{ "data_id": "24584", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL1821", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL1821", "version": 8, "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: CHEMBL1821 (TID: 214), and it has 770 rows and 69 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": "2016-07-14 14:58:40", "update_comment": null, "last_update": "2016-07-14 14:58:40", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3249345\/data_53455.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL1821", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL1821 (TID: 214), and it has 770 rows and 69 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": 770, "NumberOfFeatures": 71, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 70, "NumberOfSymbolicFeatures": 1, "RandomTreeDepth3ErrRate": null, "J48.0001.Kappa": null, "MeanMutualInformation": null, "NaiveBayesKappa": null, "Quartile1MeansOfNumericAtts": 2.0377532467532466, "REPTreeDepth1AUC": null, "CfsSubsetEval_NaiveBayesErrRate": null, "RandomTreeDepth3Kappa": null, "J48.001.AUC": null, "MeanNoiseToSignalRatio": null, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "REPTreeDepth1ErrRate": null, "CfsSubsetEval_NaiveBayesKappa": null, "StdvNominalAttDistinctValues": null, "J48.001.ErrRate": null, "MeanNominalAttDistinctValues": null, "Quartile1SkewnessOfNumericAtts": -1.1965456833631307, "REPTreeDepth1Kappa": null, "CfsSubsetEval_kNN1NAUC": null, "kNN1NAUC": null, "J48.001.Kappa": null, "MeanSkewnessOfNumericAtts": 0.11635058199419546, "Quartile1StdDevOfNumericAtts": 0.5593738311505116, "REPTreeDepth2AUC": null, "CfsSubsetEval_kNN1NErrRate": null, "kNN1NErrRate": null, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 1068.3329169042504, "Quartile2AttributeEntropy": null, "REPTreeDepth2ErrRate": null, "CfsSubsetEval_kNN1NKappa": null, "kNN1NKappa": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2KurtosisOfNumericAtts": 1.5717344786259182, "REPTreeDepth2Kappa": null, "ClassEntropy": null, "DecisionStumpAUC": null, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -0.20039352515958564, "Quartile2MeansOfNumericAtts": 4.321116883116883, "REPTreeDepth3AUC": null, "DecisionStumpErrRate": null, "MaxKurtosisOfNumericAtts": 171.1364706051437, "MinMeansOfNumericAtts": -0.03412337662337674, "Quartile2MutualInformation": null, "REPTreeDepth3ErrRate": null, "DecisionStumpKappa": null, "MaxMeansOfNumericAtts": 30260.198701298657, "MinMutualInformation": null, "Quartile2SkewnessOfNumericAtts": -0.04779843161634936, "REPTreeDepth3Kappa": null, "RandomTreeDepth1AUC": null, "Dimensionality": 0.09220779220779221, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.8250154120871657, "RandomTreeDepth1ErrRate": null, "EquivalentNumberOfAtts": null, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -4.6674391128638995, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "RandomTreeDepth1Kappa": null, "J48.00001.AUC": null, "MaxSkewnessOfNumericAtts": 11.295376604192333, "MinStdDevOfNumericAtts": 0.004313180134778085, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 4.672838153711691, "AutoCorrelation": -0.10877763328998652, "RandomTreeDepth2AUC": null, "J48.00001.ErrRate": null, "MaxStdDevOfNumericAtts": 73722.72943118442, "MinorityClassPercentage": null, "PercentageOfNumericFeatures": 98.59154929577466, "Quartile3MeansOfNumericAtts": 15.226888636363636, "CfsSubsetEval_DecisionStumpAUC": null, "RandomTreeDepth2ErrRate": null, "J48.00001.Kappa": null, "MeanAttributeEntropy": null, "MinorityClassSize": null, "PercentageOfSymbolicFeatures": 1.4084507042253522, "Quartile3MutualInformation": null, "CfsSubsetEval_DecisionStumpErrRate": null, "RandomTreeDepth2Kappa": null, "J48.0001.AUC": null, "MeanKurtosisOfNumericAtts": 6.911627060742475, "NaiveBayesAUC": null, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 0.6289494737620848, "CfsSubsetEval_DecisionStumpKappa": null, "RandomTreeDepth3AUC": null, "J48.0001.ErrRate": null, "MeanMeansOfNumericAtts": 472.0191987384038, "NaiveBayesErrRate": null, "Quartile1KurtosisOfNumericAtts": 0.7719222301049613, "Quartile3StdDevOfNumericAtts": 2.100269179636245, "CfsSubsetEval_NaiveBayesAUC": null }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "70", "type": "numeric", "distinct": "512", "missing": "0", "target": "1", "min": "4", "max": "10", "mean": "6", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "770", "missing": "0", "identifier": "1", "distr": [] }, { "name": "JGI7", "index": "1", "type": "numeric", "distinct": "25", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Eig08_AEA.dm.", "index": "2", "type": "numeric", "distinct": "442", "missing": "0", "min": "-1", "max": "3", "mean": "1", "stdev": "1" }, { "name": "Eig08_EA.ed.", "index": "3", "type": "numeric", "distinct": "451", "missing": "0", "min": "-4", "max": "9", "mean": "3", "stdev": "2" }, { "name": "SM03_AEA.ri.", "index": "4", "type": "numeric", "distinct": "451", "missing": "0", "min": "-4", "max": "9", "mean": "3", "stdev": "2" }, { "name": "ZM1Kup", "index": "5", "type": "numeric", "distinct": "568", "missing": "0", "min": "96", "max": "1726", "mean": "359", "stdev": "158" }, { "name": "Eig07_AEA.dm.", "index": "6", "type": "numeric", "distinct": "461", "missing": "0", "min": "-1", "max": "3", "mean": "2", "stdev": "1" }, { "name": "ZM2Kup", "index": "7", "type": "numeric", "distinct": "623", "missing": "0", "min": "98", "max": "1190", "mean": "340", "stdev": "130" }, { "name": "Eig10_EA.ed.", "index": "8", "type": "numeric", "distinct": "396", "missing": "0", "min": "-6", "max": "8", "mean": "2", "stdev": "2" }, { "name": "SM05_AEA.ri.", "index": "9", "type": "numeric", "distinct": "396", "missing": "0", "min": "-6", "max": "8", "mean": "2", "stdev": "2" }, { "name": "Eig05_AEA.ri.", "index": "10", "type": "numeric", "distinct": "458", "missing": "0", "min": "0", "max": "4", "mean": "3", "stdev": "1" }, { "name": "Psi_i_s", "index": "11", "type": "numeric", "distinct": "427", "missing": "0", "min": "20", "max": "241", "mean": "55", "stdev": "21" }, { "name": "JGI8", "index": "12", "type": "numeric", "distinct": "23", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Eig05_EA", "index": "13", "type": "numeric", "distinct": "406", "missing": "0", "min": "-1", "max": "3", "mean": "2", "stdev": "1" }, { "name": "SM13_AEA.bo.", "index": "14", "type": "numeric", "distinct": "406", "missing": "0", "min": "-1", "max": "3", "mean": "2", "stdev": "1" }, { "name": "Eig06_AEA.dm.", "index": "15", "type": "numeric", "distinct": "454", "missing": "0", "min": "-1", "max": "4", "mean": "2", "stdev": "1" }, { "name": "SM13_EA.ri.", "index": "16", "type": "numeric", "distinct": "515", "missing": "0", "min": "11", "max": "19", "mean": "15", "stdev": "1" }, { "name": "SM14_EA.ri.", "index": "17", "type": "numeric", "distinct": "527", "missing": "0", "min": "12", "max": "20", "mean": "16", "stdev": "1" }, { "name": "SM15_EA.ri.", "index": "18", "type": "numeric", "distinct": "518", "missing": "0", "min": "13", "max": "22", "mean": "17", "stdev": "1" }, { "name": "SM12_EA.ri.", "index": "19", "type": "numeric", "distinct": "526", "missing": "0", "min": "11", "max": "17", "mean": "14", "stdev": "1" }, { "name": "Psi_i_t", "index": "20", "type": "numeric", "distinct": "32", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SM11_EA.ri.", "index": "21", "type": "numeric", "distinct": "519", "missing": "0", "min": "9", "max": "16", "mean": "13", "stdev": "1" }, { "name": "GATS8e", "index": "22", "type": "numeric", "distinct": "487", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "0" }, { "name": "CATS2D_05_LL", "index": "23", "type": "numeric", "distinct": "40", "missing": "0", "min": "0", "max": "43", "mean": "9", "stdev": "8" }, { "name": "MPC10", "index": "24", "type": "numeric", "distinct": "248", "missing": "0", "min": "0", "max": "7", "mean": "4", "stdev": "1" }, { "name": "S0K", "index": "25", "type": "numeric", "distinct": "268", "missing": "0", "min": "28", "max": "490", "mean": "113", "stdev": "48" }, { "name": "piPC09", "index": "26", "type": "numeric", "distinct": "521", "missing": "0", "min": "0", "max": "9", "mean": "6", "stdev": "2" }, { "name": "Wap", "index": "27", "type": "numeric", "distinct": "511", "missing": "0", "min": "139", "max": "1358600", "mean": "30260", "stdev": "73723" }, { "name": "SpMin5_Bh.p.", "index": "28", "type": "numeric", "distinct": "346", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "Eig06_AEA.bo.", "index": "29", "type": "numeric", "distinct": "424", "missing": "0", "min": "0", "max": "4", "mean": "3", "stdev": "1" }, { "name": "SpDiam_EA.ri.", "index": "30", "type": "numeric", "distinct": "308", "missing": "0", "min": "4", "max": "6", "mean": "5", "stdev": "0" }, { "name": "Eig10_AEA.ed.", "index": "31", "type": "numeric", "distinct": "368", "missing": "0", "min": "0", "max": "6", "mean": "3", "stdev": "1" }, { "name": "P_VSA_m_2", "index": "32", "type": "numeric", "distinct": "579", "missing": "0", "min": "2", "max": "471", "mean": "133", "stdev": "51" }, { "name": "GGI7", "index": "33", "type": "numeric", "distinct": "299", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "0" }, { "name": "ZM1MulPer", "index": "34", "type": "numeric", "distinct": "649", "missing": "0", "min": "95", "max": "1480", "mean": "351", "stdev": "143" }, { "name": "ZM1Per", "index": "35", "type": "numeric", "distinct": "646", "missing": "0", "min": "140", "max": "1876", "mean": "478", "stdev": "188" }, { "name": "ATSC2s", "index": "36", "type": "numeric", "distinct": "667", "missing": "0", "min": "4", "max": "446", "mean": "28", "stdev": "29" }, { "name": "SpDiam_AEA.ed.", "index": "37", "type": "numeric", "distinct": "372", "missing": "0", "min": "5", "max": "8", "mean": "7", "stdev": "1" }, { "name": "Eig11_EA.dm.", "index": "38", "type": "numeric", "distinct": "12", "missing": "0", "min": "-2", "max": "1", "mean": "0", "stdev": "0" }, { "name": "Eig04_EA.ri.", "index": "39", "type": "numeric", "distinct": "454", "missing": "0", "min": "0", "max": "3", "mean": "2", "stdev": "0" }, { "name": "Eig04_EA.bo.", "index": "40", "type": "numeric", "distinct": "427", "missing": "0", "min": "0", "max": "4", "mean": "3", "stdev": "1" }, { "name": "SM14_AEA.ri.", "index": "41", "type": "numeric", "distinct": "427", "missing": "0", "min": "0", "max": "4", "mean": "3", "stdev": "1" }, { "name": "nCsp2", "index": "42", "type": "numeric", "distinct": "28", "missing": "0", "min": "0", "max": "39", "mean": "11", "stdev": "6" }, { "name": "Eig05_AEA.bo.", "index": "43", "type": "numeric", "distinct": "434", "missing": "0", "min": "0", "max": "4", "mean": "3", "stdev": "1" }, { "name": "SpMax4_Bh.m.", "index": "44", "type": "numeric", "distinct": "412", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "TIC3", "index": "45", "type": "numeric", "distinct": "586", "missing": "0", "min": "77", "max": "828", "mean": "248", "stdev": "97" }, { "name": "SM08_EA.ri.", "index": "46", "type": "numeric", "distinct": "519", "missing": "0", "min": "8", "max": "12", "mean": "10", "stdev": "1" }, { "name": "ZM1V", "index": "47", "type": "numeric", "distinct": "216", "missing": "0", "min": "92", "max": "1386", "mean": "330", "stdev": "133" }, { "name": "Eig08_AEA.ed.", "index": "48", "type": "numeric", "distinct": "401", "missing": "0", "min": "1", "max": "6", "mean": "4", "stdev": "1" }, { "name": "Eig06_AEA.ri.", "index": "49", "type": "numeric", "distinct": "438", "missing": "0", "min": "0", "max": "4", "mean": "3", "stdev": "1" }, { "name": "Eig06_EA", "index": "50", "type": "numeric", "distinct": "391", "missing": "0", "min": "-1", "max": "3", "mean": "2", "stdev": "1" }, { "name": "Eig06_EA.ri.", "index": "51", "type": "numeric", "distinct": "441", "missing": "0", "min": "-1", "max": "3", "mean": "2", "stdev": "1" }, { "name": "SM14_AEA.bo.", "index": "52", "type": "numeric", "distinct": "391", "missing": "0", "min": "-1", "max": "3", "mean": "2", "stdev": "1" }, { "name": "piID", "index": "53", "type": "numeric", "distinct": "519", "missing": "0", "min": "4", "max": "17", "mean": "9", "stdev": "2" }, { "name": "Eig07_AEA.ri.", "index": "54", "type": "numeric", "distinct": "428", "missing": "0", "min": "0", "max": "4", "mean": "2", "stdev": "1" }, { "name": "SM12_EA", "index": "55", "type": "numeric", "distinct": "477", "missing": "0", "min": "11", "max": "17", "mean": "15", "stdev": "1" }, { "name": "SM13_EA", "index": "56", "type": "numeric", "distinct": "453", "missing": "0", "min": "12", "max": "19", "mean": "16", "stdev": "1" }, { "name": "SM11_EA", "index": "57", "type": "numeric", "distinct": "465", "missing": "0", "min": "10", "max": "16", "mean": "13", "stdev": "1" }, { "name": "SM06_EA.ed.", "index": "58", "type": "numeric", "distinct": "468", "missing": "0", "min": "12", "max": "18", "mean": "15", "stdev": "1" }, { "name": "SM07_EA.ri.", "index": "59", "type": "numeric", "distinct": "482", "missing": "0", "min": "6", "max": "10", "mean": "8", "stdev": "1" }, { "name": "SpMax5_Bh.s.", "index": "60", "type": "numeric", "distinct": "435", "missing": "0", "min": "3", "max": "8", "mean": "4", "stdev": "1" }, { "name": "SM05_EA.ed.", "index": "61", "type": "numeric", "distinct": "450", "missing": "0", "min": "9", "max": "15", "mean": "13", "stdev": "1" }, { "name": "SpMax3_Bh.e.", "index": "62", "type": "numeric", "distinct": "350", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "ATS2s", "index": "63", "type": "numeric", "distinct": "509", "missing": "0", "min": "5", "max": "7", "mean": "6", "stdev": "0" }, { "name": "SM10_AEA.ed.", "index": "64", "type": "numeric", "distinct": "464", "missing": "0", "min": "17", "max": "23", "mean": "20", "stdev": "1" }, { "name": "SM07_EA.ed.", "index": "65", "type": "numeric", "distinct": "443", "missing": "0", "min": "13", "max": "21", "mean": "18", "stdev": "1" }, { "name": "SpDiam_AEA.bo.", "index": "66", "type": "numeric", "distinct": "344", "missing": "0", "min": "5", "max": "6", "mean": "6", "stdev": "0" }, { "name": "Eig07_EA.ed.", "index": "67", "type": "numeric", "distinct": "436", "missing": "0", "min": "-3", "max": "10", "mean": "3", "stdev": "2" }, { "name": "SM02_AEA.ri.", "index": "68", "type": "numeric", "distinct": "436", "missing": "0", "min": "-3", "max": "10", "mean": "3", "stdev": "2" }, { "name": "nCrs", "index": "69", "type": "numeric", "distinct": "16", "missing": "0", "min": "0", "max": "28", "mean": "3", "stdev": "3" } ], "nr_of_issues": 0, "nr_of_downvotes": 0, "nr_of_likes": 0, "nr_of_downloads": 0, "total_downloads": 0, "reach": 0, "reuse": 11, "impact_of_reuse": 0, "reach_of_reuse": 0, "impact": 11 }