{ "data_id": "40365", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL2014", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL2014", "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: CHEMBL2014 (TID: 138), and it has 1426 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": "2016-07-16 11:12:20", "update_comment": null, "last_update": "2016-07-16 11:12:20", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3694148\/data_34180.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 1, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL2014", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL2014 (TID: 138), and it has 1426 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": 1426, "NumberOfFeatures": 45, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 44, "NumberOfSymbolicFeatures": 1, "ClassEntropy": null, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "Dimensionality": 0.03155680224403927, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": 10.965198030555154, "EquivalentNumberOfAtts": null, "MeanSkewnessOfNumericAtts": 3.2996541717950416, "Quartile2MeansOfNumericAtts": 6.171736676016829, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 15.486702978021551, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": 3.156121371247441, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -0.6737665896865961, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 3.9363621552128634, "MaxKurtosisOfNumericAtts": 710.4943790635591, "MinMeansOfNumericAtts": 0, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 502.8551963534362, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 13.485246600714996, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 97.77777777777777, "Quartile3MeansOfNumericAtts": 38.294530154277744, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -0.5316241488361495, "PercentageOfSymbolicFeatures": 2.2222222222222223, "Quartile3MutualInformation": null, "MaxSkewnessOfNumericAtts": 26.673917864575163, "MinStdDevOfNumericAtts": 0, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 3.653797509881468, "MaxStdDevOfNumericAtts": 285.58866091230004, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": 0.6000187056273119, "Quartile3StdDevOfNumericAtts": 17.79023281795434, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 0.6256826788218793, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": 29.660768035588983, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 29.09371144651281, "Quartile1SkewnessOfNumericAtts": 0.9554640806662116, "AutoCorrelation": -0.027202807017544108, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.2014759919018592 }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "44", "type": "numeric", "distinct": "750", "missing": "0", "target": "1", "min": "4", "max": "11", "mean": "7", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "1426", "missing": "0", "identifier": "1", "distr": [] }, { "name": "AMW", "index": "1", "type": "numeric", "distinct": "786", "missing": "0", "min": "5", "max": "11", "mean": "7", "stdev": "1" }, { "name": "C.", "index": "2", "type": "numeric", "distinct": "158", "missing": "0", "min": "29", "max": "52", "mean": "41", "stdev": "4" }, { "name": "H.", "index": "3", "type": "numeric", "distinct": "177", "missing": "0", "min": "37", "max": "61", "mean": "49", "stdev": "4" }, { "name": "Me", "index": "4", "type": "numeric", "distinct": "63", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Mi", "index": "5", "type": "numeric", "distinct": "58", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Mp", "index": "6", "type": "numeric", "distinct": "136", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Mv", "index": "7", "type": "numeric", "distinct": "137", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "MW", "index": "8", "type": "numeric", "distinct": "959", "missing": "0", "min": "255", "max": "2244", "mean": "503", "stdev": "286" }, { "name": "N.", "index": "9", "type": "numeric", "distinct": "103", "missing": "0", "min": "1", "max": "13", "mean": "5", "stdev": "2" }, { "name": "nAB", "index": "10", "type": "numeric", "distinct": "17", "missing": "0", "min": "0", "max": "46", "mean": "14", "stdev": "6" }, { "name": "nAT", "index": "11", "type": "numeric", "distinct": "113", "missing": "0", "min": "33", "max": "320", "mean": "71", "stdev": "41" }, { "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": "35", "missing": "0", "min": "1", "max": "52", "mean": "16", "stdev": "7" }, { "name": "nBO", "index": "14", "type": "numeric", "distinct": "68", "missing": "0", "min": "20", "max": "158", "mean": "39", "stdev": "20" }, { "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": "112", "missing": "0", "min": "35", "max": "321", "mean": "75", "stdev": "40" }, { "name": "nC", "index": "17", "type": "numeric", "distinct": "58", "missing": "0", "min": "12", "max": "100", "mean": "28", "stdev": "12" }, { "name": "nCL", "index": "18", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "nCsp", "index": "19", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "nCsp2", "index": "20", "type": "numeric", "distinct": "33", "missing": "0", "min": "1", "max": "52", "mean": "15", "stdev": "7" }, { "name": "nCsp3", "index": "21", "type": "numeric", "distinct": "43", "missing": "0", "min": "1", "max": "61", "mean": "13", "stdev": "8" }, { "name": "nDB", "index": "22", "type": "numeric", "distinct": "18", "missing": "0", "min": "0", "max": "24", "mean": "2", "stdev": "4" }, { "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": "78", "missing": "0", "min": "15", "max": "163", "mean": "36", "stdev": "21" }, { "name": "nHet", "index": "25", "type": "numeric", "distinct": "35", "missing": "0", "min": "2", "max": "60", "mean": "8", "stdev": "9" }, { "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": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "nN", "index": "28", "type": "numeric", "distinct": "22", "missing": "0", "min": "1", "max": "35", "mean": "4", "stdev": "5" }, { "name": "nO", "index": "29", "type": "numeric", "distinct": "22", "missing": "0", "min": "0", "max": "28", "mean": "2", "stdev": "4" }, { "name": "nP", "index": "30", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "nS", "index": "31", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "nSK", "index": "32", "type": "numeric", "distinct": "65", "missing": "0", "min": "18", "max": "157", "mean": "36", "stdev": "20" }, { "name": "nTB", "index": "33", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "nX", "index": "34", "type": "numeric", "distinct": "8", "missing": "0", "min": "0", "max": "7", "mean": "1", "stdev": "1" }, { "name": "O.", "index": "35", "type": "numeric", "distinct": "81", "missing": "0", "min": "0", "max": "10", "mean": "3", "stdev": "2" }, { "name": "RBF", "index": "36", "type": "numeric", "distinct": "176", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "RBN", "index": "37", "type": "numeric", "distinct": "52", "missing": "0", "min": "2", "max": "78", "mean": "8", "stdev": "11" }, { "name": "SCBO", "index": "38", "type": "numeric", "distinct": "113", "missing": "0", "min": "25", "max": "195", "mean": "48", "stdev": "24" }, { "name": "Se", "index": "39", "type": "numeric", "distinct": "934", "missing": "0", "min": "33", "max": "325", "mean": "71", "stdev": "42" }, { "name": "Si", "index": "40", "type": "numeric", "distinct": "959", "missing": "0", "min": "38", "max": "369", "mean": "81", "stdev": "47" }, { "name": "Sp", "index": "41", "type": "numeric", "distinct": "907", "missing": "0", "min": "22", "max": "193", "mean": "46", "stdev": "24" }, { "name": "Sv", "index": "42", "type": "numeric", "distinct": "956", "missing": "0", "min": "21", "max": "185", "mean": "43", "stdev": "23" }, { "name": "X.", "index": "43", "type": "numeric", "distinct": "79", "missing": "0", "min": "0", "max": "15", "mean": "2", "stdev": "2" } ], "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 }