{ "data_id": "36462", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL2889", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL2889", "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: CHEMBL2889 (TID: 12388), and it has 494 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 21:18:21", "update_comment": null, "last_update": "2016-07-15 21:18:21", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3588766\/data_53631.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL2889", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL2889 (TID: 12388), and it has 494 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": 494, "NumberOfFeatures": 72, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 71, "NumberOfSymbolicFeatures": 1, "ClassEntropy": null, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "Dimensionality": 0.145748987854251, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": 1.1851783251062056, "EquivalentNumberOfAtts": null, "MeanSkewnessOfNumericAtts": 1.1862751343079752, "Quartile2MeansOfNumericAtts": 1.4096417004048583, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 1032.3193782890964, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": 1.0721202508189398, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.8053180223749279, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.6483073245670128, "MaxKurtosisOfNumericAtts": 361.1426016894635, "MinMeansOfNumericAtts": -0.7385425101214576, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 41424.706477732776, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 10.428396239359888, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.61111111111111, "Quartile3MeansOfNumericAtts": 4.954975708502024, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -7.1655750056083845, "PercentageOfSymbolicFeatures": 1.3888888888888888, "Quartile3MutualInformation": null, "MaxSkewnessOfNumericAtts": 17.667671417948203, "MinStdDevOfNumericAtts": 0.12678874463091594, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 2.032609917807513, "MaxStdDevOfNumericAtts": 72412.23882143635, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": 0.2535484887929207, "Quartile3StdDevOfNumericAtts": 1.6010551849906722, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 0.467611336032389, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": 15.720721527889753, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 618.6758602098419, "Quartile1SkewnessOfNumericAtts": -0.454979160159531, "AutoCorrelation": 0.6153732251521302, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.437432134631243 }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "71", "type": "numeric", "distinct": "245", "missing": "0", "target": "1", "min": "4", "max": "7", "mean": "5", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "494", "missing": "0", "identifier": "1", "distr": [] }, { "name": "SaaO", "index": "1", "type": "numeric", "distinct": "103", "missing": "0", "min": "0", "max": "6", "mean": "1", "stdev": "2" }, { "name": "CATS2D_09_NL", "index": "2", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "5", "mean": "1", "stdev": "1" }, { "name": "CATS2D_06_NL", "index": "3", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "5", "mean": "0", "stdev": "1" }, { "name": "CATS2D_01_AN", "index": "4", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "0", "stdev": "1" }, { "name": "CATS2D_01_DN", "index": "5", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "0", "stdev": "1" }, { "name": "CATS2D_03_DN", "index": "6", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "ZM1MulPer", "index": "7", "type": "numeric", "distinct": "469", "missing": "0", "min": "174", "max": "2036", "mean": "494", "stdev": "149" }, { "name": "nArCOOH", "index": "8", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "ZM1V", "index": "9", "type": "numeric", "distinct": "207", "missing": "0", "min": "166", "max": "1850", "mean": "458", "stdev": "137" }, { "name": "Eig09_AEA.ed.", "index": "10", "type": "numeric", "distinct": "368", "missing": "0", "min": "2", "max": "6", "mean": "4", "stdev": "1" }, { "name": "Eig08_AEA.ed.", "index": "11", "type": "numeric", "distinct": "365", "missing": "0", "min": "2", "max": "6", "mean": "4", "stdev": "1" }, { "name": "C.025", "index": "12", "type": "numeric", "distinct": "9", "missing": "0", "min": "0", "max": "11", "mean": "2", "stdev": "2" }, { "name": "DLS_cons", "index": "13", "type": "numeric", "distinct": "50", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Eig08_EA.ed.", "index": "14", "type": "numeric", "distinct": "388", "missing": "0", "min": "-2", "max": "8", "mean": "4", "stdev": "2" }, { "name": "SM03_AEA.ri.", "index": "15", "type": "numeric", "distinct": "388", "missing": "0", "min": "-2", "max": "8", "mean": "4", "stdev": "2" }, { "name": "GGI10", "index": "16", "type": "numeric", "distinct": "197", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "CATS2D_01_NL", "index": "17", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "4", "mean": "0", "stdev": "1" }, { "name": "nCar", "index": "18", "type": "numeric", "distinct": "27", "missing": "0", "min": "0", "max": "32", "mean": "13", "stdev": "6" }, { "name": "ZM1Per", "index": "19", "type": "numeric", "distinct": "469", "missing": "0", "min": "240", "max": "2525", "mean": "658", "stdev": "193" }, { "name": "Eig09_EA.ed.", "index": "20", "type": "numeric", "distinct": "378", "missing": "0", "min": "-3", "max": "8", "mean": "3", "stdev": "2" }, { "name": "SM04_AEA.ri.", "index": "21", "type": "numeric", "distinct": "378", "missing": "0", "min": "-3", "max": "8", "mean": "3", "stdev": "2" }, { "name": "Eig08_EA", "index": "22", "type": "numeric", "distinct": "335", "missing": "0", "min": "-1", "max": "3", "mean": "1", "stdev": "1" }, { "name": "SM02_AEA.dm.", "index": "23", "type": "numeric", "distinct": "335", "missing": "0", "min": "-1", "max": "3", "mean": "1", "stdev": "1" }, { "name": "CATS2D_05_AN", "index": "24", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "0", "stdev": "1" }, { "name": "CATS2D_07_NL", "index": "25", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "6", "mean": "1", "stdev": "1" }, { "name": "nROH", "index": "26", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "5", "mean": "0", "stdev": "1" }, { "name": "Eig08_AEA.dm.", "index": "27", "type": "numeric", "distinct": "371", "missing": "0", "min": "0", "max": "4", "mean": "2", "stdev": "1" }, { "name": "P_VSA_e_5", "index": "28", "type": "numeric", "distinct": "126", "missing": "0", "min": "0", "max": "742", "mean": "91", "stdev": "68" }, { "name": "Ram", "index": "29", "type": "numeric", "distinct": "18", "missing": "0", "min": "3", "max": "38", "mean": "10", "stdev": "3" }, { "name": "PCR", "index": "30", "type": "numeric", "distinct": "289", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "GGI7", "index": "31", "type": "numeric", "distinct": "309", "missing": "0", "min": "0", "max": "4", "mean": "0", "stdev": "0" }, { "name": "CATS2D_04_NL", "index": "32", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "5", "mean": "0", "stdev": "1" }, { "name": "CATS2D_03_NL", "index": "33", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "1" }, { "name": "Eig03_AEA.bo.", "index": "34", "type": "numeric", "distinct": "325", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "P_VSA_m_3", "index": "35", "type": "numeric", "distinct": "151", "missing": "0", "min": "0", "max": "742", "mean": "94", "stdev": "69" }, { "name": "nAB", "index": "36", "type": "numeric", "distinct": "20", "missing": "0", "min": "0", "max": "40", "mean": "15", "stdev": "7" }, { "name": "SpMax5_Bh.s.", "index": "37", "type": "numeric", "distinct": "310", "missing": "0", "min": "4", "max": "8", "mean": "5", "stdev": "1" }, { "name": "Eig05_AEA.ed.", "index": "38", "type": "numeric", "distinct": "363", "missing": "0", "min": "3", "max": "6", "mean": "5", "stdev": "1" }, { "name": "SdssC", "index": "39", "type": "numeric", "distinct": "400", "missing": "0", "min": "-26", "max": "6", "mean": "-1", "stdev": "2" }, { "name": "Eta_F_A", "index": "40", "type": "numeric", "distinct": "351", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "SM03_EA.ri.", "index": "41", "type": "numeric", "distinct": "348", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "Eig08_EA.ri.", "index": "42", "type": "numeric", "distinct": "362", "missing": "0", "min": "-1", "max": "3", "mean": "1", "stdev": "1" }, { "name": "CATS2D_02_NL", "index": "43", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "0", "stdev": "1" }, { "name": "ATS6m", "index": "44", "type": "numeric", "distinct": "423", "missing": "0", "min": "2", "max": "6", "mean": "4", "stdev": "0" }, { "name": "Eig10_AEA.dm.", "index": "45", "type": "numeric", "distinct": "345", "missing": "0", "min": "-1", "max": "4", "mean": "1", "stdev": "1" }, { "name": "Eta_B", "index": "46", "type": "numeric", "distinct": "254", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "0" }, { "name": "SAdon", "index": "47", "type": "numeric", "distinct": "53", "missing": "0", "min": "0", "max": "663", "mean": "50", "stdev": "46" }, { "name": "Infective.80", "index": "48", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Eig14_AEA.dm.", "index": "49", "type": "numeric", "distinct": "332", "missing": "0", "min": "-2", "max": "4", "mean": "0", "stdev": "1" }, { "name": "ZM1Kup", "index": "50", "type": "numeric", "distinct": "459", "missing": "0", "min": "165", "max": "2172", "mean": "496", "stdev": "163" }, { "name": "GGI9", "index": "51", "type": "numeric", "distinct": "256", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "Eig15_AEA.dm.", "index": "52", "type": "numeric", "distinct": "362", "missing": "0", "min": "-2", "max": "4", "mean": "0", "stdev": "1" }, { "name": "SM03_AEA.ed.", "index": "53", "type": "numeric", "distinct": "353", "missing": "0", "min": "6", "max": "9", "mean": "7", "stdev": "0" }, { "name": "CMC.80", "index": "54", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "GGI5", "index": "55", "type": "numeric", "distinct": "303", "missing": "0", "min": "0", "max": "5", "mean": "1", "stdev": "0" }, { "name": "CATS2D_07_AN", "index": "56", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "CATS2D_08_DA", "index": "57", "type": "numeric", "distinct": "8", "missing": "0", "min": "0", "max": "28", "mean": "1", "stdev": "2" }, { "name": "GMTIV", "index": "58", "type": "numeric", "distinct": "468", "missing": "0", "min": "2756", "max": "1527310", "mean": "41425", "stdev": "72412" }, { "name": "Eig04_EA.bo.", "index": "59", "type": "numeric", "distinct": "351", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SM14_AEA.ri.", "index": "60", "type": "numeric", "distinct": "351", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SM02_EA.ed.", "index": "61", "type": "numeric", "distinct": "289", "missing": "0", "min": "6", "max": "8", "mean": "7", "stdev": "0" }, { "name": "GGI4", "index": "62", "type": "numeric", "distinct": "342", "missing": "0", "min": "0", "max": "8", "mean": "2", "stdev": "1" }, { "name": "ATS3m", "index": "63", "type": "numeric", "distinct": "383", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "Eig03_EA.ed.", "index": "64", "type": "numeric", "distinct": "377", "missing": "0", "min": "5", "max": "12", "mean": "8", "stdev": "1" }, { "name": "SM12_AEA.dm.", "index": "65", "type": "numeric", "distinct": "377", "missing": "0", "min": "5", "max": "12", "mean": "8", "stdev": "1" }, { "name": "Eig03_AEA.ed.", "index": "66", "type": "numeric", "distinct": "337", "missing": "0", "min": "5", "max": "7", "mean": "6", "stdev": "0" }, { "name": "nFuranes", "index": "67", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "CATS2D_08_NL", "index": "68", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "C.034", "index": "69", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "Eig09_AEA.dm.", "index": "70", "type": "numeric", "distinct": "343", "missing": "0", "min": "-1", "max": "4", "mean": "2", "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 }