{ "data_id": "23645", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL257", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL257", "version": 7, "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: CHEMBL257 (TID: 10026), and it has 621 rows and 66 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 12:54:55", "update_comment": null, "last_update": "2016-07-14 12:54:55", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3229966\/data_53058.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL257", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL257 (TID: 10026), and it has 621 rows and 66 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": 621, "NumberOfFeatures": 68, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 67, "NumberOfSymbolicFeatures": 1, "REPTreeDepth3Kappa": null, "DecisionStumpKappa": null, "MaxMeansOfNumericAtts": 996.3632850241546, "MinMutualInformation": null, "Quartile2SkewnessOfNumericAtts": -0.18721256461966046, "RandomTreeDepth1AUC": null, "Dimensionality": 0.10950080515297907, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.9235236615577133, "RandomTreeDepth1ErrRate": null, "EquivalentNumberOfAtts": null, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -1.0367262449609416, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "RandomTreeDepth1Kappa": null, "J48.00001.AUC": null, "MaxSkewnessOfNumericAtts": 2.5642990444177163, "MinStdDevOfNumericAtts": 0.01621999409385706, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 1.3022556868027642, "AutoCorrelation": -0.22939677419354948, "RandomTreeDepth2AUC": null, "J48.00001.ErrRate": null, "MaxStdDevOfNumericAtts": 215.490359025786, "MinorityClassPercentage": null, "PercentageOfNumericFeatures": 98.52941176470588, "Quartile3MeansOfNumericAtts": 54.48151851851852, "CfsSubsetEval_DecisionStumpAUC": null, "RandomTreeDepth2ErrRate": null, "J48.00001.Kappa": null, "MeanAttributeEntropy": null, "MinorityClassSize": null, "PercentageOfSymbolicFeatures": 1.4705882352941175, "Quartile3MutualInformation": null, "CfsSubsetEval_DecisionStumpErrRate": null, "RandomTreeDepth2Kappa": null, "J48.0001.AUC": null, "MeanKurtosisOfNumericAtts": 1.013325171342819, "NaiveBayesAUC": null, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 0.2979041833373722, "CfsSubsetEval_DecisionStumpKappa": null, "RandomTreeDepth3AUC": null, "J48.0001.ErrRate": null, "MeanMeansOfNumericAtts": 86.02115145288053, "NaiveBayesErrRate": null, "Quartile1KurtosisOfNumericAtts": -0.04116311189790833, "Quartile3StdDevOfNumericAtts": 11.373867599145898, "CfsSubsetEval_NaiveBayesAUC": null, "RandomTreeDepth3ErrRate": null, "J48.0001.Kappa": null, "MeanMutualInformation": null, "NaiveBayesKappa": null, "Quartile1MeansOfNumericAtts": 4.434951690821256, "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": -0.6509990958602544, "REPTreeDepth1Kappa": null, "CfsSubsetEval_kNN1NErrRate": null, "kNN1NAUC": null, "J48.001.Kappa": null, "MeanSkewnessOfNumericAtts": -0.08298664586116494, "Quartile1StdDevOfNumericAtts": 0.2073800784059081, "REPTreeDepth2AUC": null, "CfsSubsetEval_kNN1NKappa": null, "kNN1NErrRate": null, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 18.12423531744237, "Quartile2AttributeEntropy": null, "REPTreeDepth2ErrRate": null, "ClassEntropy": null, "kNN1NKappa": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2KurtosisOfNumericAtts": 0.39884978504842383, "REPTreeDepth2Kappa": null, "REPTreeDepth3AUC": null, "DecisionStumpAUC": null, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.0865642201799002, "Quartile2MeansOfNumericAtts": 8.914334943639291, "REPTreeDepth3ErrRate": null, "DecisionStumpErrRate": null, "MaxKurtosisOfNumericAtts": 10.39135362038561, "MinMeansOfNumericAtts": 0.17391304347826075, "Quartile2MutualInformation": null }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "67", "type": "numeric", "distinct": "321", "missing": "0", "target": "1", "min": "4", "max": "10", "mean": "7", "stdev": "2" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "621", "missing": "0", "identifier": "1", "distr": [] }, { "name": "ATSC8p", "index": "1", "type": "numeric", "distinct": "599", "missing": "0", "min": "7", "max": "40", "mean": "18", "stdev": "4" }, { "name": "ATS8i", "index": "2", "type": "numeric", "distinct": "414", "missing": "0", "min": "5", "max": "7", "mean": "6", "stdev": "0" }, { "name": "F.084", "index": "3", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "0" }, { "name": "ATSC8v", "index": "4", "type": "numeric", "distinct": "607", "missing": "0", "min": "9", "max": "61", "mean": "23", "stdev": "6" }, { "name": "SpMin5_Bh.i.", "index": "5", "type": "numeric", "distinct": "233", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "P_VSA_MR_5", "index": "6", "type": "numeric", "distinct": "374", "missing": "0", "min": "8", "max": "302", "mean": "74", "stdev": "30" }, { "name": "ATSC5p", "index": "7", "type": "numeric", "distinct": "591", "missing": "0", "min": "8", "max": "28", "mean": "17", "stdev": "3" }, { "name": "CATS2D_07_AA", "index": "8", "type": "numeric", "distinct": "8", "missing": "0", "min": "0", "max": "7", "mean": "1", "stdev": "2" }, { "name": "TIC1", "index": "9", "type": "numeric", "distinct": "544", "missing": "0", "min": "143", "max": "547", "mean": "272", "stdev": "52" }, { "name": "SM03_AEA.bo.", "index": "10", "type": "numeric", "distinct": "311", "missing": "0", "min": "6", "max": "7", "mean": "7", "stdev": "0" }, { "name": "Eig13_EA.ed.", "index": "11", "type": "numeric", "distinct": "313", "missing": "0", "min": "-2", "max": "6", "mean": "3", "stdev": "1" }, { "name": "SM08_AEA.ri.", "index": "12", "type": "numeric", "distinct": "313", "missing": "0", "min": "-2", "max": "6", "mean": "3", "stdev": "1" }, { "name": "SpAD_EA.bo.", "index": "13", "type": "numeric", "distinct": "514", "missing": "0", "min": "41", "max": "132", "mean": "88", "stdev": "15" }, { "name": "X4", "index": "14", "type": "numeric", "distinct": "483", "missing": "0", "min": "5", "max": "18", "mean": "13", "stdev": "2" }, { "name": "IAC", "index": "15", "type": "numeric", "distinct": "456", "missing": "0", "min": "64", "max": "234", "mean": "122", "stdev": "25" }, { "name": "TIC0", "index": "16", "type": "numeric", "distinct": "456", "missing": "0", "min": "64", "max": "234", "mean": "122", "stdev": "25" }, { "name": "SpMin5_Bh.s.", "index": "17", "type": "numeric", "distinct": "247", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "BBI", "index": "18", "type": "numeric", "distinct": "51", "missing": "0", "min": "29", "max": "101", "mean": "64", "stdev": "11" }, { "name": "MPC02", "index": "19", "type": "numeric", "distinct": "51", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SM02_EA", "index": "20", "type": "numeric", "distinct": "51", "missing": "0", "min": "4", "max": "5", "mean": "5", "stdev": "0" }, { "name": "TIC3", "index": "21", "type": "numeric", "distinct": "522", "missing": "0", "min": "196", "max": "882", "mean": "404", "stdev": "85" }, { "name": "S2K", "index": "22", "type": "numeric", "distinct": "496", "missing": "0", "min": "8", "max": "30", "mean": "13", "stdev": "3" }, { "name": "SNar", "index": "23", "type": "numeric", "distinct": "142", "missing": "0", "min": "14", "max": "47", "mean": "29", "stdev": "5" }, { "name": "Xt", "index": "24", "type": "numeric", "distinct": "70", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "NssNH", "index": "25", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "7", "mean": "1", "stdev": "1" }, { "name": "SpAD_EA.ed.", "index": "26", "type": "numeric", "distinct": "495", "missing": "0", "min": "87", "max": "305", "mean": "199", "stdev": "36" }, { "name": "SM02_AEA.ed.", "index": "27", "type": "numeric", "distinct": "178", "missing": "0", "min": "5", "max": "7", "mean": "6", "stdev": "0" }, { "name": "Eig12_AEA.dm.", "index": "28", "type": "numeric", "distinct": "279", "missing": "0", "min": "0", "max": "3", "mean": "2", "stdev": "0" }, { "name": "Eta_C", "index": "29", "type": "numeric", "distinct": "612", "missing": "0", "min": "18", "max": "107", "mean": "42", "stdev": "10" }, { "name": "ZM2MulPer", "index": "30", "type": "numeric", "distinct": "584", "missing": "0", "min": "296", "max": "978", "mean": "676", "stdev": "143" }, { "name": "VvdwZAZ", "index": "31", "type": "numeric", "distinct": "493", "missing": "0", "min": "278", "max": "960", "mean": "524", "stdev": "95" }, { "name": "SM04_AEA.bo.", "index": "32", "type": "numeric", "distinct": "361", "missing": "0", "min": "7", "max": "8", "mean": "8", "stdev": "0" }, { "name": "X0sol", "index": "33", "type": "numeric", "distinct": "336", "missing": "0", "min": "16", "max": "53", "mean": "29", "stdev": "5" }, { "name": "SM03_AEA.ed.", "index": "34", "type": "numeric", "distinct": "342", "missing": "0", "min": "7", "max": "8", "mean": "8", "stdev": "0" }, { "name": "X3", "index": "35", "type": "numeric", "distinct": "482", "missing": "0", "min": "7", "max": "24", "mean": "15", "stdev": "3" }, { "name": "SRW06", "index": "36", "type": "numeric", "distinct": "299", "missing": "0", "min": "7", "max": "8", "mean": "7", "stdev": "0" }, { "name": "SRW08", "index": "37", "type": "numeric", "distinct": "347", "missing": "0", "min": "8", "max": "9", "mean": "9", "stdev": "0" }, { "name": "ATS3e", "index": "38", "type": "numeric", "distinct": "390", "missing": "0", "min": "5", "max": "6", "mean": "5", "stdev": "0" }, { "name": "MWC05", "index": "39", "type": "numeric", "distinct": "328", "missing": "0", "min": "7", "max": "8", "mean": "8", "stdev": "0" }, { "name": "MWC06", "index": "40", "type": "numeric", "distinct": "333", "missing": "0", "min": "8", "max": "9", "mean": "9", "stdev": "0" }, { "name": "ICR", "index": "41", "type": "numeric", "distinct": "340", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "TIC2", "index": "42", "type": "numeric", "distinct": "560", "missing": "0", "min": "176", "max": "769", "mean": "354", "stdev": "72" }, { "name": "ZM2Per", "index": "43", "type": "numeric", "distinct": "584", "missing": "0", "min": "428", "max": "1452", "mean": "996", "stdev": "215" }, { "name": "ZM2V", "index": "44", "type": "numeric", "distinct": "330", "missing": "0", "min": "278", "max": "917", "mean": "634", "stdev": "134" }, { "name": "SpMin4_Bh.i.", "index": "45", "type": "numeric", "distinct": "200", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "Eig10_AEA.ed.", "index": "46", "type": "numeric", "distinct": "314", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "X5", "index": "47", "type": "numeric", "distinct": "478", "missing": "0", "min": "4", "max": "14", "mean": "10", "stdev": "2" }, { "name": "SpAD_EA.dm.", "index": "48", "type": "numeric", "distinct": "200", "missing": "0", "min": "1", "max": "40", "mean": "12", "stdev": "6" }, { "name": "SM02_EA.ed.", "index": "49", "type": "numeric", "distinct": "317", "missing": "0", "min": "6", "max": "8", "mean": "7", "stdev": "0" }, { "name": "S1K", "index": "50", "type": "numeric", "distinct": "444", "missing": "0", "min": "16", "max": "59", "mean": "30", "stdev": "6" }, { "name": "SM04_EA.ri.", "index": "51", "type": "numeric", "distinct": "394", "missing": "0", "min": "5", "max": "7", "mean": "6", "stdev": "0" }, { "name": "GGI7", "index": "52", "type": "numeric", "distinct": "342", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "Eig13_AEA.ed.", "index": "53", "type": "numeric", "distinct": "291", "missing": "0", "min": "2", "max": "5", "mean": "4", "stdev": "0" }, { "name": "ATSC2v", "index": "54", "type": "numeric", "distinct": "557", "missing": "0", "min": "8", "max": "30", "mean": "15", "stdev": "3" }, { "name": "Se", "index": "55", "type": "numeric", "distinct": "485", "missing": "0", "min": "40", "max": "144", "mean": "75", "stdev": "13" }, { "name": "Eig11_AEA.dm.", "index": "56", "type": "numeric", "distinct": "320", "missing": "0", "min": "0", "max": "3", "mean": "2", "stdev": "0" }, { "name": "SM04_EA", "index": "57", "type": "numeric", "distinct": "238", "missing": "0", "min": "6", "max": "7", "mean": "7", "stdev": "0" }, { "name": "ATS6v", "index": "58", "type": "numeric", "distinct": "411", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SpMax6_Bh.m.", "index": "59", "type": "numeric", "distinct": "284", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "X0v", "index": "60", "type": "numeric", "distinct": "533", "missing": "0", "min": "13", "max": "42", "mean": "24", "stdev": "4" }, { "name": "ATS7e", "index": "61", "type": "numeric", "distinct": "433", "missing": "0", "min": "5", "max": "6", "mean": "5", "stdev": "0" }, { "name": "TIC4", "index": "62", "type": "numeric", "distinct": "484", "missing": "0", "min": "198", "max": "938", "mean": "417", "stdev": "88" }, { "name": "MDDD", "index": "63", "type": "numeric", "distinct": "483", "missing": "0", "min": "17", "max": "135", "mean": "54", "stdev": "17" }, { "name": "VAR", "index": "64", "type": "numeric", "distinct": "226", "missing": "0", "min": "72", "max": "601", "mean": "233", "stdev": "84" }, { "name": "SRW10", "index": "65", "type": "numeric", "distinct": "351", "missing": "0", "min": "10", "max": "11", "mean": "11", "stdev": "0" }, { "name": "MPC03", "index": "66", "type": "numeric", "distinct": "66", "missing": "0", "min": "4", "max": "5", "mean": "4", "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 }