{ "data_id": "34814", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4601", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4601", "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: CHEMBL4601 (TID: 30026), and it has 553 rows and 68 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 16:21:37", "update_comment": null, "last_update": "2016-07-15 16:21:37", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3539616\/data_53415.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4601", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL4601 (TID: 30026), and it has 553 rows and 68 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": 553, "NumberOfFeatures": 70, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 69, "NumberOfSymbolicFeatures": 1, "Quartile2KurtosisOfNumericAtts": 0.5104477254386488, "Dimensionality": 0.12658227848101267, "MeanNominalAttDistinctValues": null, "Quartile2MeansOfNumericAtts": 3.0506130198915007, "EquivalentNumberOfAtts": null, "MeanSkewnessOfNumericAtts": -0.1260654888803293, "Quartile2MutualInformation": null, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 3.4248248774416417, "Quartile2SkewnessOfNumericAtts": -0.2486902936594083, "MajorityClassSize": null, "MinAttributeEntropy": null, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.4428746102467798, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -0.7782646039155847, "MinMeansOfNumericAtts": -0.07231283905967435, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxKurtosisOfNumericAtts": 11.599337364726761, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 2.4751422640904166, "MaxMeansOfNumericAtts": 203.68158047016274, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.57142857142858, "Quartile3MeansOfNumericAtts": 6.650066907775768, "MaxMutualInformation": null, "MinSkewnessOfNumericAtts": -2.022534771004234, "PercentageOfSymbolicFeatures": 1.4285714285714286, "Quartile3MutualInformation": null, "MaxNominalAttDistinctValues": null, "MinStdDevOfNumericAtts": 0.05950858184546476, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 0.3970696832480951, "MaxSkewnessOfNumericAtts": 2.747172439539455, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": -0.06878006068600673, "Quartile3StdDevOfNumericAtts": 1.8044317586335703, "MaxStdDevOfNumericAtts": 65.175340194133, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 1.029771247739602, "StdvNominalAttDistinctValues": null, "MeanAttributeEntropy": null, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanKurtosisOfNumericAtts": 1.2234862734082157, "Quartile1SkewnessOfNumericAtts": -0.6962228294371182, "MeanMeansOfNumericAtts": 10.487944911811724, "Quartile1StdDevOfNumericAtts": 0.25780186194261395, "AutoCorrelation": 0.5364148550724642, "MeanMutualInformation": null, "Quartile2AttributeEntropy": null, "ClassEntropy": null, "MeanNoiseToSignalRatio": null }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "69", "type": "numeric", "distinct": "92", "missing": "0", "target": "1", "min": "4", "max": "9", "mean": "6", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "553", "missing": "0", "identifier": "1", "distr": [] }, { "name": "N.073", "index": "1", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "CATS2D_09_AA", "index": "2", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "C.033", "index": "3", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "H.048", "index": "4", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "nArCONR2", "index": "5", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "nN", "index": "6", "type": "numeric", "distinct": "10", "missing": "0", "min": "0", "max": "9", "mean": "5", "stdev": "2" }, { "name": "SpMax4_Bh.e.", "index": "7", "type": "numeric", "distinct": "384", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "SpMin7_Bh.v.", "index": "8", "type": "numeric", "distinct": "321", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "nPyrazines", "index": "9", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "Eig07_EA.ed.", "index": "10", "type": "numeric", "distinct": "452", "missing": "0", "min": "-1", "max": "8", "mean": "4", "stdev": "1" }, { "name": "SM02_AEA.ri.", "index": "11", "type": "numeric", "distinct": "452", "missing": "0", "min": "-1", "max": "8", "mean": "4", "stdev": "1" }, { "name": "SpMin8_Bh.p.", "index": "12", "type": "numeric", "distinct": "329", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "SpMax4_Bh.i.", "index": "13", "type": "numeric", "distinct": "380", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "CATS2D_03_DA", "index": "14", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "SpMin8_Bh.i.", "index": "15", "type": "numeric", "distinct": "289", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "D.Dtr05", "index": "16", "type": "numeric", "distinct": "389", "missing": "0", "min": "0", "max": "472", "mean": "76", "stdev": "65" }, { "name": "SpMin8_Bh.e.", "index": "17", "type": "numeric", "distinct": "301", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "C.006", "index": "18", "type": "numeric", "distinct": "10", "missing": "0", "min": "0", "max": "9", "mean": "1", "stdev": "2" }, { "name": "Rperim", "index": "19", "type": "numeric", "distinct": "31", "missing": "0", "min": "6", "max": "39", "mean": "21", "stdev": "5" }, { "name": "X4", "index": "20", "type": "numeric", "distinct": "475", "missing": "0", "min": "3", "max": "19", "mean": "9", "stdev": "2" }, { "name": "Eig15_AEA.bo.", "index": "21", "type": "numeric", "distinct": "366", "missing": "0", "min": "-1", "max": "3", "mean": "1", "stdev": "1" }, { "name": "Chi1_EA.dm.", "index": "22", "type": "numeric", "distinct": "482", "missing": "0", "min": "0", "max": "76", "mean": "25", "stdev": "14" }, { "name": "NRS", "index": "23", "type": "numeric", "distinct": "6", "missing": "0", "min": "1", "max": "6", "mean": "3", "stdev": "1" }, { "name": "Chi0_EA.dm.", "index": "24", "type": "numeric", "distinct": "469", "missing": "0", "min": "0", "max": "46", "mean": "19", "stdev": "8" }, { "name": "Eig14_AEA.ri.", "index": "25", "type": "numeric", "distinct": "428", "missing": "0", "min": "-1", "max": "2", "mean": "1", "stdev": "1" }, { "name": "SpMin8_Bh.v.", "index": "26", "type": "numeric", "distinct": "326", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "SpMax1_Bh.e.", "index": "27", "type": "numeric", "distinct": "197", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "CATS2D_07_DD", "index": "28", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "4", "mean": "0", "stdev": "0" }, { "name": "Eig01_EA.bo.", "index": "29", "type": "numeric", "distinct": "294", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SM11_AEA.ri.", "index": "30", "type": "numeric", "distinct": "294", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SpDiam_EA.bo.", "index": "31", "type": "numeric", "distinct": "295", "missing": "0", "min": "7", "max": "8", "mean": "7", "stdev": "0" }, { "name": "SpMax_EA.bo.", "index": "32", "type": "numeric", "distinct": "294", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "Eig15_AEA.ed.", "index": "33", "type": "numeric", "distinct": "337", "missing": "0", "min": "0", "max": "4", "mean": "2", "stdev": "1" }, { "name": "SpMin7_Bh.e.", "index": "34", "type": "numeric", "distinct": "309", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "ATS2i", "index": "35", "type": "numeric", "distinct": "418", "missing": "0", "min": "4", "max": "5", "mean": "5", "stdev": "0" }, { "name": "Eig14_EA.bo.", "index": "36", "type": "numeric", "distinct": "392", "missing": "0", "min": "-3", "max": "2", "mean": "0", "stdev": "1" }, { "name": "SpMin7_Bh.p.", "index": "37", "type": "numeric", "distinct": "338", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "Eig06_EA.bo.", "index": "38", "type": "numeric", "distinct": "391", "missing": "0", "min": "0", "max": "3", "mean": "2", "stdev": "0" }, { "name": "ZM2Mad", "index": "39", "type": "numeric", "distinct": "537", "missing": "0", "min": "79", "max": "380", "mean": "204", "stdev": "49" }, { "name": "SsssN", "index": "40", "type": "numeric", "distinct": "167", "missing": "0", "min": "0", "max": "7", "mean": "1", "stdev": "1" }, { "name": "Xindex", "index": "41", "type": "numeric", "distinct": "229", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "Eig14_AEA.bo.", "index": "42", "type": "numeric", "distinct": "375", "missing": "0", "min": "-1", "max": "3", "mean": "1", "stdev": "1" }, { "name": "SpMin8_Bh.m.", "index": "43", "type": "numeric", "distinct": "314", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "SpMin7_Bh.i.", "index": "44", "type": "numeric", "distinct": "306", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "IC1", "index": "45", "type": "numeric", "distinct": "395", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "SpMax7_Bh.i.", "index": "46", "type": "numeric", "distinct": "325", "missing": "0", "min": "2", "max": "3", "mean": "3", "stdev": "0" }, { "name": "SpMax4_Bh.v.", "index": "47", "type": "numeric", "distinct": "384", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SpMax8_Bh.e.", "index": "48", "type": "numeric", "distinct": "328", "missing": "0", "min": "1", "max": "3", "mean": "3", "stdev": "0" }, { "name": "MDDD", "index": "49", "type": "numeric", "distinct": "490", "missing": "0", "min": "3", "max": "81", "mean": "27", "stdev": "12" }, { "name": "nHet", "index": "50", "type": "numeric", "distinct": "13", "missing": "0", "min": "2", "max": "14", "mean": "8", "stdev": "2" }, { "name": "SpMin4_Bh.i.", "index": "51", "type": "numeric", "distinct": "344", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "SpAD_EA", "index": "52", "type": "numeric", "distinct": "497", "missing": "0", "min": "19", "max": "83", "mean": "46", "stdev": "11" }, { "name": "SpMax8_Bh.i.", "index": "53", "type": "numeric", "distinct": "340", "missing": "0", "min": "2", "max": "3", "mean": "3", "stdev": "0" }, { "name": "SpMin7_Bh.m.", "index": "54", "type": "numeric", "distinct": "329", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "SpMax4_Bh.p.", "index": "55", "type": "numeric", "distinct": "398", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SpAD_AEA.ri.", "index": "56", "type": "numeric", "distinct": "541", "missing": "0", "min": "19", "max": "83", "mean": "46", "stdev": "11" }, { "name": "ATS1e", "index": "57", "type": "numeric", "distinct": "390", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "MPC03", "index": "58", "type": "numeric", "distinct": "73", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "NsssN", "index": "59", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "1" }, { "name": "Chi1_AEA.bo.", "index": "60", "type": "numeric", "distinct": "456", "missing": "0", "min": "6", "max": "26", "mean": "15", "stdev": "3" }, { "name": "Chi1_AEA.dm.", "index": "61", "type": "numeric", "distinct": "456", "missing": "0", "min": "6", "max": "26", "mean": "15", "stdev": "3" }, { "name": "Chi1_AEA.ed.", "index": "62", "type": "numeric", "distinct": "456", "missing": "0", "min": "6", "max": "26", "mean": "15", "stdev": "3" }, { "name": "Chi1_AEA.ri.", "index": "63", "type": "numeric", "distinct": "456", "missing": "0", "min": "6", "max": "26", "mean": "15", "stdev": "3" }, { "name": "Chi1_EA", "index": "64", "type": "numeric", "distinct": "456", "missing": "0", "min": "6", "max": "26", "mean": "15", "stdev": "3" }, { "name": "SpAD_AEA.bo.", "index": "65", "type": "numeric", "distinct": "503", "missing": "0", "min": "20", "max": "84", "mean": "47", "stdev": "11" }, { "name": "LLS_02", "index": "66", "type": "numeric", "distinct": "5", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "ATS3i", "index": "67", "type": "numeric", "distinct": "428", "missing": "0", "min": "4", "max": "6", "mean": "5", "stdev": "0" }, { "name": "SpMax8_Bh.v.", "index": "68", "type": "numeric", "distinct": "325", "missing": "0", "min": "1", "max": "3", "mean": "3", "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 }