{ "data_id": "34581", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4980", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4980", "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: CHEMBL4980 (TID: 12167), and it has 1045 rows and 22 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). 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 15:45:01", "update_comment": null, "last_update": "2016-07-15 15:45:01", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3533113\/data_41568.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 1, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4980", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL4980 (TID: 12167), and it has 1045 rows and 22 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). Feature selection was also applied. " ], "weight": 5 }, "qualities": { "NumberOfInstances": 1045, "NumberOfFeatures": 24, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 23, "NumberOfSymbolicFeatures": 1, "Quartile2KurtosisOfNumericAtts": 2.414502799303632, "Dimensionality": 0.022966507177033493, "MeanNominalAttDistinctValues": null, "Quartile2MeansOfNumericAtts": 7.134984688995215, "EquivalentNumberOfAtts": null, "MeanSkewnessOfNumericAtts": 2.424090016379917, "Quartile2MutualInformation": null, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 10.261598074564828, "Quartile2SkewnessOfNumericAtts": 1.22015094310015, "MajorityClassSize": null, "MinAttributeEntropy": null, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 3.5298095740257835, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -0.7159629121239397, "MinMeansOfNumericAtts": 0.07401244019138756, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxKurtosisOfNumericAtts": 88.02058524234161, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 37.845294873667854, "MaxMeansOfNumericAtts": 320.2339043062201, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 95.83333333333334, "Quartile3MeansOfNumericAtts": 31.44641148325359, "MaxMutualInformation": null, "MinSkewnessOfNumericAtts": -0.5562141712260649, "PercentageOfSymbolicFeatures": 4.166666666666666, "Quartile3MutualInformation": null, "MaxNominalAttDistinctValues": null, "MinStdDevOfNumericAtts": 0.010680674081789425, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 4.635878443268009, "MaxSkewnessOfNumericAtts": 8.193171097369364, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": 0.3708496669614316, "Quartile3StdDevOfNumericAtts": 9.094123063834706, "MaxStdDevOfNumericAtts": 131.94259910757728, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 1.0095693779904304, "StdvNominalAttDistinctValues": null, "MeanAttributeEntropy": null, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanKurtosisOfNumericAtts": 20.772124032950856, "Quartile1SkewnessOfNumericAtts": 0.007446854017664882, "MeanMeansOfNumericAtts": 28.139648179737883, "Quartile1StdDevOfNumericAtts": 0.8893229127040242, "AutoCorrelation": -0.18120593869731874, "MeanMutualInformation": null, "Quartile2AttributeEntropy": null, "ClassEntropy": null, "MeanNoiseToSignalRatio": null }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "23", "type": "numeric", "distinct": "539", "missing": "0", "target": "1", "min": "3", "max": "11", "mean": "6", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "1045", "missing": "0", "identifier": "1", "distr": [] }, { "name": "Me", "index": "1", "type": "numeric", "distinct": "62", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "RBF", "index": "2", "type": "numeric", "distinct": "145", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Mp", "index": "3", "type": "numeric", "distinct": "123", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Mv", "index": "4", "type": "numeric", "distinct": "127", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "H.", "index": "5", "type": "numeric", "distinct": "142", "missing": "0", "min": "37", "max": "68", "mean": "49", "stdev": "4" }, { "name": "AMW", "index": "6", "type": "numeric", "distinct": "521", "missing": "0", "min": "5", "max": "11", "mean": "7", "stdev": "1" }, { "name": "nN", "index": "7", "type": "numeric", "distinct": "13", "missing": "0", "min": "0", "max": "23", "mean": "3", "stdev": "2" }, { "name": "nHet", "index": "8", "type": "numeric", "distinct": "19", "missing": "0", "min": "1", "max": "51", "mean": "5", "stdev": "4" }, { "name": "C.", "index": "9", "type": "numeric", "distinct": "132", "missing": "0", "min": "27", "max": "50", "mean": "40", "stdev": "4" }, { "name": "N.", "index": "10", "type": "numeric", "distinct": "100", "missing": "0", "min": "0", "max": "17", "mean": "6", "stdev": "3" }, { "name": "nBM", "index": "11", "type": "numeric", "distinct": "25", "missing": "0", "min": "0", "max": "32", "mean": "11", "stdev": "5" }, { "name": "MW", "index": "12", "type": "numeric", "distinct": "625", "missing": "0", "min": "146", "max": "1713", "mean": "320", "stdev": "132" }, { "name": "RBN", "index": "13", "type": "numeric", "distinct": "18", "missing": "0", "min": "0", "max": "50", "mean": "4", "stdev": "3" }, { "name": "nAB", "index": "14", "type": "numeric", "distinct": "12", "missing": "0", "min": "0", "max": "24", "mean": "10", "stdev": "5" }, { "name": "nCsp2", "index": "15", "type": "numeric", "distinct": "23", "missing": "0", "min": "0", "max": "30", "mean": "10", "stdev": "4" }, { "name": "nSK", "index": "16", "type": "numeric", "distinct": "44", "missing": "0", "min": "10", "max": "116", "mean": "23", "stdev": "9" }, { "name": "nBO", "index": "17", "type": "numeric", "distinct": "46", "missing": "0", "min": "9", "max": "118", "mean": "25", "stdev": "10" }, { "name": "SCBO", "index": "18", "type": "numeric", "distinct": "83", "missing": "0", "min": "10", "max": "145", "mean": "31", "stdev": "12" }, { "name": "nHM", "index": "19", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "4", "mean": "0", "stdev": "1" }, { "name": "nDB", "index": "20", "type": "numeric", "distinct": "12", "missing": "0", "min": "0", "max": "21", "mean": "1", "stdev": "2" }, { "name": "nBT", "index": "21", "type": "numeric", "distinct": "77", "missing": "0", "min": "23", "max": "218", "mean": "48", "stdev": "18" }, { "name": "Se", "index": "22", "type": "numeric", "distinct": "614", "missing": "0", "min": "22", "max": "219", "mean": "45", "stdev": "18" } ], "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 }