{ "data_id": "32710", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4439", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4439", "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: CHEMBL4439 (TID: 13004), and it has 692 rows and 67 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 10:55:00", "update_comment": null, "last_update": "2016-07-15 10:55:00", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3487844\/data_53245.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-CHEMBL4439", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL4439 (TID: 13004), and it has 692 rows and 67 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": 692, "NumberOfFeatures": 69, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 68, "NumberOfSymbolicFeatures": 1, "MaxSkewnessOfNumericAtts": 9.760920419383272, "MinStdDevOfNumericAtts": 0.00402936357387905, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 1.9003072137698318, "MaxStdDevOfNumericAtts": 33.38839574469468, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": 0.6237827913285958, "Quartile3StdDevOfNumericAtts": 1.3067381365773734, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 0.48482658959537583, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": 6.613425049291806, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 9.922643509860592, "Quartile1SkewnessOfNumericAtts": 0.5118111684741595, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.21605249241445035, "AutoCorrelation": 0.14314037626628087, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "ClassEntropy": null, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": 3.985466619111821, "Dimensionality": 0.09971098265895954, "MeanSkewnessOfNumericAtts": 1.4633010756784632, "Quartile2MeansOfNumericAtts": 4.20368063583815, "EquivalentNumberOfAtts": null, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 3.4919202768724262, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": 1.2164807293326065, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.5084484125244324, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.3704188182306478, "MaxKurtosisOfNumericAtts": 126.35076007947448, "MinMeansOfNumericAtts": 0.005251445086705204, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 101.9568598265896, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 7.219159117423857, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.55072463768117, "Quartile3MeansOfNumericAtts": 7.1216799132948, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -1.0966030631294075, "PercentageOfSymbolicFeatures": 1.4492753623188406, "Quartile3MutualInformation": null }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "68", "type": "numeric", "distinct": "382", "missing": "0", "target": "1", "min": "-2", "max": "9", "mean": "6", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "692", "missing": "0", "identifier": "1", "distr": [] }, { "name": "SaasC", "index": "1", "type": "numeric", "distinct": "636", "missing": "0", "min": "-4", "max": "10", "mean": "5", "stdev": "2" }, { "name": "Eig01_EA.bo.", "index": "2", "type": "numeric", "distinct": "193", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SM11_AEA.ri.", "index": "3", "type": "numeric", "distinct": "193", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SpDiam_EA.bo.", "index": "4", "type": "numeric", "distinct": "193", "missing": "0", "min": "7", "max": "8", "mean": "7", "stdev": "0" }, { "name": "SpMax_EA.bo.", "index": "5", "type": "numeric", "distinct": "193", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "JGI5", "index": "6", "type": "numeric", "distinct": "22", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Eig02_EA.bo.", "index": "7", "type": "numeric", "distinct": "276", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SM12_AEA.ri.", "index": "8", "type": "numeric", "distinct": "276", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "C.028", "index": "9", "type": "numeric", "distinct": "8", "missing": "0", "min": "0", "max": "7", "mean": "2", "stdev": "1" }, { "name": "Eig01_EA.ed.", "index": "10", "type": "numeric", "distinct": "234", "missing": "0", "min": "9", "max": "17", "mean": "11", "stdev": "1" }, { "name": "SM10_AEA.dm.", "index": "11", "type": "numeric", "distinct": "234", "missing": "0", "min": "9", "max": "17", "mean": "11", "stdev": "1" }, { "name": "SpMax_EA.ed.", "index": "12", "type": "numeric", "distinct": "234", "missing": "0", "min": "9", "max": "17", "mean": "11", "stdev": "1" }, { "name": "NdS", "index": "13", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "S.108", "index": "14", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "ATSC8s", "index": "15", "type": "numeric", "distinct": "677", "missing": "0", "min": "8", "max": "197", "mean": "43", "stdev": "22" }, { "name": "ATSC5s", "index": "16", "type": "numeric", "distinct": "679", "missing": "0", "min": "8", "max": "198", "mean": "43", "stdev": "27" }, { "name": "CATS2D_09_AP", "index": "17", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "0", "stdev": "1" }, { "name": "Eig01_AEA.ri.", "index": "18", "type": "numeric", "distinct": "220", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SpMax_AEA.ri.", "index": "19", "type": "numeric", "distinct": "220", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "MATS6i", "index": "20", "type": "numeric", "distinct": "318", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "nBnz", "index": "21", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "SAacc", "index": "22", "type": "numeric", "distinct": "272", "missing": "0", "min": "33", "max": "218", "mean": "102", "stdev": "33" }, { "name": "SpDiam_EA.ri.", "index": "23", "type": "numeric", "distinct": "217", "missing": "0", "min": "5", "max": "6", "mean": "5", "stdev": "0" }, { "name": "ATSC5e", "index": "24", "type": "numeric", "distinct": "429", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "CATS2D_01_AA", "index": "25", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "1" }, { "name": "nHAcc", "index": "26", "type": "numeric", "distinct": "12", "missing": "0", "min": "2", "max": "13", "mean": "6", "stdev": "2" }, { "name": "MAXDP", "index": "27", "type": "numeric", "distinct": "603", "missing": "0", "min": "1", "max": "8", "mean": "4", "stdev": "2" }, { "name": "nCb.", "index": "28", "type": "numeric", "distinct": "11", "missing": "0", "min": "0", "max": "11", "mean": "3", "stdev": "2" }, { "name": "SpDiam_EA.ed.", "index": "29", "type": "numeric", "distinct": "282", "missing": "0", "min": "16", "max": "27", "mean": "19", "stdev": "1" }, { "name": "CATS2D_04_AP", "index": "30", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "0" }, { "name": "SpMax1_Bh.m.", "index": "31", "type": "numeric", "distinct": "204", "missing": "0", "min": "4", "max": "11", "mean": "4", "stdev": "0" }, { "name": "nArNR2", "index": "32", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "nCbH", "index": "33", "type": "numeric", "distinct": "15", "missing": "0", "min": "0", "max": "17", "mean": "5", "stdev": "3" }, { "name": "TPSA.NO.", "index": "34", "type": "numeric", "distinct": "266", "missing": "0", "min": "28", "max": "148", "mean": "82", "stdev": "24" }, { "name": "Mi", "index": "35", "type": "numeric", "distinct": "53", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Eig01_AEA.bo.", "index": "36", "type": "numeric", "distinct": "180", "missing": "0", "min": "4", "max": "5", "mean": "5", "stdev": "0" }, { "name": "SpMax_AEA.bo.", "index": "37", "type": "numeric", "distinct": "180", "missing": "0", "min": "4", "max": "5", "mean": "5", "stdev": "0" }, { "name": "C.", "index": "38", "type": "numeric", "distinct": "130", "missing": "0", "min": "35", "max": "53", "mean": "45", "stdev": "4" }, { "name": "Eig01_AEA.ed.", "index": "39", "type": "numeric", "distinct": "183", "missing": "0", "min": "6", "max": "9", "mean": "7", "stdev": "0" }, { "name": "SpMax_AEA.ed.", "index": "40", "type": "numeric", "distinct": "183", "missing": "0", "min": "6", "max": "9", "mean": "7", "stdev": "0" }, { "name": "C.032", "index": "41", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "GGI5", "index": "42", "type": "numeric", "distinct": "267", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "0" }, { "name": "SpMax8_Bh.s.", "index": "43", "type": "numeric", "distinct": "382", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "nPyridines", "index": "44", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "N.071", "index": "45", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "SAdon", "index": "46", "type": "numeric", "distinct": "47", "missing": "0", "min": "0", "max": "151", "mean": "33", "stdev": "28" }, { "name": "CATS2D_03_AP", "index": "47", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "SsNH2", "index": "48", "type": "numeric", "distinct": "127", "missing": "0", "min": "0", "max": "12", "mean": "2", "stdev": "3" }, { "name": "nPyrimidines", "index": "49", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "CATS2D_08_DA", "index": "50", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "5", "mean": "1", "stdev": "1" }, { "name": "ATSC4e", "index": "51", "type": "numeric", "distinct": "405", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "ATSC4s", "index": "52", "type": "numeric", "distinct": "677", "missing": "0", "min": "8", "max": "290", "mean": "44", "stdev": "28" }, { "name": "SdO", "index": "53", "type": "numeric", "distinct": "316", "missing": "0", "min": "0", "max": "54", "mean": "7", "stdev": "9" }, { "name": "Eig02_AEA.ed.", "index": "54", "type": "numeric", "distinct": "252", "missing": "0", "min": "6", "max": "8", "mean": "6", "stdev": "0" }, { "name": "TIE", "index": "55", "type": "numeric", "distinct": "676", "missing": "0", "min": "15", "max": "126", "mean": "45", "stdev": "17" }, { "name": "CATS2D_08_DD", "index": "56", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "ATSC8e", "index": "57", "type": "numeric", "distinct": "400", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "C.033", "index": "58", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "ATS4s", "index": "59", "type": "numeric", "distinct": "483", "missing": "0", "min": "5", "max": "7", "mean": "6", "stdev": "0" }, { "name": "SpMax7_Bh.s.", "index": "60", "type": "numeric", "distinct": "397", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "P_VSA_LogP_6", "index": "61", "type": "numeric", "distinct": "92", "missing": "0", "min": "0", "max": "78", "mean": "13", "stdev": "12" }, { "name": "Eig01_EA.ri.", "index": "62", "type": "numeric", "distinct": "214", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SpMax_EA.ri.", "index": "63", "type": "numeric", "distinct": "214", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "Eig03_EA.ed.", "index": "64", "type": "numeric", "distinct": "373", "missing": "0", "min": "5", "max": "12", "mean": "8", "stdev": "1" }, { "name": "SM12_AEA.dm.", "index": "65", "type": "numeric", "distinct": "373", "missing": "0", "min": "5", "max": "12", "mean": "8", "stdev": "1" }, { "name": "SpMax3_Bh.s.", "index": "66", "type": "numeric", "distinct": "284", "missing": "0", "min": "5", "max": "8", "mean": "5", "stdev": "1" }, { "name": "SpDiam_AEA.bo.", "index": "67", "type": "numeric", "distinct": "318", "missing": "0", "min": "5", "max": "6", "mean": "5", "stdev": "0" } ], "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 }