{ "data_id": "23930", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL5850", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL5850", "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: CHEMBL5850 (TID: 101354), and it has 52 rows and 43 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).", "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 13:32:15", "update_comment": null, "last_update": "2016-07-14 13:32:15", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3235703\/data_36107.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-CHEMBL5850", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL5850 (TID: 101354), and it has 52 rows and 43 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). " ], "weight": 5 }, "qualities": { "NumberOfInstances": 52, "NumberOfFeatures": 45, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 44, "NumberOfSymbolicFeatures": 1, "REPTreeDepth3AUC": null, "DecisionStumpAUC": null, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.073445936044814, "Quartile2MeansOfNumericAtts": 7.5760288461538465, "REPTreeDepth3ErrRate": null, "DecisionStumpErrRate": null, "MaxKurtosisOfNumericAtts": 52.00000000000014, "MinMeansOfNumericAtts": 0, "Quartile2MutualInformation": null, "REPTreeDepth3Kappa": null, "DecisionStumpKappa": null, "MaxMeansOfNumericAtts": 637.6794230769231, "MinMutualInformation": null, "Quartile2SkewnessOfNumericAtts": 4.411201655180325, "RandomTreeDepth1AUC": null, "Dimensionality": 0.8653846153846154, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 2.582697885089659, "RandomTreeDepth1ErrRate": null, "EquivalentNumberOfAtts": null, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -0.7489696519717134, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "RandomTreeDepth1Kappa": null, "J48.00001.AUC": null, "MaxSkewnessOfNumericAtts": 7.211102550927982, "MinStdDevOfNumericAtts": 0, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 22.872140084261503, "AutoCorrelation": 0.1659607843137256, "RandomTreeDepth2AUC": null, "J48.00001.ErrRate": null, "MaxStdDevOfNumericAtts": 481.7213052492418, "MinorityClassPercentage": null, "PercentageOfNumericFeatures": 97.77777777777777, "Quartile3MeansOfNumericAtts": 43.846634615384616, "CfsSubsetEval_DecisionStumpAUC": null, "RandomTreeDepth2ErrRate": null, "J48.00001.Kappa": null, "MeanAttributeEntropy": null, "MinorityClassSize": null, "PercentageOfSymbolicFeatures": 2.2222222222222223, "Quartile3MutualInformation": null, "CfsSubsetEval_DecisionStumpErrRate": null, "RandomTreeDepth2Kappa": null, "J48.0001.AUC": null, "MeanKurtosisOfNumericAtts": 15.395896070459388, "NaiveBayesAUC": null, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 4.832268954229308, "CfsSubsetEval_DecisionStumpKappa": null, "CfsSubsetEval_NaiveBayesAUC": null, "RandomTreeDepth3AUC": null, "J48.0001.ErrRate": null, "MeanMeansOfNumericAtts": 35.33649475524476, "NaiveBayesErrRate": null, "Quartile1KurtosisOfNumericAtts": 0.7951676415362006, "Quartile3StdDevOfNumericAtts": 29.691836360899288, "CfsSubsetEval_NaiveBayesErrRate": null, "RandomTreeDepth3ErrRate": null, "J48.0001.Kappa": null, "MeanMutualInformation": null, "NaiveBayesKappa": null, "Quartile1MeansOfNumericAtts": 0.7319663461538461, "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": 0.7875845981487416, "REPTreeDepth1Kappa": null, "REPTreeDepth2AUC": null, "CfsSubsetEval_kNN1NErrRate": null, "kNN1NAUC": null, "J48.001.Kappa": null, "MeanSkewnessOfNumericAtts": 3.1865047393481283, "Quartile1StdDevOfNumericAtts": 0.20936109418246676, "REPTreeDepth2ErrRate": null, "CfsSubsetEval_kNN1NKappa": null, "kNN1NErrRate": null, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 25.191516122925172, "Quartile2AttributeEntropy": null, "REPTreeDepth2Kappa": null, "ClassEntropy": null, "kNN1NKappa": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2KurtosisOfNumericAtts": 20.097069921351167 }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "44", "type": "numeric", "distinct": "48", "missing": "0", "target": "1", "min": "4", "max": "8", "mean": "6", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "52", "missing": "0", "identifier": "1", "distr": [] }, { "name": "AMW", "index": "1", "type": "numeric", "distinct": "44", "missing": "0", "min": "7", "max": "9", "mean": "8", "stdev": "0" }, { "name": "C.", "index": "2", "type": "numeric", "distinct": "33", "missing": "0", "min": "34", "max": "46", "mean": "41", "stdev": "3" }, { "name": "H.", "index": "3", "type": "numeric", "distinct": "32", "missing": "0", "min": "41", "max": "50", "mean": "45", "stdev": "2" }, { "name": "Me", "index": "4", "type": "numeric", "distinct": "17", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Mi", "index": "5", "type": "numeric", "distinct": "24", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Mp", "index": "6", "type": "numeric", "distinct": "35", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Mv", "index": "7", "type": "numeric", "distinct": "35", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "MW", "index": "8", "type": "numeric", "distinct": "44", "missing": "0", "min": "353", "max": "3157", "mean": "638", "stdev": "482" }, { "name": "N.", "index": "9", "type": "numeric", "distinct": "23", "missing": "0", "min": "7", "max": "11", "mean": "9", "stdev": "1" }, { "name": "nAB", "index": "10", "type": "numeric", "distinct": "9", "missing": "0", "min": "6", "max": "50", "mean": "19", "stdev": "7" }, { "name": "nAT", "index": "11", "type": "numeric", "distinct": "25", "missing": "0", "min": "46", "max": "431", "mean": "83", "stdev": "66" }, { "name": "nB", "index": "12", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "nBM", "index": "13", "type": "numeric", "distinct": "14", "missing": "0", "min": "10", "max": "82", "mean": "23", "stdev": "11" }, { "name": "nBO", "index": "14", "type": "numeric", "distinct": "21", "missing": "0", "min": "28", "max": "233", "mean": "49", "stdev": "35" }, { "name": "nBR", "index": "15", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "nBT", "index": "16", "type": "numeric", "distinct": "26", "missing": "0", "min": "49", "max": "440", "mean": "87", "stdev": "67" }, { "name": "nC", "index": "17", "type": "numeric", "distinct": "17", "missing": "0", "min": "20", "max": "147", "mean": "33", "stdev": "22" }, { "name": "nCL", "index": "18", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "nCsp", "index": "19", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "nCsp2", "index": "20", "type": "numeric", "distinct": "13", "missing": "0", "min": "11", "max": "78", "mean": "22", "stdev": "11" }, { "name": "nCsp3", "index": "21", "type": "numeric", "distinct": "15", "missing": "0", "min": "4", "max": "69", "mean": "11", "stdev": "11" }, { "name": "nDB", "index": "22", "type": "numeric", "distinct": "8", "missing": "0", "min": "0", "max": "32", "mean": "4", "stdev": "6" }, { "name": "nF", "index": "23", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "1" }, { "name": "nH", "index": "24", "type": "numeric", "distinct": "21", "missing": "0", "min": "21", "max": "207", "mean": "37", "stdev": "32" }, { "name": "nHet", "index": "25", "type": "numeric", "distinct": "10", "missing": "0", "min": "5", "max": "77", "mean": "12", "stdev": "13" }, { "name": "nHM", "index": "26", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "nI", "index": "27", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "nN", "index": "28", "type": "numeric", "distinct": "7", "missing": "0", "min": "4", "max": "41", "mean": "7", "stdev": "7" }, { "name": "nO", "index": "29", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "34", "mean": "3", "stdev": "6" }, { "name": "nP", "index": "30", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "nS", "index": "31", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "nSK", "index": "32", "type": "numeric", "distinct": "19", "missing": "0", "min": "25", "max": "224", "mean": "45", "stdev": "34" }, { "name": "nTB", "index": "33", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "nX", "index": "34", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "O.", "index": "35", "type": "numeric", "distinct": "27", "missing": "0", "min": "0", "max": "8", "mean": "3", "stdev": "1" }, { "name": "RBF", "index": "36", "type": "numeric", "distinct": "31", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "RBN", "index": "37", "type": "numeric", "distinct": "11", "missing": "0", "min": "5", "max": "99", "mean": "11", "stdev": "17" }, { "name": "SCBO", "index": "38", "type": "numeric", "distinct": "29", "missing": "0", "min": "37", "max": "290", "mean": "63", "stdev": "43" }, { "name": "Se", "index": "39", "type": "numeric", "distinct": "44", "missing": "0", "min": "46", "max": "437", "mean": "83", "stdev": "68" }, { "name": "Si", "index": "40", "type": "numeric", "distinct": "44", "missing": "0", "min": "52", "max": "493", "mean": "94", "stdev": "76" }, { "name": "Sp", "index": "41", "type": "numeric", "distinct": "44", "missing": "0", "min": "32", "max": "270", "mean": "55", "stdev": "41" }, { "name": "Sv", "index": "42", "type": "numeric", "distinct": "44", "missing": "0", "min": "30", "max": "259", "mean": "52", "stdev": "39" }, { "name": "X.", "index": "43", "type": "numeric", "distinct": "17", "missing": "0", "min": "0", "max": "5", "mean": "2", "stdev": "1" } ], "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 }