0", "identifier": "1", "distr": [] }, { "name": "SssO", "index": "1", "type": "numeric", "distinct": "251", "missing": "0", "min": "0", "max": "29", "mean": "5", "stdev": "6" }, { "name": "Vindex", "index": "2", "type": "numeric", "distinct": "200", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Xindex", "index": "3", "type": "numeric", "distinct": "228", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "Chi0_EA.dm.", "index": "4", "type": "numeric", "distinct": "544", "missing": "0", "min": "2", "max": "48", "mean": "22", "stdev": "9" }, { "name": "nArOR", "index": "5", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "SpMin3_Bh.i.", "index": "6", "type": "numeric", "distinct": "321", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "O.060", "index": "7", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "Eig07_EA.bo.", "index": "8", "type": "numeric", "distinct": "411", "missing": "0", "min": "-1", "max": "3", "mean": "2", "stdev": "1" }, { "name": "SpMin3_Bh.e.", "index": "9", "type": "numeric", "distinct": "322", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "X1sol", "index": "10", "type": "numeric", "distinct": "487", "missing": "0", "min": "5", "max": "23", "mean": "14", "stdev": "3" }, { "name": "SpMax3_Bh.e.", "index": "11", "type": "numeric", "distinct": "314", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "IDET", "index": "12", "type": "numeric", "distinct": "536", "missing": "0", "min": "93", "max": "5482", "mean": "1677", "stdev": "878" }, { "name": "SpMax3_Bh.i.", "index": "13", "type": "numeric", "distinct": "299", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "P_VSA_MR_1", "index": "14", "type": "numeric", "distinct": "88", "missing": "0", "min": "2", "max": "412", "mean": "203", "stdev": "76" }, { "name": "Xu", "index": "15", "type": "numeric", "distinct": "532", "missing": "0", "min": "10", "max": "44", "mean": "28", "stdev": "6" }, { "name": "SpMax3_Bh.p.", "index": "16", "type": "numeric", "distinct": "338", "missing": "0", "min": "2", "max": "4", "mean": "4", "stdev": "0" }, { "name": "SpMax3_Bh.v.", "index": "17", "type": "numeric", "distinct": "337", "missing": "0", "min": "2", "max": "4", "mean": "4", "stdev": "0" }, { "name": "LPRS", "index": "18", "type": "numeric", "distinct": "537", "missing": "0", "min": "30", "max": "307", "mean": "152", "stdev": "49" }, { "name": "Chi0_EA.ri.", "index": "19", "type": "numeric", "distinct": "569", "missing": "0", "min": "7", "max": "35", "mean": "20", "stdev": "5" }, { "name": "MSD", "index": "20", "type": "numeric", "distinct": "517", "missing": "0", "min": "3", "max": "12", "mean": "7", "stdev": "2" }, { "name": "AECC", "index": "21", "type": "numeric", "distinct": "472", "missing": "0", "min": "4", "max": "20", "mean": "12", "stdev": "3" }, { "name": "X5", "index": "22", "type": "numeric", "distinct": "510", "missing": "0", "min": "2", "max": "17", "mean": "7", "stdev": "2" }, { "name": "X1", "index": "23", "type": "numeric", "distinct": "460", "missing": "0", "min": "5", "max": "24", "mean": "14", "stdev": "3" }, { "name": "Psi_e_0", "index": "24", "type": "numeric", "distinct": "562", "missing": "0", "min": "4", "max": "19", "mean": "11", "stdev": "3" }, { "name": "S1K", "index": "25", "type": "numeric", "distinct": "493", "missing": "0", "min": "6", "max": "32", "mean": "20", "stdev": "5" }, { "name": "Chi0_EA.bo.", "index": "26", "type": "numeric", "distinct": "518", "missing": "0", "min": "5", "max": "30", "mean": "17", "stdev": "4" }, { "name": "ON1", "index": "27", "type": "numeric", "distinct": "220", "missing": "0", "min": "2", "max": "11", "mean": "6", "stdev": "2" }, { "name": "IDMT", "index": "28", "type": "numeric", "distinct": "536", "missing": "0", "min": "566", "max": "117780", "mean": "25424", "stdev": "17064" }, { "name": "Eig05_EA", "index": "29", "type": "numeric", "distinct": "407", "missing": "0", "min": "0", "max": "3", "mean": "2", "stdev": "0" }, { "name": "SM13_AEA.bo.", "index": "30", "type": "numeric", "distinct": "407", "missing": "0", "min": "0", "max": "3", "mean": "2", "stdev": "0" }, { "name": "IDDM", "index": "31", "type": "numeric", "distinct": "301", "missing": "0", "min": "3", "max": "6", "mean": "5", "stdev": "0" }, { "name": "NssO", "index": "32", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "5", "mean": "1", "stdev": "1" }, { "name": "ATS7v", "index": "33", "type": "numeric", "distinct": "493", "missing": "0", "min": "0", "max": "5", "mean": "4", "stdev": "1" }, { "name": "SpMaxA_EA.bo.", "index": "34", "type": "numeric", "distinct": "150", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SpMaxA_AEA.ed.", "index": "35", "type": "numeric", "distinct": "197", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "SAtot", "index": "36", "type": "numeric", "distinct": "561", "missing": "0", "min": "159", "max": "820", "mean": "498", "stdev": "129" }, { "name": "Chi0_AEA.bo.", "index": "37", "type": "numeric", "distinct": "453", "missing": "0", "min": "7", "max": "34", "mean": "20", "stdev": "5" }, { "name": "Chi0_AEA.dm.", "index": "38", "type": "numeric", "distinct": "453", "missing": "0", "min": "7", "max": "34", "mean": "20", "stdev": "5" }, { "name": "Chi0_AEA.ed.", "index": "39", "type": "numeric", "distinct": "453", "missing": "0", "min": "7", "max": "34", "mean": "20", "stdev": "5" }, { "name": "Chi0_AEA.ri.", "index": "40", "type": "numeric", "distinct": "453", "missing": "0", "min": "7", "max": "34", "mean": "20", "stdev": "5" }, { "name": "Chi0_EA", "index": "41", "type": "numeric", "distinct": "453", "missing": "0", "min": "7", "max": "34", "mean": "20", "stdev": "5" }, { "name": "SpMax2_Bh.i.", "index": "42", "type": "numeric", "distinct": "240", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "SpMaxA_AEA.ri.", "index": "43", "type": "numeric", "distinct": "149", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "IDE", "index": "44", "type": "numeric", "distinct": "442", "missing": "0", "min": "2", "max": "4", "mean": "4", "stdev": "0" }, { "name": "CENT", "index": "45", "type": "numeric", "distinct": "477", "missing": "0", "min": "52", "max": "6522", "mean": "1652", "stdev": "1035" }, { "name": "CID", "index": "46", "type": "numeric", "distinct": "354", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "Chi0_EA.ed.", "index": "47", "type": "numeric", "distinct": "521", "missing": "0", "min": "4", "max": "20", "mean": "12", "stdev": "3" }, { "name": "IVDM", "index": "48", "type": "numeric", "distinct": "254", "missing": "0", "min": "3", "max": "6", "mean": "5", "stdev": "0" }, { "name": "ICR", "index": "49", "type": "numeric", "distinct": "389", "missing": "0", "min": "1", "max": "4", "mean": "3", "stdev": "0" }, { "name": "Eta_alpha", "index": "50", "type": "numeric", "distinct": "411", "missing": "0", "min": "5", "max": "23", "mean": "14", "stdev": "3" }, { "name": "VvdwMG", "index": "51", "type": "numeric", "distinct": "516", "missing": "0", "min": "72", "max": "333", "mean": "206", "stdev": "51" }, { "name": "Vx", "index": "52", "type": "numeric", "distinct": "516", "missing": "0", "min": "168", "max": "804", "mean": "494", "stdev": "124" }, { "name": "SpMaxA_EA", "index": "53", "type": "numeric", "distinct": "125", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "P_VSA_s_4", "index": "54", "type": "numeric", "distinct": "420", "missing": "0", "min": "0", "max": "174", "mean": "99", "stdev": "35" }, { "name": "XMOD", "index": "55", "type": "numeric", "distinct": "567", "missing": "0", "min": "37", "max": "154", "mean": "92", "stdev": "22" }, { "name": "X0sol", "index": "56", "type": "numeric", "distinct": "394", "missing": "0", "min": "8", "max": "32", "mean": "21", "stdev": "5" }, { "name": "ECC", "index": "57", "type": "numeric", "distinct": "359", "missing": "0", "min": "40", "max": "1023", "mean": "365", "stdev": "167" }, { "name": "SpAD_AEA.bo.", "index": "58", "type": "numeric", "distinct": "545", "missing": "0", "min": "17", "max": "87", "mean": "49", "stdev": "12" }, { "name": "ATS1p", "index": "59", "type": "numeric", "distinct": "429", "missing": "0", "min": "2", "max": "4", "mean": "4", "stdev": "0" }, { "name": "Chi1_EA.ri.", "index": "60", "type": "numeric", "distinct": "582", "missing": "0", "min": "6", "max": "30", "mean": "17", "stdev": "4" }, { "name": "S2K", "index": "61", "type": "numeric", "distinct": "528", "missing": "0", "min": "2", "max": "15", "mean": "8", "stdev": "3" }, { "name": "X2", "index": "62", "type": "numeric", "distinct": "518", "missing": "0", "min": "5", "max": "22", "mean": "13", "stdev": "3" }, { "name": "Chi1_EA.ed.", "index": "63", "type": "numeric", "distinct": "509", "missing": "0", "min": "2", "max": "10", "mean": "5", "stdev": "1" }, { "name": "X0v", "index": "64", "type": "numeric", "distinct": "550", "missing": "0", "min": "6", "max": "27", "mean": "17", "stdev": "4" }, { "name": "CSI", "index": "65", "type": "numeric", "distinct": "445", "missing": "0", "min": "84", "max": "2307", "mean": "789", "stdev": "363" }, { "name": "Eig05_AEA.ri.", "index": "66", "type": "numeric", "distinct": "427", "missing": "0", "min": "1", "max": "4", "mean": "3", "stdev": "0" }, { "name": "MDDD", "index": "67", "type": "numeric", "distinct": "530", "missing": "0", "min": "3", "max": "93", "mean": "32", "stdev": "15" }, { "name": "ATS8p", "index": "68", "type": "numeric", "distinct": "496", "missing": "0", "min": "0", "max": "5", "mean": "4", "stdev": "1" }, { "name": "Chi1_AEA.bo.", "index": "69", "type": "numeric", "distinct": "500", "missing": "0", "min": "5", "max": "28", "mean": "16", "stdev": "4" } ], "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 }