{ "data_id": "33964", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL2821", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL2821", "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: CHEMBL2821 (TID: 11288), and it has 665 rows and 70 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 14:08:31", "update_comment": null, "last_update": "2016-07-15 14:08:31", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3518174\/data_53623.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-CHEMBL2821", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL2821 (TID: 11288), and it has 665 rows and 70 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": 665, "NumberOfFeatures": 72, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 71, "NumberOfSymbolicFeatures": 1, "MaxSkewnessOfNumericAtts": 17.151423128906806, "MinStdDevOfNumericAtts": 0.030862109422217874, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 4.811918866547893, "MaxStdDevOfNumericAtts": 215569.60925207345, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": 3.019084185717357, "Quartile3StdDevOfNumericAtts": 4.828418887368602, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 0.9879699248120282, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": 22.90161959795712, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 630.3367086095519, "Quartile1SkewnessOfNumericAtts": 0.47304908698405645, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.36529052932231026, "AutoCorrelation": 0.9568960843373494, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "ClassEntropy": null, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": 12.754641780106088, "Dimensionality": 0.10827067669172932, "MeanSkewnessOfNumericAtts": 2.881837468092917, "Quartile2MeansOfNumericAtts": 3.5537924812030073, "EquivalentNumberOfAtts": null, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 3601.6815748082067, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": 2.528205191460398, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -0.2016382526988294, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.7817892971284713, "MaxKurtosisOfNumericAtts": 306.7599620253846, "MinMeansOfNumericAtts": -0.5739864661654136, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 29833.571428571395, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 30.618097293534543, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.61111111111111, "Quartile3MeansOfNumericAtts": 10.030306766917294, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -5.216419366993733, "PercentageOfSymbolicFeatures": 1.3888888888888888, "Quartile3MutualInformation": null }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "71", "type": "numeric", "distinct": "38", "missing": "0", "target": "1", "min": "4", "max": "7", "mean": "4", "stdev": "0" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "665", "missing": "0", "identifier": "1", "distr": [] }, { "name": "SdssC", "index": "1", "type": "numeric", "distinct": "507", "missing": "0", "min": "-15", "max": "4", "mean": "-1", "stdev": "2" }, { "name": "ALOGP", "index": "2", "type": "numeric", "distinct": "618", "missing": "0", "min": "-8", "max": "6", "mean": "3", "stdev": "2" }, { "name": "NdssC", "index": "3", "type": "numeric", "distinct": "12", "missing": "0", "min": "0", "max": "17", "mean": "2", "stdev": "2" }, { "name": "Eig05_EA.dm.", "index": "4", "type": "numeric", "distinct": "119", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "CATS2D_08_AA", "index": "5", "type": "numeric", "distinct": "12", "missing": "0", "min": "0", "max": "15", "mean": "1", "stdev": "2" }, { "name": "CATS2D_08_AP", "index": "6", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "7", "mean": "0", "stdev": "1" }, { "name": "Eig04_AEA.dm.", "index": "7", "type": "numeric", "distinct": "515", "missing": "0", "min": "1", "max": "4", "mean": "3", "stdev": "0" }, { "name": "Eig11_EA.dm.", "index": "8", "type": "numeric", "distinct": "13", "missing": "0", "min": "-1", "max": "2", "mean": "0", "stdev": "0" }, { "name": "Eig13_EA.dm.", "index": "9", "type": "numeric", "distinct": "23", "missing": "0", "min": "-4", "max": "2", "mean": "0", "stdev": "0" }, { "name": "nPyrrolidines", "index": "10", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "0" }, { "name": "NssNH", "index": "11", "type": "numeric", "distinct": "10", "missing": "0", "min": "0", "max": "12", "mean": "1", "stdev": "2" }, { "name": "SpMin8_Bh.e.", "index": "12", "type": "numeric", "distinct": "411", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "SpMin8_Bh.i.", "index": "13", "type": "numeric", "distinct": "397", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "SssNH", "index": "14", "type": "numeric", "distinct": "363", "missing": "0", "min": "0", "max": "29", "mean": "3", "stdev": "4" }, { "name": "Eig08_EA.dm.", "index": "15", "type": "numeric", "distinct": "23", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "ATS8m", "index": "16", "type": "numeric", "distinct": "571", "missing": "0", "min": "0", "max": "6", "mean": "3", "stdev": "1" }, { "name": "P_VSA_LogP_2", "index": "17", "type": "numeric", "distinct": "347", "missing": "0", "min": "0", "max": "458", "mean": "29", "stdev": "51" }, { "name": "CATS2D_05_AA", "index": "18", "type": "numeric", "distinct": "14", "missing": "0", "min": "0", "max": "15", "mean": "2", "stdev": "2" }, { "name": "Chi1_EA.dm.", "index": "19", "type": "numeric", "distinct": "652", "missing": "0", "min": "0", "max": "76", "mean": "22", "stdev": "11" }, { "name": "Eig07_AEA.dm.", "index": "20", "type": "numeric", "distinct": "525", "missing": "0", "min": "0", "max": "4", "mean": "2", "stdev": "1" }, { "name": "GGI4", "index": "21", "type": "numeric", "distinct": "482", "missing": "0", "min": "0", "max": "7", "mean": "2", "stdev": "1" }, { "name": "P_VSA_p_3", "index": "22", "type": "numeric", "distinct": "656", "missing": "0", "min": "37", "max": "417", "mean": "134", "stdev": "45" }, { "name": "P_VSA_v_3", "index": "23", "type": "numeric", "distinct": "656", "missing": "0", "min": "37", "max": "417", "mean": "134", "stdev": "45" }, { "name": "piPC03", "index": "24", "type": "numeric", "distinct": "447", "missing": "0", "min": "3", "max": "6", "mean": "5", "stdev": "0" }, { "name": "SpMax5_Bh.m.", "index": "25", "type": "numeric", "distinct": "448", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SpMin6_Bh.s.", "index": "26", "type": "numeric", "distinct": "376", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "Wap", "index": "27", "type": "numeric", "distinct": "638", "missing": "0", "min": "484", "max": "4133210", "mean": "29834", "stdev": "215570" }, { "name": "MPC06", "index": "28", "type": "numeric", "distinct": "156", "missing": "0", "min": "3", "max": "6", "mean": "4", "stdev": "1" }, { "name": "MWC10", "index": "29", "type": "numeric", "distinct": "520", "missing": "0", "min": "10", "max": "13", "mean": "12", "stdev": "0" }, { "name": "MWC08", "index": "30", "type": "numeric", "distinct": "521", "missing": "0", "min": "8", "max": "11", "mean": "10", "stdev": "0" }, { "name": "X4v", "index": "31", "type": "numeric", "distinct": "614", "missing": "0", "min": "1", "max": "15", "mean": "3", "stdev": "2" }, { "name": "X5v", "index": "32", "type": "numeric", "distinct": "606", "missing": "0", "min": "0", "max": "10", "mean": "2", "stdev": "1" }, { "name": "Hy", "index": "33", "type": "numeric", "distinct": "335", "missing": "0", "min": "-1", "max": "23", "mean": "0", "stdev": "3" }, { "name": "P_VSA_MR_5", "index": "34", "type": "numeric", "distinct": "608", "missing": "0", "min": "0", "max": "501", "mean": "49", "stdev": "58" }, { "name": "Uindex", "index": "35", "type": "numeric", "distinct": "652", "missing": "0", "min": "17", "max": "703", "mean": "48", "stdev": "47" }, { "name": "P_VSA_MR_2", "index": "36", "type": "numeric", "distinct": "272", "missing": "0", "min": "0", "max": "823", "mean": "90", "stdev": "98" }, { "name": "ATS7p", "index": "37", "type": "numeric", "distinct": "561", "missing": "0", "min": "1", "max": "6", "mean": "4", "stdev": "1" }, { "name": "ATS7v", "index": "38", "type": "numeric", "distinct": "558", "missing": "0", "min": "0", "max": "6", "mean": "3", "stdev": "1" }, { "name": "ATS8v", "index": "39", "type": "numeric", "distinct": "558", "missing": "0", "min": "0", "max": "6", "mean": "3", "stdev": "1" }, { "name": "ATSC7i", "index": "40", "type": "numeric", "distinct": "546", "missing": "0", "min": "0", "max": "8", "mean": "1", "stdev": "1" }, { "name": "ATSC7p", "index": "41", "type": "numeric", "distinct": "644", "missing": "0", "min": "0", "max": "62", "mean": "8", "stdev": "7" }, { "name": "ATSC7v", "index": "42", "type": "numeric", "distinct": "650", "missing": "0", "min": "0", "max": "83", "mean": "10", "stdev": "10" }, { "name": "ATSC8i", "index": "43", "type": "numeric", "distinct": "546", "missing": "0", "min": "0", "max": "9", "mean": "1", "stdev": "1" }, { "name": "CATS2D_09_DA", "index": "44", "type": "numeric", "distinct": "14", "missing": "0", "min": "0", "max": "23", "mean": "1", "stdev": "3" }, { "name": "MDDD", "index": "45", "type": "numeric", "distinct": "628", "missing": "0", "min": "4", "max": "292", "mean": "26", "stdev": "33" }, { "name": "nC..N.N2", "index": "46", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "nHAcc", "index": "47", "type": "numeric", "distinct": "22", "missing": "0", "min": "1", "max": "40", "mean": "6", "stdev": "4" }, { "name": "nHet", "index": "48", "type": "numeric", "distinct": "23", "missing": "0", "min": "2", "max": "43", "mean": "7", "stdev": "5" }, { "name": "nN", "index": "49", "type": "numeric", "distinct": "15", "missing": "0", "min": "0", "max": "21", "mean": "3", "stdev": "3" }, { "name": "P_VSA_s_5", "index": "50", "type": "numeric", "distinct": "40", "missing": "0", "min": "0", "max": "232", "mean": "21", "stdev": "29" }, { "name": "SMTI", "index": "51", "type": "numeric", "distinct": "646", "missing": "0", "min": "792", "max": "397039", "mean": "12764", "stdev": "39070" }, { "name": "SpMaxA_EA.ri.", "index": "52", "type": "numeric", "distinct": "131", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SpMin8_Bh.p.", "index": "53", "type": "numeric", "distinct": "423", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "ZM2MulPer", "index": "54", "type": "numeric", "distinct": "662", "missing": "0", "min": "134", "max": "1518", "mean": "417", "stdev": "166" }, { "name": "ZM2Per", "index": "55", "type": "numeric", "distinct": "659", "missing": "0", "min": "175", "max": "2202", "mean": "607", "stdev": "242" }, { "name": "ZM2V", "index": "56", "type": "numeric", "distinct": "327", "missing": "0", "min": "121", "max": "1428", "mean": "390", "stdev": "155" }, { "name": "ATSC7m", "index": "57", "type": "numeric", "distinct": "658", "missing": "0", "min": "4", "max": "218", "mean": "25", "stdev": "27" }, { "name": "CATS2D_07_DD", "index": "58", "type": "numeric", "distinct": "8", "missing": "0", "min": "0", "max": "9", "mean": "0", "stdev": "1" }, { "name": "MPC05", "index": "59", "type": "numeric", "distinct": "141", "missing": "0", "min": "2", "max": "6", "mean": "4", "stdev": "0" }, { "name": "ATS1v", "index": "60", "type": "numeric", "distinct": "474", "missing": "0", "min": "3", "max": "5", "mean": "3", "stdev": "0" }, { "name": "ATS2i", "index": "61", "type": "numeric", "distinct": "494", "missing": "0", "min": "4", "max": "6", "mean": "5", "stdev": "0" }, { "name": "ATS2v", "index": "62", "type": "numeric", "distinct": "485", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "ATS3e", "index": "63", "type": "numeric", "distinct": "518", "missing": "0", "min": "4", "max": "6", "mean": "5", "stdev": "0" }, { "name": "ATS3m", "index": "64", "type": "numeric", "distinct": "505", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "ATS3p", "index": "65", "type": "numeric", "distinct": "511", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "ATS3v", "index": "66", "type": "numeric", "distinct": "516", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "ATS4i", "index": "67", "type": "numeric", "distinct": "524", "missing": "0", "min": "4", "max": "7", "mean": "5", "stdev": "0" }, { "name": "ATS4m", "index": "68", "type": "numeric", "distinct": "516", "missing": "0", "min": "3", "max": "6", "mean": "4", "stdev": "0" }, { "name": "ATS4p", "index": "69", "type": "numeric", "distinct": "530", "missing": "0", "min": "3", "max": "6", "mean": "4", "stdev": "0" }, { "name": "ATS4v", "index": "70", "type": "numeric", "distinct": "523", "missing": "0", "min": "3", "max": "5", "mean": "4", "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 }