{ "data_id": "35220", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL5067", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL5067", "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: CHEMBL5067 (TID: 20112), and it has 240 rows and 62 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 17:27:27", "update_comment": null, "last_update": "2016-07-15 17:27:27", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3551607\/data_52426.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL5067", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL5067 (TID: 20112), and it has 240 rows and 62 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": 240, "NumberOfFeatures": 64, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 63, "NumberOfSymbolicFeatures": 1, "Quartile2KurtosisOfNumericAtts": 1.081504831098401, "Dimensionality": 0.26666666666666666, "MeanNominalAttDistinctValues": null, "Quartile2MeansOfNumericAtts": 4.402491666666666, "EquivalentNumberOfAtts": null, "MeanSkewnessOfNumericAtts": 0.42168766743388353, "Quartile2MutualInformation": null, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 2.671092593933967, "Quartile2SkewnessOfNumericAtts": 0.6003514426635884, "MajorityClassSize": null, "MinAttributeEntropy": null, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.4489916759664581, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.7635293532402814, "MinMeansOfNumericAtts": 0.3791666666666668, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxKurtosisOfNumericAtts": 7.885357319013664, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 1.9438128257803382, "MaxMeansOfNumericAtts": 87.66459583333334, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.4375, "Quartile3MeansOfNumericAtts": 6.703395833333333, "MaxMutualInformation": null, "MinSkewnessOfNumericAtts": -2.1484540262063025, "PercentageOfSymbolicFeatures": 1.5625, "Quartile3MutualInformation": null, "MaxNominalAttDistinctValues": null, "MinStdDevOfNumericAtts": 0.03954574615621259, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 1.0541872732401836, "MaxSkewnessOfNumericAtts": 2.637798447444561, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": 0.18126754051750504, "Quartile3StdDevOfNumericAtts": 1.517885379412711, "MaxStdDevOfNumericAtts": 38.01102900639062, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 2.5822458333333334, "StdvNominalAttDistinctValues": null, "MeanAttributeEntropy": null, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanKurtosisOfNumericAtts": 1.363536646317237, "Quartile1SkewnessOfNumericAtts": -0.32171475863106425, "MeanMeansOfNumericAtts": 8.052041335978837, "Quartile1StdDevOfNumericAtts": 0.34890977001950324, "AutoCorrelation": 0.4162845188284516, "MeanMutualInformation": null, "Quartile2AttributeEntropy": null, "ClassEntropy": null, "MeanNoiseToSignalRatio": null }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "63", "type": "numeric", "distinct": "141", "missing": "0", "target": "1", "min": "4", "max": "9", "mean": "6", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "240", "missing": "0", "identifier": "1", "distr": [] }, { "name": "Eig06_EA.ri.", "index": "1", "type": "numeric", "distinct": "173", "missing": "0", "min": "1", "max": "3", "mean": "2", "stdev": "0" }, { "name": "C.024", "index": "2", "type": "numeric", "distinct": "18", "missing": "0", "min": "0", "max": "24", "mean": "8", "stdev": "4" }, { "name": "Eig07_EA.bo.", "index": "3", "type": "numeric", "distinct": "135", "missing": "0", "min": "1", "max": "4", "mean": "2", "stdev": "0" }, { "name": "SpMin2_Bh.e.", "index": "4", "type": "numeric", "distinct": "91", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "nCar", "index": "5", "type": "numeric", "distinct": "20", "missing": "0", "min": "2", "max": "40", "mean": "15", "stdev": "6" }, { "name": "PCD", "index": "6", "type": "numeric", "distinct": "188", "missing": "0", "min": "1", "max": "9", "mean": "3", "stdev": "1" }, { "name": "PCR", "index": "7", "type": "numeric", "distinct": "146", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "P_VSA_LogP_3", "index": "8", "type": "numeric", "distinct": "54", "missing": "0", "min": "0", "max": "246", "mean": "88", "stdev": "38" }, { "name": "Eig02_AEA.bo.", "index": "9", "type": "numeric", "distinct": "73", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "nR06", "index": "10", "type": "numeric", "distinct": "7", "missing": "0", "min": "1", "max": "8", "mean": "3", "stdev": "1" }, { "name": "SpMin2_Bh.p.", "index": "11", "type": "numeric", "distinct": "103", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "SpMin2_Bh.v.", "index": "12", "type": "numeric", "distinct": "99", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "TRS", "index": "13", "type": "numeric", "distinct": "21", "missing": "0", "min": "11", "max": "78", "mean": "26", "stdev": "11" }, { "name": "Eig05_EA.ri.", "index": "14", "type": "numeric", "distinct": "171", "missing": "0", "min": "1", "max": "3", "mean": "2", "stdev": "0" }, { "name": "ALOGP", "index": "15", "type": "numeric", "distinct": "217", "missing": "0", "min": "1", "max": "13", "mean": "5", "stdev": "2" }, { "name": "ALOGP2", "index": "16", "type": "numeric", "distinct": "218", "missing": "0", "min": "1", "max": "162", "mean": "28", "stdev": "26" }, { "name": "piPC10", "index": "17", "type": "numeric", "distinct": "189", "missing": "0", "min": "4", "max": "9", "mean": "7", "stdev": "1" }, { "name": "Eig05_EA.ed.", "index": "18", "type": "numeric", "distinct": "135", "missing": "0", "min": "2", "max": "9", "mean": "6", "stdev": "1" }, { "name": "SM14_AEA.dm.", "index": "19", "type": "numeric", "distinct": "135", "missing": "0", "min": "2", "max": "9", "mean": "6", "stdev": "1" }, { "name": "Eig05_AEA.dm.", "index": "20", "type": "numeric", "distinct": "145", "missing": "0", "min": "1", "max": "3", "mean": "2", "stdev": "0" }, { "name": "Qindex", "index": "21", "type": "numeric", "distinct": "29", "missing": "0", "min": "10", "max": "52", "mean": "22", "stdev": "8" }, { "name": "piPC05", "index": "22", "type": "numeric", "distinct": "178", "missing": "0", "min": "4", "max": "7", "mean": "6", "stdev": "0" }, { "name": "ATS5p", "index": "23", "type": "numeric", "distinct": "216", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "ATSC4p", "index": "24", "type": "numeric", "distinct": "230", "missing": "0", "min": "6", "max": "37", "mean": "15", "stdev": "7" }, { "name": "Eig05_AEA.ed.", "index": "25", "type": "numeric", "distinct": "119", "missing": "0", "min": "3", "max": "6", "mean": "5", "stdev": "0" }, { "name": "ATSC3v", "index": "26", "type": "numeric", "distinct": "223", "missing": "0", "min": "9", "max": "52", "mean": "19", "stdev": "10" }, { "name": "ATS4p", "index": "27", "type": "numeric", "distinct": "220", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "piPC09", "index": "28", "type": "numeric", "distinct": "189", "missing": "0", "min": "5", "max": "8", "mean": "6", "stdev": "1" }, { "name": "Eig05_EA.bo.", "index": "29", "type": "numeric", "distinct": "108", "missing": "0", "min": "1", "max": "4", "mean": "3", "stdev": "0" }, { "name": "Eta_beta_A", "index": "30", "type": "numeric", "distinct": "143", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SM15_AEA.ri.", "index": "31", "type": "numeric", "distinct": "108", "missing": "0", "min": "1", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SpMax2_Bh.v.", "index": "32", "type": "numeric", "distinct": "95", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "Eig06_EA", "index": "33", "type": "numeric", "distinct": "138", "missing": "0", "min": "1", "max": "3", "mean": "2", "stdev": "0" }, { "name": "SM14_AEA.bo.", "index": "34", "type": "numeric", "distinct": "138", "missing": "0", "min": "1", "max": "3", "mean": "2", "stdev": "0" }, { "name": "MPC05", "index": "35", "type": "numeric", "distinct": "92", "missing": "0", "min": "4", "max": "6", "mean": "5", "stdev": "0" }, { "name": "MPC10", "index": "36", "type": "numeric", "distinct": "126", "missing": "0", "min": "3", "max": "6", "mean": "5", "stdev": "1" }, { "name": "nCIC", "index": "37", "type": "numeric", "distinct": "8", "missing": "0", "min": "2", "max": "10", "mean": "4", "stdev": "2" }, { "name": "ARR", "index": "38", "type": "numeric", "distinct": "84", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "piPC07", "index": "39", "type": "numeric", "distinct": "181", "missing": "0", "min": "5", "max": "8", "mean": "6", "stdev": "1" }, { "name": "ATSC5p", "index": "40", "type": "numeric", "distinct": "234", "missing": "0", "min": "6", "max": "40", "mean": "16", "stdev": "8" }, { "name": "Eig08_AEA.ed.", "index": "41", "type": "numeric", "distinct": "138", "missing": "0", "min": "3", "max": "6", "mean": "4", "stdev": "1" }, { "name": "piPC06", "index": "42", "type": "numeric", "distinct": "183", "missing": "0", "min": "5", "max": "7", "mean": "6", "stdev": "0" }, { "name": "SpMin1_Bh.e.", "index": "43", "type": "numeric", "distinct": "75", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "Inflammat.80", "index": "44", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "ATSC5v", "index": "45", "type": "numeric", "distinct": "233", "missing": "0", "min": "9", "max": "60", "mean": "22", "stdev": "12" }, { "name": "nBnz", "index": "46", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "6", "mean": "2", "stdev": "1" }, { "name": "X3v", "index": "47", "type": "numeric", "distinct": "235", "missing": "0", "min": "3", "max": "16", "mean": "7", "stdev": "3" }, { "name": "ATS5v", "index": "48", "type": "numeric", "distinct": "212", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "X4v", "index": "49", "type": "numeric", "distinct": "229", "missing": "0", "min": "2", "max": "12", "mean": "5", "stdev": "2" }, { "name": "ATS2p", "index": "50", "type": "numeric", "distinct": "192", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "MWC05", "index": "51", "type": "numeric", "distinct": "169", "missing": "0", "min": "7", "max": "9", "mean": "8", "stdev": "0" }, { "name": "Eig05_AEA.bo.", "index": "52", "type": "numeric", "distinct": "122", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SpMax2_Bh.p.", "index": "53", "type": "numeric", "distinct": "94", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "SpMax7_Bh.m.", "index": "54", "type": "numeric", "distinct": "161", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "CATS2D_01_LL", "index": "55", "type": "numeric", "distinct": "30", "missing": "0", "min": "1", "max": "40", "mean": "11", "stdev": "7" }, { "name": "Eig07_EA.ed.", "index": "56", "type": "numeric", "distinct": "168", "missing": "0", "min": "1", "max": "8", "mean": "4", "stdev": "2" }, { "name": "SM02_AEA.ri.", "index": "57", "type": "numeric", "distinct": "168", "missing": "0", "min": "1", "max": "8", "mean": "4", "stdev": "2" }, { "name": "SM12_AEA.ed.", "index": "58", "type": "numeric", "distinct": "168", "missing": "0", "min": "22", "max": "25", "mean": "23", "stdev": "0" }, { "name": "SM03_AEA.ed.", "index": "59", "type": "numeric", "distinct": "145", "missing": "0", "min": "7", "max": "8", "mean": "7", "stdev": "0" }, { "name": "SM04_EA", "index": "60", "type": "numeric", "distinct": "118", "missing": "0", "min": "5", "max": "7", "mean": "6", "stdev": "0" }, { "name": "ATS5i", "index": "61", "type": "numeric", "distinct": "216", "missing": "0", "min": "5", "max": "6", "mean": "5", "stdev": "0" }, { "name": "SM10_AEA.ed.", "index": "62", "type": "numeric", "distinct": "170", "missing": "0", "min": "19", "max": "21", "mean": "20", "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 }