{ "data_id": "24677", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4218", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4218", "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: CHEMBL4218 (TID: 100271), and it has 551 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 15:10:55", "update_comment": null, "last_update": "2016-07-14 15:10:55", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3251284\/data_53520.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4218", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL4218 (TID: 100271), and it has 551 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": 551, "NumberOfFeatures": 71, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 70, "NumberOfSymbolicFeatures": 1, "MeanNoiseToSignalRatio": null, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "REPTreeDepth1ErrRate": null, "CfsSubsetEval_NaiveBayesKappa": null, "RandomTreeDepth3Kappa": null, "J48.001.AUC": null, "J48.001.ErrRate": null, "MeanNominalAttDistinctValues": null, "Quartile1SkewnessOfNumericAtts": -0.18029510325738551, "REPTreeDepth1Kappa": null, "CfsSubsetEval_kNN1NAUC": null, "StdvNominalAttDistinctValues": null, "J48.001.Kappa": null, "MeanSkewnessOfNumericAtts": 0.5294314340338672, "Quartile1StdDevOfNumericAtts": 0.3906280768722459, "REPTreeDepth2AUC": null, "CfsSubsetEval_kNN1NErrRate": null, "kNN1NAUC": null, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 9.849668715562085, "Quartile2AttributeEntropy": null, "REPTreeDepth2ErrRate": null, "CfsSubsetEval_kNN1NKappa": null, "kNN1NErrRate": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2KurtosisOfNumericAtts": 0.5302881908402362, "REPTreeDepth2Kappa": null, "ClassEntropy": null, "kNN1NKappa": null, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -0.9428541044939545, "Quartile2MeansOfNumericAtts": 3.5490127041742285, "REPTreeDepth3AUC": null, "DecisionStumpAUC": null, "MaxKurtosisOfNumericAtts": 51.844232059055514, "MinMeansOfNumericAtts": 0.006294010889292196, "Quartile2MutualInformation": null, "REPTreeDepth3ErrRate": null, "DecisionStumpErrRate": null, "MaxMeansOfNumericAtts": 452.35995281306714, "MinMutualInformation": null, "Quartile2SkewnessOfNumericAtts": 0.3498576885958014, "REPTreeDepth3Kappa": null, "DecisionStumpKappa": null, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 1.1072361527454544, "RandomTreeDepth1AUC": null, "Dimensionality": 0.12885662431941924, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -2.149232308687252, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "RandomTreeDepth1ErrRate": null, "EquivalentNumberOfAtts": null, "MaxSkewnessOfNumericAtts": 5.330037623191714, "MinStdDevOfNumericAtts": 0.0033112398765237786, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 2.95402922650032, "AutoCorrelation": 0.7034654545454547, "RandomTreeDepth1Kappa": null, "J48.00001.AUC": null, "MaxStdDevOfNumericAtts": 120.79394396713747, "MinorityClassPercentage": null, "PercentageOfNumericFeatures": 98.59154929577466, "Quartile3MeansOfNumericAtts": 9.326934664246824, "CfsSubsetEval_DecisionStumpAUC": null, "RandomTreeDepth2AUC": null, "J48.00001.ErrRate": null, "MeanAttributeEntropy": null, "MinorityClassSize": null, "PercentageOfSymbolicFeatures": 1.4084507042253522, "Quartile3MutualInformation": null, "CfsSubsetEval_DecisionStumpErrRate": null, "RandomTreeDepth2ErrRate": null, "J48.00001.Kappa": null, "MeanKurtosisOfNumericAtts": 2.8652797796237772, "NaiveBayesAUC": null, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 1.2321821196859197, "CfsSubsetEval_DecisionStumpKappa": null, "RandomTreeDepth2Kappa": null, "J48.0001.AUC": null, "MeanMeansOfNumericAtts": 27.765002177858438, "NaiveBayesErrRate": null, "Quartile1KurtosisOfNumericAtts": -0.19596825330354706, "Quartile3StdDevOfNumericAtts": 5.19982060122854, "CfsSubsetEval_NaiveBayesAUC": null, "RandomTreeDepth3AUC": null, "J48.0001.ErrRate": null, "MeanMutualInformation": null, "NaiveBayesKappa": null, "Quartile1MeansOfNumericAtts": 0.9655172413793104, "REPTreeDepth1AUC": null, "CfsSubsetEval_NaiveBayesErrRate": null, "RandomTreeDepth3ErrRate": null, "J48.0001.Kappa": null }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "70", "type": "numeric", "distinct": "213", "missing": "0", "target": "1", "min": "4", "max": "9", "mean": "5", "stdev": "0" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "551", "missing": "0", "identifier": "1", "distr": [] }, { "name": "SM11_EA.dm.", "index": "1", "type": "numeric", "distinct": "177", "missing": "0", "min": "0", "max": "19", "mean": "7", "stdev": "5" }, { "name": "SM06_EA.dm.", "index": "2", "type": "numeric", "distinct": "342", "missing": "0", "min": "0", "max": "11", "mean": "5", "stdev": "2" }, { "name": "SM13_EA.dm.", "index": "3", "type": "numeric", "distinct": "172", "missing": "0", "min": "0", "max": "22", "mean": "8", "stdev": "6" }, { "name": "SM15_EA.dm.", "index": "4", "type": "numeric", "distinct": "169", "missing": "0", "min": "0", "max": "26", "mean": "10", "stdev": "7" }, { "name": "SM07_EA.dm.", "index": "5", "type": "numeric", "distinct": "183", "missing": "0", "min": "0", "max": "12", "mean": "4", "stdev": "3" }, { "name": "SM04_EA.dm.", "index": "6", "type": "numeric", "distinct": "372", "missing": "0", "min": "0", "max": "7", "mean": "4", "stdev": "2" }, { "name": "SM09_EA.dm.", "index": "7", "type": "numeric", "distinct": "180", "missing": "0", "min": "0", "max": "15", "mean": "6", "stdev": "4" }, { "name": "SpDiam_EA.dm.", "index": "8", "type": "numeric", "distinct": "156", "missing": "0", "min": "0", "max": "11", "mean": "4", "stdev": "2" }, { "name": "SM02_EA.dm.", "index": "9", "type": "numeric", "distinct": "338", "missing": "0", "min": "0", "max": "5", "mean": "3", "stdev": "1" }, { "name": "SM05_EA.dm.", "index": "10", "type": "numeric", "distinct": "179", "missing": "0", "min": "0", "max": "8", "mean": "3", "stdev": "2" }, { "name": "SM08_EA.dm.", "index": "11", "type": "numeric", "distinct": "310", "missing": "0", "min": "0", "max": "14", "mean": "6", "stdev": "3" }, { "name": "SM12_EA.dm.", "index": "12", "type": "numeric", "distinct": "266", "missing": "0", "min": "0", "max": "21", "mean": "9", "stdev": "5" }, { "name": "Eig01_EA.dm.", "index": "13", "type": "numeric", "distinct": "136", "missing": "0", "min": "0", "max": "6", "mean": "2", "stdev": "1" }, { "name": "SpMax_EA.dm.", "index": "14", "type": "numeric", "distinct": "136", "missing": "0", "min": "0", "max": "6", "mean": "2", "stdev": "1" }, { "name": "SM14_EA.dm.", "index": "15", "type": "numeric", "distinct": "255", "missing": "0", "min": "0", "max": "24", "mean": "11", "stdev": "6" }, { "name": "SM10_EA.dm.", "index": "16", "type": "numeric", "distinct": "279", "missing": "0", "min": "0", "max": "18", "mean": "8", "stdev": "4" }, { "name": "nRCONHR", "index": "17", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "1" }, { "name": "Eig02_EA.dm.", "index": "18", "type": "numeric", "distinct": "147", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "SM03_EA.dm.", "index": "19", "type": "numeric", "distinct": "93", "missing": "0", "min": "0", "max": "5", "mean": "2", "stdev": "1" }, { "name": "SssNH", "index": "20", "type": "numeric", "distinct": "337", "missing": "0", "min": "0", "max": "10", "mean": "2", "stdev": "2" }, { "name": "ATSC3e", "index": "21", "type": "numeric", "distinct": "405", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "0" }, { "name": "DECC", "index": "22", "type": "numeric", "distinct": "426", "missing": "0", "min": "1", "max": "3", "mean": "2", "stdev": "0" }, { "name": "SpMAD_EA.dm.", "index": "23", "type": "numeric", "distinct": "347", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "P_VSA_s_5", "index": "24", "type": "numeric", "distinct": "34", "missing": "0", "min": "0", "max": "110", "mean": "21", "stdev": "18" }, { "name": "SpAD_EA.dm.", "index": "25", "type": "numeric", "distinct": "381", "missing": "0", "min": "0", "max": "32", "mean": "10", "stdev": "6" }, { "name": "TPSA.NO.", "index": "26", "type": "numeric", "distinct": "421", "missing": "0", "min": "6", "max": "215", "mean": "84", "stdev": "31" }, { "name": "ATSC2s", "index": "27", "type": "numeric", "distinct": "545", "missing": "0", "min": "4", "max": "340", "mean": "43", "stdev": "37" }, { "name": "O.060", "index": "28", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "6", "mean": "1", "stdev": "1" }, { "name": "Hy", "index": "29", "type": "numeric", "distinct": "279", "missing": "0", "min": "-1", "max": "4", "mean": "0", "stdev": "1" }, { "name": "C.040", "index": "30", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "ATSC2e", "index": "31", "type": "numeric", "distinct": "376", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "ICR", "index": "32", "type": "numeric", "distinct": "339", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SAacc", "index": "33", "type": "numeric", "distinct": "425", "missing": "0", "min": "3", "max": "403", "mean": "117", "stdev": "46" }, { "name": "SpMax1_Bh.s.", "index": "34", "type": "numeric", "distinct": "95", "missing": "0", "min": "5", "max": "9", "mean": "7", "stdev": "1" }, { "name": "MW", "index": "35", "type": "numeric", "distinct": "512", "missing": "0", "min": "186", "max": "836", "mean": "368", "stdev": "75" }, { "name": "SAdon", "index": "36", "type": "numeric", "distinct": "57", "missing": "0", "min": "0", "max": "235", "mean": "35", "stdev": "31" }, { "name": "Eig03_EA.dm.", "index": "37", "type": "numeric", "distinct": "127", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "P_VSA_p_2", "index": "38", "type": "numeric", "distinct": "419", "missing": "0", "min": "5", "max": "358", "mean": "116", "stdev": "45" }, { "name": "P_VSA_v_2", "index": "39", "type": "numeric", "distinct": "440", "missing": "0", "min": "5", "max": "403", "mean": "119", "stdev": "46" }, { "name": "Eig02_AEA.dm.", "index": "40", "type": "numeric", "distinct": "359", "missing": "0", "min": "2", "max": "5", "mean": "4", "stdev": "0" }, { "name": "ATS1m", "index": "41", "type": "numeric", "distinct": "388", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "HVcpx", "index": "42", "type": "numeric", "distinct": "423", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "P_VSA_LogP_2", "index": "43", "type": "numeric", "distinct": "277", "missing": "0", "min": "0", "max": "81", "mean": "25", "stdev": "16" }, { "name": "JGI10", "index": "44", "type": "numeric", "distinct": "19", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Uindex", "index": "45", "type": "numeric", "distinct": "537", "missing": "0", "min": "16", "max": "92", "mean": "44", "stdev": "11" }, { "name": "Yindex", "index": "46", "type": "numeric", "distinct": "345", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "RBF", "index": "47", "type": "numeric", "distinct": "136", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "ECC", "index": "48", "type": "numeric", "distinct": "289", "missing": "0", "min": "62", "max": "714", "mean": "285", "stdev": "106" }, { "name": "GGI10", "index": "49", "type": "numeric", "distinct": "168", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "LLS_01", "index": "50", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "IDE", "index": "51", "type": "numeric", "distinct": "425", "missing": "0", "min": "2", "max": "4", "mean": "4", "stdev": "0" }, { "name": "AECC", "index": "52", "type": "numeric", "distinct": "434", "missing": "0", "min": "5", "max": "17", "mean": "11", "stdev": "2" }, { "name": "MSD", "index": "53", "type": "numeric", "distinct": "504", "missing": "0", "min": "3", "max": "10", "mean": "6", "stdev": "1" }, { "name": "S3K", "index": "54", "type": "numeric", "distinct": "499", "missing": "0", "min": "1", "max": "8", "mean": "4", "stdev": "1" }, { "name": "NssNH", "index": "55", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "O.", "index": "56", "type": "numeric", "distinct": "113", "missing": "0", "min": "0", "max": "23", "mean": "7", "stdev": "4" }, { "name": "ZM1Kup", "index": "57", "type": "numeric", "distinct": "536", "missing": "0", "min": "194", "max": "1201", "mean": "452", "stdev": "121" }, { "name": "GGI9", "index": "58", "type": "numeric", "distinct": "241", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "ATS2m", "index": "59", "type": "numeric", "distinct": "401", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "nHAcc", "index": "60", "type": "numeric", "distinct": "15", "missing": "0", "min": "1", "max": "17", "mean": "6", "stdev": "2" }, { "name": "Hypertens.80", "index": "61", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "H.050", "index": "62", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "7", "mean": "2", "stdev": "1" }, { "name": "P_VSA_s_3", "index": "63", "type": "numeric", "distinct": "525", "missing": "0", "min": "3", "max": "149", "mean": "41", "stdev": "19" }, { "name": "CATS2D_03_DA", "index": "64", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "5", "mean": "1", "stdev": "1" }, { "name": "ATSC8e", "index": "65", "type": "numeric", "distinct": "403", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "0" }, { "name": "Eig08_AEA.dm.", "index": "66", "type": "numeric", "distinct": "409", "missing": "0", "min": "-1", "max": "3", "mean": "2", "stdev": "0" }, { "name": "nHDon", "index": "67", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "7", "mean": "2", "stdev": "1" }, { "name": "Eig07_AEA.dm.", "index": "68", "type": "numeric", "distinct": "433", "missing": "0", "min": "0", "max": "3", "mean": "2", "stdev": "0" }, { "name": "Eig12_AEA.dm.", "index": "69", "type": "numeric", "distinct": "384", "missing": "0", "min": "-2", "max": "3", "mean": "1", "stdev": "1" } ], "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 }