{ "data_id": "35285", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3231", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3231", "version": 12, "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: CHEMBL3231 (TID: 10811), and it has 1480 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 17:38:00", "update_comment": null, "last_update": "2016-07-15 17:38:00", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3553590\/data_53651.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3231", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL3231 (TID: 10811), and it has 1480 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": 1480, "NumberOfFeatures": 72, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 71, "NumberOfSymbolicFeatures": 1, "ClassEntropy": null, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "Dimensionality": 0.04864864864864865, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": 4.788256565959442, "EquivalentNumberOfAtts": null, "MeanSkewnessOfNumericAtts": 2.0685531670052333, "Quartile2MeansOfNumericAtts": 3.260752027027027, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 2.6678051956778406, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": 0.9606541407496744, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -0.6715117219616844, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.8956609794624648, "MaxKurtosisOfNumericAtts": 257.8509050563287, "MinMeansOfNumericAtts": -0.0064283783783788484, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 58.59061891891891, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 85.6019487204728, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.61111111111111, "Quartile3MeansOfNumericAtts": 5.093918918918921, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -11.348497301433325, "PercentageOfSymbolicFeatures": 1.3888888888888888, "Quartile3MutualInformation": null, "MaxSkewnessOfNumericAtts": 11.727278453154106, "MinStdDevOfNumericAtts": 0.04888632750401909, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 4.966583448469797, "MaxStdDevOfNumericAtts": 39.394111998265615, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": 1.2170247632743303, "Quartile3StdDevOfNumericAtts": 2.9892176291817005, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 1.4859047297297296, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": 46.302352721175886, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 6.126930338789494, "Quartile1SkewnessOfNumericAtts": -0.6152171873816669, "AutoCorrelation": 0.03421906693711945, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.2281053266562927 }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "71", "type": "numeric", "distinct": "276", "missing": "0", "target": "1", "min": "4", "max": "9", "mean": "6", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "1480", "missing": "0", "identifier": "1", "distr": [] }, { "name": "C.027", "index": "1", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "N.067", "index": "2", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "9", "mean": "0", "stdev": "0" }, { "name": "C.008", "index": "3", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "10", "mean": "0", "stdev": "1" }, { "name": "SsssCH", "index": "4", "type": "numeric", "distinct": "417", "missing": "0", "min": "-12", "max": "2", "mean": "0", "stdev": "0" }, { "name": "nN.C.N.", "index": "5", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "H.052", "index": "6", "type": "numeric", "distinct": "17", "missing": "0", "min": "0", "max": "36", "mean": "2", "stdev": "3" }, { "name": "P_VSA_MR_5", "index": "7", "type": "numeric", "distinct": "1072", "missing": "0", "min": "0", "max": "984", "mean": "59", "stdev": "39" }, { "name": "NsssCH", "index": "8", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "10", "mean": "0", "stdev": "1" }, { "name": "Cl.090", "index": "9", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "H.050", "index": "10", "type": "numeric", "distinct": "12", "missing": "0", "min": "0", "max": "43", "mean": "3", "stdev": "2" }, { "name": "nHDon", "index": "11", "type": "numeric", "distinct": "12", "missing": "0", "min": "0", "max": "43", "mean": "3", "stdev": "2" }, { "name": "ATSC4v", "index": "12", "type": "numeric", "distinct": "1365", "missing": "0", "min": "1", "max": "107", "mean": "12", "stdev": "5" }, { "name": "nRNHR", "index": "13", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "8", "mean": "0", "stdev": "0" }, { "name": "SpMin4_Bh.s.", "index": "14", "type": "numeric", "distinct": "647", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "CIC0", "index": "15", "type": "numeric", "distinct": "840", "missing": "0", "min": "2", "max": "7", "mean": "4", "stdev": "0" }, { "name": "SpMin2_Bh.i.", "index": "16", "type": "numeric", "distinct": "364", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "ATSC3v", "index": "17", "type": "numeric", "distinct": "1338", "missing": "0", "min": "1", "max": "97", "mean": "11", "stdev": "5" }, { "name": "CATS2D_02_DL", "index": "18", "type": "numeric", "distinct": "12", "missing": "0", "min": "0", "max": "21", "mean": "3", "stdev": "2" }, { "name": "CATS2D_08_LL", "index": "19", "type": "numeric", "distinct": "25", "missing": "0", "min": "0", "max": "40", "mean": "5", "stdev": "4" }, { "name": "SpMin3_Bh.v.", "index": "20", "type": "numeric", "distinct": "474", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "SpMin2_Bh.e.", "index": "21", "type": "numeric", "distinct": "354", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "SpMax2_Bh.e.", "index": "22", "type": "numeric", "distinct": "353", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "ATSC2v", "index": "23", "type": "numeric", "distinct": "1276", "missing": "0", "min": "1", "max": "72", "mean": "8", "stdev": "3" }, { "name": "ATSC5v", "index": "24", "type": "numeric", "distinct": "1371", "missing": "0", "min": "0", "max": "115", "mean": "11", "stdev": "5" }, { "name": "H.049", "index": "25", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "nH", "index": "26", "type": "numeric", "distinct": "43", "missing": "0", "min": "3", "max": "168", "mean": "19", "stdev": "8" }, { "name": "ATSC1m", "index": "27", "type": "numeric", "distinct": "1245", "missing": "0", "min": "0", "max": "84", "mean": "8", "stdev": "4" }, { "name": "SpMax2_Bh.i.", "index": "28", "type": "numeric", "distinct": "330", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "SpMin3_Bh.p.", "index": "29", "type": "numeric", "distinct": "444", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "ATSC1v", "index": "30", "type": "numeric", "distinct": "1176", "missing": "0", "min": "0", "max": "40", "mean": "5", "stdev": "2" }, { "name": "SpMax4_Bh.p.", "index": "31", "type": "numeric", "distinct": "688", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SM04_EA.dm.", "index": "32", "type": "numeric", "distinct": "502", "missing": "0", "min": "0", "max": "7", "mean": "2", "stdev": "2" }, { "name": "SM06_EA.dm.", "index": "33", "type": "numeric", "distinct": "462", "missing": "0", "min": "0", "max": "11", "mean": "3", "stdev": "2" }, { "name": "SpMax2_Bh.p.", "index": "34", "type": "numeric", "distinct": "403", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "SM08_EA.dm.", "index": "35", "type": "numeric", "distinct": "405", "missing": "0", "min": "0", "max": "14", "mean": "3", "stdev": "3" }, { "name": "SpMin3_Bh.m.", "index": "36", "type": "numeric", "distinct": "502", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "SpMax2_Bh.v.", "index": "37", "type": "numeric", "distinct": "389", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "SpMin4_Bh.e.", "index": "38", "type": "numeric", "distinct": "634", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "ATS3i", "index": "39", "type": "numeric", "distinct": "821", "missing": "0", "min": "3", "max": "7", "mean": "5", "stdev": "0" }, { "name": "SpDiam_EA.dm.", "index": "40", "type": "numeric", "distinct": "139", "missing": "0", "min": "0", "max": "9", "mean": "3", "stdev": "2" }, { "name": "NRS", "index": "41", "type": "numeric", "distinct": "6", "missing": "0", "min": "1", "max": "6", "mean": "3", "stdev": "1" }, { "name": "SpMax4_Bh.v.", "index": "42", "type": "numeric", "distinct": "706", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SpMAD_AEA.dm.", "index": "43", "type": "numeric", "distinct": "242", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "SpMin6_Bh.s.", "index": "44", "type": "numeric", "distinct": "584", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "SpMin6_Bh.m.", "index": "45", "type": "numeric", "distinct": "591", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "ATSC6v", "index": "46", "type": "numeric", "distinct": "1371", "missing": "0", "min": "0", "max": "121", "mean": "10", "stdev": "6" }, { "name": "X1Per", "index": "47", "type": "numeric", "distinct": "1268", "missing": "0", "min": "2", "max": "44", "mean": "7", "stdev": "2" }, { "name": "RBN", "index": "48", "type": "numeric", "distinct": "18", "missing": "0", "min": "0", "max": "78", "mean": "4", "stdev": "3" }, { "name": "X1MulPer", "index": "49", "type": "numeric", "distinct": "1277", "missing": "0", "min": "2", "max": "53", "mean": "8", "stdev": "2" }, { "name": "SpMin3_Bh.s.", "index": "50", "type": "numeric", "distinct": "558", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SM10_EA.dm.", "index": "51", "type": "numeric", "distinct": "331", "missing": "0", "min": "0", "max": "18", "mean": "4", "stdev": "4" }, { "name": "SpMin2_Bh.v.", "index": "52", "type": "numeric", "distinct": "293", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "ATS2i", "index": "53", "type": "numeric", "distinct": "805", "missing": "0", "min": "3", "max": "7", "mean": "5", "stdev": "0" }, { "name": "SpMin5_Bh.v.", "index": "54", "type": "numeric", "distinct": "588", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "ON1V", "index": "55", "type": "numeric", "distinct": "1059", "missing": "0", "min": "1", "max": "20", "mean": "3", "stdev": "1" }, { "name": "ATSC8v", "index": "56", "type": "numeric", "distinct": "1357", "missing": "0", "min": "0", "max": "129", "mean": "10", "stdev": "6" }, { "name": "X1Kup", "index": "57", "type": "numeric", "distinct": "1275", "missing": "0", "min": "3", "max": "54", "mean": "8", "stdev": "2" }, { "name": "ATS1e", "index": "58", "type": "numeric", "distinct": "735", "missing": "0", "min": "3", "max": "6", "mean": "4", "stdev": "0" }, { "name": "Si", "index": "59", "type": "numeric", "distinct": "1186", "missing": "0", "min": "15", "max": "377", "mean": "52", "stdev": "16" }, { "name": "SM12_EA.dm.", "index": "60", "type": "numeric", "distinct": "308", "missing": "0", "min": "0", "max": "21", "mean": "5", "stdev": "5" }, { "name": "SM14_EA.dm.", "index": "61", "type": "numeric", "distinct": "285", "missing": "0", "min": "0", "max": "25", "mean": "5", "stdev": "6" }, { "name": "ATS1i", "index": "62", "type": "numeric", "distinct": "746", "missing": "0", "min": "3", "max": "6", "mean": "4", "stdev": "0" }, { "name": "Hy", "index": "63", "type": "numeric", "distinct": "559", "missing": "0", "min": "-1", "max": "32", "mean": "1", "stdev": "1" }, { "name": "nBT", "index": "64", "type": "numeric", "distinct": "81", "missing": "0", "min": "14", "max": "336", "mean": "49", "stdev": "15" }, { "name": "ATS4i", "index": "65", "type": "numeric", "distinct": "870", "missing": "0", "min": "3", "max": "7", "mean": "5", "stdev": "0" }, { "name": "SpMin8_Bh.i.", "index": "66", "type": "numeric", "distinct": "600", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "CATS2D_07_DA", "index": "67", "type": "numeric", "distinct": "8", "missing": "0", "min": "0", "max": "10", "mean": "1", "stdev": "1" }, { "name": "SpMin4_Bh.m.", "index": "68", "type": "numeric", "distinct": "568", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "ATSC4m", "index": "69", "type": "numeric", "distinct": "1403", "missing": "0", "min": "4", "max": "245", "mean": "26", "stdev": "13" }, { "name": "ATS3e", "index": "70", "type": "numeric", "distinct": "807", "missing": "0", "min": "3", "max": "7", "mean": "5", "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 }