{ "data_id": "33106", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL214", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL214", "version": 11, "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: CHEMBL214 (TID: 51), and it has 3356 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": "2016-07-15 11:55:44", "update_comment": null, "last_update": "2016-07-15 11:55:44", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3497100\/data_34431.arff", "kaggle_url": null, "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 1, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL214", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL214 (TID: 51), and it has 3356 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": 3356, "NumberOfFeatures": 45, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 44, "NumberOfSymbolicFeatures": 1, "MeanKurtosisOfNumericAtts": 12.153484625005147, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 23.236975132733775, "Quartile1SkewnessOfNumericAtts": 0.14790327443175452, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.26143123157704773, "AutoCorrelation": -0.150700447093892, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "ClassEntropy": null, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": 2.7754735944316122, "Dimensionality": 0.013408820023837902, "MeanSkewnessOfNumericAtts": 1.512825455856656, "Quartile2MeansOfNumericAtts": 5.6673569725864095, "EquivalentNumberOfAtts": null, "MeanStdDevOfNumericAtts": 5.076952193117312, "Quartile2MutualInformation": null, "MajorityClassPercentage": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": 0.4800857320264701, "MajorityClassSize": null, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -0.5563218342813796, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 1.9869020530425747, "MaxKurtosisOfNumericAtts": 182.06028482983422, "MinMeansOfNumericAtts": 0, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 391.00428784266984, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 3.5891486925077567, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 97.77777777777777, "Quartile3MeansOfNumericAtts": 30.431987485101313, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -0.2561604823820793, "PercentageOfSymbolicFeatures": 2.2222222222222223, "Quartile3MutualInformation": null, "MaxSkewnessOfNumericAtts": 12.763911494340443, "MinStdDevOfNumericAtts": 0, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 1.3989614011995672, "MaxStdDevOfNumericAtts": 84.40893533195536, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": 1.3117006275536387, "Quartile3StdDevOfNumericAtts": 5.709436507970894, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 0.4950834326579254, "StdvNominalAttDistinctValues": null }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "44", "type": "numeric", "distinct": "1380", "missing": "0", "target": "1", "min": "4", "max": "11", "mean": "7", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "3356", "missing": "0", "identifier": "1", "distr": [] }, { "name": "AMW", "index": "1", "type": "numeric", "distinct": "1285", "missing": "0", "min": "6", "max": "12", "mean": "7", "stdev": "1" }, { "name": "C.", "index": "2", "type": "numeric", "distinct": "155", "missing": "0", "min": "27", "max": "57", "mean": "41", "stdev": "3" }, { "name": "H.", "index": "3", "type": "numeric", "distinct": "199", "missing": "0", "min": "19", "max": "66", "mean": "48", "stdev": "4" }, { "name": "Me", "index": "4", "type": "numeric", "distinct": "82", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Mi", "index": "5", "type": "numeric", "distinct": "64", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Mp", "index": "6", "type": "numeric", "distinct": "140", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Mv", "index": "7", "type": "numeric", "distinct": "159", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "MW", "index": "8", "type": "numeric", "distinct": "1901", "missing": "0", "min": "161", "max": "1106", "mean": "391", "stdev": "84" }, { "name": "N.", "index": "9", "type": "numeric", "distinct": "126", "missing": "0", "min": "0", "max": "20", "mean": "6", "stdev": "3" }, { "name": "nAB", "index": "10", "type": "numeric", "distinct": "20", "missing": "0", "min": "0", "max": "32", "mean": "14", "stdev": "5" }, { "name": "nAT", "index": "11", "type": "numeric", "distinct": "80", "missing": "0", "min": "20", "max": "155", "mean": "54", "stdev": "11" }, { "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": "0", "max": "36", "mean": "15", "stdev": "5" }, { "name": "nBO", "index": "14", "type": "numeric", "distinct": "50", "missing": "0", "min": "9", "max": "84", "mean": "31", "stdev": "7" }, { "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": "87", "missing": "0", "min": "21", "max": "162", "mean": "57", "stdev": "12" }, { "name": "nC", "index": "17", "type": "numeric", "distinct": "37", "missing": "0", "min": "8", "max": "61", "mean": "22", "stdev": "5" }, { "name": "nCL", "index": "18", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "1" }, { "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": "31", "missing": "0", "min": "0", "max": "34", "mean": "13", "stdev": "4" }, { "name": "nCsp3", "index": "21", "type": "numeric", "distinct": "27", "missing": "0", "min": "0", "max": "27", "mean": "9", "stdev": "3" }, { "name": "nDB", "index": "22", "type": "numeric", "distinct": "9", "missing": "0", "min": "0", "max": "10", "mean": "1", "stdev": "1" }, { "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": "50", "missing": "0", "min": "4", "max": "78", "mean": "26", "stdev": "6" }, { "name": "nHet", "index": "25", "type": "numeric", "distinct": "16", "missing": "0", "min": "1", "max": "16", "mean": "6", "stdev": "2" }, { "name": "nHM", "index": "26", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "5", "mean": "0", "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": "9", "missing": "0", "min": "0", "max": "8", "mean": "3", "stdev": "1" }, { "name": "nO", "index": "29", "type": "numeric", "distinct": "10", "missing": "0", "min": "0", "max": "12", "mean": "2", "stdev": "1" }, { "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": "4", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "0" }, { "name": "nSK", "index": "32", "type": "numeric", "distinct": "47", "missing": "0", "min": "10", "max": "77", "mean": "28", "stdev": "6" }, { "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": "100", "missing": "0", "min": "0", "max": "23", "mean": "3", "stdev": "2" }, { "name": "RBF", "index": "36", "type": "numeric", "distinct": "188", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "RBN", "index": "37", "type": "numeric", "distinct": "23", "missing": "0", "min": "0", "max": "25", "mean": "6", "stdev": "3" }, { "name": "SCBO", "index": "38", "type": "numeric", "distinct": "109", "missing": "0", "min": "9", "max": "106", "mean": "39", "stdev": "9" }, { "name": "Se", "index": "39", "type": "numeric", "distinct": "1869", "missing": "0", "min": "20", "max": "154", "mean": "54", "stdev": "11" }, { "name": "Si", "index": "40", "type": "numeric", "distinct": "1949", "missing": "0", "min": "23", "max": "174", "mean": "61", "stdev": "13" }, { "name": "Sp", "index": "41", "type": "numeric", "distinct": "1723", "missing": "0", "min": "14", "max": "102", "mean": "36", "stdev": "7" }, { "name": "Sv", "index": "42", "type": "numeric", "distinct": "1937", "missing": "0", "min": "13", "max": "95", "mean": "34", "stdev": "7" }, { "name": "X.", "index": "43", "type": "numeric", "distinct": "81", "missing": "0", "min": "0", "max": "14", "mean": "1", "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 }