{ "data_id": "24213", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4501", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4501", "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: CHEMBL4501 (TID: 12944), and it has 887 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 14:09:34", "update_comment": null, "last_update": "2016-07-14 14:09:34", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3241606\/data_53574.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4501", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL4501 (TID: 12944), and it has 887 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": 887, "NumberOfFeatures": 71, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 70, "NumberOfSymbolicFeatures": 1, "REPTreeDepth3Kappa": null, "DecisionStumpKappa": null, "MaxMeansOfNumericAtts": 392.7545546786922, "MinMutualInformation": null, "Quartile2SkewnessOfNumericAtts": 0.2489667570506371, "RandomTreeDepth1AUC": null, "Dimensionality": 0.08004509582863585, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.6609955955458824, "RandomTreeDepth1ErrRate": null, "EquivalentNumberOfAtts": null, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -1.5195029368514263, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "RandomTreeDepth1Kappa": null, "J48.00001.AUC": null, "MaxSkewnessOfNumericAtts": 10.733993550041912, "MinStdDevOfNumericAtts": 0.07028300339152979, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 28.036586906369752, "AutoCorrelation": 0.22256433408577878, "RandomTreeDepth2AUC": null, "J48.00001.ErrRate": null, "MaxStdDevOfNumericAtts": 126.77025521211692, "MinorityClassPercentage": null, "PercentageOfNumericFeatures": 98.59154929577466, "Quartile3MeansOfNumericAtts": 3.994424464487035, "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": 20.069025053399283, "NaiveBayesAUC": null, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 3.4695167078672857, "CfsSubsetEval_DecisionStumpKappa": null, "RandomTreeDepth3AUC": null, "J48.0001.ErrRate": null, "MeanMeansOfNumericAtts": 11.802234917055886, "NaiveBayesErrRate": null, "Quartile1KurtosisOfNumericAtts": 1.07063710646516, "Quartile3StdDevOfNumericAtts": 1.4651844847732831, "CfsSubsetEval_NaiveBayesAUC": null, "RandomTreeDepth3ErrRate": null, "J48.0001.Kappa": null, "MeanMutualInformation": null, "NaiveBayesKappa": null, "Quartile1MeansOfNumericAtts": 0.8452277339346113, "REPTreeDepth1AUC": null, "CfsSubsetEval_NaiveBayesErrRate": null, "RandomTreeDepth3Kappa": null, "J48.001.AUC": null, "MeanNoiseToSignalRatio": null, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "REPTreeDepth1ErrRate": null, "CfsSubsetEval_NaiveBayesKappa": null, "CfsSubsetEval_kNN1NAUC": null, "StdvNominalAttDistinctValues": null, "J48.001.ErrRate": null, "MeanNominalAttDistinctValues": null, "Quartile1SkewnessOfNumericAtts": -0.737464673980075, "REPTreeDepth1Kappa": null, "CfsSubsetEval_kNN1NErrRate": null, "kNN1NAUC": null, "J48.001.Kappa": null, "MeanSkewnessOfNumericAtts": 1.6892814145100314, "Quartile1StdDevOfNumericAtts": 0.31803003811023933, "REPTreeDepth2AUC": null, "CfsSubsetEval_kNN1NKappa": null, "kNN1NErrRate": null, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 3.7656017972489915, "Quartile2AttributeEntropy": null, "REPTreeDepth2ErrRate": null, "ClassEntropy": null, "kNN1NKappa": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2KurtosisOfNumericAtts": 3.2055828415649357, "REPTreeDepth2Kappa": null, "REPTreeDepth3AUC": null, "DecisionStumpAUC": null, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -0.3937520010691924, "Quartile2MeansOfNumericAtts": 2.8169661781285233, "REPTreeDepth3ErrRate": null, "DecisionStumpErrRate": null, "MaxKurtosisOfNumericAtts": 144.270092556108, "MinMeansOfNumericAtts": 0.2029312288613298, "Quartile2MutualInformation": null }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "70", "type": "numeric", "distinct": "163", "missing": "0", "target": "1", "min": "4", "max": "9", "mean": "6", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "887", "missing": "0", "identifier": "1", "distr": [] }, { "name": "CATS2D_06_PL", "index": "1", "type": "numeric", "distinct": "9", "missing": "0", "min": "0", "max": "16", "mean": "1", "stdev": "2" }, { "name": "SsNH2", "index": "2", "type": "numeric", "distinct": "297", "missing": "0", "min": "0", "max": "68", "mean": "3", "stdev": "5" }, { "name": "SaaaC", "index": "3", "type": "numeric", "distinct": "503", "missing": "0", "min": "0", "max": "9", "mean": "1", "stdev": "1" }, { "name": "nArNH2", "index": "4", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "CATS2D_02_AP", "index": "5", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "11", "mean": "0", "stdev": "1" }, { "name": "N.069", "index": "6", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "CATS2D_05_PL", "index": "7", "type": "numeric", "distinct": "10", "missing": "0", "min": "0", "max": "16", "mean": "1", "stdev": "2" }, { "name": "SpMax1_Bh.p.", "index": "8", "type": "numeric", "distinct": "273", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "CATS2D_00_DD", "index": "9", "type": "numeric", "distinct": "8", "missing": "0", "min": "0", "max": "12", "mean": "0", "stdev": "1" }, { "name": "CATS2D_00_DP", "index": "10", "type": "numeric", "distinct": "8", "missing": "0", "min": "0", "max": "12", "mean": "0", "stdev": "1" }, { "name": "CATS2D_00_PP", "index": "11", "type": "numeric", "distinct": "8", "missing": "0", "min": "0", "max": "12", "mean": "0", "stdev": "1" }, { "name": "NsNH2", "index": "12", "type": "numeric", "distinct": "8", "missing": "0", "min": "0", "max": "12", "mean": "0", "stdev": "1" }, { "name": "CATS2D_08_DP", "index": "13", "type": "numeric", "distinct": "8", "missing": "0", "min": "0", "max": "12", "mean": "0", "stdev": "1" }, { "name": "CATS2D_04_PL", "index": "14", "type": "numeric", "distinct": "10", "missing": "0", "min": "0", "max": "12", "mean": "1", "stdev": "1" }, { "name": "Eig09_AEA.ri.", "index": "15", "type": "numeric", "distinct": "568", "missing": "0", "min": "-1", "max": "4", "mean": "2", "stdev": "1" }, { "name": "SpMax7_Bh.m.", "index": "16", "type": "numeric", "distinct": "496", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SpMax1_Bh.v.", "index": "17", "type": "numeric", "distinct": "259", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "Eig08_AEA.bo.", "index": "18", "type": "numeric", "distinct": "536", "missing": "0", "min": "0", "max": "4", "mean": "3", "stdev": "0" }, { "name": "Eig01_EA.bo.", "index": "19", "type": "numeric", "distinct": "410", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SM11_AEA.ri.", "index": "20", "type": "numeric", "distinct": "410", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SpDiam_EA.bo.", "index": "21", "type": "numeric", "distinct": "411", "missing": "0", "min": "6", "max": "8", "mean": "7", "stdev": "0" }, { "name": "SpMax_EA.bo.", "index": "22", "type": "numeric", "distinct": "410", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "C.025", "index": "23", "type": "numeric", "distinct": "9", "missing": "0", "min": "0", "max": "8", "mean": "3", "stdev": "2" }, { "name": "CATS2D_03_PL", "index": "24", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "6", "mean": "0", "stdev": "1" }, { "name": "CATS2D_03_AP", "index": "25", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "8", "mean": "0", "stdev": "1" }, { "name": "SM15_EA.bo.", "index": "26", "type": "numeric", "distinct": "657", "missing": "0", "min": "19", "max": "25", "mean": "23", "stdev": "1" }, { "name": "Eig09_EA.ed.", "index": "27", "type": "numeric", "distinct": "648", "missing": "0", "min": "-4", "max": "9", "mean": "3", "stdev": "2" }, { "name": "SM04_AEA.ri.", "index": "28", "type": "numeric", "distinct": "648", "missing": "0", "min": "-4", "max": "9", "mean": "3", "stdev": "2" }, { "name": "ICR", "index": "29", "type": "numeric", "distinct": "481", "missing": "0", "min": "1", "max": "5", "mean": "3", "stdev": "0" }, { "name": "SpMax8_Bh.p.", "index": "30", "type": "numeric", "distinct": "464", "missing": "0", "min": "0", "max": "4", "mean": "3", "stdev": "0" }, { "name": "Hy", "index": "31", "type": "numeric", "distinct": "428", "missing": "0", "min": "-1", "max": "32", "mean": "1", "stdev": "2" }, { "name": "Eig09_EA", "index": "32", "type": "numeric", "distinct": "526", "missing": "0", "min": "-1", "max": "3", "mean": "1", "stdev": "1" }, { "name": "SM03_AEA.dm.", "index": "33", "type": "numeric", "distinct": "526", "missing": "0", "min": "-1", "max": "3", "mean": "1", "stdev": "1" }, { "name": "Eig08_AEA.ri.", "index": "34", "type": "numeric", "distinct": "572", "missing": "0", "min": "0", "max": "4", "mean": "2", "stdev": "0" }, { "name": "SM14_EA.bo.", "index": "35", "type": "numeric", "distinct": "660", "missing": "0", "min": "18", "max": "24", "mean": "21", "stdev": "1" }, { "name": "CATS2D_02_PL", "index": "36", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "5", "mean": "0", "stdev": "1" }, { "name": "ZM1Mad", "index": "37", "type": "numeric", "distinct": "833", "missing": "0", "min": "79", "max": "963", "mean": "182", "stdev": "59" }, { "name": "CATS2D_08_DD", "index": "38", "type": "numeric", "distinct": "9", "missing": "0", "min": "0", "max": "19", "mean": "0", "stdev": "1" }, { "name": "CATS2D_06_DL", "index": "39", "type": "numeric", "distinct": "18", "missing": "0", "min": "0", "max": "23", "mean": "3", "stdev": "3" }, { "name": "ATS2m", "index": "40", "type": "numeric", "distinct": "571", "missing": "0", "min": "3", "max": "6", "mean": "4", "stdev": "0" }, { "name": "SM13_EA.bo.", "index": "41", "type": "numeric", "distinct": "646", "missing": "0", "min": "16", "max": "22", "mean": "20", "stdev": "1" }, { "name": "Eig09_AEA.ed.", "index": "42", "type": "numeric", "distinct": "576", "missing": "0", "min": "1", "max": "6", "mean": "4", "stdev": "1" }, { "name": "GATS1s", "index": "43", "type": "numeric", "distinct": "405", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "CATS2D_05_DL", "index": "44", "type": "numeric", "distinct": "21", "missing": "0", "min": "0", "max": "33", "mean": "3", "stdev": "3" }, { "name": "SpMax7_Bh.i.", "index": "45", "type": "numeric", "distinct": "476", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "H.050", "index": "46", "type": "numeric", "distinct": "14", "missing": "0", "min": "0", "max": "43", "mean": "3", "stdev": "3" }, { "name": "nHDon", "index": "47", "type": "numeric", "distinct": "14", "missing": "0", "min": "0", "max": "43", "mean": "3", "stdev": "3" }, { "name": "SpMax2_Bh.i.", "index": "48", "type": "numeric", "distinct": "274", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "IDE", "index": "49", "type": "numeric", "distinct": "595", "missing": "0", "min": "2", "max": "6", "mean": "4", "stdev": "0" }, { "name": "Eig08_EA", "index": "50", "type": "numeric", "distinct": "528", "missing": "0", "min": "-1", "max": "3", "mean": "1", "stdev": "0" }, { "name": "SM02_AEA.dm.", "index": "51", "type": "numeric", "distinct": "528", "missing": "0", "min": "-1", "max": "3", "mean": "1", "stdev": "0" }, { "name": "Yindex", "index": "52", "type": "numeric", "distinct": "441", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Eig08_EA.ri.", "index": "53", "type": "numeric", "distinct": "560", "missing": "0", "min": "-1", "max": "3", "mean": "1", "stdev": "0" }, { "name": "SpMax6_Bh.m.", "index": "54", "type": "numeric", "distinct": "527", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SpMax8_Bh.v.", "index": "55", "type": "numeric", "distinct": "476", "missing": "0", "min": "0", "max": "4", "mean": "3", "stdev": "0" }, { "name": "Eig11_EA.bo.", "index": "56", "type": "numeric", "distinct": "563", "missing": "0", "min": "-3", "max": "3", "mean": "1", "stdev": "1" }, { "name": "X3v", "index": "57", "type": "numeric", "distinct": "796", "missing": "0", "min": "2", "max": "31", "mean": "5", "stdev": "2" }, { "name": "MW", "index": "58", "type": "numeric", "distinct": "775", "missing": "0", "min": "188", "max": "2269", "mean": "393", "stdev": "127" }, { "name": "Eig08_EA.ed.", "index": "59", "type": "numeric", "distinct": "660", "missing": "0", "min": "-3", "max": "9", "mean": "4", "stdev": "1" }, { "name": "SM03_AEA.ri.", "index": "60", "type": "numeric", "distinct": "660", "missing": "0", "min": "-3", "max": "9", "mean": "4", "stdev": "1" }, { "name": "ATS1m", "index": "61", "type": "numeric", "distinct": "547", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SpMax5_Bh.m.", "index": "62", "type": "numeric", "distinct": "531", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "MSD", "index": "63", "type": "numeric", "distinct": "734", "missing": "0", "min": "3", "max": "28", "mean": "7", "stdev": "2" }, { "name": "SpMax8_Bh.m.", "index": "64", "type": "numeric", "distinct": "511", "missing": "0", "min": "1", "max": "4", "mean": "3", "stdev": "0" }, { "name": "AECC", "index": "65", "type": "numeric", "distinct": "625", "missing": "0", "min": "4", "max": "51", "mean": "11", "stdev": "3" }, { "name": "Eig07_AEA.bo.", "index": "66", "type": "numeric", "distinct": "538", "missing": "0", "min": "1", "max": "4", "mean": "3", "stdev": "0" }, { "name": "Eig06_AEA.ed.", "index": "67", "type": "numeric", "distinct": "601", "missing": "0", "min": "3", "max": "6", "mean": "5", "stdev": "1" }, { "name": "DECC", "index": "68", "type": "numeric", "distinct": "597", "missing": "0", "min": "1", "max": "9", "mean": "2", "stdev": "1" }, { "name": "Chi1_EA.dm.", "index": "69", "type": "numeric", "distinct": "756", "missing": "0", "min": "0", "max": "158", "mean": "24", "stdev": "15" } ], "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 }