{ "data_id": "33930", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL2563", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL2563", "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: CHEMBL2563 (TID: 12283), and it has 157 rows and 66 features (not including molecule IDs and class feature: molecule_id and pXC50). The features represent 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 14:03:05", "update_comment": null, "last_update": "2016-07-15 14:03:05", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3517192\/data_53027.arff", "kaggle_url": null, "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL2563", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL2563 (TID: 12283), and it has 157 rows and 66 features (not including molecule IDs and class feature: molecule_id and pXC50). The features represent 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": 157, "NumberOfFeatures": 68, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 67, "NumberOfSymbolicFeatures": 1, "MaxSkewnessOfNumericAtts": 4.585519540352561, "MinStdDevOfNumericAtts": 0.044955188459836475, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 1.6346235379136642, "MaxStdDevOfNumericAtts": 42.32005299896313, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": 0.02614034429303702, "Quartile3StdDevOfNumericAtts": 1.4830141258933485, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 0.21019108280254803, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": 2.6176594490020686, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 7.219113318756535, "Quartile1SkewnessOfNumericAtts": -0.02663729677797571, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.22737133143455243, "AutoCorrelation": 0.15520512820512813, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "ClassEntropy": null, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": 1.3164629017866916, "Dimensionality": 0.43312101910828027, "MeanSkewnessOfNumericAtts": 0.8011957172263551, "Quartile2MeansOfNumericAtts": 0.9318535031847134, "EquivalentNumberOfAtts": null, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 4.024561467818683, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": 0.8288850049269472, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.643461823385678, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.5498949463906547, "MaxKurtosisOfNumericAtts": 25.9243540658858, "MinMeansOfNumericAtts": -0.525515923566879, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 96.66975159235669, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 2.851104714225524, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.52941176470588, "Quartile3MeansOfNumericAtts": 4.050955414012738, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -3.0304762372687044, "PercentageOfSymbolicFeatures": 1.4705882352941175, "Quartile3MutualInformation": null }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "67", "type": "numeric", "distinct": "94", "missing": "0", "target": "1", "min": "4", "max": "9", "mean": "5", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "157", "missing": "0", "identifier": "1", "distr": [] }, { "name": "CATS2D_01_DD", "index": "1", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "nRNHO", "index": "2", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "1" }, { "name": "O.056", "index": "3", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "1" }, { "name": "P_VSA_MR_3", "index": "4", "type": "numeric", "distinct": "11", "missing": "0", "min": "0", "max": "144", "mean": "24", "stdev": "27" }, { "name": "GATS5m", "index": "5", "type": "numeric", "distinct": "139", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "MATS3s", "index": "6", "type": "numeric", "distinct": "125", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "MATS5m", "index": "7", "type": "numeric", "distinct": "131", "missing": "0", "min": "-1", "max": "0", "mean": "0", "stdev": "0" }, { "name": "CATS2D_03_DA", "index": "8", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "6", "mean": "1", "stdev": "1" }, { "name": "MAXDN", "index": "9", "type": "numeric", "distinct": "126", "missing": "0", "min": "2", "max": "6", "mean": "2", "stdev": "1" }, { "name": "GATS4s", "index": "10", "type": "numeric", "distinct": "135", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "MATS2e", "index": "11", "type": "numeric", "distinct": "114", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "P_VSA_LogP_3", "index": "12", "type": "numeric", "distinct": "61", "missing": "0", "min": "9", "max": "256", "mean": "97", "stdev": "42" }, { "name": "H.051", "index": "13", "type": "numeric", "distinct": "10", "missing": "0", "min": "0", "max": "10", "mean": "2", "stdev": "2" }, { "name": "MATS1e", "index": "14", "type": "numeric", "distinct": "112", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "GATS3s", "index": "15", "type": "numeric", "distinct": "137", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "MATS5v", "index": "16", "type": "numeric", "distinct": "121", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "nRSR", "index": "17", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "NssS", "index": "18", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "SssS", "index": "19", "type": "numeric", "distinct": "25", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "ATSC3s", "index": "20", "type": "numeric", "distinct": "152", "missing": "0", "min": "20", "max": "282", "mean": "66", "stdev": "37" }, { "name": "MATS3e", "index": "21", "type": "numeric", "distinct": "117", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "GATS7m", "index": "22", "type": "numeric", "distinct": "128", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "S.107", "index": "23", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "MATS1s", "index": "24", "type": "numeric", "distinct": "100", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "CATS2D_03_AL", "index": "25", "type": "numeric", "distinct": "14", "missing": "0", "min": "0", "max": "15", "mean": "5", "stdev": "3" }, { "name": "P_VSA_MR_8", "index": "26", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "77", "mean": "8", "stdev": "16" }, { "name": "P_VSA_i_1", "index": "27", "type": "numeric", "distinct": "8", "missing": "0", "min": "0", "max": "77", "mean": "8", "stdev": "15" }, { "name": "CATS2D_04_DA", "index": "28", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "1" }, { "name": "nROH", "index": "29", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "1" }, { "name": "SsOH", "index": "30", "type": "numeric", "distinct": "114", "missing": "0", "min": "0", "max": "37", "mean": "8", "stdev": "5" }, { "name": "GATS2e", "index": "31", "type": "numeric", "distinct": "123", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "GATS7v", "index": "32", "type": "numeric", "distinct": "133", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "GATS5p", "index": "33", "type": "numeric", "distinct": "132", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "SM04_EA.dm.", "index": "34", "type": "numeric", "distinct": "89", "missing": "0", "min": "1", "max": "6", "mean": "4", "stdev": "1" }, { "name": "Eig01_AEA.dm.", "index": "35", "type": "numeric", "distinct": "54", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SpMax_AEA.dm.", "index": "36", "type": "numeric", "distinct": "54", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SM12_EA.dm.", "index": "37", "type": "numeric", "distinct": "64", "missing": "0", "min": "1", "max": "16", "mean": "9", "stdev": "4" }, { "name": "SM14_EA.dm.", "index": "38", "type": "numeric", "distinct": "60", "missing": "0", "min": "1", "max": "19", "mean": "11", "stdev": "4" }, { "name": "P_VSA_LogP_4", "index": "39", "type": "numeric", "distinct": "58", "missing": "0", "min": "30", "max": "209", "mean": "79", "stdev": "39" }, { "name": "SaasN", "index": "40", "type": "numeric", "distinct": "15", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "SdssC", "index": "41", "type": "numeric", "distinct": "139", "missing": "0", "min": "-4", "max": "0", "mean": "-1", "stdev": "1" }, { "name": "GATS6s", "index": "42", "type": "numeric", "distinct": "142", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "GATS3e", "index": "43", "type": "numeric", "distinct": "137", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "SpDiam_AEA.dm.", "index": "44", "type": "numeric", "distinct": "55", "missing": "0", "min": "6", "max": "7", "mean": "6", "stdev": "0" }, { "name": "CATS2D_03_DD", "index": "45", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "1" }, { "name": "P_VSA_MR_6", "index": "46", "type": "numeric", "distinct": "121", "missing": "0", "min": "5", "max": "210", "mean": "93", "stdev": "42" }, { "name": "Eig01_EA.dm.", "index": "47", "type": "numeric", "distinct": "35", "missing": "0", "min": "1", "max": "4", "mean": "2", "stdev": "1" }, { "name": "SpMax_EA.dm.", "index": "48", "type": "numeric", "distinct": "35", "missing": "0", "min": "1", "max": "4", "mean": "2", "stdev": "1" }, { "name": "MATS8e", "index": "49", "type": "numeric", "distinct": "136", "missing": "0", "min": "-1", "max": "1", "mean": "0", "stdev": "0" }, { "name": "MATS7v", "index": "50", "type": "numeric", "distinct": "123", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "GATS5s", "index": "51", "type": "numeric", "distinct": "141", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "GATS7p", "index": "52", "type": "numeric", "distinct": "127", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "O.057", "index": "53", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "1" }, { "name": "Eig03_AEA.dm.", "index": "54", "type": "numeric", "distinct": "90", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "nArOH", "index": "55", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "0" }, { "name": "SM06_EA.dm.", "index": "56", "type": "numeric", "distinct": "84", "missing": "0", "min": "1", "max": "8", "mean": "5", "stdev": "2" }, { "name": "SM08_EA.dm.", "index": "57", "type": "numeric", "distinct": "78", "missing": "0", "min": "1", "max": "11", "mean": "6", "stdev": "2" }, { "name": "SM10_EA.dm.", "index": "58", "type": "numeric", "distinct": "70", "missing": "0", "min": "1", "max": "14", "mean": "8", "stdev": "3" }, { "name": "SpMaxA_EA.dm.", "index": "59", "type": "numeric", "distinct": "72", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "CATS2D_07_PL", "index": "60", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "0", "stdev": "1" }, { "name": "SdsCH", "index": "61", "type": "numeric", "distinct": "32", "missing": "0", "min": "0", "max": "7", "mean": "1", "stdev": "1" }, { "name": "C.016", "index": "62", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "0", "stdev": "1" }, { "name": "NdsCH", "index": "63", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "nR.Cs", "index": "64", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "0", "stdev": "1" }, { "name": "CATS2D_06_PL", "index": "65", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "0", "stdev": "1" }, { "name": "CATS2D_06_DL", "index": "66", "type": "numeric", "distinct": "14", "missing": "0", "min": "0", "max": "16", "mean": "4", "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 }