{ "data_id": "24312", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL5387", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL5387", "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: CHEMBL5387 (TID: 100968), and it has 160 rows and 61 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 14:22:43", "update_comment": null, "last_update": "2016-07-14 14:22:43", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3243689\/data_52308.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL5387", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL5387 (TID: 100968), and it has 160 rows and 61 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": 160, "NumberOfFeatures": 63, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 62, "NumberOfSymbolicFeatures": 1, "REPTreeDepth3Kappa": null, "DecisionStumpKappa": null, "MaxMeansOfNumericAtts": 59.3027875, "MinMutualInformation": null, "Quartile2SkewnessOfNumericAtts": -0.51204179975275, "RandomTreeDepth1AUC": null, "Dimensionality": 0.39375, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.4075262252378582, "RandomTreeDepth1ErrRate": null, "EquivalentNumberOfAtts": null, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -1.5789149034104943, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "RandomTreeDepth1Kappa": null, "J48.00001.AUC": null, "MaxSkewnessOfNumericAtts": 3.0943962163370733, "MinStdDevOfNumericAtts": 0.007954657272758145, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 1.2563766503798115, "AutoCorrelation": 0.2815597484276728, "RandomTreeDepth2AUC": null, "J48.00001.ErrRate": null, "MaxStdDevOfNumericAtts": 68.71248684268016, "MinorityClassPercentage": null, "PercentageOfNumericFeatures": 98.4126984126984, "Quartile3MeansOfNumericAtts": 6.312265625, "CfsSubsetEval_DecisionStumpAUC": null, "RandomTreeDepth2ErrRate": null, "J48.00001.Kappa": null, "MeanAttributeEntropy": null, "MinorityClassSize": null, "PercentageOfSymbolicFeatures": 1.5873015873015872, "Quartile3MutualInformation": null, "CfsSubsetEval_DecisionStumpErrRate": null, "RandomTreeDepth2Kappa": null, "J48.0001.AUC": null, "MeanKurtosisOfNumericAtts": 0.8993327414203253, "NaiveBayesAUC": null, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 0.581149451182418, "CfsSubsetEval_DecisionStumpKappa": null, "RandomTreeDepth3AUC": null, "J48.0001.ErrRate": null, "MeanMeansOfNumericAtts": 6.001417137096774, "NaiveBayesErrRate": null, "Quartile1KurtosisOfNumericAtts": -0.2788796090709724, "Quartile3StdDevOfNumericAtts": 0.78086448818472, "CfsSubsetEval_NaiveBayesAUC": null, "RandomTreeDepth3ErrRate": null, "J48.0001.Kappa": null, "MeanMutualInformation": null, "NaiveBayesKappa": null, "Quartile1MeansOfNumericAtts": 0.6596015625000001, "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": -0.9252314471436253, "REPTreeDepth1Kappa": null, "CfsSubsetEval_kNN1NErrRate": null, "kNN1NAUC": null, "J48.001.Kappa": null, "MeanSkewnessOfNumericAtts": -0.0008215505090655515, "Quartile1StdDevOfNumericAtts": 0.15087627800137496, "REPTreeDepth2AUC": null, "CfsSubsetEval_kNN1NKappa": null, "kNN1NErrRate": null, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 1.9734394397396473, "Quartile2AttributeEntropy": null, "REPTreeDepth2ErrRate": null, "ClassEntropy": null, "kNN1NKappa": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2KurtosisOfNumericAtts": 0.1313363945141186, "REPTreeDepth2Kappa": null, "REPTreeDepth3AUC": null, "DecisionStumpAUC": null, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.1033908675183777, "Quartile2MeansOfNumericAtts": 3.1853, "REPTreeDepth3ErrRate": null, "DecisionStumpErrRate": null, "MaxKurtosisOfNumericAtts": 9.846583770462074, "MinMeansOfNumericAtts": 0.0736375, "Quartile2MutualInformation": null }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "62", "type": "numeric", "distinct": "115", "missing": "0", "target": "1", "min": "4", "max": "9", "mean": "6", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "160", "missing": "0", "identifier": "1", "distr": [] }, { "name": "SpDiam_EA.bo.", "index": "1", "type": "numeric", "distinct": "55", "missing": "0", "min": "6", "max": "8", "mean": "7", "stdev": "0" }, { "name": "Eig07_EA.bo.", "index": "2", "type": "numeric", "distinct": "82", "missing": "0", "min": "2", "max": "3", "mean": "2", "stdev": "0" }, { "name": "Eig01_EA.bo.", "index": "3", "type": "numeric", "distinct": "54", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SM11_AEA.ri.", "index": "4", "type": "numeric", "distinct": "54", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SpMax_EA.bo.", "index": "5", "type": "numeric", "distinct": "54", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "DLS_cons", "index": "6", "type": "numeric", "distinct": "25", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SM15_EA.bo.", "index": "7", "type": "numeric", "distinct": "92", "missing": "0", "min": "19", "max": "23", "mean": "22", "stdev": "1" }, { "name": "Eig06_AEA.bo.", "index": "8", "type": "numeric", "distinct": "89", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "Eig08_AEA.bo.", "index": "9", "type": "numeric", "distinct": "76", "missing": "0", "min": "3", "max": "3", "mean": "3", "stdev": "0" }, { "name": "SM13_EA.bo.", "index": "10", "type": "numeric", "distinct": "94", "missing": "0", "min": "17", "max": "20", "mean": "19", "stdev": "1" }, { "name": "SM14_EA.bo.", "index": "11", "type": "numeric", "distinct": "93", "missing": "0", "min": "18", "max": "22", "mean": "21", "stdev": "1" }, { "name": "SM11_EA.bo.", "index": "12", "type": "numeric", "distinct": "96", "missing": "0", "min": "14", "max": "17", "mean": "16", "stdev": "1" }, { "name": "SM12_EA.bo.", "index": "13", "type": "numeric", "distinct": "94", "missing": "0", "min": "16", "max": "19", "mean": "18", "stdev": "1" }, { "name": "Eig13_AEA.bo.", "index": "14", "type": "numeric", "distinct": "69", "missing": "0", "min": "1", "max": "3", "mean": "2", "stdev": "1" }, { "name": "Eig08_EA", "index": "15", "type": "numeric", "distinct": "66", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "SM02_AEA.dm.", "index": "16", "type": "numeric", "distinct": "66", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "RBF", "index": "17", "type": "numeric", "distinct": "61", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "GATS5m", "index": "18", "type": "numeric", "distinct": "110", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "nRCONHR", "index": "19", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "nRCOOR", "index": "20", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "PW3", "index": "21", "type": "numeric", "distinct": "46", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "S3K", "index": "22", "type": "numeric", "distinct": "115", "missing": "0", "min": "3", "max": "9", "mean": "5", "stdev": "1" }, { "name": "SdsCH", "index": "23", "type": "numeric", "distinct": "18", "missing": "0", "min": "0", "max": "4", "mean": "0", "stdev": "1" }, { "name": "SpMax1_Bh.e.", "index": "24", "type": "numeric", "distinct": "61", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "SpMax1_Bh.i.", "index": "25", "type": "numeric", "distinct": "66", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "SpMax1_Bh.p.", "index": "26", "type": "numeric", "distinct": "73", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "SpMax1_Bh.v.", "index": "27", "type": "numeric", "distinct": "70", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "X2A", "index": "28", "type": "numeric", "distinct": "41", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "X3A", "index": "29", "type": "numeric", "distinct": "35", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "X4A", "index": "30", "type": "numeric", "distinct": "33", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "X5A", "index": "31", "type": "numeric", "distinct": "28", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SM03_EA.bo.", "index": "32", "type": "numeric", "distinct": "48", "missing": "0", "min": "4", "max": "5", "mean": "5", "stdev": "0" }, { "name": "Eig13_EA.bo.", "index": "33", "type": "numeric", "distinct": "71", "missing": "0", "min": "-2", "max": "2", "mean": "1", "stdev": "1" }, { "name": "nCrt", "index": "34", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "7", "mean": "1", "stdev": "2" }, { "name": "nCt", "index": "35", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "7", "mean": "1", "stdev": "2" }, { "name": "Chi1_EA.dm.", "index": "36", "type": "numeric", "distinct": "107", "missing": "0", "min": "0", "max": "56", "mean": "24", "stdev": "12" }, { "name": "Eig07_AEA.bo.", "index": "37", "type": "numeric", "distinct": "76", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SM09_EA.bo.", "index": "38", "type": "numeric", "distinct": "93", "missing": "0", "min": "12", "max": "14", "mean": "13", "stdev": "1" }, { "name": "Eig08_EA.bo.", "index": "39", "type": "numeric", "distinct": "82", "missing": "0", "min": "2", "max": "3", "mean": "2", "stdev": "0" }, { "name": "Eig09_AEA.bo.", "index": "40", "type": "numeric", "distinct": "74", "missing": "0", "min": "2", "max": "3", "mean": "3", "stdev": "0" }, { "name": "GGI10", "index": "41", "type": "numeric", "distinct": "81", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Eig08_AEA.ri.", "index": "42", "type": "numeric", "distinct": "101", "missing": "0", "min": "2", "max": "3", "mean": "3", "stdev": "0" }, { "name": "SpMax1_Bh.m.", "index": "43", "type": "numeric", "distinct": "78", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "C.003", "index": "44", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "6", "mean": "1", "stdev": "2" }, { "name": "Eig09_EA.ed.", "index": "45", "type": "numeric", "distinct": "85", "missing": "0", "min": "2", "max": "5", "mean": "3", "stdev": "1" }, { "name": "SM04_AEA.ri.", "index": "46", "type": "numeric", "distinct": "85", "missing": "0", "min": "2", "max": "5", "mean": "3", "stdev": "1" }, { "name": "piPC06", "index": "47", "type": "numeric", "distinct": "97", "missing": "0", "min": "5", "max": "7", "mean": "6", "stdev": "1" }, { "name": "piPC08", "index": "48", "type": "numeric", "distinct": "99", "missing": "0", "min": "5", "max": "8", "mean": "7", "stdev": "1" }, { "name": "piPC09", "index": "49", "type": "numeric", "distinct": "101", "missing": "0", "min": "5", "max": "8", "mean": "7", "stdev": "1" }, { "name": "piPC10", "index": "50", "type": "numeric", "distinct": "99", "missing": "0", "min": "5", "max": "9", "mean": "7", "stdev": "1" }, { "name": "SM10_EA.bo.", "index": "51", "type": "numeric", "distinct": "93", "missing": "0", "min": "13", "max": "16", "mean": "15", "stdev": "1" }, { "name": "Eig14_AEA.ri.", "index": "52", "type": "numeric", "distinct": "91", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "1" }, { "name": "Eig14_EA.ri.", "index": "53", "type": "numeric", "distinct": "91", "missing": "0", "min": "-1", "max": "1", "mean": "0", "stdev": "1" }, { "name": "C.034", "index": "54", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "1" }, { "name": "D.Dtr09", "index": "55", "type": "numeric", "distinct": "50", "missing": "0", "min": "0", "max": "255", "mean": "59", "stdev": "69" }, { "name": "SM03_AEA.bo.", "index": "56", "type": "numeric", "distinct": "84", "missing": "0", "min": "6", "max": "7", "mean": "6", "stdev": "0" }, { "name": "C.016", "index": "57", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "Eig02_AEA.bo.", "index": "58", "type": "numeric", "distinct": "75", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "NdsCH", "index": "59", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "P_VSA_LogP_2", "index": "60", "type": "numeric", "distinct": "60", "missing": "0", "min": "0", "max": "60", "mean": "29", "stdev": "13" }, { "name": "PW4", "index": "61", "type": "numeric", "distinct": "48", "missing": "0", "min": "0", "max": "0", "mean": "0", "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 }