{ "data_id": "32567", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL2487", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL2487", "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: CHEMBL2487 (TID: 10656), and it has 263 rows and 66 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 10:32:48", "update_comment": null, "last_update": "2016-07-15 10:32:48", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3484291\/data_53130.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-CHEMBL2487", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL2487 (TID: 10656), and it has 263 rows and 66 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": 263, "NumberOfFeatures": 68, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 67, "NumberOfSymbolicFeatures": 1, "MaxSkewnessOfNumericAtts": 4.863704184821683, "MinStdDevOfNumericAtts": 0.0036081746537131847, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 0.8232084741608205, "MaxStdDevOfNumericAtts": 135.62170591652787, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": -1.0342564637095881, "Quartile3StdDevOfNumericAtts": 3.729031677090538, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 0.4752851711026613, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": 2.5168706319441676, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 16.808590772373872, "Quartile1SkewnessOfNumericAtts": 0.10681341051236695, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.4344581621607525, "AutoCorrelation": -0.20851908396946567, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "ClassEntropy": null, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": -0.48771922535833756, "Dimensionality": 0.2585551330798479, "MeanSkewnessOfNumericAtts": 0.7161668515169284, "Quartile2MeansOfNumericAtts": 3.3959505703422055, "EquivalentNumberOfAtts": null, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 5.939807369429202, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": 0.3642314928749167, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.6409708816780095, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.953996553679981, "MaxKurtosisOfNumericAtts": 40.107297654636454, "MinMeansOfNumericAtts": -4.626007604562737, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 420.7828897338403, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 2.6596832659625216, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.52941176470588, "Quartile3MeansOfNumericAtts": 6.961091254752851, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -4.98413717979312, "PercentageOfSymbolicFeatures": 1.4705882352941175, "Quartile3MutualInformation": null }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "67", "type": "numeric", "distinct": "212", "missing": "0", "target": "1", "min": "4", "max": "10", "mean": "7", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "263", "missing": "0", "identifier": "1", "distr": [] }, { "name": "nRCOOH", "index": "1", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "SM12_EA.dm.", "index": "2", "type": "numeric", "distinct": "50", "missing": "0", "min": "0", "max": "16", "mean": "5", "stdev": "5" }, { "name": "SM14_EA.dm.", "index": "3", "type": "numeric", "distinct": "48", "missing": "0", "min": "0", "max": "19", "mean": "6", "stdev": "6" }, { "name": "JGI6", "index": "4", "type": "numeric", "distinct": "27", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SM10_EA.dm.", "index": "5", "type": "numeric", "distinct": "54", "missing": "0", "min": "0", "max": "13", "mean": "5", "stdev": "4" }, { "name": "Eig01_EA.dm.", "index": "6", "type": "numeric", "distinct": "36", "missing": "0", "min": "0", "max": "4", "mean": "2", "stdev": "1" }, { "name": "SpMax_EA.dm.", "index": "7", "type": "numeric", "distinct": "36", "missing": "0", "min": "0", "max": "4", "mean": "2", "stdev": "1" }, { "name": "SpDiam_EA.dm.", "index": "8", "type": "numeric", "distinct": "38", "missing": "0", "min": "0", "max": "7", "mean": "3", "stdev": "2" }, { "name": "SM04_EA.dm.", "index": "9", "type": "numeric", "distinct": "78", "missing": "0", "min": "0", "max": "6", "mean": "2", "stdev": "2" }, { "name": "GATS5i", "index": "10", "type": "numeric", "distinct": "173", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "C.025", "index": "11", "type": "numeric", "distinct": "8", "missing": "0", "min": "0", "max": "8", "mean": "2", "stdev": "1" }, { "name": "GATS6e", "index": "12", "type": "numeric", "distinct": "228", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "0" }, { "name": "SpMaxA_EA.dm.", "index": "13", "type": "numeric", "distinct": "79", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "CATS2D_02_DA", "index": "14", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "7", "mean": "1", "stdev": "1" }, { "name": "CATS2D_02_LL", "index": "15", "type": "numeric", "distinct": "28", "missing": "0", "min": "0", "max": "32", "mean": "13", "stdev": "5" }, { "name": "CATS2D_02_NL", "index": "16", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "0", "stdev": "1" }, { "name": "C.040", "index": "17", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "0", "stdev": "1" }, { "name": "SpMin1_Bh.v.", "index": "18", "type": "numeric", "distinct": "103", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "CATS2D_01_LL", "index": "19", "type": "numeric", "distinct": "22", "missing": "0", "min": "0", "max": "27", "mean": "10", "stdev": "5" }, { "name": "BLTA96", "index": "20", "type": "numeric", "distinct": "154", "missing": "0", "min": "-7", "max": "0", "mean": "-5", "stdev": "1" }, { "name": "BLTF96", "index": "21", "type": "numeric", "distinct": "145", "missing": "0", "min": "-6", "max": "0", "mean": "-4", "stdev": "1" }, { "name": "MLOGP", "index": "22", "type": "numeric", "distinct": "187", "missing": "0", "min": "-1", "max": "6", "mean": "3", "stdev": "1" }, { "name": "MLOGP2", "index": "23", "type": "numeric", "distinct": "191", "missing": "0", "min": "0", "max": "35", "mean": "12", "stdev": "6" }, { "name": "SM05_EA.dm.", "index": "24", "type": "numeric", "distinct": "28", "missing": "0", "min": "0", "max": "7", "mean": "2", "stdev": "2" }, { "name": "SM07_EA.dm.", "index": "25", "type": "numeric", "distinct": "30", "missing": "0", "min": "0", "max": "9", "mean": "3", "stdev": "3" }, { "name": "BLTD48", "index": "26", "type": "numeric", "distinct": "151", "missing": "0", "min": "-7", "max": "0", "mean": "-5", "stdev": "1" }, { "name": "Eig02_EA.ed.", "index": "27", "type": "numeric", "distinct": "120", "missing": "0", "min": "5", "max": "14", "mean": "10", "stdev": "2" }, { "name": "SM11_AEA.dm.", "index": "28", "type": "numeric", "distinct": "120", "missing": "0", "min": "5", "max": "14", "mean": "10", "stdev": "2" }, { "name": "CATS2D_03_NL", "index": "29", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "4", "mean": "0", "stdev": "1" }, { "name": "SM09_EA.dm.", "index": "30", "type": "numeric", "distinct": "27", "missing": "0", "min": "0", "max": "12", "mean": "3", "stdev": "4" }, { "name": "SM11_EA.dm.", "index": "31", "type": "numeric", "distinct": "27", "missing": "0", "min": "0", "max": "15", "mean": "4", "stdev": "5" }, { "name": "SM13_EA.dm.", "index": "32", "type": "numeric", "distinct": "27", "missing": "0", "min": "0", "max": "17", "mean": "5", "stdev": "5" }, { "name": "SM15_EA.dm.", "index": "33", "type": "numeric", "distinct": "26", "missing": "0", "min": "0", "max": "20", "mean": "6", "stdev": "6" }, { "name": "SpDiam_EA.ed.", "index": "34", "type": "numeric", "distinct": "102", "missing": "0", "min": "12", "max": "27", "mean": "19", "stdev": "4" }, { "name": "SM08_EA.dm.", "index": "35", "type": "numeric", "distinct": "63", "missing": "0", "min": "0", "max": "11", "mean": "4", "stdev": "3" }, { "name": "SpMax8_Bh.s.", "index": "36", "type": "numeric", "distinct": "160", "missing": "0", "min": "2", "max": "6", "mean": "4", "stdev": "0" }, { "name": "CATS2D_05_AL", "index": "37", "type": "numeric", "distinct": "20", "missing": "0", "min": "0", "max": "26", "mean": "6", "stdev": "5" }, { "name": "C.004", "index": "38", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "0" }, { "name": "nCq", "index": "39", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "0" }, { "name": "ON0", "index": "40", "type": "numeric", "distinct": "96", "missing": "0", "min": "6", "max": "29", "mean": "14", "stdev": "5" }, { "name": "Eig02_AEA.ed.", "index": "41", "type": "numeric", "distinct": "98", "missing": "0", "min": "5", "max": "8", "mean": "6", "stdev": "1" }, { "name": "SM14_EA.ri.", "index": "42", "type": "numeric", "distinct": "226", "missing": "0", "min": "14", "max": "19", "mean": "16", "stdev": "1" }, { "name": "SM15_EA.ri.", "index": "43", "type": "numeric", "distinct": "228", "missing": "0", "min": "15", "max": "20", "mean": "17", "stdev": "1" }, { "name": "Eig07_AEA.ed.", "index": "44", "type": "numeric", "distinct": "126", "missing": "0", "min": "1", "max": "6", "mean": "4", "stdev": "1" }, { "name": "CATS2D_04_LL", "index": "45", "type": "numeric", "distinct": "22", "missing": "0", "min": "0", "max": "23", "mean": "8", "stdev": "4" }, { "name": "VvdwZAZ", "index": "46", "type": "numeric", "distinct": "210", "missing": "0", "min": "122", "max": "744", "mean": "354", "stdev": "118" }, { "name": "ATS6s", "index": "47", "type": "numeric", "distinct": "245", "missing": "0", "min": "3", "max": "7", "mean": "6", "stdev": "1" }, { "name": "IDDM", "index": "48", "type": "numeric", "distinct": "139", "missing": "0", "min": "3", "max": "6", "mean": "5", "stdev": "0" }, { "name": "JGI8", "index": "49", "type": "numeric", "distinct": "18", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "ZM1MulPer", "index": "50", "type": "numeric", "distinct": "227", "missing": "0", "min": "188", "max": "847", "mean": "421", "stdev": "136" }, { "name": "nCrq", "index": "51", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "0" }, { "name": "GATS6s", "index": "52", "type": "numeric", "distinct": "232", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "0" }, { "name": "Psi_e_0", "index": "53", "type": "numeric", "distinct": "233", "missing": "0", "min": "4", "max": "21", "mean": "10", "stdev": "3" }, { "name": "ATS2s", "index": "54", "type": "numeric", "distinct": "222", "missing": "0", "min": "5", "max": "7", "mean": "6", "stdev": "0" }, { "name": "HDcpx", "index": "55", "type": "numeric", "distinct": "127", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "F.084", "index": "56", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "0" }, { "name": "SdssC", "index": "57", "type": "numeric", "distinct": "130", "missing": "0", "min": "-3", "max": "2", "mean": "0", "stdev": "1" }, { "name": "ATS3s", "index": "58", "type": "numeric", "distinct": "232", "missing": "0", "min": "5", "max": "7", "mean": "6", "stdev": "0" }, { "name": "JGI5", "index": "59", "type": "numeric", "distinct": "28", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "IDM", "index": "60", "type": "numeric", "distinct": "171", "missing": "0", "min": "5", "max": "10", "mean": "8", "stdev": "1" }, { "name": "GGI3", "index": "61", "type": "numeric", "distinct": "85", "missing": "0", "min": "0", "max": "5", "mean": "2", "stdev": "1" }, { "name": "CATS2D_07_NL", "index": "62", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "0", "stdev": "1" }, { "name": "SpMax1_Bh.s.", "index": "63", "type": "numeric", "distinct": "80", "missing": "0", "min": "5", "max": "9", "mean": "7", "stdev": "1" }, { "name": "SpMin2_Bh.e.", "index": "64", "type": "numeric", "distinct": "102", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "Psi_i_s", "index": "65", "type": "numeric", "distinct": "204", "missing": "0", "min": "32", "max": "122", "mean": "63", "stdev": "21" }, { "name": "Eta_epsi", "index": "66", "type": "numeric", "distinct": "206", "missing": "0", "min": "11", "max": "62", "mean": "30", "stdev": "11" } ], "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 }