{ "data_id": "35267", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3251", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3251", "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: CHEMBL3251 (TID: 11531), and it has 89 rows and 63 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 17:34:48", "update_comment": null, "last_update": "2016-07-15 17:34:48", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3552738\/data_52502.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3251", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL3251 (TID: 11531), and it has 89 rows and 63 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": 89, "NumberOfFeatures": 65, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 64, "NumberOfSymbolicFeatures": 1, "Quartile2KurtosisOfNumericAtts": -0.054946796466710746, "Dimensionality": 0.7303370786516854, "MeanNominalAttDistinctValues": null, "Quartile2MeansOfNumericAtts": 2.42114606741573, "EquivalentNumberOfAtts": null, "MeanSkewnessOfNumericAtts": 0.6549516901891618, "Quartile2MutualInformation": null, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 3.96722661837715, "Quartile2SkewnessOfNumericAtts": 0.5793022117592107, "MajorityClassSize": null, "MinAttributeEntropy": null, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.7244102246977038, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.8912868122999844, "MinMeansOfNumericAtts": -2.4602471910112365, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxKurtosisOfNumericAtts": 70.33191353297381, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 1.0715170514854058, "MaxMeansOfNumericAtts": 55.519, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.46153846153847, "Quartile3MeansOfNumericAtts": 5.388974719101125, "MaxMutualInformation": null, "MinSkewnessOfNumericAtts": -2.3265927697712967, "PercentageOfSymbolicFeatures": 1.5384615384615385, "Quartile3MutualInformation": null, "MaxNominalAttDistinctValues": null, "MinStdDevOfNumericAtts": 0.027342916574924613, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 1.2679971785611264, "MaxSkewnessOfNumericAtts": 7.975275894408562, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": -0.7544513987019014, "Quartile3StdDevOfNumericAtts": 2.0233006917236787, "MaxStdDevOfNumericAtts": 78.36106061947537, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 0.455056179775281, "StdvNominalAttDistinctValues": null, "MeanAttributeEntropy": null, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanKurtosisOfNumericAtts": 2.879813802437522, "Quartile1SkewnessOfNumericAtts": -0.25360738225851404, "MeanMeansOfNumericAtts": 6.029337605337078, "Quartile1StdDevOfNumericAtts": 0.3234559801684399, "AutoCorrelation": 0.4872840909090908, "MeanMutualInformation": null, "Quartile2AttributeEntropy": null, "ClassEntropy": null, "MeanNoiseToSignalRatio": null }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "64", "type": "numeric", "distinct": "32", "missing": "0", "target": "1", "min": "4", "max": "7", "mean": "5", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "89", "missing": "0", "identifier": "1", "distr": [] }, { "name": "CATS2D_08_NL", "index": "1", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "6", "mean": "0", "stdev": "1" }, { "name": "Eig01_EA.bo.", "index": "2", "type": "numeric", "distinct": "46", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SM11_AEA.ri.", "index": "3", "type": "numeric", "distinct": "46", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SpDiam_EA.bo.", "index": "4", "type": "numeric", "distinct": "46", "missing": "0", "min": "7", "max": "8", "mean": "7", "stdev": "0" }, { "name": "SpMax_EA.bo.", "index": "5", "type": "numeric", "distinct": "46", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "CATS2D_01_AN", "index": "6", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "4", "mean": "0", "stdev": "1" }, { "name": "CATS2D_01_DN", "index": "7", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "1" }, { "name": "CATS2D_02_NL", "index": "8", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "CATS2D_03_NL", "index": "9", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "7", "mean": "1", "stdev": "1" }, { "name": "SpMax1_Bh.p.", "index": "10", "type": "numeric", "distinct": "60", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "C.040", "index": "11", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "nRCONHR", "index": "12", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "nBM", "index": "13", "type": "numeric", "distinct": "14", "missing": "0", "min": "7", "max": "29", "mean": "16", "stdev": "4" }, { "name": "Uc", "index": "14", "type": "numeric", "distinct": "14", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "Ui", "index": "15", "type": "numeric", "distinct": "14", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "CATS2D_07_NL", "index": "16", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "14", "mean": "0", "stdev": "2" }, { "name": "SdO", "index": "17", "type": "numeric", "distinct": "83", "missing": "0", "min": "0", "max": "60", "mean": "21", "stdev": "13" }, { "name": "SaaO", "index": "18", "type": "numeric", "distinct": "29", "missing": "0", "min": "0", "max": "6", "mean": "2", "stdev": "3" }, { "name": "Yindex", "index": "19", "type": "numeric", "distinct": "77", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "CATS2D_09_AL", "index": "20", "type": "numeric", "distinct": "10", "missing": "0", "min": "0", "max": "10", "mean": "3", "stdev": "3" }, { "name": "CATS2D_03_AL", "index": "21", "type": "numeric", "distinct": "14", "missing": "0", "min": "0", "max": "14", "mean": "6", "stdev": "5" }, { "name": "CATS2D_09_NL", "index": "22", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "NdO", "index": "23", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "5", "mean": "2", "stdev": "1" }, { "name": "O.058", "index": "24", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "5", "mean": "2", "stdev": "1" }, { "name": "SM14_EA.bo.", "index": "25", "type": "numeric", "distinct": "79", "missing": "0", "min": "19", "max": "22", "mean": "21", "stdev": "1" }, { "name": "SM15_EA.bo.", "index": "26", "type": "numeric", "distinct": "79", "missing": "0", "min": "20", "max": "24", "mean": "22", "stdev": "1" }, { "name": "SpMax2_Bh.i.", "index": "27", "type": "numeric", "distinct": "54", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "CATS2D_04_DA", "index": "28", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "8", "mean": "2", "stdev": "2" }, { "name": "SssssC", "index": "29", "type": "numeric", "distinct": "48", "missing": "0", "min": "-16", "max": "0", "mean": "-2", "stdev": "4" }, { "name": "Eig15_AEA.dm.", "index": "30", "type": "numeric", "distinct": "72", "missing": "0", "min": "-2", "max": "2", "mean": "0", "stdev": "1" }, { "name": "SpMax1_Bh.v.", "index": "31", "type": "numeric", "distinct": "57", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "SpMax1_Bh.e.", "index": "32", "type": "numeric", "distinct": "60", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "Vindex", "index": "33", "type": "numeric", "distinct": "60", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SpMax2_Bh.e.", "index": "34", "type": "numeric", "distinct": "57", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "NdssC", "index": "35", "type": "numeric", "distinct": "9", "missing": "0", "min": "0", "max": "12", "mean": "3", "stdev": "2" }, { "name": "H.051", "index": "36", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "5", "mean": "1", "stdev": "2" }, { "name": "P_VSA_MR_7", "index": "37", "type": "numeric", "distinct": "20", "missing": "0", "min": "0", "max": "151", "mean": "35", "stdev": "41" }, { "name": "Eig05_AEA.dm.", "index": "38", "type": "numeric", "distinct": "53", "missing": "0", "min": "1", "max": "3", "mean": "3", "stdev": "0" }, { "name": "D.Dtr09", "index": "39", "type": "numeric", "distinct": "35", "missing": "0", "min": "0", "max": "239", "mean": "56", "stdev": "78" }, { "name": "SRW09", "index": "40", "type": "numeric", "distinct": "18", "missing": "0", "min": "0", "max": "8", "mean": "3", "stdev": "3" }, { "name": "SM11_EA.bo.", "index": "41", "type": "numeric", "distinct": "81", "missing": "0", "min": "15", "max": "18", "mean": "17", "stdev": "1" }, { "name": "SM12_EA.bo.", "index": "42", "type": "numeric", "distinct": "79", "missing": "0", "min": "16", "max": "19", "mean": "18", "stdev": "1" }, { "name": "SpMax3_Bh.s.", "index": "43", "type": "numeric", "distinct": "28", "missing": "0", "min": "5", "max": "9", "mean": "7", "stdev": "1" }, { "name": "SpMax1_Bh.m.", "index": "44", "type": "numeric", "distinct": "49", "missing": "0", "min": "4", "max": "7", "mean": "4", "stdev": "0" }, { "name": "Xindex", "index": "45", "type": "numeric", "distinct": "70", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "MATS5i", "index": "46", "type": "numeric", "distinct": "80", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SM06_EA.bo.", "index": "47", "type": "numeric", "distinct": "72", "missing": "0", "min": "8", "max": "11", "mean": "10", "stdev": "0" }, { "name": "SM13_EA.bo.", "index": "48", "type": "numeric", "distinct": "82", "missing": "0", "min": "17", "max": "21", "mean": "19", "stdev": "1" }, { "name": "C.013", "index": "49", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "1" }, { "name": "C.027", "index": "50", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "C.028", "index": "51", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "F.083", "index": "52", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "9", "mean": "1", "stdev": "2" }, { "name": "H.049", "index": "53", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "Mi", "index": "54", "type": "numeric", "distinct": "48", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "nCRX3", "index": "55", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "1" }, { "name": "nF", "index": "56", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "9", "mean": "1", "stdev": "2" }, { "name": "nPyrimidines", "index": "57", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "NsF", "index": "58", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "9", "mean": "1", "stdev": "2" }, { "name": "nX", "index": "59", "type": "numeric", "distinct": "8", "missing": "0", "min": "0", "max": "10", "mean": "2", "stdev": "3" }, { "name": "P_VSA_e_6", "index": "60", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "135", "mean": "21", "stdev": "32" }, { "name": "SpMAD_EA.dm.", "index": "61", "type": "numeric", "distinct": "64", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "SpMax4_Bh.s.", "index": "62", "type": "numeric", "distinct": "33", "missing": "0", "min": "4", "max": "8", "mean": "6", "stdev": "1" }, { "name": "SsF", "index": "63", "type": "numeric", "distinct": "33", "missing": "0", "min": "0", "max": "116", "mean": "19", "stdev": "28" } ], "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 }