{ "data_id": "24124", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL5703", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL5703", "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: CHEMBL5703 (TID: 101508), and it has 532 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 13:57:46", "update_comment": null, "last_update": "2016-07-14 13:57:46", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3239905\/data_53390.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-CHEMBL5703", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL5703 (TID: 101508), and it has 532 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": 532, "NumberOfFeatures": 70, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 69, "NumberOfSymbolicFeatures": 1, "REPTreeDepth3AUC": null, "DecisionStumpAUC": null, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -0.7454215443186087, "Quartile2MeansOfNumericAtts": 3.617077067669173, "REPTreeDepth3ErrRate": null, "DecisionStumpErrRate": null, "MaxKurtosisOfNumericAtts": 127.78573881137035, "MinMeansOfNumericAtts": 0.27274624060150376, "Quartile2MutualInformation": null, "REPTreeDepth3Kappa": null, "DecisionStumpKappa": null, "MaxMeansOfNumericAtts": 38665.898496240596, "MinMutualInformation": null, "Quartile2SkewnessOfNumericAtts": -0.13065576055544134, "RandomTreeDepth1AUC": null, "Dimensionality": 0.13157894736842105, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.4112530897679061, "RandomTreeDepth1ErrRate": null, "EquivalentNumberOfAtts": null, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -2.2022370414058043, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "RandomTreeDepth1Kappa": null, "J48.00001.AUC": null, "MaxSkewnessOfNumericAtts": 10.273897700766248, "MinStdDevOfNumericAtts": 0.153295873233546, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 1.8381520963915547, "AutoCorrelation": 0.7260903954802258, "RandomTreeDepth2AUC": null, "J48.00001.ErrRate": null, "MaxStdDevOfNumericAtts": 92984.0417221163, "MinorityClassPercentage": null, "PercentageOfNumericFeatures": 98.57142857142858, "Quartile3MeansOfNumericAtts": 6.27751597744361, "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": 2.982941319488801, "NaiveBayesAUC": null, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 0.5157997518082129, "CfsSubsetEval_DecisionStumpKappa": null, "CfsSubsetEval_NaiveBayesAUC": null, "RandomTreeDepth3AUC": null, "J48.0001.ErrRate": null, "MeanMeansOfNumericAtts": 574.7139138062549, "NaiveBayesErrRate": null, "Quartile1KurtosisOfNumericAtts": -0.1649173008257927, "Quartile3StdDevOfNumericAtts": 1.3360960341594377, "CfsSubsetEval_NaiveBayesErrRate": null, "RandomTreeDepth3ErrRate": null, "J48.0001.Kappa": null, "MeanMutualInformation": null, "NaiveBayesKappa": null, "Quartile1MeansOfNumericAtts": 1.7001325187969925, "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": -0.7846822972514043, "REPTreeDepth1Kappa": null, "REPTreeDepth2AUC": null, "CfsSubsetEval_kNN1NErrRate": null, "kNN1NAUC": null, "J48.001.Kappa": null, "MeanSkewnessOfNumericAtts": 0.021280048412894353, "Quartile1StdDevOfNumericAtts": 0.2524012893978874, "REPTreeDepth2ErrRate": null, "CfsSubsetEval_kNN1NKappa": null, "kNN1NErrRate": null, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 1351.8005629842323, "Quartile2AttributeEntropy": null, "REPTreeDepth2Kappa": null, "ClassEntropy": null, "kNN1NKappa": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2KurtosisOfNumericAtts": 0.6663854311521034 }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "69", "type": "numeric", "distinct": "38", "missing": "0", "target": "1", "min": "5", "max": "8", "mean": "6", "stdev": "0" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "532", "missing": "0", "identifier": "1", "distr": [] }, { "name": "Chi0_EA.dm.", "index": "1", "type": "numeric", "distinct": "467", "missing": "0", "min": "0", "max": "46", "mean": "18", "stdev": "8" }, { "name": "Chi1_EA.dm.", "index": "2", "type": "numeric", "distinct": "474", "missing": "0", "min": "0", "max": "77", "mean": "24", "stdev": "14" }, { "name": "ATSC3m", "index": "3", "type": "numeric", "distinct": "515", "missing": "0", "min": "5", "max": "59", "mean": "22", "stdev": "8" }, { "name": "Eig06_EA", "index": "4", "type": "numeric", "distinct": "361", "missing": "0", "min": "1", "max": "3", "mean": "2", "stdev": "0" }, { "name": "SM14_AEA.bo.", "index": "5", "type": "numeric", "distinct": "361", "missing": "0", "min": "1", "max": "3", "mean": "2", "stdev": "0" }, { "name": "ATS5i", "index": "6", "type": "numeric", "distinct": "433", "missing": "0", "min": "3", "max": "6", "mean": "5", "stdev": "0" }, { "name": "Wap", "index": "7", "type": "numeric", "distinct": "464", "missing": "0", "min": "1862", "max": "1325540", "mean": "38666", "stdev": "92984" }, { "name": "TPC", "index": "8", "type": "numeric", "distinct": "412", "missing": "0", "min": "6", "max": "11", "mean": "8", "stdev": "1" }, { "name": "SpMax7_Bh.m.", "index": "9", "type": "numeric", "distinct": "349", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "Eig08_AEA.dm.", "index": "10", "type": "numeric", "distinct": "388", "missing": "0", "min": "0", "max": "3", "mean": "2", "stdev": "0" }, { "name": "Eig10_AEA.dm.", "index": "11", "type": "numeric", "distinct": "356", "missing": "0", "min": "-1", "max": "3", "mean": "1", "stdev": "1" }, { "name": "Eig07_AEA.dm.", "index": "12", "type": "numeric", "distinct": "393", "missing": "0", "min": "1", "max": "3", "mean": "2", "stdev": "0" }, { "name": "Eig09_AEA.dm.", "index": "13", "type": "numeric", "distinct": "392", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "0" }, { "name": "Eig06_AEA.ri.", "index": "14", "type": "numeric", "distinct": "414", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "Eig06_EA.ed.", "index": "15", "type": "numeric", "distinct": "451", "missing": "0", "min": "2", "max": "9", "mean": "5", "stdev": "1" }, { "name": "SM15_AEA.dm.", "index": "16", "type": "numeric", "distinct": "451", "missing": "0", "min": "2", "max": "9", "mean": "5", "stdev": "1" }, { "name": "IAC", "index": "17", "type": "numeric", "distinct": "467", "missing": "0", "min": "37", "max": "137", "mean": "77", "stdev": "19" }, { "name": "TIC0", "index": "18", "type": "numeric", "distinct": "467", "missing": "0", "min": "37", "max": "137", "mean": "77", "stdev": "19" }, { "name": "GGI8", "index": "19", "type": "numeric", "distinct": "290", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "SpMax7_Bh.p.", "index": "20", "type": "numeric", "distinct": "321", "missing": "0", "min": "2", "max": "3", "mean": "3", "stdev": "0" }, { "name": "Eig06_EA.ri.", "index": "21", "type": "numeric", "distinct": "415", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "ATS5e", "index": "22", "type": "numeric", "distinct": "431", "missing": "0", "min": "3", "max": "6", "mean": "5", "stdev": "0" }, { "name": "MPC10", "index": "23", "type": "numeric", "distinct": "236", "missing": "0", "min": "2", "max": "8", "mean": "5", "stdev": "1" }, { "name": "piPC03", "index": "24", "type": "numeric", "distinct": "349", "missing": "0", "min": "4", "max": "6", "mean": "5", "stdev": "0" }, { "name": "ATSC4p", "index": "25", "type": "numeric", "distinct": "514", "missing": "0", "min": "3", "max": "21", "mean": "9", "stdev": "3" }, { "name": "SpMin7_Bh.v.", "index": "26", "type": "numeric", "distinct": "328", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "SpMax8_Bh.m.", "index": "27", "type": "numeric", "distinct": "329", "missing": "0", "min": "2", "max": "3", "mean": "3", "stdev": "0" }, { "name": "SpMin8_Bh.v.", "index": "28", "type": "numeric", "distinct": "309", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "SpMax8_Bh.i.", "index": "29", "type": "numeric", "distinct": "316", "missing": "0", "min": "2", "max": "3", "mean": "3", "stdev": "0" }, { "name": "SpMax8_Bh.p.", "index": "30", "type": "numeric", "distinct": "311", "missing": "0", "min": "1", "max": "3", "mean": "3", "stdev": "0" }, { "name": "Eig08_EA.ed.", "index": "31", "type": "numeric", "distinct": "422", "missing": "0", "min": "-1", "max": "8", "mean": "4", "stdev": "1" }, { "name": "SM03_AEA.ri.", "index": "32", "type": "numeric", "distinct": "422", "missing": "0", "min": "-1", "max": "8", "mean": "4", "stdev": "1" }, { "name": "ATS8m", "index": "33", "type": "numeric", "distinct": "443", "missing": "0", "min": "0", "max": "5", "mean": "3", "stdev": "1" }, { "name": "Eta_L", "index": "34", "type": "numeric", "distinct": "486", "missing": "0", "min": "3", "max": "11", "mean": "6", "stdev": "2" }, { "name": "P_VSA_i_3", "index": "35", "type": "numeric", "distinct": "320", "missing": "0", "min": "24", "max": "550", "mean": "241", "stdev": "83" }, { "name": "Eig08_AEA.ed.", "index": "36", "type": "numeric", "distinct": "390", "missing": "0", "min": "2", "max": "6", "mean": "4", "stdev": "1" }, { "name": "ATS2m", "index": "37", "type": "numeric", "distinct": "387", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "Eig10_AEA.ed.", "index": "38", "type": "numeric", "distinct": "354", "missing": "0", "min": "2", "max": "5", "mean": "4", "stdev": "1" }, { "name": "Eig06_AEA.bo.", "index": "39", "type": "numeric", "distinct": "374", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "Eig07_AEA.ri.", "index": "40", "type": "numeric", "distinct": "410", "missing": "0", "min": "1", "max": "3", "mean": "3", "stdev": "0" }, { "name": "ATS3m", "index": "41", "type": "numeric", "distinct": "399", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SpMin7_Bh.s.", "index": "42", "type": "numeric", "distinct": "251", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "CATS2D_02_AL", "index": "43", "type": "numeric", "distinct": "15", "missing": "0", "min": "0", "max": "14", "mean": "5", "stdev": "3" }, { "name": "Eig11_AEA.dm.", "index": "44", "type": "numeric", "distinct": "340", "missing": "0", "min": "-1", "max": "2", "mean": "1", "stdev": "1" }, { "name": "S1K", "index": "45", "type": "numeric", "distinct": "434", "missing": "0", "min": "9", "max": "32", "mean": "18", "stdev": "4" }, { "name": "SpMin7_Bh.m.", "index": "46", "type": "numeric", "distinct": "316", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "MWC05", "index": "47", "type": "numeric", "distinct": "369", "missing": "0", "min": "7", "max": "9", "mean": "8", "stdev": "0" }, { "name": "Eig06_AEA.dm.", "index": "48", "type": "numeric", "distinct": "408", "missing": "0", "min": "1", "max": "3", "mean": "2", "stdev": "0" }, { "name": "ATSC5m", "index": "49", "type": "numeric", "distinct": "524", "missing": "0", "min": "4", "max": "63", "mean": "25", "stdev": "10" }, { "name": "X3v", "index": "50", "type": "numeric", "distinct": "494", "missing": "0", "min": "2", "max": "11", "mean": "5", "stdev": "1" }, { "name": "SsssN", "index": "51", "type": "numeric", "distinct": "118", "missing": "0", "min": "0", "max": "8", "mean": "1", "stdev": "1" }, { "name": "SpMax8_Bh.v.", "index": "52", "type": "numeric", "distinct": "310", "missing": "0", "min": "1", "max": "3", "mean": "3", "stdev": "0" }, { "name": "SpMax7_Bh.v.", "index": "53", "type": "numeric", "distinct": "325", "missing": "0", "min": "2", "max": "3", "mean": "3", "stdev": "0" }, { "name": "ATS1m", "index": "54", "type": "numeric", "distinct": "369", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "SpMin7_Bh.e.", "index": "55", "type": "numeric", "distinct": "314", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "SpMin7_Bh.i.", "index": "56", "type": "numeric", "distinct": "309", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "RDSQ", "index": "57", "type": "numeric", "distinct": "489", "missing": "0", "min": "102", "max": "598", "mean": "245", "stdev": "78" }, { "name": "Eig08_EA", "index": "58", "type": "numeric", "distinct": "368", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "SM02_AEA.dm.", "index": "59", "type": "numeric", "distinct": "368", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "SpAD_AEA.dm.", "index": "60", "type": "numeric", "distinct": "510", "missing": "0", "min": "26", "max": "85", "mean": "48", "stdev": "11" }, { "name": "Eig07_EA.ri.", "index": "61", "type": "numeric", "distinct": "402", "missing": "0", "min": "0", "max": "2", "mean": "2", "stdev": "0" }, { "name": "MWC04", "index": "62", "type": "numeric", "distinct": "277", "missing": "0", "min": "6", "max": "8", "mean": "7", "stdev": "0" }, { "name": "Eig07_EA.ed.", "index": "63", "type": "numeric", "distinct": "444", "missing": "0", "min": "0", "max": "8", "mean": "4", "stdev": "1" }, { "name": "SM02_AEA.ri.", "index": "64", "type": "numeric", "distinct": "444", "missing": "0", "min": "0", "max": "8", "mean": "4", "stdev": "1" }, { "name": "Eig09_EA.bo.", "index": "65", "type": "numeric", "distinct": "365", "missing": "0", "min": "-1", "max": "3", "mean": "2", "stdev": "1" }, { "name": "SM04_EA.bo.", "index": "66", "type": "numeric", "distinct": "373", "missing": "0", "min": "7", "max": "8", "mean": "7", "stdev": "0" }, { "name": "SpMin7_Bh.p.", "index": "67", "type": "numeric", "distinct": "330", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "ATSC5p", "index": "68", "type": "numeric", "distinct": "514", "missing": "0", "min": "2", "max": "24", "mean": "9", "stdev": "3" } ], "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 }