{ "data_id": "32904", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4898", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4898", "version": 9, "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: CHEMBL4898 (TID: 100413), and it has 998 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 11:24:39", "update_comment": null, "last_update": "2016-07-15 11:24:39", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3492464\/data_35880.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-CHEMBL4898", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL4898 (TID: 100413), and it has 998 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": 998, "NumberOfFeatures": 45, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 44, "NumberOfSymbolicFeatures": 1, "MaxSkewnessOfNumericAtts": 31.59113799786276, "MinStdDevOfNumericAtts": 0, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 1.8181242036726197, "MaxStdDevOfNumericAtts": 92.65304807131778, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": 0.627770192802803, "Quartile3StdDevOfNumericAtts": 6.484992927716149, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 0.6081335170340681, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": 29.235960453479148, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 22.151033726544, "Quartile1SkewnessOfNumericAtts": 0.49113357019888765, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.4348148274889184, "AutoCorrelation": 0.41360280842527497, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "ClassEntropy": null, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": 1.1715992322278455, "Dimensionality": 0.045090180360721446, "MeanSkewnessOfNumericAtts": 2.0505020914268353, "Quartile2MeansOfNumericAtts": 4.428356713426853, "EquivalentNumberOfAtts": null, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 5.7678661936069915, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": 0.8772724359322962, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -0.0926634964346933, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 2.4606393692560053, "MaxKurtosisOfNumericAtts": 998.0000000000039, "MinMeansOfNumericAtts": 0, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 383.96648296593185, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 5.066295276701316, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 97.77777777777777, "Quartile3MeansOfNumericAtts": 29.57540080160321, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -0.4741807365728374, "PercentageOfSymbolicFeatures": 2.2222222222222223, "Quartile3MutualInformation": null }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "44", "type": "numeric", "distinct": "94", "missing": "0", "target": "1", "min": "4", "max": "9", "mean": "6", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "998", "missing": "0", "identifier": "1", "distr": [] }, { "name": "AMW", "index": "1", "type": "numeric", "distinct": "743", "missing": "0", "min": "6", "max": "19", "mean": "9", "stdev": "1" }, { "name": "C.", "index": "2", "type": "numeric", "distinct": "150", "missing": "0", "min": "30", "max": "56", "mean": "44", "stdev": "4" }, { "name": "H.", "index": "3", "type": "numeric", "distinct": "189", "missing": "0", "min": "18", "max": "57", "mean": "40", "stdev": "5" }, { "name": "Me", "index": "4", "type": "numeric", "distinct": "86", "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": "163", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Mv", "index": "7", "type": "numeric", "distinct": "166", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "MW", "index": "8", "type": "numeric", "distinct": "872", "missing": "0", "min": "151", "max": "776", "mean": "384", "stdev": "93" }, { "name": "N.", "index": "9", "type": "numeric", "distinct": "147", "missing": "0", "min": "0", "max": "35", "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": "73", "missing": "0", "min": "14", "max": "109", "mean": "46", "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": "5", "max": "35", "mean": "20", "stdev": "5" }, { "name": "nBO", "index": "14", "type": "numeric", "distinct": "46", "missing": "0", "min": "11", "max": "59", "mean": "30", "stdev": "8" }, { "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": "77", "missing": "0", "min": "15", "max": "110", "mean": "49", "stdev": "14" }, { "name": "nC", "index": "17", "type": "numeric", "distinct": "33", "missing": "0", "min": "6", "max": "40", "mean": "20", "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": "27", "missing": "0", "min": "5", "max": "32", "mean": "16", "stdev": "4" }, { "name": "nCsp3", "index": "21", "type": "numeric", "distinct": "17", "missing": "0", "min": "0", "max": "16", "mean": "4", "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": "1", "stdev": "1" }, { "name": "nH", "index": "24", "type": "numeric", "distinct": "43", "missing": "0", "min": "3", "max": "53", "mean": "19", "stdev": "7" }, { "name": "nHet", "index": "25", "type": "numeric", "distinct": "17", "missing": "0", "min": "2", "max": "23", "mean": "7", "stdev": "2" }, { "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": "13", "missing": "0", "min": "0", "max": "21", "mean": "4", "stdev": "2" }, { "name": "nO", "index": "29", "type": "numeric", "distinct": "9", "missing": "0", "min": "0", "max": "8", "mean": "2", "stdev": "1" }, { "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": "1" }, { "name": "nSK", "index": "32", "type": "numeric", "distinct": "41", "missing": "0", "min": "10", "max": "56", "mean": "27", "stdev": "7" }, { "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": "99", "missing": "0", "min": "0", "max": "17", "mean": "4", "stdev": "3" }, { "name": "RBF", "index": "36", "type": "numeric", "distinct": "145", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "RBN", "index": "37", "type": "numeric", "distinct": "17", "missing": "0", "min": "0", "max": "18", "mean": "4", "stdev": "3" }, { "name": "SCBO", "index": "38", "type": "numeric", "distinct": "104", "missing": "0", "min": "16", "max": "75", "mean": "41", "stdev": "10" }, { "name": "Se", "index": "39", "type": "numeric", "distinct": "855", "missing": "0", "min": "15", "max": "110", "mean": "47", "stdev": "13" }, { "name": "Si", "index": "40", "type": "numeric", "distinct": "883", "missing": "0", "min": "16", "max": "127", "mean": "52", "stdev": "15" }, { "name": "Sp", "index": "41", "type": "numeric", "distinct": "836", "missing": "0", "min": "11", "max": "67", "mean": "32", "stdev": "8" }, { "name": "Sv", "index": "42", "type": "numeric", "distinct": "884", "missing": "0", "min": "11", "max": "64", "mean": "31", "stdev": "8" }, { "name": "X.", "index": "43", "type": "numeric", "distinct": "86", "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 }