{ "data_id": "24325", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL1916", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL1916", "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: CHEMBL1916 (TID: 218), and it has 613 rows and 69 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 14:24:25", "update_comment": null, "last_update": "2016-07-14 14:24:25", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3243994\/data_53491.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL1916", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL1916 (TID: 218), and it has 613 rows and 69 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": 613, "NumberOfFeatures": 71, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 70, "NumberOfSymbolicFeatures": 1, "Quartile3StdDevOfNumericAtts": 5.325059166450667, "CfsSubsetEval_NaiveBayesAUC": null, "RandomTreeDepth3AUC": null, "J48.0001.ErrRate": null, "MeanMeansOfNumericAtts": 1052.5516481472848, "NaiveBayesErrRate": null, "Quartile1KurtosisOfNumericAtts": -0.7027610763067466, "REPTreeDepth1AUC": null, "CfsSubsetEval_NaiveBayesErrRate": null, "RandomTreeDepth3ErrRate": null, "J48.0001.Kappa": null, "MeanMutualInformation": null, "NaiveBayesKappa": null, "Quartile1MeansOfNumericAtts": 1.0175367047308312, "REPTreeDepth1ErrRate": null, "CfsSubsetEval_NaiveBayesKappa": null, "RandomTreeDepth3Kappa": null, "J48.001.AUC": null, "MeanNoiseToSignalRatio": null, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "REPTreeDepth1Kappa": null, "CfsSubsetEval_kNN1NAUC": null, "StdvNominalAttDistinctValues": null, "J48.001.ErrRate": null, "MeanNominalAttDistinctValues": null, "Quartile1SkewnessOfNumericAtts": -0.09149711531633434, "REPTreeDepth2AUC": null, "CfsSubsetEval_kNN1NErrRate": null, "kNN1NAUC": null, "J48.001.Kappa": null, "MeanSkewnessOfNumericAtts": 0.8659797472473558, "Quartile1StdDevOfNumericAtts": 0.4830846320674401, "Quartile2AttributeEntropy": null, "REPTreeDepth2ErrRate": null, "CfsSubsetEval_kNN1NKappa": null, "kNN1NErrRate": null, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 2728.634655874664, "Quartile2KurtosisOfNumericAtts": 0.03364062601494977, "REPTreeDepth2Kappa": null, "ClassEntropy": null, "kNN1NKappa": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2MeansOfNumericAtts": 3.7612969004893966, "REPTreeDepth3AUC": null, "DecisionStumpAUC": null, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.323159976709589, "Quartile2MutualInformation": null, "REPTreeDepth3ErrRate": null, "DecisionStumpErrRate": null, "MaxKurtosisOfNumericAtts": 395.91798487098424, "MinMeansOfNumericAtts": 0.1321370309951061, "Quartile2SkewnessOfNumericAtts": 0.5765871026794077, "REPTreeDepth3Kappa": null, "DecisionStumpKappa": null, "MaxMeansOfNumericAtts": 49857.916802610096, "MinMutualInformation": null, "Quartile2StdDevOfNumericAtts": 1.200003545178889, "RandomTreeDepth1AUC": null, "Dimensionality": 0.11582381729200653, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfBinaryFeatures": 0, "Quartile3AttributeEntropy": null, "RandomTreeDepth1ErrRate": null, "EquivalentNumberOfAtts": null, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -1.1288745372290232, "PercentageOfInstancesWithMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 1.7082765751591076, "AutoCorrelation": -0.07472712418300793, "RandomTreeDepth1Kappa": null, "J48.00001.AUC": null, "MaxSkewnessOfNumericAtts": 18.28575027118212, "MinStdDevOfNumericAtts": 0.038044361115155224, "PercentageOfMissingValues": 0, "Quartile3MeansOfNumericAtts": 14.672872349102773, "CfsSubsetEval_DecisionStumpAUC": null, "RandomTreeDepth2AUC": null, "J48.00001.ErrRate": null, "MaxStdDevOfNumericAtts": 167938.10936067632, "MinorityClassPercentage": null, "PercentageOfNumericFeatures": 98.59154929577466, "Quartile3MutualInformation": null, "CfsSubsetEval_DecisionStumpErrRate": null, "RandomTreeDepth2ErrRate": null, "J48.00001.Kappa": null, "MeanAttributeEntropy": null, "MinorityClassSize": null, "PercentageOfSymbolicFeatures": 1.4084507042253522, "Quartile3SkewnessOfNumericAtts": 1.2891606159427915, "CfsSubsetEval_DecisionStumpKappa": null, "RandomTreeDepth2Kappa": null, "J48.0001.AUC": null, "MeanKurtosisOfNumericAtts": 6.907530353498623, "NaiveBayesAUC": null, "Quartile1AttributeEntropy": null }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "70", "type": "numeric", "distinct": "440", "missing": "0", "target": "1", "min": "4", "max": "11", "mean": "7", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "613", "missing": "0", "identifier": "1", "distr": [] }, { "name": "N.068", "index": "1", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "nRNR2", "index": "2", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "D.Dtr09", "index": "3", "type": "numeric", "distinct": "170", "missing": "0", "min": "0", "max": "638", "mean": "54", "stdev": "92" }, { "name": "SsssN", "index": "4", "type": "numeric", "distinct": "296", "missing": "0", "min": "0", "max": "10", "mean": "2", "stdev": "2" }, { "name": "nR09", "index": "5", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "5", "mean": "1", "stdev": "1" }, { "name": "piID", "index": "6", "type": "numeric", "distinct": "433", "missing": "0", "min": "5", "max": "16", "mean": "10", "stdev": "2" }, { "name": "SdsCH", "index": "7", "type": "numeric", "distinct": "107", "missing": "0", "min": "0", "max": "9", "mean": "1", "stdev": "2" }, { "name": "NsssN", "index": "8", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "O.060", "index": "9", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "5", "mean": "1", "stdev": "1" }, { "name": "C.016", "index": "10", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "5", "mean": "0", "stdev": "1" }, { "name": "SssO", "index": "11", "type": "numeric", "distinct": "302", "missing": "0", "min": "0", "max": "78", "mean": "7", "stdev": "8" }, { "name": "nArCNO", "index": "12", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "NNRS", "index": "13", "type": "numeric", "distinct": "16", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "NssO", "index": "14", "type": "numeric", "distinct": "8", "missing": "0", "min": "0", "max": "12", "mean": "1", "stdev": "1" }, { "name": "NdsCH", "index": "15", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "5", "mean": "0", "stdev": "1" }, { "name": "CATS2D_04_AA", "index": "16", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "6", "mean": "1", "stdev": "1" }, { "name": "IDDE", "index": "17", "type": "numeric", "distinct": "275", "missing": "0", "min": "3", "max": "6", "mean": "4", "stdev": "1" }, { "name": "D.Dtr10", "index": "18", "type": "numeric", "distinct": "215", "missing": "0", "min": "0", "max": "618", "mean": "75", "stdev": "95" }, { "name": "SaasC", "index": "19", "type": "numeric", "distinct": "519", "missing": "0", "min": "-5", "max": "10", "mean": "3", "stdev": "2" }, { "name": "IC5", "index": "20", "type": "numeric", "distinct": "369", "missing": "0", "min": "3", "max": "7", "mean": "5", "stdev": "0" }, { "name": "C.039", "index": "21", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "Eig08_AEA.bo.", "index": "22", "type": "numeric", "distinct": "361", "missing": "0", "min": "0", "max": "4", "mean": "3", "stdev": "1" }, { "name": "Eig09_AEA.bo.", "index": "23", "type": "numeric", "distinct": "350", "missing": "0", "min": "0", "max": "4", "mean": "2", "stdev": "1" }, { "name": "SM02_EA.ed.", "index": "24", "type": "numeric", "distinct": "311", "missing": "0", "min": "5", "max": "8", "mean": "7", "stdev": "0" }, { "name": "SM02_AEA.bo.", "index": "25", "type": "numeric", "distinct": "266", "missing": "0", "min": "4", "max": "6", "mean": "5", "stdev": "0" }, { "name": "Wap", "index": "26", "type": "numeric", "distinct": "412", "missing": "0", "min": "496", "max": "3769680", "mean": "49858", "stdev": "167938" }, { "name": "TPC", "index": "27", "type": "numeric", "distinct": "357", "missing": "0", "min": "5", "max": "12", "mean": "7", "stdev": "1" }, { "name": "H.047", "index": "28", "type": "numeric", "distinct": "34", "missing": "0", "min": "0", "max": "34", "mean": "16", "stdev": "8" }, { "name": "Eig10_AEA.dm.", "index": "29", "type": "numeric", "distinct": "411", "missing": "0", "min": "-2", "max": "3", "mean": "1", "stdev": "1" }, { "name": "SpAD_EA.bo.", "index": "30", "type": "numeric", "distinct": "477", "missing": "0", "min": "18", "max": "113", "mean": "55", "stdev": "19" }, { "name": "piPC01", "index": "31", "type": "numeric", "distinct": "93", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "SCBO", "index": "32", "type": "numeric", "distinct": "93", "missing": "0", "min": "12", "max": "74", "mean": "37", "stdev": "13" }, { "name": "Chi1_AEA.bo.", "index": "33", "type": "numeric", "distinct": "409", "missing": "0", "min": "6", "max": "34", "mean": "15", "stdev": "5" }, { "name": "Chi1_AEA.dm.", "index": "34", "type": "numeric", "distinct": "409", "missing": "0", "min": "6", "max": "34", "mean": "15", "stdev": "5" }, { "name": "Chi1_AEA.ed.", "index": "35", "type": "numeric", "distinct": "409", "missing": "0", "min": "6", "max": "34", "mean": "15", "stdev": "5" }, { "name": "Chi1_AEA.ri.", "index": "36", "type": "numeric", "distinct": "409", "missing": "0", "min": "6", "max": "34", "mean": "15", "stdev": "5" }, { "name": "Chi1_EA", "index": "37", "type": "numeric", "distinct": "409", "missing": "0", "min": "6", "max": "34", "mean": "15", "stdev": "5" }, { "name": "Eig10_EA.ri.", "index": "38", "type": "numeric", "distinct": "395", "missing": "0", "min": "-2", "max": "2", "mean": "1", "stdev": "1" }, { "name": "SpMax4_Bh.p.", "index": "39", "type": "numeric", "distinct": "354", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "TIC1", "index": "40", "type": "numeric", "distinct": "481", "missing": "0", "min": "45", "max": "425", "mean": "171", "stdev": "66" }, { "name": "Eig09_EA.bo.", "index": "41", "type": "numeric", "distinct": "369", "missing": "0", "min": "-2", "max": "3", "mean": "1", "stdev": "1" }, { "name": "Eig07_AEA.bo.", "index": "42", "type": "numeric", "distinct": "351", "missing": "0", "min": "0", "max": "4", "mean": "3", "stdev": "1" }, { "name": "nR10", "index": "43", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "6", "mean": "1", "stdev": "1" }, { "name": "SpMin3_Bh.p.", "index": "44", "type": "numeric", "distinct": "268", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "CATS2D_03_AA", "index": "45", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "8", "mean": "1", "stdev": "1" }, { "name": "nCIC", "index": "46", "type": "numeric", "distinct": "9", "missing": "0", "min": "1", "max": "10", "mean": "4", "stdev": "1" }, { "name": "TRS", "index": "47", "type": "numeric", "distinct": "32", "missing": "0", "min": "6", "max": "58", "mean": "23", "stdev": "8" }, { "name": "MPC01", "index": "48", "type": "numeric", "distinct": "47", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "MWC01", "index": "49", "type": "numeric", "distinct": "47", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "nBO", "index": "50", "type": "numeric", "distinct": "47", "missing": "0", "min": "12", "max": "70", "mean": "29", "stdev": "10" }, { "name": "SRW02", "index": "51", "type": "numeric", "distinct": "47", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SpAD_AEA.bo.", "index": "52", "type": "numeric", "distinct": "473", "missing": "0", "min": "17", "max": "109", "mean": "44", "stdev": "16" }, { "name": "Eig15_AEA.bo.", "index": "53", "type": "numeric", "distinct": "315", "missing": "0", "min": "-1", "max": "3", "mean": "1", "stdev": "1" }, { "name": "IC4", "index": "54", "type": "numeric", "distinct": "371", "missing": "0", "min": "3", "max": "6", "mean": "5", "stdev": "0" }, { "name": "Chi1_EA.ri.", "index": "55", "type": "numeric", "distinct": "531", "missing": "0", "min": "6", "max": "36", "mean": "15", "stdev": "5" }, { "name": "RDSQ", "index": "56", "type": "numeric", "distinct": "446", "missing": "0", "min": "60", "max": "838", "mean": "236", "stdev": "118" }, { "name": "SpMax4_Bh.v.", "index": "57", "type": "numeric", "distinct": "349", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SRW07", "index": "58", "type": "numeric", "distinct": "34", "missing": "0", "min": "0", "max": "7", "mean": "4", "stdev": "2" }, { "name": "SMTI", "index": "59", "type": "numeric", "distinct": "439", "missing": "0", "min": "631", "max": "81783", "mean": "10966", "stdev": "10826" }, { "name": "Eta_betaS", "index": "60", "type": "numeric", "distinct": "100", "missing": "0", "min": "6", "max": "42", "mean": "17", "stdev": "6" }, { "name": "AMR", "index": "61", "type": "numeric", "distinct": "511", "missing": "0", "min": "40", "max": "230", "mean": "105", "stdev": "35" }, { "name": "UNIP", "index": "62", "type": "numeric", "distinct": "197", "missing": "0", "min": "18", "max": "430", "mean": "112", "stdev": "73" }, { "name": "GMTI", "index": "63", "type": "numeric", "distinct": "439", "missing": "0", "min": "558", "max": "85685", "mean": "11658", "stdev": "11602" }, { "name": "IDDM", "index": "64", "type": "numeric", "distinct": "263", "missing": "0", "min": "3", "max": "6", "mean": "5", "stdev": "0" }, { "name": "BIC0", "index": "65", "type": "numeric", "distinct": "142", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SIC0", "index": "66", "type": "numeric", "distinct": "152", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "nArOR", "index": "67", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "5", "mean": "1", "stdev": "1" }, { "name": "X2sol", "index": "68", "type": "numeric", "distinct": "440", "missing": "0", "min": "4", "max": "30", "mean": "12", "stdev": "4" }, { "name": "HVcpx", "index": "69", "type": "numeric", "distinct": "374", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" } ], "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 }