{ "data_id": "26661", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL5608", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL5608", "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: CHEMBL5608 (TID: 101034), and it has 746 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": "2016-07-14 19:46:08", "update_comment": null, "last_update": "2016-07-14 19:46:08", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3309446\/data_53522.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL5608", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL5608 (TID: 101034), and it has 746 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": 746, "NumberOfFeatures": 71, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 70, "NumberOfSymbolicFeatures": 1, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 2.094506032171582, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": 4.886316416443305, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 1181.2330127154348, "Quartile1SkewnessOfNumericAtts": -0.8335097708021937, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.49164681413458333, "AutoCorrelation": 0.22617986577181332, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "ClassEntropy": null, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": 1.0931603620559596, "Dimensionality": 0.09517426273458444, "MeanSkewnessOfNumericAtts": 0.1876601192119681, "Quartile2MeansOfNumericAtts": 5.926735924932976, "EquivalentNumberOfAtts": null, "MeanStdDevOfNumericAtts": 815.3282009540619, "Quartile2MutualInformation": null, "MajorityClassPercentage": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": 0.20283931633107505, "MajorityClassSize": null, "MinKurtosisOfNumericAtts": -0.520690682226923, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 1.378128605073912, "MaxAttributeEntropy": null, "MaxKurtosisOfNumericAtts": 99.78956762512846, "MinMeansOfNumericAtts": 0.11528150134048255, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 31096.35924932975, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 2.758099858319599, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.59154929577466, "Quartile3MeansOfNumericAtts": 31.87717091152815, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -1.9078672399928047, "PercentageOfSymbolicFeatures": 1.4084507042253522, "Quartile3MutualInformation": null, "MaxSkewnessOfNumericAtts": 6.442451598225256, "MinStdDevOfNumericAtts": 0.06935847883096838, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 0.8300021331922945, "MaxStdDevOfNumericAtts": 21059.74836652543, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": 0.13565991400691302, "Quartile3StdDevOfNumericAtts": 12.108575299663237 }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "70", "type": "numeric", "distinct": "81", "missing": "0", "target": "1", "min": "4", "max": "9", "mean": "6", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "746", "missing": "0", "identifier": "1", "distr": [] }, { "name": "CATS2D_08_DP", "index": "1", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "0", "stdev": "0" }, { "name": "CATS2D_05_DL", "index": "2", "type": "numeric", "distinct": "16", "missing": "0", "min": "0", "max": "16", "mean": "3", "stdev": "3" }, { "name": "Eig10_AEA.dm.", "index": "3", "type": "numeric", "distinct": "493", "missing": "0", "min": "-2", "max": "3", "mean": "1", "stdev": "1" }, { "name": "P_VSA_MR_6", "index": "4", "type": "numeric", "distinct": "644", "missing": "0", "min": "7", "max": "204", "mean": "102", "stdev": "38" }, { "name": "CATS2D_04_DL", "index": "5", "type": "numeric", "distinct": "14", "missing": "0", "min": "0", "max": "14", "mean": "4", "stdev": "3" }, { "name": "Eig06_AEA.dm.", "index": "6", "type": "numeric", "distinct": "558", "missing": "0", "min": "0", "max": "3", "mean": "2", "stdev": "0" }, { "name": "SsNH2", "index": "7", "type": "numeric", "distinct": "215", "missing": "0", "min": "0", "max": "13", "mean": "2", "stdev": "3" }, { "name": "BID", "index": "8", "type": "numeric", "distinct": "136", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "Dz", "index": "9", "type": "numeric", "distinct": "250", "missing": "0", "min": "22", "max": "110", "mean": "59", "stdev": "15" }, { "name": "HDcpx", "index": "10", "type": "numeric", "distinct": "249", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "IDM", "index": "11", "type": "numeric", "distinct": "577", "missing": "0", "min": "5", "max": "10", "mean": "8", "stdev": "1" }, { "name": "SMTIV", "index": "12", "type": "numeric", "distinct": "720", "missing": "0", "min": "1010", "max": "90641", "mean": "17422", "stdev": "11660" }, { "name": "X0sol", "index": "13", "type": "numeric", "distinct": "451", "missing": "0", "min": "7", "max": "32", "mean": "19", "stdev": "4" }, { "name": "GMTIV", "index": "14", "type": "numeric", "distinct": "725", "missing": "0", "min": "1644", "max": "169376", "mean": "31096", "stdev": "21060" }, { "name": "SpMax7_Bh.m.", "index": "15", "type": "numeric", "distinct": "466", "missing": "0", "min": "1", "max": "4", "mean": "3", "stdev": "0" }, { "name": "Eig06_EA.ed.", "index": "16", "type": "numeric", "distinct": "620", "missing": "0", "min": "-2", "max": "9", "mean": "5", "stdev": "1" }, { "name": "SM15_AEA.dm.", "index": "17", "type": "numeric", "distinct": "620", "missing": "0", "min": "-2", "max": "9", "mean": "5", "stdev": "1" }, { "name": "Eig11_AEA.dm.", "index": "18", "type": "numeric", "distinct": "487", "missing": "0", "min": "-2", "max": "2", "mean": "1", "stdev": "1" }, { "name": "Eig03_AEA.ed.", "index": "19", "type": "numeric", "distinct": "490", "missing": "0", "min": "4", "max": "7", "mean": "6", "stdev": "0" }, { "name": "SpMax3_Bh.m.", "index": "20", "type": "numeric", "distinct": "395", "missing": "0", "min": "3", "max": "7", "mean": "4", "stdev": "0" }, { "name": "Chi1_EA.ri.", "index": "21", "type": "numeric", "distinct": "709", "missing": "0", "min": "6", "max": "30", "mean": "16", "stdev": "4" }, { "name": "S0K", "index": "22", "type": "numeric", "distinct": "240", "missing": "0", "min": "31", "max": "268", "mean": "125", "stdev": "39" }, { "name": "X0", "index": "23", "type": "numeric", "distinct": "348", "missing": "0", "min": "7", "max": "34", "mean": "19", "stdev": "5" }, { "name": "X1sol", "index": "24", "type": "numeric", "distinct": "604", "missing": "0", "min": "5", "max": "23", "mean": "13", "stdev": "3" }, { "name": "XMOD", "index": "25", "type": "numeric", "distinct": "710", "missing": "0", "min": "35", "max": "154", "mean": "85", "stdev": "20" }, { "name": "SpMax5_Bh.m.", "index": "26", "type": "numeric", "distinct": "481", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "Eig06_AEA.ed.", "index": "27", "type": "numeric", "distinct": "542", "missing": "0", "min": "2", "max": "6", "mean": "5", "stdev": "1" }, { "name": "Eig11_EA.ri.", "index": "28", "type": "numeric", "distinct": "515", "missing": "0", "min": "-2", "max": "2", "mean": "1", "stdev": "1" }, { "name": "Eig11_EA.bo.", "index": "29", "type": "numeric", "distinct": "501", "missing": "0", "min": "-3", "max": "3", "mean": "1", "stdev": "1" }, { "name": "SpMax4_Bh.m.", "index": "30", "type": "numeric", "distinct": "474", "missing": "0", "min": "2", "max": "7", "mean": "3", "stdev": "0" }, { "name": "Eig09_EA.ri.", "index": "31", "type": "numeric", "distinct": "505", "missing": "0", "min": "-1", "max": "2", "mean": "1", "stdev": "1" }, { "name": "SpAD_AEA.dm.", "index": "32", "type": "numeric", "distinct": "710", "missing": "0", "min": "16", "max": "89", "mean": "47", "stdev": "12" }, { "name": "Eta_betaS", "index": "33", "type": "numeric", "distinct": "94", "missing": "0", "min": "7", "max": "34", "mean": "18", "stdev": "5" }, { "name": "Eig07_AEA.dm.", "index": "34", "type": "numeric", "distinct": "528", "missing": "0", "min": "-1", "max": "3", "mean": "2", "stdev": "1" }, { "name": "ZM2Mad", "index": "35", "type": "numeric", "distinct": "722", "missing": "0", "min": "84", "max": "380", "mean": "199", "stdev": "50" }, { "name": "Eig09_AEA.dm.", "index": "36", "type": "numeric", "distinct": "511", "missing": "0", "min": "-2", "max": "3", "mean": "1", "stdev": "1" }, { "name": "Eig11_EA", "index": "37", "type": "numeric", "distinct": "457", "missing": "0", "min": "-2", "max": "2", "mean": "1", "stdev": "1" }, { "name": "SM05_AEA.dm.", "index": "38", "type": "numeric", "distinct": "457", "missing": "0", "min": "-2", "max": "2", "mean": "1", "stdev": "1" }, { "name": "SpMax7_Bh.s.", "index": "39", "type": "numeric", "distinct": "526", "missing": "0", "min": "2", "max": "7", "mean": "4", "stdev": "0" }, { "name": "X0v", "index": "40", "type": "numeric", "distinct": "680", "missing": "0", "min": "6", "max": "27", "mean": "15", "stdev": "4" }, { "name": "CSI", "index": "41", "type": "numeric", "distinct": "508", "missing": "0", "min": "79", "max": "2307", "mean": "678", "stdev": "332" }, { "name": "X2sol", "index": "42", "type": "numeric", "distinct": "649", "missing": "0", "min": "5", "max": "22", "mean": "12", "stdev": "3" }, { "name": "Chi0_EA.bo.", "index": "43", "type": "numeric", "distinct": "648", "missing": "0", "min": "5", "max": "30", "mean": "16", "stdev": "4" }, { "name": "ON1", "index": "44", "type": "numeric", "distinct": "251", "missing": "0", "min": "2", "max": "11", "mean": "6", "stdev": "1" }, { "name": "MDDD", "index": "45", "type": "numeric", "distinct": "667", "missing": "0", "min": "2", "max": "93", "mean": "27", "stdev": "14" }, { "name": "ECC", "index": "46", "type": "numeric", "distinct": "393", "missing": "0", "min": "37", "max": "1023", "mean": "313", "stdev": "152" }, { "name": "Eig05_EA.ed.", "index": "47", "type": "numeric", "distinct": "618", "missing": "0", "min": "1", "max": "10", "mean": "6", "stdev": "1" }, { "name": "SM14_AEA.dm.", "index": "48", "type": "numeric", "distinct": "618", "missing": "0", "min": "1", "max": "10", "mean": "6", "stdev": "1" }, { "name": "SpMax5_Bh.p.", "index": "49", "type": "numeric", "distinct": "465", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "CATS2D_05_PL", "index": "50", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "6", "mean": "1", "stdev": "1" }, { "name": "Eig06_EA", "index": "51", "type": "numeric", "distinct": "485", "missing": "0", "min": "-1", "max": "3", "mean": "2", "stdev": "0" }, { "name": "Eig06_EA.bo.", "index": "52", "type": "numeric", "distinct": "514", "missing": "0", "min": "-1", "max": "3", "mean": "2", "stdev": "0" }, { "name": "SM14_AEA.bo.", "index": "53", "type": "numeric", "distinct": "485", "missing": "0", "min": "-1", "max": "3", "mean": "2", "stdev": "0" }, { "name": "Eig03_EA.ed.", "index": "54", "type": "numeric", "distinct": "598", "missing": "0", "min": "4", "max": "12", "mean": "8", "stdev": "1" }, { "name": "SM12_AEA.dm.", "index": "55", "type": "numeric", "distinct": "598", "missing": "0", "min": "4", "max": "12", "mean": "8", "stdev": "1" }, { "name": "ZM1MulPer", "index": "56", "type": "numeric", "distinct": "724", "missing": "0", "min": "165", "max": "842", "mean": "448", "stdev": "117" }, { "name": "SpAD_AEA.ed.", "index": "57", "type": "numeric", "distinct": "678", "missing": "0", "min": "17", "max": "88", "mean": "47", "stdev": "12" }, { "name": "Eig03_AEA.ri.", "index": "58", "type": "numeric", "distinct": "453", "missing": "0", "min": "2", "max": "4", "mean": "4", "stdev": "0" }, { "name": "ATSC8m", "index": "59", "type": "numeric", "distinct": "720", "missing": "0", "min": "0", "max": "247", "mean": "21", "stdev": "14" }, { "name": "IDET", "index": "60", "type": "numeric", "distinct": "679", "missing": "0", "min": "88", "max": "5482", "mean": "1390", "stdev": "803" }, { "name": "IDMT", "index": "61", "type": "numeric", "distinct": "681", "missing": "0", "min": "562", "max": "117780", "mean": "19933", "stdev": "15512" }, { "name": "LPRS", "index": "62", "type": "numeric", "distinct": "682", "missing": "0", "min": "30", "max": "307", "mean": "136", "stdev": "45" }, { "name": "SMTI", "index": "63", "type": "numeric", "distinct": "667", "missing": "0", "min": "505", "max": "53358", "mean": "10144", "stdev": "7053" }, { "name": "UNIP", "index": "64", "type": "numeric", "distinct": "199", "missing": "0", "min": "16", "max": "343", "mean": "110", "stdev": "51" }, { "name": "Xu", "index": "65", "type": "numeric", "distinct": "673", "missing": "0", "min": "10", "max": "44", "mean": "26", "stdev": "6" }, { "name": "Eig05_EA", "index": "66", "type": "numeric", "distinct": "502", "missing": "0", "min": "0", "max": "3", "mean": "2", "stdev": "0" }, { "name": "SM13_AEA.bo.", "index": "67", "type": "numeric", "distinct": "502", "missing": "0", "min": "0", "max": "3", "mean": "2", "stdev": "0" }, { "name": "Chi0_EA.ri.", "index": "68", "type": "numeric", "distinct": "710", "missing": "0", "min": "7", "max": "35", "mean": "19", "stdev": "5" }, { "name": "SpMax6_Bh.m.", "index": "69", "type": "numeric", "distinct": "485", "missing": "0", "min": "2", "max": "4", "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 }