{ "data_id": "32901", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL2284", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL2284", "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: CHEMBL2284 (TID: 11757), and it has 798 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": "2016-07-15 11:24:06", "update_comment": null, "last_update": "2016-07-15 11:24:06", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3492335\/data_53562.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-CHEMBL2284", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL2284 (TID: 11757), and it has 798 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": 798, "NumberOfFeatures": 71, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 70, "NumberOfSymbolicFeatures": 1, "MaxSkewnessOfNumericAtts": 6.328701324041872, "MinStdDevOfNumericAtts": 0.05009373496313771, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 2.2199269456102546, "MaxStdDevOfNumericAtts": 72.45896536935652, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": 0.7758326855541757, "Quartile3StdDevOfNumericAtts": 4.502391607967693, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 0.09555137844611547, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": 7.676666204723481, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 17.90517330827068, "Quartile1SkewnessOfNumericAtts": 0.32657285423303173, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.595660795698687, "AutoCorrelation": 0.761289836888331, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "ClassEntropy": null, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": 5.589540692035693, "Dimensionality": 0.08897243107769423, "MeanSkewnessOfNumericAtts": 1.3927437420755189, "Quartile2MeansOfNumericAtts": 3.149578947368421, "EquivalentNumberOfAtts": null, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 7.625080817872517, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": 1.3740605338973553, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -0.7171655680996909, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.8952398834753861, "MaxKurtosisOfNumericAtts": 55.745292280265865, "MinMeansOfNumericAtts": -2.280300751879699, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 180.88419423558898, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 9.382975987120457, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.59154929577466, "Quartile3MeansOfNumericAtts": 15.274986215538847, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -5.338970518823845, "PercentageOfSymbolicFeatures": 1.4084507042253522, "Quartile3MutualInformation": null }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "70", "type": "numeric", "distinct": "70", "missing": "0", "target": "1", "min": "4", "max": "7", "mean": "4", "stdev": "0" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "798", "missing": "0", "identifier": "1", "distr": [] }, { "name": "SsssCH", "index": "1", "type": "numeric", "distinct": "179", "missing": "0", "min": "-13", "max": "2", "mean": "0", "stdev": "1" }, { "name": "O.056", "index": "2", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "6", "mean": "0", "stdev": "1" }, { "name": "C.008", "index": "3", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "6", "mean": "0", "stdev": "1" }, { "name": "P_VSA_MR_3", "index": "4", "type": "numeric", "distinct": "18", "missing": "0", "min": "0", "max": "258", "mean": "11", "stdev": "30" }, { "name": "SsOH", "index": "5", "type": "numeric", "distinct": "241", "missing": "0", "min": "0", "max": "56", "mean": "5", "stdev": "8" }, { "name": "CATS2D_03_DA", "index": "6", "type": "numeric", "distinct": "8", "missing": "0", "min": "0", "max": "7", "mean": "1", "stdev": "1" }, { "name": "P_VSA_LogP_3", "index": "7", "type": "numeric", "distinct": "129", "missing": "0", "min": "0", "max": "326", "mean": "65", "stdev": "40" }, { "name": "nOxolanes", "index": "8", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "ATS1s", "index": "9", "type": "numeric", "distinct": "484", "missing": "0", "min": "4", "max": "6", "mean": "5", "stdev": "0" }, { "name": "GGI8", "index": "10", "type": "numeric", "distinct": "260", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "nOHs", "index": "11", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "0" }, { "name": "IC2", "index": "12", "type": "numeric", "distinct": "507", "missing": "0", "min": "2", "max": "6", "mean": "4", "stdev": "0" }, { "name": "TIC1", "index": "13", "type": "numeric", "distinct": "631", "missing": "0", "min": "44", "max": "474", "mean": "133", "stdev": "48" }, { "name": "TIC2", "index": "14", "type": "numeric", "distinct": "633", "missing": "0", "min": "58", "max": "601", "mean": "160", "stdev": "62" }, { "name": "NsssCH", "index": "15", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "8", "mean": "1", "stdev": "1" }, { "name": "Chi0_AEA.bo.", "index": "16", "type": "numeric", "distinct": "476", "missing": "0", "min": "5", "max": "43", "mean": "15", "stdev": "4" }, { "name": "Chi0_AEA.dm.", "index": "17", "type": "numeric", "distinct": "476", "missing": "0", "min": "5", "max": "43", "mean": "15", "stdev": "4" }, { "name": "Chi0_AEA.ed.", "index": "18", "type": "numeric", "distinct": "476", "missing": "0", "min": "5", "max": "43", "mean": "15", "stdev": "4" }, { "name": "Chi0_AEA.ri.", "index": "19", "type": "numeric", "distinct": "476", "missing": "0", "min": "5", "max": "43", "mean": "15", "stdev": "4" }, { "name": "Chi0_EA", "index": "20", "type": "numeric", "distinct": "476", "missing": "0", "min": "5", "max": "43", "mean": "15", "stdev": "4" }, { "name": "Chi0_EA.ri.", "index": "21", "type": "numeric", "distinct": "698", "missing": "0", "min": "5", "max": "44", "mean": "16", "stdev": "5" }, { "name": "Eig15_AEA.bo.", "index": "22", "type": "numeric", "distinct": "397", "missing": "0", "min": "-1", "max": "3", "mean": "0", "stdev": "1" }, { "name": "Eig15_AEA.dm.", "index": "23", "type": "numeric", "distinct": "492", "missing": "0", "min": "-2", "max": "2", "mean": "0", "stdev": "1" }, { "name": "HDcpx", "index": "24", "type": "numeric", "distinct": "252", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "IDM", "index": "25", "type": "numeric", "distinct": "545", "missing": "0", "min": "5", "max": "11", "mean": "8", "stdev": "1" }, { "name": "IVDM", "index": "26", "type": "numeric", "distinct": "267", "missing": "0", "min": "3", "max": "6", "mean": "4", "stdev": "0" }, { "name": "ON0", "index": "27", "type": "numeric", "distinct": "140", "missing": "0", "min": "5", "max": "34", "mean": "12", "stdev": "3" }, { "name": "S0K", "index": "28", "type": "numeric", "distinct": "216", "missing": "0", "min": "24", "max": "385", "mean": "100", "stdev": "39" }, { "name": "SpMaxA_AEA.dm.", "index": "29", "type": "numeric", "distinct": "172", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "TIC3", "index": "30", "type": "numeric", "distinct": "532", "missing": "0", "min": "58", "max": "669", "mean": "177", "stdev": "70" }, { "name": "TIC4", "index": "31", "type": "numeric", "distinct": "493", "missing": "0", "min": "58", "max": "691", "mean": "181", "stdev": "72" }, { "name": "X1", "index": "32", "type": "numeric", "distinct": "481", "missing": "0", "min": "4", "max": "31", "mean": "11", "stdev": "3" }, { "name": "X1Mad", "index": "33", "type": "numeric", "distinct": "704", "missing": "0", "min": "4", "max": "28", "mean": "10", "stdev": "3" }, { "name": "Chi0_EA.dm.", "index": "34", "type": "numeric", "distinct": "604", "missing": "0", "min": "0", "max": "42", "mean": "16", "stdev": "8" }, { "name": "Eig13_EA", "index": "35", "type": "numeric", "distinct": "391", "missing": "0", "min": "-2", "max": "2", "mean": "0", "stdev": "1" }, { "name": "Eig13_EA.ed.", "index": "36", "type": "numeric", "distinct": "448", "missing": "0", "min": "-7", "max": "6", "mean": "-1", "stdev": "2" }, { "name": "SM07_AEA.dm.", "index": "37", "type": "numeric", "distinct": "391", "missing": "0", "min": "-2", "max": "2", "mean": "0", "stdev": "1" }, { "name": "SM08_AEA.ri.", "index": "38", "type": "numeric", "distinct": "448", "missing": "0", "min": "-7", "max": "6", "mean": "-1", "stdev": "2" }, { "name": "Eig10_AEA.ri.", "index": "39", "type": "numeric", "distinct": "534", "missing": "0", "min": "-1", "max": "3", "mean": "1", "stdev": "1" }, { "name": "Eig10_EA", "index": "40", "type": "numeric", "distinct": "450", "missing": "0", "min": "-2", "max": "2", "mean": "0", "stdev": "1" }, { "name": "SM04_AEA.dm.", "index": "41", "type": "numeric", "distinct": "450", "missing": "0", "min": "-2", "max": "2", "mean": "0", "stdev": "1" }, { "name": "CATS2D_08_DD", "index": "42", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "0", "stdev": "0" }, { "name": "CATS2D_07_DD", "index": "43", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "0", "stdev": "0" }, { "name": "BID", "index": "44", "type": "numeric", "distinct": "145", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "CID", "index": "45", "type": "numeric", "distinct": "383", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "Eig15_EA.bo.", "index": "46", "type": "numeric", "distinct": "467", "missing": "0", "min": "-3", "max": "2", "mean": "-1", "stdev": "1" }, { "name": "Eta_F", "index": "47", "type": "numeric", "distinct": "777", "missing": "0", "min": "2", "max": "94", "mean": "22", "stdev": "10" }, { "name": "Eta_FL", "index": "48", "type": "numeric", "distinct": "663", "missing": "0", "min": "1", "max": "16", "mean": "6", "stdev": "2" }, { "name": "IDDE", "index": "49", "type": "numeric", "distinct": "299", "missing": "0", "min": "1", "max": "6", "mean": "4", "stdev": "1" }, { "name": "IDDM", "index": "50", "type": "numeric", "distinct": "278", "missing": "0", "min": "3", "max": "6", "mean": "4", "stdev": "0" }, { "name": "LPRS", "index": "51", "type": "numeric", "distinct": "643", "missing": "0", "min": "24", "max": "424", "mean": "108", "stdev": "44" }, { "name": "nSK", "index": "52", "type": "numeric", "distinct": "40", "missing": "0", "min": "8", "max": "65", "mean": "23", "stdev": "7" }, { "name": "X0", "index": "53", "type": "numeric", "distinct": "321", "missing": "0", "min": "6", "max": "46", "mean": "16", "stdev": "5" }, { "name": "nROR", "index": "54", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "O.059", "index": "55", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "5", "mean": "0", "stdev": "0" }, { "name": "H.047", "index": "56", "type": "numeric", "distinct": "29", "missing": "0", "min": "0", "max": "31", "mean": "10", "stdev": "5" }, { "name": "Eig10_EA.bo.", "index": "57", "type": "numeric", "distinct": "500", "missing": "0", "min": "-3", "max": "3", "mean": "0", "stdev": "1" }, { "name": "ATS7v", "index": "58", "type": "numeric", "distinct": "639", "missing": "0", "min": "0", "max": "5", "mean": "3", "stdev": "1" }, { "name": "ATS8v", "index": "59", "type": "numeric", "distinct": "637", "missing": "0", "min": "0", "max": "5", "mean": "3", "stdev": "1" }, { "name": "Eig11_AEA.ri.", "index": "60", "type": "numeric", "distinct": "513", "missing": "0", "min": "-1", "max": "3", "mean": "1", "stdev": "1" }, { "name": "Eig13_AEA.ri.", "index": "61", "type": "numeric", "distinct": "506", "missing": "0", "min": "-1", "max": "3", "mean": "0", "stdev": "1" }, { "name": "Eig13_EA.ri.", "index": "62", "type": "numeric", "distinct": "491", "missing": "0", "min": "-2", "max": "2", "mean": "0", "stdev": "1" }, { "name": "Eig14_AEA.dm.", "index": "63", "type": "numeric", "distinct": "482", "missing": "0", "min": "-2", "max": "2", "mean": "0", "stdev": "1" }, { "name": "Eig15_AEA.ri.", "index": "64", "type": "numeric", "distinct": "479", "missing": "0", "min": "-1", "max": "3", "mean": "0", "stdev": "1" }, { "name": "Eig15_EA.ed.", "index": "65", "type": "numeric", "distinct": "452", "missing": "0", "min": "-7", "max": "5", "mean": "-2", "stdev": "2" }, { "name": "Eig15_EA.ri.", "index": "66", "type": "numeric", "distinct": "501", "missing": "0", "min": "-2", "max": "2", "mean": "-1", "stdev": "1" }, { "name": "SM10_AEA.ri.", "index": "67", "type": "numeric", "distinct": "452", "missing": "0", "min": "-7", "max": "5", "mean": "-2", "stdev": "2" }, { "name": "SNar", "index": "68", "type": "numeric", "distinct": "175", "missing": "0", "min": "4", "max": "47", "mean": "16", "stdev": "5" }, { "name": "SpAD_EA.ri.", "index": "69", "type": "numeric", "distinct": "765", "missing": "0", "min": "9", "max": "105", "mean": "35", "stdev": "11" } ], "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 }