{ "data_id": "27415", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL238", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL238", "version": 7, "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: CHEMBL238 (TID: 155), and it has 2759 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 21:31:37", "update_comment": null, "last_update": "2016-07-14 21:31:37", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3329938\/data_34444.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 1, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL238", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL238 (TID: 155), and it has 2759 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": 2759, "NumberOfFeatures": 45, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 44, "NumberOfSymbolicFeatures": 1, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 0.6346753352664009, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": 25.220504188981668, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 19.95321227223302, "Quartile1SkewnessOfNumericAtts": 0.8378708700208577, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.34985424366175266, "AutoCorrelation": 0.00324836838288411, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "ClassEntropy": null, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": 10.66571491397944, "Dimensionality": 0.016310257339615802, "MeanSkewnessOfNumericAtts": 2.591282474452383, "Quartile2MeansOfNumericAtts": 3.938292859731786, "EquivalentNumberOfAtts": null, "MeanStdDevOfNumericAtts": 5.541921241945001, "Quartile2MutualInformation": null, "MajorityClassPercentage": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": 2.3154729509257415, "MajorityClassSize": null, "MinKurtosisOfNumericAtts": -0.553360851379638, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 1.9677990690336564, "MaxAttributeEntropy": null, "MaxKurtosisOfNumericAtts": 377.3351758422669, "MinMeansOfNumericAtts": 0, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 335.50042769119244, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 29.299486244815533, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 97.77777777777777, "Quartile3MeansOfNumericAtts": 24.808988764044948, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -0.7164104192882892, "PercentageOfSymbolicFeatures": 2.2222222222222223, "Quartile3MutualInformation": null, "MaxSkewnessOfNumericAtts": 12.482933293935215, "MinStdDevOfNumericAtts": 0, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 3.5130153109248745, "MaxStdDevOfNumericAtts": 93.39693865897576, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": 1.678053744694855, "Quartile3StdDevOfNumericAtts": 6.13668628361373 }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "44", "type": "numeric", "distinct": "1264", "missing": "0", "target": "1", "min": "3", "max": "10", "mean": "6", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "2759", "missing": "0", "identifier": "1", "distr": [] }, { "name": "AMW", "index": "1", "type": "numeric", "distinct": "1196", "missing": "0", "min": "5", "max": "20", "mean": "7", "stdev": "1" }, { "name": "C.", "index": "2", "type": "numeric", "distinct": "151", "missing": "0", "min": "28", "max": "58", "mean": "42", "stdev": "3" }, { "name": "H.", "index": "3", "type": "numeric", "distinct": "192", "missing": "0", "min": "19", "max": "63", "mean": "49", "stdev": "4" }, { "name": "Me", "index": "4", "type": "numeric", "distinct": "84", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Mi", "index": "5", "type": "numeric", "distinct": "77", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Mp", "index": "6", "type": "numeric", "distinct": "168", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Mv", "index": "7", "type": "numeric", "distinct": "173", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "MW", "index": "8", "type": "numeric", "distinct": "1473", "missing": "0", "min": "135", "max": "1746", "mean": "336", "stdev": "93" }, { "name": "N.", "index": "9", "type": "numeric", "distinct": "90", "missing": "0", "min": "0", "max": "22", "mean": "4", "stdev": "2" }, { "name": "nAB", "index": "10", "type": "numeric", "distinct": "17", "missing": "0", "min": "0", "max": "30", "mean": "11", "stdev": "4" }, { "name": "nAT", "index": "11", "type": "numeric", "distinct": "87", "missing": "0", "min": "18", "max": "247", "mean": "45", "stdev": "13" }, { "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": "29", "missing": "0", "min": "0", "max": "40", "mean": "11", "stdev": "4" }, { "name": "nBO", "index": "14", "type": "numeric", "distinct": "58", "missing": "0", "min": "10", "max": "127", "mean": "25", "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": "93", "missing": "0", "min": "18", "max": "255", "mean": "48", "stdev": "14" }, { "name": "nC", "index": "17", "type": "numeric", "distinct": "44", "missing": "0", "min": "8", "max": "72", "mean": "19", "stdev": "5" }, { "name": "nCL", "index": "18", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "nCsp", "index": "19", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "0", "stdev": "0" }, { "name": "nCsp2", "index": "20", "type": "numeric", "distinct": "26", "missing": "0", "min": "0", "max": "39", "mean": "11", "stdev": "4" }, { "name": "nCsp3", "index": "21", "type": "numeric", "distinct": "30", "missing": "0", "min": "0", "max": "72", "mean": "8", "stdev": "3" }, { "name": "nDB", "index": "22", "type": "numeric", "distinct": "8", "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": "58", "missing": "0", "min": "4", "max": "128", "mean": "22", "stdev": "7" }, { "name": "nHet", "index": "25", "type": "numeric", "distinct": "15", "missing": "0", "min": "1", "max": "47", "mean": "4", "stdev": "2" }, { "name": "nHM", "index": "26", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "6", "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": "9", "missing": "0", "min": "0", "max": "8", "mean": "2", "stdev": "1" }, { "name": "nO", "index": "29", "type": "numeric", "distinct": "10", "missing": "0", "min": "0", "max": "47", "mean": "1", "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": "5", "missing": "0", "min": "0", "max": "4", "mean": "0", "stdev": "0" }, { "name": "nSK", "index": "32", "type": "numeric", "distinct": "52", "missing": "0", "min": "10", "max": "119", "mean": "23", "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": "87", "missing": "0", "min": "0", "max": "19", "mean": "3", "stdev": "2" }, { "name": "RBF", "index": "36", "type": "numeric", "distinct": "164", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "RBN", "index": "37", "type": "numeric", "distinct": "24", "missing": "0", "min": "0", "max": "32", "mean": "5", "stdev": "3" }, { "name": "SCBO", "index": "38", "type": "numeric", "distinct": "104", "missing": "0", "min": "12", "max": "127", "mean": "32", "stdev": "9" }, { "name": "Se", "index": "39", "type": "numeric", "distinct": "1451", "missing": "0", "min": "19", "max": "255", "mean": "45", "stdev": "13" }, { "name": "Si", "index": "40", "type": "numeric", "distinct": "1496", "missing": "0", "min": "19", "max": "283", "mean": "51", "stdev": "15" }, { "name": "Sp", "index": "41", "type": "numeric", "distinct": "1362", "missing": "0", "min": "14", "max": "142", "mean": "30", "stdev": "8" }, { "name": "Sv", "index": "42", "type": "numeric", "distinct": "1478", "missing": "0", "min": "13", "max": "139", "mean": "28", "stdev": "8" }, { "name": "X.", "index": "43", "type": "numeric", "distinct": "89", "missing": "0", "min": "0", "max": "22", "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 }