{ "data_id": "27847", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL2068", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL2068", "version": 8, "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: CHEMBL2068 (TID: 30008), and it has 837 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": "2016-07-14 22:32:41", "update_comment": null, "last_update": "2016-07-14 22:32:41", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3342273\/data_53572.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-CHEMBL2068", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL2068 (TID: 30008), and it has 837 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": 837, "NumberOfFeatures": 71, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 70, "NumberOfSymbolicFeatures": 1, "MaxSkewnessOfNumericAtts": 12.492084655468304, "MinStdDevOfNumericAtts": 0.013600724379898753, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 5.294996260582411, "MaxStdDevOfNumericAtts": 201089.2498036818, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": 1.5130559719090448, "Quartile3StdDevOfNumericAtts": 3.0669184681865356, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 1.840468339307049, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": 24.065644727321672, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 898.3795171360304, "Quartile1SkewnessOfNumericAtts": -0.18437207241613807, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.3867540331432828, "AutoCorrelation": 0.47201435406698633, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "ClassEntropy": null, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": 3.3036760203321096, "Dimensionality": 0.08482676224611709, "MeanSkewnessOfNumericAtts": 2.3964012431411077, "Quartile2MeansOfNumericAtts": 3.0429689366786143, "EquivalentNumberOfAtts": null, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 5694.657469441206, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": 0.5514241295991945, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -0.12070966164633878, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.816107148793217, "MaxKurtosisOfNumericAtts": 160.62685114714668, "MinMeansOfNumericAtts": 0.07481720430107527, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 31025.00955794491, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 41.30497567286249, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.59154929577466, "Quartile3MeansOfNumericAtts": 6.151924731182795, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -1.9198214861745375, "PercentageOfSymbolicFeatures": 1.4084507042253522, "Quartile3MutualInformation": null }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "70", "type": "numeric", "distinct": "113", "missing": "0", "target": "1", "min": "4", "max": "9", "mean": "6", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "837", "missing": "0", "identifier": "1", "distr": [] }, { "name": "CATS2D_08_DP", "index": "1", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "8", "mean": "0", "stdev": "1" }, { "name": "DECC", "index": "2", "type": "numeric", "distinct": "569", "missing": "0", "min": "0", "max": "11", "mean": "2", "stdev": "1" }, { "name": "CATS2D_05_DL", "index": "3", "type": "numeric", "distinct": "25", "missing": "0", "min": "0", "max": "53", "mean": "4", "stdev": "5" }, { "name": "AECC", "index": "4", "type": "numeric", "distinct": "614", "missing": "0", "min": "4", "max": "59", "mean": "12", "stdev": "5" }, { "name": "Xindex", "index": "5", "type": "numeric", "distinct": "270", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "Eta_beta_A", "index": "6", "type": "numeric", "distinct": "316", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "PDI", "index": "7", "type": "numeric", "distinct": "198", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "D.Dtr06", "index": "8", "type": "numeric", "distinct": "747", "missing": "0", "min": "0", "max": "6438", "mean": "287", "stdev": "458" }, { "name": "Chi1_EA.dm.", "index": "9", "type": "numeric", "distinct": "719", "missing": "0", "min": "0", "max": "127", "mean": "25", "stdev": "16" }, { "name": "IDE", "index": "10", "type": "numeric", "distinct": "565", "missing": "0", "min": "2", "max": "6", "mean": "4", "stdev": "0" }, { "name": "Eta_betaP_A", "index": "11", "type": "numeric", "distinct": "287", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Chi0_EA.dm.", "index": "12", "type": "numeric", "distinct": "711", "missing": "0", "min": "0", "max": "144", "mean": "19", "stdev": "14" }, { "name": "CATS2D_02_DA", "index": "13", "type": "numeric", "distinct": "15", "missing": "0", "min": "0", "max": "28", "mean": "2", "stdev": "3" }, { "name": "Eig03_EA.bo.", "index": "14", "type": "numeric", "distinct": "471", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SM13_AEA.ri.", "index": "15", "type": "numeric", "distinct": "471", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "CATS2D_08_DD", "index": "16", "type": "numeric", "distinct": "10", "missing": "0", "min": "0", "max": "11", "mean": "0", "stdev": "1" }, { "name": "Eig09_AEA.dm.", "index": "17", "type": "numeric", "distinct": "554", "missing": "0", "min": "-1", "max": "4", "mean": "1", "stdev": "1" }, { "name": "MSD", "index": "18", "type": "numeric", "distinct": "696", "missing": "0", "min": "3", "max": "34", "mean": "7", "stdev": "3" }, { "name": "Eig08_EA.bo.", "index": "19", "type": "numeric", "distinct": "543", "missing": "0", "min": "-1", "max": "3", "mean": "2", "stdev": "1" }, { "name": "Eig08_AEA.ri.", "index": "20", "type": "numeric", "distinct": "550", "missing": "0", "min": "0", "max": "4", "mean": "2", "stdev": "0" }, { "name": "ATS2m", "index": "21", "type": "numeric", "distinct": "542", "missing": "0", "min": "3", "max": "6", "mean": "4", "stdev": "0" }, { "name": "SssNH", "index": "22", "type": "numeric", "distinct": "544", "missing": "0", "min": "0", "max": "64", "mean": "4", "stdev": "6" }, { "name": "UNIP", "index": "23", "type": "numeric", "distinct": "216", "missing": "0", "min": "19", "max": "4291", "mean": "154", "stdev": "325" }, { "name": "Eig08_AEA.bo.", "index": "24", "type": "numeric", "distinct": "503", "missing": "0", "min": "0", "max": "4", "mean": "3", "stdev": "0" }, { "name": "Yindex", "index": "25", "type": "numeric", "distinct": "422", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "Eig11_EA.ed.", "index": "26", "type": "numeric", "distinct": "560", "missing": "0", "min": "-6", "max": "9", "mean": "2", "stdev": "2" }, { "name": "SM06_AEA.ri.", "index": "27", "type": "numeric", "distinct": "560", "missing": "0", "min": "-6", "max": "9", "mean": "2", "stdev": "2" }, { "name": "Vindex", "index": "28", "type": "numeric", "distinct": "216", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Eig09_AEA.ed.", "index": "29", "type": "numeric", "distinct": "544", "missing": "0", "min": "1", "max": "6", "mean": "4", "stdev": "1" }, { "name": "Eig08_EA.ed.", "index": "30", "type": "numeric", "distinct": "622", "missing": "0", "min": "-3", "max": "9", "mean": "4", "stdev": "2" }, { "name": "SM03_AEA.ri.", "index": "31", "type": "numeric", "distinct": "622", "missing": "0", "min": "-3", "max": "9", "mean": "4", "stdev": "2" }, { "name": "Eig08_EA.ri.", "index": "32", "type": "numeric", "distinct": "546", "missing": "0", "min": "-1", "max": "3", "mean": "1", "stdev": "0" }, { "name": "ATS4m", "index": "33", "type": "numeric", "distinct": "593", "missing": "0", "min": "3", "max": "6", "mean": "4", "stdev": "0" }, { "name": "GMTI", "index": "34", "type": "numeric", "distinct": "737", "missing": "0", "min": "583", "max": "2929860", "mean": "31025", "stdev": "201089" }, { "name": "Eig10_EA.bo.", "index": "35", "type": "numeric", "distinct": "539", "missing": "0", "min": "-2", "max": "3", "mean": "1", "stdev": "1" }, { "name": "Eig06_EA", "index": "36", "type": "numeric", "distinct": "521", "missing": "0", "min": "0", "max": "3", "mean": "2", "stdev": "0" }, { "name": "SM14_AEA.bo.", "index": "37", "type": "numeric", "distinct": "521", "missing": "0", "min": "0", "max": "3", "mean": "2", "stdev": "0" }, { "name": "Eig07_AEA.dm.", "index": "38", "type": "numeric", "distinct": "566", "missing": "0", "min": "0", "max": "4", "mean": "2", "stdev": "1" }, { "name": "SpMax7_Bh.p.", "index": "39", "type": "numeric", "distinct": "447", "missing": "0", "min": "1", "max": "4", "mean": "3", "stdev": "0" }, { "name": "HVcpx", "index": "40", "type": "numeric", "distinct": "556", "missing": "0", "min": "2", "max": "6", "mean": "3", "stdev": "0" }, { "name": "Eig10_AEA.bo.", "index": "41", "type": "numeric", "distinct": "513", "missing": "0", "min": "0", "max": "4", "mean": "2", "stdev": "1" }, { "name": "X4", "index": "42", "type": "numeric", "distinct": "719", "missing": "0", "min": "3", "max": "55", "mean": "9", "stdev": "4" }, { "name": "NssNH", "index": "43", "type": "numeric", "distinct": "10", "missing": "0", "min": "0", "max": "25", "mean": "1", "stdev": "2" }, { "name": "X5", "index": "44", "type": "numeric", "distinct": "717", "missing": "0", "min": "2", "max": "43", "mean": "7", "stdev": "4" }, { "name": "SpMax7_Bh.m.", "index": "45", "type": "numeric", "distinct": "477", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "ATS1m", "index": "46", "type": "numeric", "distinct": "526", "missing": "0", "min": "3", "max": "6", "mean": "4", "stdev": "0" }, { "name": "Eig08_AEA.dm.", "index": "47", "type": "numeric", "distinct": "548", "missing": "0", "min": "-1", "max": "4", "mean": "2", "stdev": "1" }, { "name": "X2sol", "index": "48", "type": "numeric", "distinct": "705", "missing": "0", "min": "5", "max": "93", "mean": "13", "stdev": "7" }, { "name": "JGI2", "index": "49", "type": "numeric", "distinct": "75", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Eig05_EA.ed.", "index": "50", "type": "numeric", "distinct": "672", "missing": "0", "min": "2", "max": "10", "mean": "6", "stdev": "1" }, { "name": "SM14_AEA.dm.", "index": "51", "type": "numeric", "distinct": "672", "missing": "0", "min": "2", "max": "10", "mean": "6", "stdev": "1" }, { "name": "Eta_C_A", "index": "52", "type": "numeric", "distinct": "424", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "Eig06_EA.ed.", "index": "53", "type": "numeric", "distinct": "673", "missing": "0", "min": "-1", "max": "10", "mean": "5", "stdev": "1" }, { "name": "SM15_AEA.dm.", "index": "54", "type": "numeric", "distinct": "673", "missing": "0", "min": "-1", "max": "10", "mean": "5", "stdev": "1" }, { "name": "SMTI", "index": "55", "type": "numeric", "distinct": "739", "missing": "0", "min": "637", "max": "2830240", "mean": "29860", "stdev": "194356" }, { "name": "Eig05_EA.ri.", "index": "56", "type": "numeric", "distinct": "575", "missing": "0", "min": "1", "max": "3", "mean": "2", "stdev": "0" }, { "name": "LPRS", "index": "57", "type": "numeric", "distinct": "749", "missing": "0", "min": "35", "max": "1901", "mean": "159", "stdev": "151" }, { "name": "Eig07_EA.bo.", "index": "58", "type": "numeric", "distinct": "537", "missing": "0", "min": "-1", "max": "3", "mean": "2", "stdev": "0" }, { "name": "CATS2D_04_PL", "index": "59", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "5", "mean": "1", "stdev": "1" }, { "name": "SpAD_EA.bo.", "index": "60", "type": "numeric", "distinct": "750", "missing": "0", "min": "23", "max": "394", "mean": "65", "stdev": "31" }, { "name": "Eig12_AEA.ed.", "index": "61", "type": "numeric", "distinct": "502", "missing": "0", "min": "0", "max": "6", "mean": "3", "stdev": "1" }, { "name": "Eig06_EA.bo.", "index": "62", "type": "numeric", "distinct": "546", "missing": "0", "min": "0", "max": "4", "mean": "2", "stdev": "0" }, { "name": "CSI", "index": "63", "type": "numeric", "distinct": "545", "missing": "0", "min": "94", "max": "26619", "mean": "937", "stdev": "1997" }, { "name": "SpMax1_Bh.p.", "index": "64", "type": "numeric", "distinct": "264", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "IAC", "index": "65", "type": "numeric", "distinct": "705", "missing": "0", "min": "32", "max": "702", "mean": "85", "stdev": "57" }, { "name": "TIC0", "index": "66", "type": "numeric", "distinct": "705", "missing": "0", "min": "32", "max": "702", "mean": "85", "stdev": "57" }, { "name": "C.025", "index": "67", "type": "numeric", "distinct": "9", "missing": "0", "min": "0", "max": "8", "mean": "3", "stdev": "2" }, { "name": "Eig10_EA.ed.", "index": "68", "type": "numeric", "distinct": "604", "missing": "0", "min": "-5", "max": "9", "mean": "2", "stdev": "2" }, { "name": "SM05_AEA.ri.", "index": "69", "type": "numeric", "distinct": "604", "missing": "0", "min": "-5", "max": "9", "mean": "2", "stdev": "2" } ], "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 }