{ "data_id": "23551", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL2725", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL2725", "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: CHEMBL2725 (TID: 12802), and it has 218 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 12:42:35", "update_comment": null, "last_update": "2016-07-14 12:42:35", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3228066\/data_53576.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL2725", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL2725 (TID: 12802), and it has 218 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": 218, "NumberOfFeatures": 71, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 70, "NumberOfSymbolicFeatures": 1, "REPTreeDepth3Kappa": null, "DecisionStumpKappa": null, "MaxMeansOfNumericAtts": 38.07938990825688, "MinMutualInformation": null, "Quartile2SkewnessOfNumericAtts": -0.03064148065357355, "RandomTreeDepth1AUC": null, "Dimensionality": 0.3256880733944954, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.5129236954293772, "RandomTreeDepth1ErrRate": null, "EquivalentNumberOfAtts": null, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -1.6379553459287735, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "RandomTreeDepth1Kappa": null, "J48.00001.AUC": null, "MaxSkewnessOfNumericAtts": 3.6179629896963448, "MinStdDevOfNumericAtts": 0.01712829325407202, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 1.1509647559053438, "AutoCorrelation": -0.05899078341013859, "RandomTreeDepth2AUC": null, "J48.00001.ErrRate": null, "MaxStdDevOfNumericAtts": 48.21119891369287, "MinorityClassPercentage": null, "PercentageOfNumericFeatures": 98.59154929577466, "Quartile3MeansOfNumericAtts": 13.198379587155964, "CfsSubsetEval_DecisionStumpAUC": null, "RandomTreeDepth2ErrRate": null, "J48.00001.Kappa": null, "MeanAttributeEntropy": null, "MinorityClassSize": null, "PercentageOfSymbolicFeatures": 1.4084507042253522, "Quartile3MutualInformation": null, "CfsSubsetEval_DecisionStumpErrRate": null, "RandomTreeDepth2Kappa": null, "J48.0001.AUC": null, "MeanKurtosisOfNumericAtts": 0.8793683559626111, "NaiveBayesAUC": null, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 0.6604774409772821, "CfsSubsetEval_DecisionStumpKappa": null, "RandomTreeDepth3AUC": null, "J48.0001.ErrRate": null, "MeanMeansOfNumericAtts": 8.120345216251637, "NaiveBayesErrRate": null, "Quartile1KurtosisOfNumericAtts": -0.3840889576466723, "Quartile3StdDevOfNumericAtts": 1.217630828871974, "CfsSubsetEval_NaiveBayesAUC": null, "RandomTreeDepth3ErrRate": null, "J48.0001.Kappa": null, "MeanMutualInformation": null, "NaiveBayesKappa": null, "Quartile1MeansOfNumericAtts": 0.9125401376146789, "REPTreeDepth1AUC": null, "CfsSubsetEval_NaiveBayesErrRate": null, "RandomTreeDepth3Kappa": null, "J48.001.AUC": null, "MeanNoiseToSignalRatio": null, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "REPTreeDepth1ErrRate": null, "CfsSubsetEval_NaiveBayesKappa": null, "CfsSubsetEval_kNN1NAUC": null, "StdvNominalAttDistinctValues": null, "J48.001.ErrRate": null, "MeanNominalAttDistinctValues": null, "Quartile1SkewnessOfNumericAtts": -0.20876352423245198, "REPTreeDepth1Kappa": null, "CfsSubsetEval_kNN1NErrRate": null, "kNN1NAUC": null, "J48.001.Kappa": null, "MeanSkewnessOfNumericAtts": 0.23473767776363855, "Quartile1StdDevOfNumericAtts": 0.23492275637152735, "REPTreeDepth2AUC": null, "CfsSubsetEval_kNN1NKappa": null, "kNN1NErrRate": null, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 1.5639335054268675, "Quartile2AttributeEntropy": null, "REPTreeDepth2ErrRate": null, "ClassEntropy": null, "kNN1NKappa": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2KurtosisOfNumericAtts": 0.31440973316579823, "REPTreeDepth2Kappa": null, "REPTreeDepth3AUC": null, "DecisionStumpAUC": null, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.2063912056246497, "Quartile2MeansOfNumericAtts": 3.992669724770642, "REPTreeDepth3ErrRate": null, "DecisionStumpErrRate": null, "MaxKurtosisOfNumericAtts": 19.50315237688869, "MinMeansOfNumericAtts": -0.04705045871559632, "Quartile2MutualInformation": null }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "70", "type": "numeric", "distinct": "167", "missing": "0", "target": "1", "min": "1", "max": "9", "mean": "6", "stdev": "2" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "218", "missing": "0", "identifier": "1", "distr": [] }, { "name": "C.028", "index": "1", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "piPC10", "index": "2", "type": "numeric", "distinct": "149", "missing": "0", "min": "0", "max": "9", "mean": "6", "stdev": "2" }, { "name": "NaaN", "index": "3", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "SaaN", "index": "4", "type": "numeric", "distinct": "54", "missing": "0", "min": "0", "max": "8", "mean": "1", "stdev": "2" }, { "name": "CATS2D_05_NL", "index": "5", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "piPC08", "index": "6", "type": "numeric", "distinct": "145", "missing": "0", "min": "4", "max": "8", "mean": "6", "stdev": "1" }, { "name": "N.075", "index": "7", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "piPC09", "index": "8", "type": "numeric", "distinct": "144", "missing": "0", "min": "2", "max": "8", "mean": "6", "stdev": "1" }, { "name": "PDI", "index": "9", "type": "numeric", "distinct": "109", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "GATS6s", "index": "10", "type": "numeric", "distinct": "177", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "piPC06", "index": "11", "type": "numeric", "distinct": "145", "missing": "0", "min": "4", "max": "7", "mean": "6", "stdev": "1" }, { "name": "piPC07", "index": "12", "type": "numeric", "distinct": "147", "missing": "0", "min": "4", "max": "7", "mean": "6", "stdev": "1" }, { "name": "nCconj", "index": "13", "type": "numeric", "distinct": "10", "missing": "0", "min": "0", "max": "9", "mean": "4", "stdev": "3" }, { "name": "piPC04", "index": "14", "type": "numeric", "distinct": "135", "missing": "0", "min": "4", "max": "6", "mean": "5", "stdev": "0" }, { "name": "IC1", "index": "15", "type": "numeric", "distinct": "162", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SIC3", "index": "16", "type": "numeric", "distinct": "110", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Eig02_AEA.bo.", "index": "17", "type": "numeric", "distinct": "115", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "piPC03", "index": "18", "type": "numeric", "distinct": "117", "missing": "0", "min": "4", "max": "6", "mean": "4", "stdev": "0" }, { "name": "SM03_EA.dm.", "index": "19", "type": "numeric", "distinct": "44", "missing": "0", "min": "0", "max": "4", "mean": "2", "stdev": "1" }, { "name": "Eig02_EA.bo.", "index": "20", "type": "numeric", "distinct": "129", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SM12_AEA.ri.", "index": "21", "type": "numeric", "distinct": "129", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "C.018", "index": "22", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "CIC4", "index": "23", "type": "numeric", "distinct": "134", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "CIC3", "index": "24", "type": "numeric", "distinct": "143", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "SIC4", "index": "25", "type": "numeric", "distinct": "98", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SIC5", "index": "26", "type": "numeric", "distinct": "96", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "MATS7p", "index": "27", "type": "numeric", "distinct": "144", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "SIC1", "index": "28", "type": "numeric", "distinct": "131", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SM15_EA.bo.", "index": "29", "type": "numeric", "distinct": "147", "missing": "0", "min": "18", "max": "24", "mean": "22", "stdev": "1" }, { "name": "SM13_EA.bo.", "index": "30", "type": "numeric", "distinct": "148", "missing": "0", "min": "16", "max": "21", "mean": "19", "stdev": "1" }, { "name": "SM14_EA.bo.", "index": "31", "type": "numeric", "distinct": "146", "missing": "0", "min": "17", "max": "23", "mean": "20", "stdev": "1" }, { "name": "CIC5", "index": "32", "type": "numeric", "distinct": "136", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "MATS6s", "index": "33", "type": "numeric", "distinct": "166", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SM09_EA.bo.", "index": "34", "type": "numeric", "distinct": "152", "missing": "0", "min": "11", "max": "15", "mean": "13", "stdev": "1" }, { "name": "GATS1v", "index": "35", "type": "numeric", "distinct": "135", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Eig02_EA", "index": "36", "type": "numeric", "distinct": "124", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SM10_AEA.bo.", "index": "37", "type": "numeric", "distinct": "124", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "GATS3p", "index": "38", "type": "numeric", "distinct": "162", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "SM12_EA.bo.", "index": "39", "type": "numeric", "distinct": "146", "missing": "0", "min": "15", "max": "20", "mean": "18", "stdev": "1" }, { "name": "nRCOOR", "index": "40", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "SM10_EA.bo.", "index": "41", "type": "numeric", "distinct": "152", "missing": "0", "min": "12", "max": "16", "mean": "15", "stdev": "1" }, { "name": "SM15_EA.dm.", "index": "42", "type": "numeric", "distinct": "66", "missing": "0", "min": "0", "max": "23", "mean": "13", "stdev": "7" }, { "name": "SM11_EA.bo.", "index": "43", "type": "numeric", "distinct": "147", "missing": "0", "min": "13", "max": "18", "mean": "16", "stdev": "1" }, { "name": "BIC1", "index": "44", "type": "numeric", "distinct": "123", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SM11_EA.ri.", "index": "45", "type": "numeric", "distinct": "177", "missing": "0", "min": "11", "max": "16", "mean": "13", "stdev": "1" }, { "name": "SM12_EA.ri.", "index": "46", "type": "numeric", "distinct": "182", "missing": "0", "min": "12", "max": "17", "mean": "14", "stdev": "1" }, { "name": "GATS7p", "index": "47", "type": "numeric", "distinct": "155", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Eig01_AEA.ed.", "index": "48", "type": "numeric", "distinct": "74", "missing": "0", "min": "6", "max": "9", "mean": "7", "stdev": "1" }, { "name": "SpMax_AEA.ed.", "index": "49", "type": "numeric", "distinct": "74", "missing": "0", "min": "6", "max": "9", "mean": "7", "stdev": "1" }, { "name": "D.Dtr09", "index": "50", "type": "numeric", "distinct": "35", "missing": "0", "min": "0", "max": "354", "mean": "23", "stdev": "48" }, { "name": "SM05_EA.ri.", "index": "51", "type": "numeric", "distinct": "168", "missing": "0", "min": "5", "max": "8", "mean": "6", "stdev": "0" }, { "name": "SM08_EA.ri.", "index": "52", "type": "numeric", "distinct": "182", "missing": "0", "min": "9", "max": "12", "mean": "10", "stdev": "1" }, { "name": "GATS3v", "index": "53", "type": "numeric", "distinct": "132", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "X3A", "index": "54", "type": "numeric", "distinct": "57", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "MATS6e", "index": "55", "type": "numeric", "distinct": "170", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Mv", "index": "56", "type": "numeric", "distinct": "103", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SM08_AEA.bo.", "index": "57", "type": "numeric", "distinct": "157", "missing": "0", "min": "12", "max": "14", "mean": "13", "stdev": "0" }, { "name": "Eig01_EA", "index": "58", "type": "numeric", "distinct": "83", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "Eig01_EA.ed.", "index": "59", "type": "numeric", "distinct": "88", "missing": "0", "min": "8", "max": "18", "mean": "13", "stdev": "2" }, { "name": "SM09_AEA.bo.", "index": "60", "type": "numeric", "distinct": "83", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SM09_EA.ed.", "index": "61", "type": "numeric", "distinct": "130", "missing": "0", "min": "19", "max": "26", "mean": "23", "stdev": "2" }, { "name": "SM10_AEA.dm.", "index": "62", "type": "numeric", "distinct": "88", "missing": "0", "min": "8", "max": "18", "mean": "13", "stdev": "2" }, { "name": "SM10_EA.ed.", "index": "63", "type": "numeric", "distinct": "129", "missing": "0", "min": "21", "max": "29", "mean": "26", "stdev": "2" }, { "name": "SM11_EA.ed.", "index": "64", "type": "numeric", "distinct": "129", "missing": "0", "min": "23", "max": "32", "mean": "28", "stdev": "2" }, { "name": "SM12_EA.ed.", "index": "65", "type": "numeric", "distinct": "122", "missing": "0", "min": "25", "max": "35", "mean": "31", "stdev": "2" }, { "name": "SM13_EA.ed.", "index": "66", "type": "numeric", "distinct": "127", "missing": "0", "min": "27", "max": "38", "mean": "33", "stdev": "2" }, { "name": "SM14_EA.ed.", "index": "67", "type": "numeric", "distinct": "127", "missing": "0", "min": "29", "max": "41", "mean": "36", "stdev": "3" }, { "name": "SM15_EA.ed.", "index": "68", "type": "numeric", "distinct": "122", "missing": "0", "min": "31", "max": "44", "mean": "38", "stdev": "3" }, { "name": "SpDiam_EA", "index": "69", "type": "numeric", "distinct": "83", "missing": "0", "min": "5", "max": "6", "mean": "5", "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 }