{ "data_id": "26730", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4101", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4101", "version": 8, "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: CHEMBL4101 (TID: 11969), and it has 1246 rows and 43 features (not including molecule IDs and class feature: molecule_id and pXC50). The features represent Basic Molecular Descriptors which were generated from SMILES strings. Missing value imputation was applied to this dataset (By choosing the Median).", "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": "2016-07-14 19:55:49", "update_comment": null, "last_update": "2016-07-14 19:55:49", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3311327\/data_35365.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 1, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4101", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL4101 (TID: 11969), and it has 1246 rows and 43 features (not including molecule IDs and class feature: molecule_id and pXC50). The features represent Basic Molecular Descriptors which were generated from SMILES strings. Missing value imputation was applied to this dataset (By choosing the Median). " ], "weight": 5 }, "qualities": { "NumberOfInstances": 1246, "NumberOfFeatures": 45, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 44, "NumberOfSymbolicFeatures": 1, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 0.5568741974317817, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": 44.445379315155265, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 22.474065008025683, "Quartile1SkewnessOfNumericAtts": 1.1566117881265607, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.3978022437683597, "AutoCorrelation": 0.17903453815261128, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "ClassEntropy": null, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": 9.591676674868234, "Dimensionality": 0.036115569823434994, "MeanSkewnessOfNumericAtts": 3.355455584002193, "Quartile2MeansOfNumericAtts": 4.934189406099514, "EquivalentNumberOfAtts": null, "MeanStdDevOfNumericAtts": 8.459030892634898, "Quartile2MutualInformation": null, "MajorityClassPercentage": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": 2.4666767758134887, "MajorityClassSize": null, "MinKurtosisOfNumericAtts": -0.23493530045838762, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 3.2389048322627154, "MaxAttributeEntropy": null, "MaxKurtosisOfNumericAtts": 1246.0000000000016, "MinMeansOfNumericAtts": 0, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 389.18293739967896, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 23.21052603282719, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 97.77777777777777, "Quartile3MeansOfNumericAtts": 29.94562600321028, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -0.697957346964221, "PercentageOfSymbolicFeatures": 2.2222222222222223, "Quartile3MutualInformation": null, "MaxSkewnessOfNumericAtts": 35.29872518944528, "MinStdDevOfNumericAtts": 0, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 3.8484078221051585, "MaxStdDevOfNumericAtts": 143.14753469535108, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": 2.212004194842816, "Quartile3StdDevOfNumericAtts": 9.334831358955212 }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "44", "type": "numeric", "distinct": "129", "missing": "0", "target": "1", "min": "4", "max": "9", "mean": "6", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "1246", "missing": "0", "identifier": "1", "distr": [] }, { "name": "AMW", "index": "1", "type": "numeric", "distinct": "876", "missing": "0", "min": "6", "max": "19", "mean": "8", "stdev": "1" }, { "name": "C.", "index": "2", "type": "numeric", "distinct": "174", "missing": "0", "min": "28", "max": "56", "mean": "43", "stdev": "5" }, { "name": "H.", "index": "3", "type": "numeric", "distinct": "207", "missing": "0", "min": "20", "max": "57", "mean": "40", "stdev": "6" }, { "name": "Me", "index": "4", "type": "numeric", "distinct": "85", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Mi", "index": "5", "type": "numeric", "distinct": "81", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Mp", "index": "6", "type": "numeric", "distinct": "186", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Mv", "index": "7", "type": "numeric", "distinct": "191", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "MW", "index": "8", "type": "numeric", "distinct": "1054", "missing": "0", "min": "151", "max": "1678", "mean": "389", "stdev": "143" }, { "name": "N.", "index": "9", "type": "numeric", "distinct": "166", "missing": "0", "min": "0", "max": "33", "mean": "10", "stdev": "4" }, { "name": "nAB", "index": "10", "type": "numeric", "distinct": "26", "missing": "0", "min": "0", "max": "34", "mean": "18", "stdev": "5" }, { "name": "nAT", "index": "11", "type": "numeric", "distinct": "96", "missing": "0", "min": "13", "max": "241", "mean": "47", "stdev": "21" }, { "name": "nB", "index": "12", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "nBM", "index": "13", "type": "numeric", "distinct": "31", "missing": "0", "min": "4", "max": "38", "mean": "19", "stdev": "5" }, { "name": "nBO", "index": "14", "type": "numeric", "distinct": "64", "missing": "0", "min": "11", "max": "122", "mean": "31", "stdev": "11" }, { "name": "nBR", "index": "15", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "nBT", "index": "16", "type": "numeric", "distinct": "101", "missing": "0", "min": "14", "max": "242", "mean": "50", "stdev": "21" }, { "name": "nC", "index": "17", "type": "numeric", "distinct": "44", "missing": "0", "min": "4", "max": "69", "mean": "20", "stdev": "7" }, { "name": "nCL", "index": "18", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "0" }, { "name": "nCsp", "index": "19", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "0" }, { "name": "nCsp2", "index": "20", "type": "numeric", "distinct": "27", "missing": "0", "min": "4", "max": "32", "mean": "16", "stdev": "5" }, { "name": "nCsp3", "index": "21", "type": "numeric", "distinct": "32", "missing": "0", "min": "0", "max": "44", "mean": "4", "stdev": "5" }, { "name": "nDB", "index": "22", "type": "numeric", "distinct": "15", "missing": "0", "min": "0", "max": "17", "mean": "1", "stdev": "2" }, { "name": "nF", "index": "23", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "6", "mean": "0", "stdev": "1" }, { "name": "nH", "index": "24", "type": "numeric", "distinct": "60", "missing": "0", "min": "3", "max": "126", "mean": "20", "stdev": "11" }, { "name": "nHet", "index": "25", "type": "numeric", "distinct": "30", "missing": "0", "min": "2", "max": "49", "mean": "8", "stdev": "4" }, { "name": "nHM", "index": "26", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "nI", "index": "27", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "nN", "index": "28", "type": "numeric", "distinct": "23", "missing": "0", "min": "0", "max": "34", "mean": "5", "stdev": "3" }, { "name": "nO", "index": "29", "type": "numeric", "distinct": "15", "missing": "0", "min": "0", "max": "14", "mean": "2", "stdev": "2" }, { "name": "nP", "index": "30", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "nS", "index": "31", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "0" }, { "name": "nSK", "index": "32", "type": "numeric", "distinct": "59", "missing": "0", "min": "10", "max": "118", "mean": "28", "stdev": "10" }, { "name": "nTB", "index": "33", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "nX", "index": "34", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "6", "mean": "1", "stdev": "1" }, { "name": "O.", "index": "35", "type": "numeric", "distinct": "115", "missing": "0", "min": "0", "max": "18", "mean": "4", "stdev": "3" }, { "name": "RBF", "index": "36", "type": "numeric", "distinct": "167", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "RBN", "index": "37", "type": "numeric", "distinct": "30", "missing": "0", "min": "0", "max": "68", "mean": "5", "stdev": "6" }, { "name": "SCBO", "index": "38", "type": "numeric", "distinct": "125", "missing": "0", "min": "16", "max": "150", "mean": "41", "stdev": "13" }, { "name": "Se", "index": "39", "type": "numeric", "distinct": "1036", "missing": "0", "min": "14", "max": "243", "mean": "48", "stdev": "21" }, { "name": "Si", "index": "40", "type": "numeric", "distinct": "1066", "missing": "0", "min": "15", "max": "279", "mean": "54", "stdev": "25" }, { "name": "Sp", "index": "41", "type": "numeric", "distinct": "1005", "missing": "0", "min": "11", "max": "145", "mean": "32", "stdev": "13" }, { "name": "Sv", "index": "42", "type": "numeric", "distinct": "1072", "missing": "0", "min": "10", "max": "137", "mean": "31", "stdev": "12" }, { "name": "X.", "index": "43", "type": "numeric", "distinct": "85", "missing": "0", "min": "0", "max": "18", "mean": "2", "stdev": "3" } ], "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 }