{ "data_id": "34832", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL5570", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL5570", "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: CHEMBL5570 (TID: 101021), and it has 81 rows and 61 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 16:24:34", "update_comment": null, "last_update": "2016-07-15 16:24:34", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3540160\/data_52230.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL5570", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL5570 (TID: 101021), and it has 81 rows and 61 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": 81, "NumberOfFeatures": 63, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 62, "NumberOfSymbolicFeatures": 1, "Quartile2KurtosisOfNumericAtts": 0.16380998653290346, "Dimensionality": 0.7777777777777778, "MeanNominalAttDistinctValues": null, "Quartile2MeansOfNumericAtts": 3.2550617283950616, "EquivalentNumberOfAtts": null, "MeanSkewnessOfNumericAtts": 0.2208433642473052, "Quartile2MutualInformation": null, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 1.1299885052771943, "Quartile2SkewnessOfNumericAtts": 0.3809515830411558, "MajorityClassSize": null, "MinAttributeEntropy": null, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.5109903238918632, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.677828601241284, "MinMeansOfNumericAtts": -0.3089506172839508, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxKurtosisOfNumericAtts": 5.942719839416937, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 0.6377418134257192, "MaxMeansOfNumericAtts": 36.58425925925926, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.4126984126984, "Quartile3MeansOfNumericAtts": 6.928429012345679, "MaxMutualInformation": null, "MinSkewnessOfNumericAtts": -1.1377196184168255, "PercentageOfSymbolicFeatures": 1.5873015873015872, "Quartile3MutualInformation": null, "MaxNominalAttDistinctValues": null, "MinStdDevOfNumericAtts": 0.0017699480357859997, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 0.8332863050073988, "MaxSkewnessOfNumericAtts": 2.1895948606796294, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": -0.7167147329402827, "Quartile3StdDevOfNumericAtts": 1.4778736207702738, "MaxStdDevOfNumericAtts": 4.582508343260201, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 0.37037037037037046, "StdvNominalAttDistinctValues": null, "MeanAttributeEntropy": null, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanKurtosisOfNumericAtts": 0.16000155381350592, "Quartile1SkewnessOfNumericAtts": -0.5650551608207852, "MeanMeansOfNumericAtts": 5.6625266825965745, "Quartile1StdDevOfNumericAtts": 0.09461304505151627, "AutoCorrelation": 0.2862625, "MeanMutualInformation": null, "Quartile2AttributeEntropy": null, "ClassEntropy": null, "MeanNoiseToSignalRatio": null }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "62", "type": "numeric", "distinct": "70", "missing": "0", "target": "1", "min": "5", "max": "9", "mean": "8", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "81", "missing": "0", "identifier": "1", "distr": [] }, { "name": "SpMin1_Bh.p.", "index": "1", "type": "numeric", "distinct": "35", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "SpMin2_Bh.m.", "index": "2", "type": "numeric", "distinct": "34", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "SpMin1_Bh.e.", "index": "3", "type": "numeric", "distinct": "33", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "CATS2D_03_LL", "index": "4", "type": "numeric", "distinct": "13", "missing": "0", "min": "5", "max": "18", "mean": "12", "stdev": "5" }, { "name": "NssCH2", "index": "5", "type": "numeric", "distinct": "13", "missing": "0", "min": "0", "max": "14", "mean": "7", "stdev": "3" }, { "name": "CATS2D_05_DA", "index": "6", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "SpMin1_Bh.m.", "index": "7", "type": "numeric", "distinct": "35", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "CATS2D_02_LL", "index": "8", "type": "numeric", "distinct": "14", "missing": "0", "min": "7", "max": "21", "mean": "16", "stdev": "4" }, { "name": "CATS2D_08_AL", "index": "9", "type": "numeric", "distinct": "15", "missing": "0", "min": "2", "max": "17", "mean": "10", "stdev": "4" }, { "name": "CATS2D_03_DL", "index": "10", "type": "numeric", "distinct": "7", "missing": "0", "min": "1", "max": "9", "mean": "4", "stdev": "2" }, { "name": "CATS2D_05_DD", "index": "11", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "C.034", "index": "12", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "JGI1", "index": "13", "type": "numeric", "distinct": "50", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SpDiam_AEA.ed.", "index": "14", "type": "numeric", "distinct": "31", "missing": "0", "min": "6", "max": "7", "mean": "7", "stdev": "0" }, { "name": "MATS3m", "index": "15", "type": "numeric", "distinct": "65", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SdssC", "index": "16", "type": "numeric", "distinct": "78", "missing": "0", "min": "-2", "max": "1", "mean": "0", "stdev": "1" }, { "name": "MATS2s", "index": "17", "type": "numeric", "distinct": "69", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "GATS2m", "index": "18", "type": "numeric", "distinct": "65", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "ATS8p", "index": "19", "type": "numeric", "distinct": "75", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "MATS3p", "index": "20", "type": "numeric", "distinct": "65", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "X5v", "index": "21", "type": "numeric", "distinct": "79", "missing": "0", "min": "2", "max": "5", "mean": "3", "stdev": "1" }, { "name": "SpMin1_Bh.i.", "index": "22", "type": "numeric", "distinct": "28", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "CATS2D_01_LL", "index": "23", "type": "numeric", "distinct": "13", "missing": "0", "min": "5", "max": "17", "mean": "12", "stdev": "3" }, { "name": "ATS8e", "index": "24", "type": "numeric", "distinct": "79", "missing": "0", "min": "5", "max": "5", "mean": "5", "stdev": "0" }, { "name": "ATS8i", "index": "25", "type": "numeric", "distinct": "74", "missing": "0", "min": "5", "max": "6", "mean": "5", "stdev": "0" }, { "name": "ATSC8v", "index": "26", "type": "numeric", "distinct": "81", "missing": "0", "min": "8", "max": "27", "mean": "18", "stdev": "4" }, { "name": "SssCH2", "index": "27", "type": "numeric", "distinct": "73", "missing": "0", "min": "0", "max": "15", "mean": "7", "stdev": "3" }, { "name": "ATSC8p", "index": "28", "type": "numeric", "distinct": "81", "missing": "0", "min": "6", "max": "18", "mean": "12", "stdev": "3" }, { "name": "MATS3e", "index": "29", "type": "numeric", "distinct": "72", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "NssNH", "index": "30", "type": "numeric", "distinct": "4", "missing": "0", "min": "1", "max": "4", "mean": "2", "stdev": "1" }, { "name": "SssNH", "index": "31", "type": "numeric", "distinct": "76", "missing": "0", "min": "3", "max": "12", "mean": "6", "stdev": "3" }, { "name": "ATSC6v", "index": "32", "type": "numeric", "distinct": "81", "missing": "0", "min": "7", "max": "27", "mean": "17", "stdev": "4" }, { "name": "SpMin1_Bh.v.", "index": "33", "type": "numeric", "distinct": "40", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "MATS6i", "index": "34", "type": "numeric", "distinct": "69", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "C.002", "index": "35", "type": "numeric", "distinct": "8", "missing": "0", "min": "0", "max": "8", "mean": "4", "stdev": "2" }, { "name": "CATS2D_02_DL", "index": "36", "type": "numeric", "distinct": "8", "missing": "0", "min": "2", "max": "14", "mean": "4", "stdev": "3" }, { "name": "CATS2D_04_DL", "index": "37", "type": "numeric", "distinct": "8", "missing": "0", "min": "2", "max": "10", "mean": "4", "stdev": "1" }, { "name": "StsC", "index": "38", "type": "numeric", "distinct": "21", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "SpMAD_AEA.dm.", "index": "39", "type": "numeric", "distinct": "56", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "SM13_EA.ed.", "index": "40", "type": "numeric", "distinct": "57", "missing": "0", "min": "31", "max": "35", "mean": "32", "stdev": "1" }, { "name": "SM14_EA.ed.", "index": "41", "type": "numeric", "distinct": "63", "missing": "0", "min": "33", "max": "37", "mean": "34", "stdev": "1" }, { "name": "C.043", "index": "42", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "N.074", "index": "43", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "nArCN", "index": "44", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "nCsp", "index": "45", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "nTB", "index": "46", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "NtN", "index": "47", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "NtsC", "index": "48", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "StN", "index": "49", "type": "numeric", "distinct": "24", "missing": "0", "min": "0", "max": "18", "mean": "3", "stdev": "5" }, { "name": "CATS2D_09_AL", "index": "50", "type": "numeric", "distinct": "15", "missing": "0", "min": "0", "max": "15", "mean": "8", "stdev": "4" }, { "name": "MATS3v", "index": "51", "type": "numeric", "distinct": "70", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "JGI8", "index": "52", "type": "numeric", "distinct": "9", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Eig01_AEA.ed.", "index": "53", "type": "numeric", "distinct": "16", "missing": "0", "min": "7", "max": "8", "mean": "7", "stdev": "0" }, { "name": "Eig01_EA", "index": "54", "type": "numeric", "distinct": "26", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "Eig01_EA.ed.", "index": "55", "type": "numeric", "distinct": "21", "missing": "0", "min": "10", "max": "14", "mean": "11", "stdev": "1" }, { "name": "SM09_AEA.bo.", "index": "56", "type": "numeric", "distinct": "26", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SM10_AEA.dm.", "index": "57", "type": "numeric", "distinct": "21", "missing": "0", "min": "10", "max": "14", "mean": "11", "stdev": "1" }, { "name": "SM15_EA.ed.", "index": "58", "type": "numeric", "distinct": "59", "missing": "0", "min": "35", "max": "40", "mean": "37", "stdev": "1" }, { "name": "SpDiam_EA", "index": "59", "type": "numeric", "distinct": "26", "missing": "0", "min": "5", "max": "6", "mean": "5", "stdev": "0" }, { "name": "SpMax_AEA.ed.", "index": "60", "type": "numeric", "distinct": "16", "missing": "0", "min": "7", "max": "8", "mean": "7", "stdev": "0" }, { "name": "SpMax_EA", "index": "61", "type": "numeric", "distinct": "26", "missing": "0", "min": "3", "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 }