{ "data_id": "23650", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL5351", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL5351", "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: CHEMBL5351 (TID: 101163), and it has 77 rows and 59 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 12:55:35", "update_comment": null, "last_update": "2016-07-14 12:55:35", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3230127\/data_51919.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL5351", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL5351 (TID: 101163), and it has 77 rows and 59 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": 77, "NumberOfFeatures": 61, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 60, "NumberOfSymbolicFeatures": 1, "REPTreeDepth3Kappa": null, "DecisionStumpKappa": null, "MaxMeansOfNumericAtts": 35.01945454545454, "MinMutualInformation": null, "Quartile2SkewnessOfNumericAtts": 0.30837375588251326, "RandomTreeDepth1AUC": null, "Dimensionality": 0.7922077922077922, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 1.1157550086960115, "RandomTreeDepth1ErrRate": null, "EquivalentNumberOfAtts": null, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -0.2449157968094508, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "RandomTreeDepth1Kappa": null, "J48.00001.AUC": null, "MaxSkewnessOfNumericAtts": 2.628551862664996, "MinStdDevOfNumericAtts": 0.1887618677605131, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 0.20470240262051487, "AutoCorrelation": 0.3627236842105262, "RandomTreeDepth2AUC": null, "J48.00001.ErrRate": null, "MaxStdDevOfNumericAtts": 46.980245735344816, "MinorityClassPercentage": null, "PercentageOfNumericFeatures": 98.36065573770492, "Quartile3MeansOfNumericAtts": 16.816318181818183, "CfsSubsetEval_DecisionStumpAUC": null, "RandomTreeDepth2ErrRate": null, "J48.00001.Kappa": null, "MeanAttributeEntropy": null, "MinorityClassSize": null, "PercentageOfSymbolicFeatures": 1.639344262295082, "Quartile3MutualInformation": null, "CfsSubsetEval_DecisionStumpErrRate": null, "RandomTreeDepth2Kappa": null, "J48.0001.AUC": null, "MeanKurtosisOfNumericAtts": -0.2160942207708587, "NaiveBayesAUC": null, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 0.4703187560530165, "CfsSubsetEval_DecisionStumpKappa": null, "RandomTreeDepth3AUC": null, "J48.0001.ErrRate": null, "MeanMeansOfNumericAtts": 10.681009307359307, "NaiveBayesErrRate": null, "Quartile1KurtosisOfNumericAtts": -1.0168086328665962, "Quartile3StdDevOfNumericAtts": 1.9614888598210003, "CfsSubsetEval_NaiveBayesAUC": null, "RandomTreeDepth3ErrRate": null, "J48.0001.Kappa": null, "MeanMutualInformation": null, "NaiveBayesKappa": null, "Quartile1MeansOfNumericAtts": 3.2990714285714287, "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": 0.14991013888310178, "REPTreeDepth1Kappa": null, "CfsSubsetEval_kNN1NErrRate": null, "kNN1NAUC": null, "J48.001.Kappa": null, "MeanSkewnessOfNumericAtts": 0.3864383612587945, "Quartile1StdDevOfNumericAtts": 0.5891838256550425, "REPTreeDepth2AUC": null, "CfsSubsetEval_kNN1NKappa": null, "kNN1NErrRate": null, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 2.465918428700782, "Quartile2AttributeEntropy": null, "REPTreeDepth2ErrRate": null, "ClassEntropy": null, "kNN1NKappa": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2KurtosisOfNumericAtts": -0.3361993650422701, "REPTreeDepth2Kappa": null, "REPTreeDepth3AUC": null, "DecisionStumpAUC": null, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.6243730895753483, "Quartile2MeansOfNumericAtts": 6.627876623376624, "REPTreeDepth3ErrRate": null, "DecisionStumpErrRate": null, "MaxKurtosisOfNumericAtts": 7.0593255996033974, "MinMeansOfNumericAtts": 0.3405584415584416, "Quartile2MutualInformation": null }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "60", "type": "numeric", "distinct": "65", "missing": "0", "target": "1", "min": "4", "max": "7", "mean": "5", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "77", "missing": "0", "identifier": "1", "distr": [] }, { "name": "Eig02_EA.dm.", "index": "1", "type": "numeric", "distinct": "22", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "Eig02_AEA.dm.", "index": "2", "type": "numeric", "distinct": "35", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "Eig01_AEA.bo.", "index": "3", "type": "numeric", "distinct": "29", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SpMax_AEA.bo.", "index": "4", "type": "numeric", "distinct": "29", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SpAD_EA.dm.", "index": "5", "type": "numeric", "distinct": "27", "missing": "0", "min": "0", "max": "20", "mean": "7", "stdev": "5" }, { "name": "SM03_EA.dm.", "index": "6", "type": "numeric", "distinct": "14", "missing": "0", "min": "0", "max": "4", "mean": "2", "stdev": "1" }, { "name": "SM05_EA.dm.", "index": "7", "type": "numeric", "distinct": "19", "missing": "0", "min": "0", "max": "7", "mean": "3", "stdev": "2" }, { "name": "SM07_EA.dm.", "index": "8", "type": "numeric", "distinct": "19", "missing": "0", "min": "0", "max": "10", "mean": "4", "stdev": "3" }, { "name": "SM09_EA.dm.", "index": "9", "type": "numeric", "distinct": "18", "missing": "0", "min": "0", "max": "13", "mean": "6", "stdev": "4" }, { "name": "SpDiam_AEA.bo.", "index": "10", "type": "numeric", "distinct": "63", "missing": "0", "min": "5", "max": "6", "mean": "5", "stdev": "0" }, { "name": "SM02_EA.dm.", "index": "11", "type": "numeric", "distinct": "27", "missing": "0", "min": "0", "max": "4", "mean": "2", "stdev": "1" }, { "name": "Eig01_AEA.ed.", "index": "12", "type": "numeric", "distinct": "23", "missing": "0", "min": "6", "max": "8", "mean": "7", "stdev": "0" }, { "name": "Eig01_EA", "index": "13", "type": "numeric", "distinct": "26", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "Eig01_EA.ed.", "index": "14", "type": "numeric", "distinct": "26", "missing": "0", "min": "8", "max": "15", "mean": "10", "stdev": "1" }, { "name": "SM09_AEA.bo.", "index": "15", "type": "numeric", "distinct": "26", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SM10_AEA.dm.", "index": "16", "type": "numeric", "distinct": "26", "missing": "0", "min": "8", "max": "15", "mean": "10", "stdev": "1" }, { "name": "SpDiam_AEA.ed.", "index": "17", "type": "numeric", "distinct": "62", "missing": "0", "min": "6", "max": "8", "mean": "6", "stdev": "0" }, { "name": "SpDiam_EA", "index": "18", "type": "numeric", "distinct": "40", "missing": "0", "min": "5", "max": "6", "mean": "5", "stdev": "0" }, { "name": "SpDiam_EA.ed.", "index": "19", "type": "numeric", "distinct": "29", "missing": "0", "min": "14", "max": "23", "mean": "17", "stdev": "2" }, { "name": "SpMax_AEA.ed.", "index": "20", "type": "numeric", "distinct": "23", "missing": "0", "min": "6", "max": "8", "mean": "7", "stdev": "0" }, { "name": "SpMax_EA", "index": "21", "type": "numeric", "distinct": "26", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SpMax_EA.ed.", "index": "22", "type": "numeric", "distinct": "26", "missing": "0", "min": "8", "max": "15", "mean": "10", "stdev": "1" }, { "name": "SM06_EA.dm.", "index": "23", "type": "numeric", "distinct": "26", "missing": "0", "min": "0", "max": "10", "mean": "4", "stdev": "3" }, { "name": "SM08_EA.dm.", "index": "24", "type": "numeric", "distinct": "25", "missing": "0", "min": "0", "max": "12", "mean": "5", "stdev": "4" }, { "name": "SM11_EA.dm.", "index": "25", "type": "numeric", "distinct": "18", "missing": "0", "min": "0", "max": "16", "mean": "7", "stdev": "5" }, { "name": "SM13_EA.dm.", "index": "26", "type": "numeric", "distinct": "17", "missing": "0", "min": "0", "max": "20", "mean": "8", "stdev": "6" }, { "name": "SM15_EA.dm.", "index": "27", "type": "numeric", "distinct": "16", "missing": "0", "min": "0", "max": "23", "mean": "10", "stdev": "7" }, { "name": "SM04_EA.dm.", "index": "28", "type": "numeric", "distinct": "27", "missing": "0", "min": "0", "max": "7", "mean": "3", "stdev": "2" }, { "name": "SM10_EA.dm.", "index": "29", "type": "numeric", "distinct": "25", "missing": "0", "min": "0", "max": "15", "mean": "7", "stdev": "5" }, { "name": "SM12_EA.dm.", "index": "30", "type": "numeric", "distinct": "24", "missing": "0", "min": "0", "max": "18", "mean": "8", "stdev": "6" }, { "name": "SM14_EA.dm.", "index": "31", "type": "numeric", "distinct": "23", "missing": "0", "min": "0", "max": "21", "mean": "9", "stdev": "7" }, { "name": "Eig01_AEA.ri.", "index": "32", "type": "numeric", "distinct": "36", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SM11_EA.ed.", "index": "33", "type": "numeric", "distinct": "29", "missing": "0", "min": "23", "max": "30", "mean": "26", "stdev": "1" }, { "name": "SM12_EA.ed.", "index": "34", "type": "numeric", "distinct": "30", "missing": "0", "min": "25", "max": "33", "mean": "28", "stdev": "2" }, { "name": "SM13_EA.ed.", "index": "35", "type": "numeric", "distinct": "29", "missing": "0", "min": "27", "max": "36", "mean": "30", "stdev": "2" }, { "name": "SM14_EA.ed.", "index": "36", "type": "numeric", "distinct": "29", "missing": "0", "min": "29", "max": "38", "mean": "33", "stdev": "2" }, { "name": "SM15_EA.ed.", "index": "37", "type": "numeric", "distinct": "28", "missing": "0", "min": "31", "max": "41", "mean": "35", "stdev": "2" }, { "name": "SpMax_AEA.ri.", "index": "38", "type": "numeric", "distinct": "36", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "Eig01_EA.dm.", "index": "39", "type": "numeric", "distinct": "17", "missing": "0", "min": "0", "max": "5", "mean": "2", "stdev": "1" }, { "name": "SpDiam_EA.dm.", "index": "40", "type": "numeric", "distinct": "21", "missing": "0", "min": "0", "max": "9", "mean": "4", "stdev": "2" }, { "name": "SpMax_EA.dm.", "index": "41", "type": "numeric", "distinct": "17", "missing": "0", "min": "0", "max": "5", "mean": "2", "stdev": "1" }, { "name": "SM05_EA.ed.", "index": "42", "type": "numeric", "distinct": "27", "missing": "0", "min": "10", "max": "14", "mean": "12", "stdev": "1" }, { "name": "SM06_EA.ed.", "index": "43", "type": "numeric", "distinct": "59", "missing": "0", "min": "13", "max": "17", "mean": "14", "stdev": "1" }, { "name": "SM07_EA.ed.", "index": "44", "type": "numeric", "distinct": "27", "missing": "0", "min": "15", "max": "19", "mean": "16", "stdev": "1" }, { "name": "SM08_EA.ed.", "index": "45", "type": "numeric", "distinct": "43", "missing": "0", "min": "17", "max": "22", "mean": "19", "stdev": "1" }, { "name": "SM09_EA.ed.", "index": "46", "type": "numeric", "distinct": "28", "missing": "0", "min": "19", "max": "25", "mean": "21", "stdev": "1" }, { "name": "SM10_EA.ed.", "index": "47", "type": "numeric", "distinct": "29", "missing": "0", "min": "21", "max": "27", "mean": "23", "stdev": "1" }, { "name": "SM12_AEA.ed.", "index": "48", "type": "numeric", "distinct": "50", "missing": "0", "min": "21", "max": "25", "mean": "23", "stdev": "1" }, { "name": "SM13_AEA.ed.", "index": "49", "type": "numeric", "distinct": "45", "missing": "0", "min": "23", "max": "27", "mean": "25", "stdev": "1" }, { "name": "SM13_EA", "index": "50", "type": "numeric", "distinct": "30", "missing": "0", "min": "13", "max": "17", "mean": "15", "stdev": "1" }, { "name": "SM14_AEA.ed.", "index": "51", "type": "numeric", "distinct": "37", "missing": "0", "min": "25", "max": "29", "mean": "26", "stdev": "1" }, { "name": "SM14_EA", "index": "52", "type": "numeric", "distinct": "52", "missing": "0", "min": "14", "max": "18", "mean": "16", "stdev": "1" }, { "name": "SM15_AEA.ed.", "index": "53", "type": "numeric", "distinct": "37", "missing": "0", "min": "26", "max": "32", "mean": "28", "stdev": "1" }, { "name": "SM15_EA", "index": "54", "type": "numeric", "distinct": "31", "missing": "0", "min": "15", "max": "20", "mean": "17", "stdev": "1" }, { "name": "Eig03_EA.dm.", "index": "55", "type": "numeric", "distinct": "19", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "C.040", "index": "56", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "1" }, { "name": "SpMAD_EA.dm.", "index": "57", "type": "numeric", "distinct": "58", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "CATS2D_02_AL", "index": "58", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "6", "mean": "2", "stdev": "1" }, { "name": "P_VSA_MR_7", "index": "59", "type": "numeric", "distinct": "14", "missing": "0", "min": "0", "max": "237", "mean": "23", "stdev": "47" } ], "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 }