{ "data_id": "35568", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4803", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4803", "version": 11, "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: CHEMBL4803 (TID: 11573), and it has 713 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": "2016-07-15 18:23:55", "update_comment": null, "last_update": "2016-07-15 18:23:55", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3562019\/data_53406.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4803", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL4803 (TID: 11573), and it has 713 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": 713, "NumberOfFeatures": 70, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 69, "NumberOfSymbolicFeatures": 1, "ClassEntropy": null, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "Dimensionality": 0.09817671809256662, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": 0.6696395997076001, "EquivalentNumberOfAtts": null, "MeanSkewnessOfNumericAtts": 0.4739650933613355, "Quartile2MeansOfNumericAtts": 1.14446002805049, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 200.1337489906915, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": 0.15926878643034076, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.6289409616909394, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.8798945865710284, "MaxKurtosisOfNumericAtts": 13.44239971212137, "MinMeansOfNumericAtts": -0.9969845722300126, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 13948.962131837274, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 2.3275695139732946, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.57142857142858, "Quartile3MeansOfNumericAtts": 4.826462833099579, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -1.4360290378048908, "PercentageOfSymbolicFeatures": 1.4285714285714286, "Quartile3MutualInformation": null, "MaxSkewnessOfNumericAtts": 3.924882272361242, "MinStdDevOfNumericAtts": 0.039272869892127166, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 1.5489593325633724, "MaxStdDevOfNumericAtts": 13344.843654809783, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": -0.5233318043805009, "Quartile3StdDevOfNumericAtts": 2.0172440217151557, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 0.22827349228611493, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": 1.3995536594853477, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 214.93953011362433, "Quartile1SkewnessOfNumericAtts": -0.7084456807792359, "AutoCorrelation": 0.34339185393258453, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.5731222479053513 }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "69", "type": "numeric", "distinct": "345", "missing": "0", "target": "1", "min": "4", "max": "8", "mean": "5", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "713", "missing": "0", "identifier": "1", "distr": [] }, { "name": "SaaN", "index": "1", "type": "numeric", "distinct": "254", "missing": "0", "min": "0", "max": "25", "mean": "3", "stdev": "4" }, { "name": "N.075", "index": "2", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "6", "mean": "1", "stdev": "1" }, { "name": "NaaN", "index": "3", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "6", "mean": "1", "stdev": "1" }, { "name": "C.042", "index": "4", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "nImidazoles", "index": "5", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "MATS1i", "index": "6", "type": "numeric", "distinct": "324", "missing": "0", "min": "-1", "max": "0", "mean": "0", "stdev": "0" }, { "name": "CATS2D_04_AA", "index": "7", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "5", "mean": "0", "stdev": "1" }, { "name": "Eta_betaS_A", "index": "8", "type": "numeric", "distinct": "105", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "H.049", "index": "9", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "0", "stdev": "1" }, { "name": "nArOR", "index": "10", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "1" }, { "name": "O.060", "index": "11", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "1" }, { "name": "NssO", "index": "12", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "1" }, { "name": "SssO", "index": "13", "type": "numeric", "distinct": "143", "missing": "0", "min": "0", "max": "17", "mean": "2", "stdev": "3" }, { "name": "MATS1p", "index": "14", "type": "numeric", "distinct": "262", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "C.032", "index": "15", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "ATSC7e", "index": "16", "type": "numeric", "distinct": "369", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "Eig02_EA.bo.", "index": "17", "type": "numeric", "distinct": "308", "missing": "0", "min": "0", "max": "4", "mean": "3", "stdev": "1" }, { "name": "SM12_AEA.ri.", "index": "18", "type": "numeric", "distinct": "308", "missing": "0", "min": "0", "max": "4", "mean": "3", "stdev": "1" }, { "name": "ZM1MulPer", "index": "19", "type": "numeric", "distinct": "611", "missing": "0", "min": "67", "max": "669", "mean": "290", "stdev": "143" }, { "name": "ZM1V", "index": "20", "type": "numeric", "distinct": "208", "missing": "0", "min": "62", "max": "618", "mean": "271", "stdev": "133" }, { "name": "Eig08_AEA.dm.", "index": "21", "type": "numeric", "distinct": "484", "missing": "0", "min": "-2", "max": "2", "mean": "1", "stdev": "1" }, { "name": "Eig03_EA.ed.", "index": "22", "type": "numeric", "distinct": "395", "missing": "0", "min": "-2", "max": "11", "mean": "6", "stdev": "2" }, { "name": "SM12_AEA.dm.", "index": "23", "type": "numeric", "distinct": "395", "missing": "0", "min": "-2", "max": "11", "mean": "6", "stdev": "2" }, { "name": "ATSC8e", "index": "24", "type": "numeric", "distinct": "372", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "nAB", "index": "25", "type": "numeric", "distinct": "15", "missing": "0", "min": "0", "max": "26", "mean": "10", "stdev": "7" }, { "name": "Psi_i_s", "index": "26", "type": "numeric", "distinct": "333", "missing": "0", "min": "13", "max": "93", "mean": "44", "stdev": "18" }, { "name": "SAdon", "index": "27", "type": "numeric", "distinct": "52", "missing": "0", "min": "0", "max": "187", "mean": "46", "stdev": "31" }, { "name": "Eig03_AEA.bo.", "index": "28", "type": "numeric", "distinct": "401", "missing": "0", "min": "0", "max": "4", "mean": "3", "stdev": "1" }, { "name": "C.027", "index": "29", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "0", "stdev": "1" }, { "name": "ATSC5e", "index": "30", "type": "numeric", "distinct": "419", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "ATSC4e", "index": "31", "type": "numeric", "distinct": "408", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "ATS1s", "index": "32", "type": "numeric", "distinct": "476", "missing": "0", "min": "4", "max": "5", "mean": "5", "stdev": "0" }, { "name": "Eig14_AEA.dm.", "index": "33", "type": "numeric", "distinct": "303", "missing": "0", "min": "-2", "max": "1", "mean": "0", "stdev": "1" }, { "name": "Eig02_AEA.bo.", "index": "34", "type": "numeric", "distinct": "343", "missing": "0", "min": "1", "max": "5", "mean": "4", "stdev": "0" }, { "name": "nN", "index": "35", "type": "numeric", "distinct": "9", "missing": "0", "min": "1", "max": "10", "mean": "3", "stdev": "1" }, { "name": "P_VSA_LogP_4", "index": "36", "type": "numeric", "distinct": "123", "missing": "0", "min": "0", "max": "149", "mean": "37", "stdev": "35" }, { "name": "GMTIV", "index": "37", "type": "numeric", "distinct": "624", "missing": "0", "min": "195", "max": "63459", "mean": "13949", "stdev": "13345" }, { "name": "CATS2D_02_AA", "index": "38", "type": "numeric", "distinct": "9", "missing": "0", "min": "0", "max": "8", "mean": "1", "stdev": "1" }, { "name": "Eig14_EA", "index": "39", "type": "numeric", "distinct": "260", "missing": "0", "min": "-2", "max": "1", "mean": "0", "stdev": "1" }, { "name": "Eig14_EA.bo.", "index": "40", "type": "numeric", "distinct": "272", "missing": "0", "min": "-3", "max": "1", "mean": "0", "stdev": "1" }, { "name": "Eig14_EA.ed.", "index": "41", "type": "numeric", "distinct": "289", "missing": "0", "min": "-7", "max": "2", "mean": "-1", "stdev": "2" }, { "name": "Eig14_EA.ri.", "index": "42", "type": "numeric", "distinct": "338", "missing": "0", "min": "-2", "max": "1", "mean": "0", "stdev": "1" }, { "name": "SM08_AEA.dm.", "index": "43", "type": "numeric", "distinct": "260", "missing": "0", "min": "-2", "max": "1", "mean": "0", "stdev": "1" }, { "name": "SM09_AEA.ri.", "index": "44", "type": "numeric", "distinct": "289", "missing": "0", "min": "-7", "max": "2", "mean": "-1", "stdev": "2" }, { "name": "IDDM", "index": "45", "type": "numeric", "distinct": "266", "missing": "0", "min": "2", "max": "5", "mean": "4", "stdev": "1" }, { "name": "H.048", "index": "46", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "SpMax2_Bh.i.", "index": "47", "type": "numeric", "distinct": "359", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "Eig09_AEA.dm.", "index": "48", "type": "numeric", "distinct": "445", "missing": "0", "min": "-2", "max": "2", "mean": "0", "stdev": "1" }, { "name": "IDM", "index": "49", "type": "numeric", "distinct": "411", "missing": "0", "min": "3", "max": "9", "mean": "7", "stdev": "1" }, { "name": "Dz", "index": "50", "type": "numeric", "distinct": "167", "missing": "0", "min": "11", "max": "76", "mean": "42", "stdev": "17" }, { "name": "Eig10_AEA.dm.", "index": "51", "type": "numeric", "distinct": "424", "missing": "0", "min": "-2", "max": "2", "mean": "0", "stdev": "1" }, { "name": "Eig15_AEA.dm.", "index": "52", "type": "numeric", "distinct": "298", "missing": "0", "min": "-2", "max": "1", "mean": "0", "stdev": "1" }, { "name": "H.050", "index": "53", "type": "numeric", "distinct": "11", "missing": "0", "min": "0", "max": "10", "mean": "2", "stdev": "1" }, { "name": "nHDon", "index": "54", "type": "numeric", "distinct": "11", "missing": "0", "min": "0", "max": "10", "mean": "2", "stdev": "1" }, { "name": "MATS1m", "index": "55", "type": "numeric", "distinct": "155", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "CATS2D_09_AL", "index": "56", "type": "numeric", "distinct": "9", "missing": "0", "min": "0", "max": "9", "mean": "1", "stdev": "2" }, { "name": "Eig14_AEA.ed.", "index": "57", "type": "numeric", "distinct": "267", "missing": "0", "min": "0", "max": "3", "mean": "2", "stdev": "1" }, { "name": "Eig03_EA.bo.", "index": "58", "type": "numeric", "distinct": "399", "missing": "0", "min": "-1", "max": "4", "mean": "3", "stdev": "1" }, { "name": "SM13_AEA.ri.", "index": "59", "type": "numeric", "distinct": "399", "missing": "0", "min": "-1", "max": "4", "mean": "3", "stdev": "1" }, { "name": "X0", "index": "60", "type": "numeric", "distinct": "207", "missing": "0", "min": "4", "max": "24", "mean": "14", "stdev": "5" }, { "name": "ATS2s", "index": "61", "type": "numeric", "distinct": "502", "missing": "0", "min": "4", "max": "6", "mean": "5", "stdev": "0" }, { "name": "Eta_betaS", "index": "62", "type": "numeric", "distinct": "82", "missing": "0", "min": "3", "max": "25", "mean": "13", "stdev": "5" }, { "name": "nBM", "index": "63", "type": "numeric", "distinct": "25", "missing": "0", "min": "1", "max": "26", "mean": "11", "stdev": "7" }, { "name": "Uc", "index": "64", "type": "numeric", "distinct": "25", "missing": "0", "min": "1", "max": "5", "mean": "3", "stdev": "1" }, { "name": "DELS", "index": "65", "type": "numeric", "distinct": "666", "missing": "0", "min": "4", "max": "72", "mean": "18", "stdev": "12" }, { "name": "C.007", "index": "66", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "SaasN", "index": "67", "type": "numeric", "distinct": "107", "missing": "0", "min": "0", "max": "4", "mean": "0", "stdev": "1" }, { "name": "CATS2D_04_DL", "index": "68", "type": "numeric", "distinct": "10", "missing": "0", "min": "0", "max": "9", "mean": "3", "stdev": "2" } ], "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 }