{ "data_id": "23900", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4078", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4078", "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: CHEMBL4078 (TID: 17018), and it has 1468 rows and 30 features (not including molecule IDs and class feature: molecule_id and pXC50). The features represent Basic 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 13:28:22", "update_comment": null, "last_update": "2016-07-14 13:28:22", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3235265\/data_41635.arff", "kaggle_url": null, "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 1, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4078", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL4078 (TID: 17018), and it has 1468 rows and 30 features (not including molecule IDs and class feature: molecule_id and pXC50). The features represent Basic 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": 1468, "NumberOfFeatures": 32, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 31, "NumberOfSymbolicFeatures": 1, "REPTreeDepth3AUC": null, "DecisionStumpAUC": null, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -0.7904899765160378, "Quartile2MeansOfNumericAtts": 14.289509536784735, "REPTreeDepth3ErrRate": null, "DecisionStumpErrRate": null, "MaxKurtosisOfNumericAtts": 22.98207503164403, "MinMeansOfNumericAtts": 0.04155313351498564, "Quartile2MutualInformation": null, "REPTreeDepth3Kappa": null, "DecisionStumpKappa": null, "MaxMeansOfNumericAtts": 416.1852111716621, "MinMutualInformation": null, "Quartile2SkewnessOfNumericAtts": 0.7266846224838456, "RandomTreeDepth1AUC": null, "Dimensionality": 0.021798365122615803, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 6.393713018950677, "RandomTreeDepth1ErrRate": null, "EquivalentNumberOfAtts": null, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -0.18291961086849587, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "RandomTreeDepth1Kappa": null, "J48.00001.AUC": null, "MaxSkewnessOfNumericAtts": 4.841958021459339, "MinStdDevOfNumericAtts": 0.016575285878448854, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 2.0299160823110802, "AutoCorrelation": 0.16602590320381805, "RandomTreeDepth2AUC": null, "J48.00001.ErrRate": null, "MaxStdDevOfNumericAtts": 117.55846676614996, "MinorityClassPercentage": null, "PercentageOfNumericFeatures": 96.875, "Quartile3MeansOfNumericAtts": 38.121643051771116, "CfsSubsetEval_DecisionStumpAUC": null, "RandomTreeDepth2ErrRate": null, "J48.00001.Kappa": null, "MeanAttributeEntropy": null, "MinorityClassSize": null, "PercentageOfSymbolicFeatures": 3.125, "Quartile3MutualInformation": null, "CfsSubsetEval_DecisionStumpErrRate": null, "RandomTreeDepth2Kappa": null, "J48.0001.AUC": null, "MeanKurtosisOfNumericAtts": 2.8098814838690926, "NaiveBayesAUC": null, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 1.0313293262073906, "CfsSubsetEval_DecisionStumpKappa": null, "CfsSubsetEval_NaiveBayesAUC": null, "RandomTreeDepth3AUC": null, "J48.0001.ErrRate": null, "MeanMeansOfNumericAtts": 33.22101599718731, "NaiveBayesErrRate": null, "Quartile1KurtosisOfNumericAtts": 1.038737024370589, "Quartile3StdDevOfNumericAtts": 10.82463170973966, "CfsSubsetEval_NaiveBayesErrRate": null, "RandomTreeDepth3ErrRate": null, "J48.0001.Kappa": null, "MeanMutualInformation": null, "NaiveBayesKappa": null, "Quartile1MeansOfNumericAtts": 2.739100817438692, "REPTreeDepth1AUC": null, "CfsSubsetEval_NaiveBayesKappa": null, "RandomTreeDepth3Kappa": null, "J48.001.AUC": null, "MeanNoiseToSignalRatio": null, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "REPTreeDepth1ErrRate": null, "CfsSubsetEval_kNN1NAUC": null, "StdvNominalAttDistinctValues": null, "J48.001.ErrRate": null, "MeanNominalAttDistinctValues": null, "Quartile1SkewnessOfNumericAtts": 0.5797953930456639, "REPTreeDepth1Kappa": null, "REPTreeDepth2AUC": null, "CfsSubsetEval_kNN1NErrRate": null, "kNN1NAUC": null, "J48.001.Kappa": null, "MeanSkewnessOfNumericAtts": 1.017467241814687, "Quartile1StdDevOfNumericAtts": 1.2847650953465217, "REPTreeDepth2ErrRate": null, "CfsSubsetEval_kNN1NKappa": null, "kNN1NErrRate": null, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 10.236427261615322, "Quartile2AttributeEntropy": null, "REPTreeDepth2Kappa": null, "ClassEntropy": null, "kNN1NKappa": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2KurtosisOfNumericAtts": 1.3125094412701057 }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "31", "type": "numeric", "distinct": "895", "missing": "0", "target": "1", "min": "4", "max": "10", "mean": "6", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "1468", "missing": "0", "identifier": "1", "distr": [] }, { "name": "nC", "index": "1", "type": "numeric", "distinct": "45", "missing": "0", "min": "6", "max": "61", "mean": "24", "stdev": "7" }, { "name": "Sp", "index": "2", "type": "numeric", "distinct": "1086", "missing": "0", "min": "13", "max": "98", "mean": "38", "stdev": "11" }, { "name": "nBT", "index": "3", "type": "numeric", "distinct": "101", "missing": "0", "min": "19", "max": "162", "mean": "61", "stdev": "19" }, { "name": "nAT", "index": "4", "type": "numeric", "distinct": "94", "missing": "0", "min": "19", "max": "153", "mean": "58", "stdev": "18" }, { "name": "Sv", "index": "5", "type": "numeric", "distinct": "1130", "missing": "0", "min": "12", "max": "94", "mean": "36", "stdev": "10" }, { "name": "nP", "index": "6", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "O.", "index": "7", "type": "numeric", "distinct": "146", "missing": "0", "min": "0", "max": "24", "mean": "5", "stdev": "4" }, { "name": "nSK", "index": "8", "type": "numeric", "distinct": "54", "missing": "0", "min": "11", "max": "79", "mean": "30", "stdev": "9" }, { "name": "Si", "index": "9", "type": "numeric", "distinct": "1146", "missing": "0", "min": "22", "max": "173", "mean": "65", "stdev": "20" }, { "name": "Me", "index": "10", "type": "numeric", "distinct": "92", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "nAB", "index": "11", "type": "numeric", "distinct": "27", "missing": "0", "min": "0", "max": "46", "mean": "14", "stdev": "8" }, { "name": "Se", "index": "12", "type": "numeric", "distinct": "1137", "missing": "0", "min": "20", "max": "154", "mean": "57", "stdev": "18" }, { "name": "AMW", "index": "13", "type": "numeric", "distinct": "950", "missing": "0", "min": "5", "max": "12", "mean": "7", "stdev": "1" }, { "name": "nH", "index": "14", "type": "numeric", "distinct": "59", "missing": "0", "min": "6", "max": "84", "mean": "27", "stdev": "11" }, { "name": "nBO", "index": "15", "type": "numeric", "distinct": "60", "missing": "0", "min": "10", "max": "88", "mean": "33", "stdev": "10" }, { "name": "nCsp2", "index": "16", "type": "numeric", "distinct": "35", "missing": "0", "min": "0", "max": "44", "mean": "15", "stdev": "6" }, { "name": "nCsp3", "index": "17", "type": "numeric", "distinct": "33", "missing": "0", "min": "0", "max": "33", "mean": "9", "stdev": "6" }, { "name": "nO", "index": "18", "type": "numeric", "distinct": "13", "missing": "0", "min": "0", "max": "12", "mean": "3", "stdev": "2" }, { "name": "nHM", "index": "19", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "6", "mean": "0", "stdev": "1" }, { "name": "H.", "index": "20", "type": "numeric", "distinct": "249", "missing": "0", "min": "13", "max": "65", "mean": "47", "stdev": "7" }, { "name": "nDB", "index": "21", "type": "numeric", "distinct": "8", "missing": "0", "min": "0", "max": "7", "mean": "2", "stdev": "2" }, { "name": "SCBO", "index": "22", "type": "numeric", "distinct": "123", "missing": "0", "min": "11", "max": "106", "mean": "42", "stdev": "13" }, { "name": "RBN", "index": "23", "type": "numeric", "distinct": "26", "missing": "0", "min": "0", "max": "30", "mean": "7", "stdev": "4" }, { "name": "MW", "index": "24", "type": "numeric", "distinct": "1122", "missing": "0", "min": "151", "max": "1083", "mean": "416", "stdev": "118" }, { "name": "nBM", "index": "25", "type": "numeric", "distinct": "38", "missing": "0", "min": "0", "max": "48", "mean": "16", "stdev": "7" }, { "name": "Mv", "index": "26", "type": "numeric", "distinct": "210", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "nN", "index": "27", "type": "numeric", "distinct": "9", "missing": "0", "min": "0", "max": "8", "mean": "3", "stdev": "2" }, { "name": "nHet", "index": "28", "type": "numeric", "distinct": "18", "missing": "0", "min": "1", "max": "24", "mean": "6", "stdev": "3" }, { "name": "nTB", "index": "29", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "0" }, { "name": "Mp", "index": "30", "type": "numeric", "distinct": "173", "missing": "0", "min": "1", "max": "1", "mean": "1", "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 }