{ "data_id": "24772", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL5011", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL5011", "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: CHEMBL5011 (TID: 101263), and it has 111 rows and 60 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 15:23:43", "update_comment": null, "last_update": "2016-07-14 15:23:43", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3253349\/data_52005.arff", "kaggle_url": null, "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL5011", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL5011 (TID: 101263), and it has 111 rows and 60 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": 111, "NumberOfFeatures": 62, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 61, "NumberOfSymbolicFeatures": 1, "REPTreeDepth3AUC": null, "DecisionStumpAUC": null, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.3928598975996584, "Quartile2MeansOfNumericAtts": 3.859846846846847, "REPTreeDepth3ErrRate": null, "DecisionStumpErrRate": null, "MaxKurtosisOfNumericAtts": 16.384645753319685, "MinMeansOfNumericAtts": -0.031837837837837835, "Quartile2MutualInformation": null, "REPTreeDepth3Kappa": null, "DecisionStumpKappa": null, "MaxMeansOfNumericAtts": 428.43978378378375, "MinMutualInformation": null, "Quartile2SkewnessOfNumericAtts": 0.144354524796847, "RandomTreeDepth1AUC": null, "Dimensionality": 0.5585585585585585, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.4530647463370598, "RandomTreeDepth1ErrRate": null, "EquivalentNumberOfAtts": null, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -3.2028022100205296, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "RandomTreeDepth1Kappa": null, "J48.00001.AUC": null, "MaxSkewnessOfNumericAtts": 2.1293665206785715, "MinStdDevOfNumericAtts": 0.013159128145992566, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 7.446714145245975, "AutoCorrelation": 0.19615454545454555, "RandomTreeDepth2AUC": null, "J48.00001.ErrRate": null, "MaxStdDevOfNumericAtts": 193.19223655521813, "MinorityClassPercentage": null, "PercentageOfNumericFeatures": 98.38709677419355, "Quartile3MeansOfNumericAtts": 7.6555045045045045, "CfsSubsetEval_DecisionStumpAUC": null, "RandomTreeDepth2ErrRate": null, "J48.00001.Kappa": null, "MeanAttributeEntropy": null, "MinorityClassSize": null, "PercentageOfSymbolicFeatures": 1.6129032258064515, "Quartile3MutualInformation": null, "CfsSubsetEval_DecisionStumpErrRate": null, "RandomTreeDepth2Kappa": null, "J48.0001.AUC": null, "MeanKurtosisOfNumericAtts": 3.258165633473527, "NaiveBayesAUC": null, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 0.599885970459756, "CfsSubsetEval_DecisionStumpKappa": null, "CfsSubsetEval_NaiveBayesAUC": null, "RandomTreeDepth3AUC": null, "J48.0001.ErrRate": null, "MeanMeansOfNumericAtts": 19.262738591050063, "NaiveBayesErrRate": null, "Quartile1KurtosisOfNumericAtts": -0.6593684088617597, "Quartile3StdDevOfNumericAtts": 1.4196010053144308, "CfsSubsetEval_NaiveBayesErrRate": null, "RandomTreeDepth3ErrRate": null, "J48.0001.Kappa": null, "MeanMutualInformation": null, "NaiveBayesKappa": null, "Quartile1MeansOfNumericAtts": 0.9313693693693693, "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": -1.9517897060796623, "REPTreeDepth1Kappa": null, "REPTreeDepth2AUC": null, "CfsSubsetEval_kNN1NErrRate": null, "kNN1NAUC": null, "J48.001.Kappa": null, "MeanSkewnessOfNumericAtts": -0.4016095479625123, "Quartile1StdDevOfNumericAtts": 0.22639717281912164, "REPTreeDepth2ErrRate": null, "CfsSubsetEval_kNN1NKappa": null, "kNN1NErrRate": null, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 8.891018830261297, "Quartile2AttributeEntropy": null, "REPTreeDepth2Kappa": null, "ClassEntropy": null, "kNN1NKappa": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2KurtosisOfNumericAtts": 0.854435297999756 }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "61", "type": "numeric", "distinct": "93", "missing": "0", "target": "1", "min": "4", "max": "8", "mean": "6", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "111", "missing": "0", "identifier": "1", "distr": [] }, { "name": "MATS5v", "index": "1", "type": "numeric", "distinct": "97", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "ATSC7e", "index": "2", "type": "numeric", "distinct": "98", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "MATS8v", "index": "3", "type": "numeric", "distinct": "92", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "SpMax4_Bh.m.", "index": "4", "type": "numeric", "distinct": "70", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "X0Av", "index": "5", "type": "numeric", "distinct": "64", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Eta_F_A", "index": "6", "type": "numeric", "distinct": "94", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "H.", "index": "7", "type": "numeric", "distinct": "58", "missing": "0", "min": "34", "max": "64", "mean": "46", "stdev": "8" }, { "name": "ATS7s", "index": "8", "type": "numeric", "distinct": "103", "missing": "0", "min": "3", "max": "7", "mean": "6", "stdev": "0" }, { "name": "IC3", "index": "9", "type": "numeric", "distinct": "84", "missing": "0", "min": "4", "max": "5", "mean": "5", "stdev": "0" }, { "name": "Eig09_EA.ed.", "index": "10", "type": "numeric", "distinct": "57", "missing": "0", "min": "-4", "max": "4", "mean": "2", "stdev": "1" }, { "name": "SM04_AEA.ri.", "index": "11", "type": "numeric", "distinct": "57", "missing": "0", "min": "-4", "max": "4", "mean": "2", "stdev": "1" }, { "name": "P_VSA_i_4", "index": "12", "type": "numeric", "distinct": "22", "missing": "0", "min": "0", "max": "143", "mean": "41", "stdev": "31" }, { "name": "Eig04_EA.ri.", "index": "13", "type": "numeric", "distinct": "74", "missing": "0", "min": "1", "max": "3", "mean": "2", "stdev": "0" }, { "name": "Eig03_EA.dm.", "index": "14", "type": "numeric", "distinct": "18", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "ATSC1e", "index": "15", "type": "numeric", "distinct": "64", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Eig04_EA.dm.", "index": "16", "type": "numeric", "distinct": "13", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "SpMax7_Bh.s.", "index": "17", "type": "numeric", "distinct": "81", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "ATSC7s", "index": "18", "type": "numeric", "distinct": "109", "missing": "0", "min": "4", "max": "222", "mean": "76", "stdev": "50" }, { "name": "MATS5m", "index": "19", "type": "numeric", "distinct": "87", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SAacc", "index": "20", "type": "numeric", "distinct": "30", "missing": "0", "min": "33", "max": "140", "mean": "70", "stdev": "29" }, { "name": "P_VSA_m_3", "index": "21", "type": "numeric", "distinct": "17", "missing": "0", "min": "0", "max": "119", "mean": "53", "stdev": "27" }, { "name": "Eig05_AEA.ri.", "index": "22", "type": "numeric", "distinct": "84", "missing": "0", "min": "1", "max": "4", "mean": "3", "stdev": "0" }, { "name": "ATSC2i", "index": "23", "type": "numeric", "distinct": "75", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "0" }, { "name": "Eig05_EA.ed.", "index": "24", "type": "numeric", "distinct": "63", "missing": "0", "min": "0", "max": "9", "mean": "6", "stdev": "1" }, { "name": "SM14_AEA.dm.", "index": "25", "type": "numeric", "distinct": "63", "missing": "0", "min": "0", "max": "9", "mean": "6", "stdev": "1" }, { "name": "SssNH", "index": "26", "type": "numeric", "distinct": "83", "missing": "0", "min": "0", "max": "7", "mean": "2", "stdev": "2" }, { "name": "SsF", "index": "27", "type": "numeric", "distinct": "45", "missing": "0", "min": "0", "max": "82", "mean": "19", "stdev": "24" }, { "name": "Eta_betaS_A", "index": "28", "type": "numeric", "distinct": "45", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Psi_i_s", "index": "29", "type": "numeric", "distinct": "65", "missing": "0", "min": "22", "max": "98", "mean": "60", "stdev": "16" }, { "name": "ZM1Kup", "index": "30", "type": "numeric", "distinct": "78", "missing": "0", "min": "97", "max": "900", "mean": "428", "stdev": "193" }, { "name": "ATS4m", "index": "31", "type": "numeric", "distinct": "96", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "Eig03_AEA.ed.", "index": "32", "type": "numeric", "distinct": "59", "missing": "0", "min": "5", "max": "7", "mean": "6", "stdev": "0" }, { "name": "Eig03_EA.ed.", "index": "33", "type": "numeric", "distinct": "64", "missing": "0", "min": "4", "max": "12", "mean": "8", "stdev": "1" }, { "name": "SM12_AEA.dm.", "index": "34", "type": "numeric", "distinct": "64", "missing": "0", "min": "4", "max": "12", "mean": "8", "stdev": "1" }, { "name": "SpAD_EA.dm.", "index": "35", "type": "numeric", "distinct": "34", "missing": "0", "min": "0", "max": "21", "mean": "8", "stdev": "5" }, { "name": "MPC09", "index": "36", "type": "numeric", "distinct": "53", "missing": "0", "min": "0", "max": "6", "mean": "4", "stdev": "1" }, { "name": "Me", "index": "37", "type": "numeric", "distinct": "45", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Eig04_AEA.ri.", "index": "38", "type": "numeric", "distinct": "75", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "Eig04_EA", "index": "39", "type": "numeric", "distinct": "55", "missing": "0", "min": "1", "max": "3", "mean": "2", "stdev": "0" }, { "name": "SM12_AEA.bo.", "index": "40", "type": "numeric", "distinct": "55", "missing": "0", "min": "1", "max": "3", "mean": "2", "stdev": "0" }, { "name": "Psi_e_1", "index": "41", "type": "numeric", "distinct": "105", "missing": "0", "min": "2", "max": "7", "mean": "4", "stdev": "1" }, { "name": "ATSC5e", "index": "42", "type": "numeric", "distinct": "103", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "Eig05_EA.ri.", "index": "43", "type": "numeric", "distinct": "88", "missing": "0", "min": "0", "max": "2", "mean": "2", "stdev": "0" }, { "name": "P_VSA_s_6", "index": "44", "type": "numeric", "distinct": "22", "missing": "0", "min": "25", "max": "137", "mean": "58", "stdev": "27" }, { "name": "Eig05_AEA.ed.", "index": "45", "type": "numeric", "distinct": "58", "missing": "0", "min": "2", "max": "6", "mean": "5", "stdev": "0" }, { "name": "Eig03_EA.bo.", "index": "46", "type": "numeric", "distinct": "64", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SM13_AEA.ri.", "index": "47", "type": "numeric", "distinct": "64", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "Eig02_AEA.dm.", "index": "48", "type": "numeric", "distinct": "79", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "ATSC5s", "index": "49", "type": "numeric", "distinct": "109", "missing": "0", "min": "21", "max": "199", "mean": "78", "stdev": "45" }, { "name": "GGI7", "index": "50", "type": "numeric", "distinct": "59", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "GGI6", "index": "51", "type": "numeric", "distinct": "56", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "P_VSA_LogP_2", "index": "52", "type": "numeric", "distinct": "30", "missing": "0", "min": "0", "max": "64", "mean": "22", "stdev": "12" }, { "name": "ATSC4s", "index": "53", "type": "numeric", "distinct": "109", "missing": "0", "min": "19", "max": "199", "mean": "74", "stdev": "49" }, { "name": "SpMax8_Bh.s.", "index": "54", "type": "numeric", "distinct": "68", "missing": "0", "min": "2", "max": "5", "mean": "4", "stdev": "0" }, { "name": "MPC10", "index": "55", "type": "numeric", "distinct": "54", "missing": "0", "min": "0", "max": "6", "mean": "4", "stdev": "1" }, { "name": "MPC08", "index": "56", "type": "numeric", "distinct": "47", "missing": "0", "min": "1", "max": "6", "mean": "4", "stdev": "1" }, { "name": "X3Av", "index": "57", "type": "numeric", "distinct": "46", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "X4Av", "index": "58", "type": "numeric", "distinct": "41", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "nHet", "index": "59", "type": "numeric", "distinct": "10", "missing": "0", "min": "1", "max": "10", "mean": "5", "stdev": "2" }, { "name": "SM10_EA", "index": "60", "type": "numeric", "distinct": "66", "missing": "0", "min": "11", "max": "13", "mean": "12", "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 }