{ "data_id": "24431", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL2065", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL2065", "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: CHEMBL2065 (TID: 13), and it has 182 rows and 68 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 14:38:12", "update_comment": null, "last_update": "2016-07-14 14:38:12", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3245938\/data_53399.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL2065", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL2065 (TID: 13), and it has 182 rows and 68 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": 182, "NumberOfFeatures": 70, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 69, "NumberOfSymbolicFeatures": 1, "REPTreeDepth3ErrRate": null, "DecisionStumpErrRate": null, "MaxKurtosisOfNumericAtts": 30.601586105983678, "MinMeansOfNumericAtts": 0.11523626373626374, "Quartile2MutualInformation": null, "REPTreeDepth3Kappa": null, "DecisionStumpKappa": null, "MaxMeansOfNumericAtts": 170.6191813186813, "MinMutualInformation": null, "Quartile2SkewnessOfNumericAtts": 0.08865580600111703, "RandomTreeDepth1AUC": null, "Dimensionality": 0.38461538461538464, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.7887427166303722, "RandomTreeDepth1ErrRate": null, "EquivalentNumberOfAtts": null, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -1.637045681455028, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "RandomTreeDepth1Kappa": null, "J48.00001.AUC": null, "MaxSkewnessOfNumericAtts": 4.398633474920775, "MinStdDevOfNumericAtts": 0.013124536008925351, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 2.307576574043338, "AutoCorrelation": -0.30986187845303825, "RandomTreeDepth2AUC": null, "J48.00001.ErrRate": null, "MaxStdDevOfNumericAtts": 57.813674145330076, "MinorityClassPercentage": null, "PercentageOfNumericFeatures": 98.57142857142858, "Quartile3MeansOfNumericAtts": 5.625975274725275, "CfsSubsetEval_DecisionStumpAUC": null, "RandomTreeDepth2ErrRate": null, "J48.00001.Kappa": null, "MeanAttributeEntropy": null, "MinorityClassSize": null, "PercentageOfSymbolicFeatures": 1.4285714285714286, "Quartile3MutualInformation": null, "CfsSubsetEval_DecisionStumpErrRate": null, "RandomTreeDepth2Kappa": null, "J48.0001.AUC": null, "MeanKurtosisOfNumericAtts": 2.286391208361459, "NaiveBayesAUC": null, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 0.9880264993960719, "CfsSubsetEval_DecisionStumpKappa": null, "RandomTreeDepth3AUC": null, "J48.0001.ErrRate": null, "MeanMeansOfNumericAtts": 15.48827337155598, "NaiveBayesErrRate": null, "Quartile1KurtosisOfNumericAtts": -0.6076030461334936, "Quartile3StdDevOfNumericAtts": 3.183776002137564, "CfsSubsetEval_NaiveBayesAUC": null, "RandomTreeDepth3ErrRate": null, "J48.0001.Kappa": null, "MeanMutualInformation": null, "NaiveBayesKappa": null, "Quartile1MeansOfNumericAtts": 0.879326923076923, "REPTreeDepth1AUC": null, "CfsSubsetEval_NaiveBayesErrRate": null, "RandomTreeDepth3Kappa": null, "J48.001.AUC": null, "MeanNoiseToSignalRatio": null, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "REPTreeDepth1ErrRate": null, "CfsSubsetEval_NaiveBayesKappa": null, "StdvNominalAttDistinctValues": null, "J48.001.ErrRate": null, "MeanNominalAttDistinctValues": null, "Quartile1SkewnessOfNumericAtts": -0.8005787718402635, "REPTreeDepth1Kappa": null, "CfsSubsetEval_kNN1NAUC": null, "kNN1NAUC": null, "J48.001.Kappa": null, "MeanSkewnessOfNumericAtts": 0.29881940561681286, "Quartile1StdDevOfNumericAtts": 0.14737908979500747, "REPTreeDepth2AUC": null, "CfsSubsetEval_kNN1NErrRate": null, "CfsSubsetEval_kNN1NKappa": null, "kNN1NErrRate": null, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 6.693566565589307, "Quartile2AttributeEntropy": null, "REPTreeDepth2ErrRate": null, "ClassEntropy": null, "kNN1NKappa": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2KurtosisOfNumericAtts": 0.1456611612610499, "REPTreeDepth2Kappa": null, "DecisionStumpAUC": null, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.633190876705605, "Quartile2MeansOfNumericAtts": 2.597098901098901, "REPTreeDepth3AUC": null }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "69", "type": "numeric", "distinct": "114", "missing": "0", "target": "1", "min": "1", "max": "9", "mean": "6", "stdev": "2" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "182", "missing": "0", "identifier": "1", "distr": [] }, { "name": "SdsCH", "index": "1", "type": "numeric", "distinct": "69", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "C.018", "index": "2", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "GNar", "index": "3", "type": "numeric", "distinct": "92", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "X0A", "index": "4", "type": "numeric", "distinct": "68", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "D.Dtr09", "index": "5", "type": "numeric", "distinct": "35", "missing": "0", "min": "0", "max": "232", "mean": "24", "stdev": "40" }, { "name": "GATS6s", "index": "6", "type": "numeric", "distinct": "160", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "0" }, { "name": "nR09", "index": "7", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "SM11_EA.dm.", "index": "8", "type": "numeric", "distinct": "45", "missing": "0", "min": "0", "max": "15", "mean": "8", "stdev": "5" }, { "name": "SM13_EA.dm.", "index": "9", "type": "numeric", "distinct": "44", "missing": "0", "min": "0", "max": "17", "mean": "10", "stdev": "6" }, { "name": "SM15_EA.dm.", "index": "10", "type": "numeric", "distinct": "45", "missing": "0", "min": "0", "max": "20", "mean": "12", "stdev": "7" }, { "name": "SIC1", "index": "11", "type": "numeric", "distinct": "101", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SM07_EA.dm.", "index": "12", "type": "numeric", "distinct": "41", "missing": "0", "min": "0", "max": "9", "mean": "5", "stdev": "3" }, { "name": "SM09_EA.dm.", "index": "13", "type": "numeric", "distinct": "44", "missing": "0", "min": "0", "max": "12", "mean": "7", "stdev": "4" }, { "name": "SRW07", "index": "14", "type": "numeric", "distinct": "20", "missing": "0", "min": "0", "max": "6", "mean": "4", "stdev": "2" }, { "name": "SRW09", "index": "15", "type": "numeric", "distinct": "37", "missing": "0", "min": "0", "max": "8", "mean": "5", "stdev": "3" }, { "name": "SM05_EA.dm.", "index": "16", "type": "numeric", "distinct": "43", "missing": "0", "min": "0", "max": "7", "mean": "4", "stdev": "2" }, { "name": "SpMax1_Bh.e.", "index": "17", "type": "numeric", "distinct": "104", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "D.Dtr05", "index": "18", "type": "numeric", "distinct": "89", "missing": "0", "min": "0", "max": "326", "mean": "54", "stdev": "56" }, { "name": "nR05", "index": "19", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "SRW05", "index": "20", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "2", "stdev": "1" }, { "name": "MCD", "index": "21", "type": "numeric", "distinct": "69", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SM10_EA.dm.", "index": "22", "type": "numeric", "distinct": "66", "missing": "0", "min": "0", "max": "14", "mean": "10", "stdev": "5" }, { "name": "SM12_EA.dm.", "index": "23", "type": "numeric", "distinct": "62", "missing": "0", "min": "0", "max": "16", "mean": "12", "stdev": "6" }, { "name": "SM14_EA.dm.", "index": "24", "type": "numeric", "distinct": "59", "missing": "0", "min": "0", "max": "19", "mean": "14", "stdev": "7" }, { "name": "SIC2", "index": "25", "type": "numeric", "distinct": "106", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SpDiam_EA.dm.", "index": "26", "type": "numeric", "distinct": "37", "missing": "0", "min": "0", "max": "7", "mean": "5", "stdev": "2" }, { "name": "P_VSA_LogP_6", "index": "27", "type": "numeric", "distinct": "21", "missing": "0", "min": "0", "max": "90", "mean": "15", "stdev": "13" }, { "name": "HNar", "index": "28", "type": "numeric", "distinct": "87", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "PDI", "index": "29", "type": "numeric", "distinct": "90", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "P_VSA_m_3", "index": "30", "type": "numeric", "distinct": "36", "missing": "0", "min": "93", "max": "544", "mean": "145", "stdev": "50" }, { "name": "X2A", "index": "31", "type": "numeric", "distinct": "53", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Eig01_EA.dm.", "index": "32", "type": "numeric", "distinct": "36", "missing": "0", "min": "0", "max": "4", "mean": "3", "stdev": "1" }, { "name": "SpMax_EA.dm.", "index": "33", "type": "numeric", "distinct": "36", "missing": "0", "min": "0", "max": "4", "mean": "3", "stdev": "1" }, { "name": "GATS6e", "index": "34", "type": "numeric", "distinct": "152", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "P_VSA_e_5", "index": "35", "type": "numeric", "distinct": "32", "missing": "0", "min": "93", "max": "544", "mean": "144", "stdev": "51" }, { "name": "NdsCH", "index": "36", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "CIC2", "index": "37", "type": "numeric", "distinct": "125", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "CIC4", "index": "38", "type": "numeric", "distinct": "118", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "CIC5", "index": "39", "type": "numeric", "distinct": "120", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "SpMax1_Bh.i.", "index": "40", "type": "numeric", "distinct": "112", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "SIC4", "index": "41", "type": "numeric", "distinct": "90", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SIC5", "index": "42", "type": "numeric", "distinct": "91", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Eig03_AEA.dm.", "index": "43", "type": "numeric", "distinct": "108", "missing": "0", "min": "1", "max": "4", "mean": "3", "stdev": "1" }, { "name": "Eta_betaS_A", "index": "44", "type": "numeric", "distinct": "65", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SIC3", "index": "45", "type": "numeric", "distinct": "97", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "IC1", "index": "46", "type": "numeric", "distinct": "139", "missing": "0", "min": "2", "max": "5", "mean": "4", "stdev": "0" }, { "name": "BIC1", "index": "47", "type": "numeric", "distinct": "102", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "CIC1", "index": "48", "type": "numeric", "distinct": "137", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "RCI", "index": "49", "type": "numeric", "distinct": "23", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "RFD", "index": "50", "type": "numeric", "distinct": "23", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "P_VSA_s_6", "index": "51", "type": "numeric", "distinct": "63", "missing": "0", "min": "93", "max": "544", "mean": "160", "stdev": "53" }, { "name": "piPC10", "index": "52", "type": "numeric", "distinct": "117", "missing": "0", "min": "0", "max": "9", "mean": "5", "stdev": "2" }, { "name": "Eig05_AEA.dm.", "index": "53", "type": "numeric", "distinct": "137", "missing": "0", "min": "0", "max": "4", "mean": "3", "stdev": "1" }, { "name": "nCconj", "index": "54", "type": "numeric", "distinct": "9", "missing": "0", "min": "0", "max": "8", "mean": "3", "stdev": "3" }, { "name": "MATS5s", "index": "55", "type": "numeric", "distinct": "147", "missing": "0", "min": "-1", "max": "0", "mean": "0", "stdev": "0" }, { "name": "GATS5s", "index": "56", "type": "numeric", "distinct": "158", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "0" }, { "name": "X1A", "index": "57", "type": "numeric", "distinct": "47", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Eig01_AEA.bo.", "index": "58", "type": "numeric", "distinct": "80", "missing": "0", "min": "4", "max": "5", "mean": "5", "stdev": "0" }, { "name": "SpMax_AEA.bo.", "index": "59", "type": "numeric", "distinct": "80", "missing": "0", "min": "4", "max": "5", "mean": "5", "stdev": "0" }, { "name": "nCIR", "index": "60", "type": "numeric", "distinct": "10", "missing": "0", "min": "1", "max": "15", "mean": "4", "stdev": "2" }, { "name": "nCIC", "index": "61", "type": "numeric", "distinct": "8", "missing": "0", "min": "1", "max": "8", "mean": "3", "stdev": "1" }, { "name": "TRS", "index": "62", "type": "numeric", "distinct": "22", "missing": "0", "min": "5", "max": "46", "mean": "14", "stdev": "6" }, { "name": "P_VSA_v_2", "index": "63", "type": "numeric", "distinct": "74", "missing": "0", "min": "96", "max": "583", "mean": "164", "stdev": "56" }, { "name": "Rbrid", "index": "64", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "SaaN", "index": "65", "type": "numeric", "distinct": "48", "missing": "0", "min": "0", "max": "8", "mean": "2", "stdev": "3" }, { "name": "C.034", "index": "66", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "1" }, { "name": "P_VSA_MR_2", "index": "67", "type": "numeric", "distinct": "56", "missing": "0", "min": "93", "max": "476", "mean": "171", "stdev": "58" }, { "name": "H.048", "index": "68", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" } ], "nr_of_issues": 0, "nr_of_downvotes": 0, "nr_of_likes": 0, "nr_of_downloads": 0, "total_downloads": 0, "reach": 0, "reuse": 11, "impact_of_reuse": 0, "reach_of_reuse": 0, "impact": 11 }