{ "data_id": "35272", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3009", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3009", "version": 10, "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: CHEMBL3009 (TID: 12699), and it has 789 rows and 69 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 17:35:35", "update_comment": null, "last_update": "2016-07-15 17:35:35", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3552875\/data_53511.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3009", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL3009 (TID: 12699), and it has 789 rows and 69 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": 789, "NumberOfFeatures": 71, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 70, "NumberOfSymbolicFeatures": 1, "ClassEntropy": null, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "Dimensionality": 0.08998732572877059, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": 1.9236777180109987, "EquivalentNumberOfAtts": null, "MeanSkewnessOfNumericAtts": 0.2764633328154096, "Quartile2MeansOfNumericAtts": 7.006762357414448, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 23.019458557207663, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": 0.770203867972074, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.099521690554801, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 2.1414661840156715, "MaxKurtosisOfNumericAtts": 17.022668001647666, "MinMeansOfNumericAtts": 0.10604182509505704, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 1488.2491216730039, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 2.2775918384633753, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.59154929577466, "Quartile3MeansOfNumericAtts": 19.036989860583017, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -2.0502804992042543, "PercentageOfSymbolicFeatures": 1.4084507042253522, "Quartile3MutualInformation": null, "MaxSkewnessOfNumericAtts": 2.89188119841474, "MinStdDevOfNumericAtts": 0.02506903209676952, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 0.8765601125083302, "MaxStdDevOfNumericAtts": 917.0910536138446, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": 1.5477083768601552, "Quartile3StdDevOfNumericAtts": 4.680348299627399, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 1.6715459442332066, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": 2.607767807872431, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 53.125415100488866, "Quartile1SkewnessOfNumericAtts": -0.6978720014891103, "AutoCorrelation": 0.6206091370558378, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.5190426944294714 }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "70", "type": "numeric", "distinct": "94", "missing": "0", "target": "1", "min": "5", "max": "9", "mean": "6", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "789", "missing": "0", "identifier": "1", "distr": [] }, { "name": "Chi1_EA.dm.", "index": "1", "type": "numeric", "distinct": "681", "missing": "0", "min": "0", "max": "77", "mean": "25", "stdev": "14" }, { "name": "Chi0_EA.dm.", "index": "2", "type": "numeric", "distinct": "676", "missing": "0", "min": "0", "max": "54", "mean": "19", "stdev": "9" }, { "name": "ATS7m", "index": "3", "type": "numeric", "distinct": "614", "missing": "0", "min": "0", "max": "5", "mean": "4", "stdev": "1" }, { "name": "SpMax8_Bh.m.", "index": "4", "type": "numeric", "distinct": "458", "missing": "0", "min": "1", "max": "3", "mean": "3", "stdev": "0" }, { "name": "Eig10_EA", "index": "5", "type": "numeric", "distinct": "474", "missing": "0", "min": "-2", "max": "2", "mean": "1", "stdev": "1" }, { "name": "SM04_AEA.dm.", "index": "6", "type": "numeric", "distinct": "474", "missing": "0", "min": "-2", "max": "2", "mean": "1", "stdev": "1" }, { "name": "ATS1m", "index": "7", "type": "numeric", "distinct": "509", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "MW", "index": "8", "type": "numeric", "distinct": "697", "missing": "0", "min": "188", "max": "852", "mean": "391", "stdev": "91" }, { "name": "S2K", "index": "9", "type": "numeric", "distinct": "680", "missing": "0", "min": "2", "max": "24", "mean": "8", "stdev": "2" }, { "name": "XMOD", "index": "10", "type": "numeric", "distinct": "757", "missing": "0", "min": "39", "max": "195", "mean": "88", "stdev": "20" }, { "name": "ATS8m", "index": "11", "type": "numeric", "distinct": "614", "missing": "0", "min": "0", "max": "5", "mean": "3", "stdev": "1" }, { "name": "MDDD", "index": "12", "type": "numeric", "distinct": "696", "missing": "0", "min": "4", "max": "113", "mean": "29", "stdev": "15" }, { "name": "nPyrimidines", "index": "13", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "X1sol", "index": "14", "type": "numeric", "distinct": "616", "missing": "0", "min": "6", "max": "30", "mean": "14", "stdev": "3" }, { "name": "PHI", "index": "15", "type": "numeric", "distinct": "677", "missing": "0", "min": "1", "max": "20", "mean": "5", "stdev": "2" }, { "name": "X1v", "index": "16", "type": "numeric", "distinct": "733", "missing": "0", "min": "4", "max": "22", "mean": "9", "stdev": "2" }, { "name": "ON1", "index": "17", "type": "numeric", "distinct": "237", "missing": "0", "min": "2", "max": "13", "mean": "6", "stdev": "1" }, { "name": "Neoplastic.80", "index": "18", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Chi0_EA.ri.", "index": "19", "type": "numeric", "distinct": "751", "missing": "0", "min": "8", "max": "43", "mean": "19", "stdev": "5" }, { "name": "Eig11_EA", "index": "20", "type": "numeric", "distinct": "472", "missing": "0", "min": "-2", "max": "2", "mean": "1", "stdev": "1" }, { "name": "SM05_AEA.dm.", "index": "21", "type": "numeric", "distinct": "472", "missing": "0", "min": "-2", "max": "2", "mean": "1", "stdev": "1" }, { "name": "Chi0_EA.ed.", "index": "22", "type": "numeric", "distinct": "686", "missing": "0", "min": "4", "max": "24", "mean": "11", "stdev": "3" }, { "name": "X0sol", "index": "23", "type": "numeric", "distinct": "461", "missing": "0", "min": "9", "max": "42", "mean": "19", "stdev": "5" }, { "name": "Eig11_AEA.dm.", "index": "24", "type": "numeric", "distinct": "500", "missing": "0", "min": "-2", "max": "3", "mean": "1", "stdev": "1" }, { "name": "VAR", "index": "25", "type": "numeric", "distinct": "210", "missing": "0", "min": "11", "max": "503", "mean": "119", "stdev": "61" }, { "name": "Eta_alpha", "index": "26", "type": "numeric", "distinct": "489", "missing": "0", "min": "6", "max": "29", "mean": "13", "stdev": "3" }, { "name": "ATSC3m", "index": "27", "type": "numeric", "distinct": "767", "missing": "0", "min": "5", "max": "63", "mean": "23", "stdev": "9" }, { "name": "S1K", "index": "28", "type": "numeric", "distinct": "631", "missing": "0", "min": "7", "max": "47", "mean": "19", "stdev": "5" }, { "name": "AMR", "index": "29", "type": "numeric", "distinct": "759", "missing": "0", "min": "44", "max": "230", "mean": "108", "stdev": "25" }, { "name": "IVDM", "index": "30", "type": "numeric", "distinct": "290", "missing": "0", "min": "3", "max": "6", "mean": "5", "stdev": "0" }, { "name": "Eig11_AEA.ri.", "index": "31", "type": "numeric", "distinct": "520", "missing": "0", "min": "-1", "max": "3", "mean": "2", "stdev": "1" }, { "name": "Eig10_AEA.ri.", "index": "32", "type": "numeric", "distinct": "534", "missing": "0", "min": "-1", "max": "3", "mean": "2", "stdev": "1" }, { "name": "Eig10_AEA.dm.", "index": "33", "type": "numeric", "distinct": "522", "missing": "0", "min": "-2", "max": "3", "mean": "1", "stdev": "1" }, { "name": "SpMin7_Bh.i.", "index": "34", "type": "numeric", "distinct": "420", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "Eig09_AEA.dm.", "index": "35", "type": "numeric", "distinct": "535", "missing": "0", "min": "-1", "max": "3", "mean": "1", "stdev": "1" }, { "name": "SpMin7_Bh.e.", "index": "36", "type": "numeric", "distinct": "422", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "SpMax7_Bh.m.", "index": "37", "type": "numeric", "distinct": "460", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "Infective.80", "index": "38", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Eig10_AEA.bo.", "index": "39", "type": "numeric", "distinct": "493", "missing": "0", "min": "0", "max": "4", "mean": "2", "stdev": "1" }, { "name": "IDET", "index": "40", "type": "numeric", "distinct": "709", "missing": "0", "min": "120", "max": "8321", "mean": "1488", "stdev": "917" }, { "name": "X2sol", "index": "41", "type": "numeric", "distinct": "668", "missing": "0", "min": "6", "max": "28", "mean": "12", "stdev": "3" }, { "name": "ECC", "index": "42", "type": "numeric", "distinct": "385", "missing": "0", "min": "47", "max": "1307", "mean": "331", "stdev": "164" }, { "name": "DLS_02", "index": "43", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "X1", "index": "44", "type": "numeric", "distinct": "559", "missing": "0", "min": "5", "max": "29", "mean": "14", "stdev": "3" }, { "name": "Eig07_AEA.dm.", "index": "45", "type": "numeric", "distinct": "547", "missing": "0", "min": "0", "max": "3", "mean": "2", "stdev": "0" }, { "name": "SpMaxA_EA.ri.", "index": "46", "type": "numeric", "distinct": "122", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Chi0_AEA.bo.", "index": "47", "type": "numeric", "distinct": "547", "missing": "0", "min": "7", "max": "41", "mean": "19", "stdev": "4" }, { "name": "Chi0_AEA.dm.", "index": "48", "type": "numeric", "distinct": "547", "missing": "0", "min": "7", "max": "41", "mean": "19", "stdev": "4" }, { "name": "Chi0_AEA.ed.", "index": "49", "type": "numeric", "distinct": "547", "missing": "0", "min": "7", "max": "41", "mean": "19", "stdev": "4" }, { "name": "Chi0_AEA.ri.", "index": "50", "type": "numeric", "distinct": "547", "missing": "0", "min": "7", "max": "41", "mean": "19", "stdev": "4" }, { "name": "Chi0_EA", "index": "51", "type": "numeric", "distinct": "547", "missing": "0", "min": "7", "max": "41", "mean": "19", "stdev": "4" }, { "name": "Eig15_AEA.bo.", "index": "52", "type": "numeric", "distinct": "508", "missing": "0", "min": "-1", "max": "3", "mean": "1", "stdev": "1" }, { "name": "ICR", "index": "53", "type": "numeric", "distinct": "430", "missing": "0", "min": "1", "max": "4", "mean": "3", "stdev": "0" }, { "name": "Chi1_EA.ri.", "index": "54", "type": "numeric", "distinct": "745", "missing": "0", "min": "7", "max": "35", "mean": "16", "stdev": "4" }, { "name": "Chi1_EA.ed.", "index": "55", "type": "numeric", "distinct": "671", "missing": "0", "min": "2", "max": "11", "mean": "5", "stdev": "1" }, { "name": "Eta_betaS", "index": "56", "type": "numeric", "distinct": "94", "missing": "0", "min": "7", "max": "42", "mean": "18", "stdev": "5" }, { "name": "Dz", "index": "57", "type": "numeric", "distinct": "253", "missing": "0", "min": "24", "max": "135", "mean": "61", "stdev": "15" }, { "name": "Chi0_EA.bo.", "index": "58", "type": "numeric", "distinct": "666", "missing": "0", "min": "6", "max": "37", "mean": "17", "stdev": "4" }, { "name": "VvdwZAZ", "index": "59", "type": "numeric", "distinct": "723", "missing": "0", "min": "119", "max": "739", "mean": "331", "stdev": "84" }, { "name": "LPRS", "index": "60", "type": "numeric", "distinct": "712", "missing": "0", "min": "35", "max": "391", "mean": "142", "stdev": "46" }, { "name": "X0v", "index": "61", "type": "numeric", "distinct": "719", "missing": "0", "min": "7", "max": "35", "mean": "16", "stdev": "4" }, { "name": "Eta_L", "index": "62", "type": "numeric", "distinct": "709", "missing": "0", "min": "2", "max": "14", "mean": "6", "stdev": "2" }, { "name": "Eig07_EA", "index": "63", "type": "numeric", "distinct": "485", "missing": "0", "min": "-1", "max": "3", "mean": "2", "stdev": "0" }, { "name": "SM15_AEA.bo.", "index": "64", "type": "numeric", "distinct": "485", "missing": "0", "min": "-1", "max": "3", "mean": "2", "stdev": "0" }, { "name": "IAC", "index": "65", "type": "numeric", "distinct": "678", "missing": "0", "min": "26", "max": "186", "mean": "78", "stdev": "21" }, { "name": "TIC0", "index": "66", "type": "numeric", "distinct": "678", "missing": "0", "min": "26", "max": "186", "mean": "78", "stdev": "21" }, { "name": "S3K", "index": "67", "type": "numeric", "distinct": "697", "missing": "0", "min": "1", "max": "19", "mean": "4", "stdev": "2" }, { "name": "Xu", "index": "68", "type": "numeric", "distinct": "700", "missing": "0", "min": "11", "max": "50", "mean": "27", "stdev": "6" }, { "name": "SpMax8_Bh.v.", "index": "69", "type": "numeric", "distinct": "427", "missing": "0", "min": "0", "max": "3", "mean": "3", "stdev": "0" } ], "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 }