{ "data_id": "33867", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL2363", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL2363", "version": 9, "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: CHEMBL2363 (TID: 10358), and it has 903 rows and 67 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": "2016-07-15 13:53:39", "update_comment": null, "last_update": "2016-07-15 13:53:39", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3515899\/data_53211.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-CHEMBL2363", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL2363 (TID: 10358), and it has 903 rows and 67 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": 903, "NumberOfFeatures": 69, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 68, "NumberOfSymbolicFeatures": 1, "MaxSkewnessOfNumericAtts": 14.837716790688512, "MinStdDevOfNumericAtts": 0.0444518257282229, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 1.1122213369079863, "MaxStdDevOfNumericAtts": 67.91000473946367, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": -0.06699275331067012, "Quartile3StdDevOfNumericAtts": 1.5154528467637336, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 1.5757607973421928, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": 6.311120715124408, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 4.937195557292685, "Quartile1SkewnessOfNumericAtts": -1.6434939645057869, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.18557182075581363, "AutoCorrelation": -0.17217627494456725, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "ClassEntropy": null, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": 1.6204013092138374, "Dimensionality": 0.07641196013289037, "MeanSkewnessOfNumericAtts": 0.14311174647291702, "Quartile2MeansOfNumericAtts": 2.39012015503876, "EquivalentNumberOfAtts": null, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 2.627671748261014, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": 0.20882502208676712, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -0.9208705256726071, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.3168806561406004, "MaxKurtosisOfNumericAtts": 236.69684686380614, "MinMeansOfNumericAtts": -0.004318936877076413, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 65.97040753045405, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 6.055568076948725, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.55072463768117, "Quartile3MeansOfNumericAtts": 4.074513012181617, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -2.6164784432167347, "PercentageOfSymbolicFeatures": 1.4492753623188406, "Quartile3MutualInformation": null }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "68", "type": "numeric", "distinct": "522", "missing": "0", "target": "1", "min": "4", "max": "11", "mean": "6", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "903", "missing": "0", "identifier": "1", "distr": [] }, { "name": "SpMin2_Bh.i.", "index": "1", "type": "numeric", "distinct": "252", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "SpMin1_Bh.v.", "index": "2", "type": "numeric", "distinct": "187", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "SpMin2_Bh.v.", "index": "3", "type": "numeric", "distinct": "211", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "nR10", "index": "4", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "SpMin2_Bh.m.", "index": "5", "type": "numeric", "distinct": "268", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "CATS2D_07_PL", "index": "6", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "6", "mean": "2", "stdev": "1" }, { "name": "Eig06_EA.bo.", "index": "7", "type": "numeric", "distinct": "384", "missing": "0", "min": "0", "max": "3", "mean": "2", "stdev": "0" }, { "name": "Eta_betaP", "index": "8", "type": "numeric", "distinct": "39", "missing": "0", "min": "7", "max": "33", "mean": "18", "stdev": "4" }, { "name": "DECC", "index": "9", "type": "numeric", "distinct": "387", "missing": "0", "min": "1", "max": "3", "mean": "2", "stdev": "0" }, { "name": "SpMin2_Bh.e.", "index": "10", "type": "numeric", "distinct": "267", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "Ui", "index": "11", "type": "numeric", "distinct": "23", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "nBM", "index": "12", "type": "numeric", "distinct": "20", "missing": "0", "min": "6", "max": "31", "mean": "17", "stdev": "3" }, { "name": "Uc", "index": "13", "type": "numeric", "distinct": "20", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "Eig05_EA.bo.", "index": "14", "type": "numeric", "distinct": "326", "missing": "0", "min": "1", "max": "3", "mean": "3", "stdev": "0" }, { "name": "SM15_AEA.ri.", "index": "15", "type": "numeric", "distinct": "326", "missing": "0", "min": "1", "max": "3", "mean": "3", "stdev": "0" }, { "name": "nR06", "index": "16", "type": "numeric", "distinct": "5", "missing": "0", "min": "1", "max": "5", "mean": "3", "stdev": "1" }, { "name": "SpMin1_Bh.p.", "index": "17", "type": "numeric", "distinct": "161", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "GATS6i", "index": "18", "type": "numeric", "distinct": "433", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "TRS", "index": "19", "type": "numeric", "distinct": "13", "missing": "0", "min": "12", "max": "37", "mean": "18", "stdev": "4" }, { "name": "nPyridines", "index": "20", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "ICR", "index": "21", "type": "numeric", "distinct": "314", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "CATS2D_07_DL", "index": "22", "type": "numeric", "distinct": "10", "missing": "0", "min": "0", "max": "9", "mean": "2", "stdev": "2" }, { "name": "Xindex", "index": "23", "type": "numeric", "distinct": "226", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "Vindex", "index": "24", "type": "numeric", "distinct": "180", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Eig03_EA.ri.", "index": "25", "type": "numeric", "distinct": "467", "missing": "0", "min": "2", "max": "3", "mean": "2", "stdev": "0" }, { "name": "Eig05_AEA.bo.", "index": "26", "type": "numeric", "distinct": "296", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SpMax2_Bh.e.", "index": "27", "type": "numeric", "distinct": "251", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "Eig06_AEA.ed.", "index": "28", "type": "numeric", "distinct": "324", "missing": "0", "min": "3", "max": "5", "mean": "5", "stdev": "0" }, { "name": "Yindex", "index": "29", "type": "numeric", "distinct": "355", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SpMax2_Bh.v.", "index": "30", "type": "numeric", "distinct": "265", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "SpMax2_Bh.p.", "index": "31", "type": "numeric", "distinct": "265", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "D.Dtr10", "index": "32", "type": "numeric", "distinct": "299", "missing": "0", "min": "0", "max": "270", "mean": "66", "stdev": "68" }, { "name": "Eig06_EA", "index": "33", "type": "numeric", "distinct": "333", "missing": "0", "min": "0", "max": "2", "mean": "2", "stdev": "0" }, { "name": "SM14_AEA.bo.", "index": "34", "type": "numeric", "distinct": "333", "missing": "0", "min": "0", "max": "2", "mean": "2", "stdev": "0" }, { "name": "SpMax2_Bh.i.", "index": "35", "type": "numeric", "distinct": "232", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "C.043", "index": "36", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "Eig06_AEA.ri.", "index": "37", "type": "numeric", "distinct": "416", "missing": "0", "min": "1", "max": "3", "mean": "3", "stdev": "0" }, { "name": "SpMax2_Bh.m.", "index": "38", "type": "numeric", "distinct": "297", "missing": "0", "min": "3", "max": "11", "mean": "4", "stdev": "0" }, { "name": "SRW09", "index": "39", "type": "numeric", "distinct": "23", "missing": "0", "min": "0", "max": "8", "mean": "2", "stdev": "3" }, { "name": "nCar", "index": "40", "type": "numeric", "distinct": "17", "missing": "0", "min": "4", "max": "24", "mean": "13", "stdev": "3" }, { "name": "D.Dtr09", "index": "41", "type": "numeric", "distinct": "156", "missing": "0", "min": "0", "max": "291", "mean": "23", "stdev": "46" }, { "name": "nR09", "index": "42", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "0" }, { "name": "IDE", "index": "43", "type": "numeric", "distinct": "433", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "Eig05_EA.ri.", "index": "44", "type": "numeric", "distinct": "334", "missing": "0", "min": "1", "max": "3", "mean": "2", "stdev": "0" }, { "name": "Rperim", "index": "45", "type": "numeric", "distinct": "18", "missing": "0", "min": "10", "max": "31", "mean": "16", "stdev": "3" }, { "name": "MATS6i", "index": "46", "type": "numeric", "distinct": "404", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SpMax1_Bh.s.", "index": "47", "type": "numeric", "distinct": "94", "missing": "0", "min": "5", "max": "9", "mean": "6", "stdev": "1" }, { "name": "SM07_EA.dm.", "index": "48", "type": "numeric", "distinct": "44", "missing": "0", "min": "0", "max": "10", "mean": "1", "stdev": "2" }, { "name": "SM09_EA.dm.", "index": "49", "type": "numeric", "distinct": "38", "missing": "0", "min": "0", "max": "13", "mean": "2", "stdev": "3" }, { "name": "SM11_EA.dm.", "index": "50", "type": "numeric", "distinct": "36", "missing": "0", "min": "0", "max": "15", "mean": "2", "stdev": "4" }, { "name": "SM13_EA.dm.", "index": "51", "type": "numeric", "distinct": "35", "missing": "0", "min": "0", "max": "18", "mean": "2", "stdev": "5" }, { "name": "SM15_EA.dm.", "index": "52", "type": "numeric", "distinct": "35", "missing": "0", "min": "0", "max": "21", "mean": "3", "stdev": "5" }, { "name": "SRW07", "index": "53", "type": "numeric", "distinct": "11", "missing": "0", "min": "0", "max": "6", "mean": "1", "stdev": "2" }, { "name": "HVcpx", "index": "54", "type": "numeric", "distinct": "411", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "N.075", "index": "55", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "4", "mean": "2", "stdev": "1" }, { "name": "NaaN", "index": "56", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "4", "mean": "2", "stdev": "1" }, { "name": "Eig01_EA.bo.", "index": "57", "type": "numeric", "distinct": "195", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SM11_AEA.ri.", "index": "58", "type": "numeric", "distinct": "195", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SpDiam_EA.bo.", "index": "59", "type": "numeric", "distinct": "194", "missing": "0", "min": "7", "max": "8", "mean": "7", "stdev": "0" }, { "name": "SpMax_EA.bo.", "index": "60", "type": "numeric", "distinct": "195", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "nAB", "index": "61", "type": "numeric", "distinct": "14", "missing": "0", "min": "6", "max": "29", "mean": "16", "stdev": "3" }, { "name": "SpMin2_Bh.s.", "index": "62", "type": "numeric", "distinct": "294", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SM03_EA.dm.", "index": "63", "type": "numeric", "distinct": "25", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "SM05_EA.dm.", "index": "64", "type": "numeric", "distinct": "46", "missing": "0", "min": "0", "max": "7", "mean": "1", "stdev": "2" }, { "name": "Eig03_AEA.bo.", "index": "65", "type": "numeric", "distinct": "391", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "CATS2D_06_DA", "index": "66", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "5", "mean": "1", "stdev": "1" }, { "name": "piPC05", "index": "67", "type": "numeric", "distinct": "450", "missing": "0", "min": "5", "max": "7", "mean": "6", "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 }