{ "data_id": "33003", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4708", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4708", "version": 10, "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: CHEMBL4708 (TID: 10277), and it has 886 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 11:39:44", "update_comment": null, "last_update": "2016-07-15 11:39:44", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3494513\/data_53610.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4708", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL4708 (TID: 10277), and it has 886 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": 886, "NumberOfFeatures": 71, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 70, "NumberOfSymbolicFeatures": 1, "ClassEntropy": null, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "Dimensionality": 0.08013544018058691, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": 0.9377038480831936, "EquivalentNumberOfAtts": null, "MeanSkewnessOfNumericAtts": 0.28724588421592573, "Quartile2MeansOfNumericAtts": 3.309182844243792, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 334.56821535310337, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": -0.19801470551916567, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -0.9649233458776809, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.7388947803847983, "MaxKurtosisOfNumericAtts": 58.63079619684019, "MinMeansOfNumericAtts": -0.10607449209932282, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 32393.22686230249, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 2.702184174596309, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.59154929577466, "Quartile3MeansOfNumericAtts": 7.76979881489842, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -1.5859975809694853, "PercentageOfSymbolicFeatures": 1.4084507042253522, "Quartile3MutualInformation": null, "MaxSkewnessOfNumericAtts": 5.487424329469862, "MinStdDevOfNumericAtts": 0.07850174266397174, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 0.83159934365564, "MaxStdDevOfNumericAtts": 23064.504881621702, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": 0.1996565252580449, "Quartile3StdDevOfNumericAtts": 2.6685788326461934, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 1.6201467268623024, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": 4.506076536004326, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 477.98387562076766, "Quartile1SkewnessOfNumericAtts": -0.49030414761574326, "AutoCorrelation": 0.2774011299435018, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.3594230922327799 }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "70", "type": "numeric", "distinct": "75", "missing": "0", "target": "1", "min": "5", "max": "10", "mean": "6", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "886", "missing": "0", "identifier": "1", "distr": [] }, { "name": "P_VSA_s_5", "index": "1", "type": "numeric", "distinct": "62", "missing": "0", "min": "0", "max": "99", "mean": "30", "stdev": "19" }, { "name": "CATS2D_02_DA", "index": "2", "type": "numeric", "distinct": "10", "missing": "0", "min": "0", "max": "12", "mean": "2", "stdev": "1" }, { "name": "P_VSA_e_3", "index": "3", "type": "numeric", "distinct": "307", "missing": "0", "min": "0", "max": "472", "mean": "78", "stdev": "36" }, { "name": "Eta_beta", "index": "4", "type": "numeric", "distinct": "154", "missing": "0", "min": "15", "max": "69", "mean": "38", "stdev": "9" }, { "name": "SpMax6_Bh.m.", "index": "5", "type": "numeric", "distinct": "532", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "Ui", "index": "6", "type": "numeric", "distinct": "30", "missing": "0", "min": "2", "max": "4", "mean": "4", "stdev": "0" }, { "name": "H.048", "index": "7", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "1" }, { "name": "Hy", "index": "8", "type": "numeric", "distinct": "421", "missing": "0", "min": "-1", "max": "15", "mean": "1", "stdev": "1" }, { "name": "H.050", "index": "9", "type": "numeric", "distinct": "11", "missing": "0", "min": "0", "max": "20", "mean": "3", "stdev": "2" }, { "name": "nHDon", "index": "10", "type": "numeric", "distinct": "11", "missing": "0", "min": "0", "max": "20", "mean": "3", "stdev": "2" }, { "name": "Eig07_AEA.bo.", "index": "11", "type": "numeric", "distinct": "526", "missing": "0", "min": "1", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SssNH", "index": "12", "type": "numeric", "distinct": "576", "missing": "0", "min": "0", "max": "11", "mean": "3", "stdev": "3" }, { "name": "C.033", "index": "13", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "1" }, { "name": "CATS2D_02_DL", "index": "14", "type": "numeric", "distinct": "11", "missing": "0", "min": "0", "max": "10", "mean": "3", "stdev": "2" }, { "name": "P_VSA_MR_6", "index": "15", "type": "numeric", "distinct": "735", "missing": "0", "min": "7", "max": "204", "mean": "102", "stdev": "38" }, { "name": "SpMax4_Bh.m.", "index": "16", "type": "numeric", "distinct": "510", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "P_VSA_m_2", "index": "17", "type": "numeric", "distinct": "817", "missing": "0", "min": "59", "max": "631", "mean": "197", "stdev": "53" }, { "name": "nPyrroles", "index": "18", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "ZM2Mad", "index": "19", "type": "numeric", "distinct": "851", "missing": "0", "min": "90", "max": "380", "mean": "202", "stdev": "50" }, { "name": "SpMax5_Bh.m.", "index": "20", "type": "numeric", "distinct": "521", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "TPSA.Tot.", "index": "21", "type": "numeric", "distinct": "556", "missing": "0", "min": "25", "max": "393", "mean": "96", "stdev": "33" }, { "name": "Eta_FL", "index": "22", "type": "numeric", "distinct": "776", "missing": "0", "min": "3", "max": "14", "mean": "7", "stdev": "2" }, { "name": "SpMax2_Bh.i.", "index": "23", "type": "numeric", "distinct": "275", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "SAdon", "index": "24", "type": "numeric", "distinct": "99", "missing": "0", "min": "0", "max": "335", "mean": "52", "stdev": "32" }, { "name": "ATS2m", "index": "25", "type": "numeric", "distinct": "557", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "Eta_betaP", "index": "26", "type": "numeric", "distinct": "54", "missing": "0", "min": "8", "max": "36", "mean": "20", "stdev": "5" }, { "name": "ATSC5m", "index": "27", "type": "numeric", "distinct": "867", "missing": "0", "min": "4", "max": "64", "mean": "25", "stdev": "10" }, { "name": "IC5", "index": "28", "type": "numeric", "distinct": "504", "missing": "0", "min": "3", "max": "6", "mean": "5", "stdev": "0" }, { "name": "Eig04_EA.bo.", "index": "29", "type": "numeric", "distinct": "552", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SM14_AEA.ri.", "index": "30", "type": "numeric", "distinct": "552", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "nN", "index": "31", "type": "numeric", "distinct": "13", "missing": "0", "min": "0", "max": "21", "mean": "5", "stdev": "2" }, { "name": "SpMax8_Bh.m.", "index": "32", "type": "numeric", "distinct": "494", "missing": "0", "min": "1", "max": "3", "mean": "3", "stdev": "0" }, { "name": "CATS2D_04_DL", "index": "33", "type": "numeric", "distinct": "14", "missing": "0", "min": "0", "max": "14", "mean": "4", "stdev": "3" }, { "name": "ATS1m", "index": "34", "type": "numeric", "distinct": "537", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "Eig08_EA.bo.", "index": "35", "type": "numeric", "distinct": "565", "missing": "0", "min": "-2", "max": "3", "mean": "2", "stdev": "1" }, { "name": "nBM", "index": "36", "type": "numeric", "distinct": "28", "missing": "0", "min": "7", "max": "35", "mean": "20", "stdev": "5" }, { "name": "Uc", "index": "37", "type": "numeric", "distinct": "28", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "Eig13_AEA.ri.", "index": "38", "type": "numeric", "distinct": "627", "missing": "0", "min": "-1", "max": "3", "mean": "1", "stdev": "1" }, { "name": "Eig13_EA.ri.", "index": "39", "type": "numeric", "distinct": "602", "missing": "0", "min": "-2", "max": "2", "mean": "0", "stdev": "1" }, { "name": "SpMax3_Bh.e.", "index": "40", "type": "numeric", "distinct": "400", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "SpMax3_Bh.v.", "index": "41", "type": "numeric", "distinct": "429", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "Chi1_EA.dm.", "index": "42", "type": "numeric", "distinct": "767", "missing": "0", "min": "0", "max": "79", "mean": "24", "stdev": "14" }, { "name": "Eig07_EA", "index": "43", "type": "numeric", "distinct": "530", "missing": "0", "min": "-1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "SM15_AEA.bo.", "index": "44", "type": "numeric", "distinct": "530", "missing": "0", "min": "-1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "Eig08_AEA.bo.", "index": "45", "type": "numeric", "distinct": "526", "missing": "0", "min": "0", "max": "4", "mean": "3", "stdev": "0" }, { "name": "Eig08_AEA.dm.", "index": "46", "type": "numeric", "distinct": "571", "missing": "0", "min": "-1", "max": "3", "mean": "2", "stdev": "0" }, { "name": "Eig07_AEA.ri.", "index": "47", "type": "numeric", "distinct": "590", "missing": "0", "min": "0", "max": "3", "mean": "3", "stdev": "0" }, { "name": "SpMax7_Bh.m.", "index": "48", "type": "numeric", "distinct": "500", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "X1sol", "index": "49", "type": "numeric", "distinct": "677", "missing": "0", "min": "6", "max": "26", "mean": "13", "stdev": "3" }, { "name": "Eig10_AEA.ed.", "index": "50", "type": "numeric", "distinct": "543", "missing": "0", "min": "1", "max": "5", "mean": "4", "stdev": "1" }, { "name": "Eig12_EA.bo.", "index": "51", "type": "numeric", "distinct": "574", "missing": "0", "min": "-3", "max": "3", "mean": "1", "stdev": "1" }, { "name": "GMTIV", "index": "52", "type": "numeric", "distinct": "856", "missing": "0", "min": "3094", "max": "227651", "mean": "32393", "stdev": "23065" }, { "name": "Eig09_AEA.ri.", "index": "53", "type": "numeric", "distinct": "573", "missing": "0", "min": "-1", "max": "3", "mean": "2", "stdev": "1" }, { "name": "Eig14_EA.bo.", "index": "54", "type": "numeric", "distinct": "607", "missing": "0", "min": "-3", "max": "2", "mean": "0", "stdev": "1" }, { "name": "NssNH", "index": "55", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "Eig09_EA.bo.", "index": "56", "type": "numeric", "distinct": "560", "missing": "0", "min": "-2", "max": "3", "mean": "2", "stdev": "1" }, { "name": "X4sol", "index": "57", "type": "numeric", "distinct": "749", "missing": "0", "min": "4", "max": "19", "mean": "9", "stdev": "2" }, { "name": "Eig09_EA.ri.", "index": "58", "type": "numeric", "distinct": "560", "missing": "0", "min": "-1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "Eig09_EA", "index": "59", "type": "numeric", "distinct": "505", "missing": "0", "min": "-1", "max": "2", "mean": "1", "stdev": "1" }, { "name": "SM03_AEA.dm.", "index": "60", "type": "numeric", "distinct": "505", "missing": "0", "min": "-1", "max": "2", "mean": "1", "stdev": "1" }, { "name": "ATSC5p", "index": "61", "type": "numeric", "distinct": "840", "missing": "0", "min": "1", "max": "24", "mean": "9", "stdev": "3" }, { "name": "Eig08_EA.ed.", "index": "62", "type": "numeric", "distinct": "663", "missing": "0", "min": "-3", "max": "8", "mean": "4", "stdev": "1" }, { "name": "SM03_AEA.ri.", "index": "63", "type": "numeric", "distinct": "663", "missing": "0", "min": "-3", "max": "8", "mean": "4", "stdev": "1" }, { "name": "Eig13_AEA.bo.", "index": "64", "type": "numeric", "distinct": "551", "missing": "0", "min": "-1", "max": "3", "mean": "2", "stdev": "1" }, { "name": "IC4", "index": "65", "type": "numeric", "distinct": "510", "missing": "0", "min": "3", "max": "6", "mean": "5", "stdev": "0" }, { "name": "Eig13_EA.bo.", "index": "66", "type": "numeric", "distinct": "590", "missing": "0", "min": "-3", "max": "2", "mean": "0", "stdev": "1" }, { "name": "Eig07_EA.ri.", "index": "67", "type": "numeric", "distinct": "576", "missing": "0", "min": "0", "max": "2", "mean": "2", "stdev": "0" }, { "name": "X2sol", "index": "68", "type": "numeric", "distinct": "739", "missing": "0", "min": "6", "max": "24", "mean": "12", "stdev": "3" }, { "name": "SpMax5_Bh.e.", "index": "69", "type": "numeric", "distinct": "494", "missing": "0", "min": "2", "max": "4", "mean": "3", "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 }