{ "data_id": "28358", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3268", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3268", "version": 8, "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: CHEMBL3268 (TID: 11941), and it has 199 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": "2016-07-14 23:47:21", "update_comment": null, "last_update": "2016-07-14 23:47:21", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3357998\/data_53053.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3268", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL3268 (TID: 11941), and it has 199 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": 199, "NumberOfFeatures": 68, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 67, "NumberOfSymbolicFeatures": 1, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 1.1809045226130668, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": 0.15170547724877054, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 703.3266723168077, "Quartile1SkewnessOfNumericAtts": -0.007681382253807064, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.33002532969099946, "AutoCorrelation": 0.3604848484848483, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "ClassEntropy": null, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": -0.28494130072736956, "Dimensionality": 0.3417085427135678, "MeanSkewnessOfNumericAtts": 0.46389951430515136, "Quartile2MeansOfNumericAtts": 2.8983819095477386, "EquivalentNumberOfAtts": null, "MeanStdDevOfNumericAtts": 562.6891409769878, "Quartile2MutualInformation": null, "MajorityClassPercentage": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": 0.6457750435240721, "MajorityClassSize": null, "MinKurtosisOfNumericAtts": -1.8505944911935848, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.5870711674983127, "MaxAttributeEntropy": null, "MaxKurtosisOfNumericAtts": 4.406981354654188, "MinMeansOfNumericAtts": 0.09851256281407035, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 29041.994974874342, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 0.6979268978826485, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.52941176470588, "Quartile3MeansOfNumericAtts": 8.99710552763819, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -0.8071887841185892, "PercentageOfSymbolicFeatures": 1.4705882352941175, "Quartile3MutualInformation": null, "MaxSkewnessOfNumericAtts": 1.9492600549005585, "MinStdDevOfNumericAtts": 0.03638571502464851, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 1.0297655700832586, "MaxStdDevOfNumericAtts": 23786.805362394916, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": -0.7802762882712884, "Quartile3StdDevOfNumericAtts": 1.869953553845229 }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "67", "type": "numeric", "distinct": "91", "missing": "0", "target": "1", "min": "4", "max": "8", "mean": "5", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "199", "missing": "0", "identifier": "1", "distr": [] }, { "name": "CATS2D_04_AP", "index": "1", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "2", "stdev": "1" }, { "name": "CATS2D_02_PL", "index": "2", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "1" }, { "name": "SsNH2", "index": "3", "type": "numeric", "distinct": "104", "missing": "0", "min": "0", "max": "12", "mean": "4", "stdev": "3" }, { "name": "CATS2D_06_PL", "index": "4", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "5", "mean": "2", "stdev": "2" }, { "name": "CATS2D_04_DA", "index": "5", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "5", "mean": "2", "stdev": "1" }, { "name": "N.069", "index": "6", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "1" }, { "name": "nArNH2", "index": "7", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "1" }, { "name": "CATS2D_02_AP", "index": "8", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "CATS2D_00_DD", "index": "9", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "1" }, { "name": "CATS2D_00_DP", "index": "10", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "1" }, { "name": "CATS2D_00_PP", "index": "11", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "1" }, { "name": "NsNH2", "index": "12", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "1" }, { "name": "CATS2D_05_PL", "index": "13", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "SaaN", "index": "14", "type": "numeric", "distinct": "176", "missing": "0", "min": "0", "max": "22", "mean": "11", "stdev": "5" }, { "name": "CATS2D_04_PL", "index": "15", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "SpMax5_Bh.p.", "index": "16", "type": "numeric", "distinct": "159", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "N.075", "index": "17", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "5", "mean": "3", "stdev": "1" }, { "name": "NaaN", "index": "18", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "5", "mean": "3", "stdev": "1" }, { "name": "HVcpx", "index": "19", "type": "numeric", "distinct": "152", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "Eig05_AEA.dm.", "index": "20", "type": "numeric", "distinct": "160", "missing": "0", "min": "2", "max": "3", "mean": "2", "stdev": "0" }, { "name": "P_VSA_p_3", "index": "21", "type": "numeric", "distinct": "174", "missing": "0", "min": "62", "max": "251", "mean": "119", "stdev": "44" }, { "name": "P_VSA_v_3", "index": "22", "type": "numeric", "distinct": "174", "missing": "0", "min": "62", "max": "251", "mean": "119", "stdev": "44" }, { "name": "IDE", "index": "23", "type": "numeric", "distinct": "151", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "AECC", "index": "24", "type": "numeric", "distinct": "141", "missing": "0", "min": "6", "max": "20", "mean": "10", "stdev": "3" }, { "name": "Eig04_AEA.dm.", "index": "25", "type": "numeric", "distinct": "159", "missing": "0", "min": "2", "max": "3", "mean": "3", "stdev": "0" }, { "name": "Eig06_AEA.bo.", "index": "26", "type": "numeric", "distinct": "133", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "GGI10", "index": "27", "type": "numeric", "distinct": "93", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "ICR", "index": "28", "type": "numeric", "distinct": "130", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SpAD_EA.dm.", "index": "29", "type": "numeric", "distinct": "93", "missing": "0", "min": "0", "max": "19", "mean": "5", "stdev": "5" }, { "name": "DECC", "index": "30", "type": "numeric", "distinct": "136", "missing": "0", "min": "1", "max": "4", "mean": "2", "stdev": "1" }, { "name": "MSD", "index": "31", "type": "numeric", "distinct": "159", "missing": "0", "min": "4", "max": "11", "mean": "6", "stdev": "2" }, { "name": "nPyrazoles", "index": "32", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Eig03_AEA.dm.", "index": "33", "type": "numeric", "distinct": "168", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SpMax7_Bh.p.", "index": "34", "type": "numeric", "distinct": "126", "missing": "0", "min": "2", "max": "3", "mean": "3", "stdev": "0" }, { "name": "S2K", "index": "35", "type": "numeric", "distinct": "161", "missing": "0", "min": "4", "max": "14", "mean": "7", "stdev": "2" }, { "name": "SpMax6_Bh.m.", "index": "36", "type": "numeric", "distinct": "154", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "S3K", "index": "37", "type": "numeric", "distinct": "170", "missing": "0", "min": "2", "max": "8", "mean": "4", "stdev": "2" }, { "name": "SM12_EA.bo.", "index": "38", "type": "numeric", "distinct": "149", "missing": "0", "min": "17", "max": "20", "mean": "19", "stdev": "1" }, { "name": "SM13_EA.bo.", "index": "39", "type": "numeric", "distinct": "148", "missing": "0", "min": "18", "max": "22", "mean": "20", "stdev": "1" }, { "name": "SM14_EA.bo.", "index": "40", "type": "numeric", "distinct": "145", "missing": "0", "min": "20", "max": "24", "mean": "22", "stdev": "1" }, { "name": "SM15_EA.bo.", "index": "41", "type": "numeric", "distinct": "145", "missing": "0", "min": "21", "max": "25", "mean": "23", "stdev": "1" }, { "name": "ATSC4p", "index": "42", "type": "numeric", "distinct": "189", "missing": "0", "min": "4", "max": "21", "mean": "9", "stdev": "4" }, { "name": "Eig06_EA", "index": "43", "type": "numeric", "distinct": "138", "missing": "0", "min": "1", "max": "3", "mean": "2", "stdev": "0" }, { "name": "SM14_AEA.bo.", "index": "44", "type": "numeric", "distinct": "138", "missing": "0", "min": "1", "max": "3", "mean": "2", "stdev": "0" }, { "name": "AMR", "index": "45", "type": "numeric", "distinct": "176", "missing": "0", "min": "68", "max": "191", "mean": "104", "stdev": "25" }, { "name": "Chi1_EA.dm.", "index": "46", "type": "numeric", "distinct": "147", "missing": "0", "min": "2", "max": "76", "mean": "22", "stdev": "16" }, { "name": "N.", "index": "47", "type": "numeric", "distinct": "81", "missing": "0", "min": "2", "max": "22", "mean": "12", "stdev": "3" }, { "name": "SMTIV", "index": "48", "type": "numeric", "distinct": "186", "missing": "0", "min": "4446", "max": "81432", "mean": "16529", "stdev": "13186" }, { "name": "CSI", "index": "49", "type": "numeric", "distinct": "151", "missing": "0", "min": "262", "max": "2134", "mean": "632", "stdev": "364" }, { "name": "Yindex", "index": "50", "type": "numeric", "distinct": "144", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Eig06_AEA.ri.", "index": "51", "type": "numeric", "distinct": "152", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "MDDD", "index": "52", "type": "numeric", "distinct": "161", "missing": "0", "min": "10", "max": "84", "mean": "26", "stdev": "15" }, { "name": "SpMaxA_EA.bo.", "index": "53", "type": "numeric", "distinct": "85", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SpMax4_Bh.m.", "index": "54", "type": "numeric", "distinct": "170", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "Vindex", "index": "55", "type": "numeric", "distinct": "109", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "ECC", "index": "56", "type": "numeric", "distinct": "133", "missing": "0", "min": "123", "max": "946", "mean": "292", "stdev": "166" }, { "name": "PHI", "index": "57", "type": "numeric", "distinct": "161", "missing": "0", "min": "2", "max": "10", "mean": "5", "stdev": "2" }, { "name": "Eig07_AEA.dm.", "index": "58", "type": "numeric", "distinct": "158", "missing": "0", "min": "1", "max": "3", "mean": "2", "stdev": "0" }, { "name": "Eig06_AEA.dm.", "index": "59", "type": "numeric", "distinct": "153", "missing": "0", "min": "1", "max": "3", "mean": "2", "stdev": "0" }, { "name": "SpMax7_Bh.m.", "index": "60", "type": "numeric", "distinct": "152", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SpMax5_Bh.v.", "index": "61", "type": "numeric", "distinct": "172", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "Eig08_AEA.dm.", "index": "62", "type": "numeric", "distinct": "164", "missing": "0", "min": "1", "max": "3", "mean": "2", "stdev": "0" }, { "name": "SpMax5_Bh.m.", "index": "63", "type": "numeric", "distinct": "173", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "GMTIV", "index": "64", "type": "numeric", "distinct": "185", "missing": "0", "min": "6570", "max": "145677", "mean": "29042", "stdev": "23787" }, { "name": "C.030", "index": "65", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "SpMaxA_EA.ed.", "index": "66", "type": "numeric", "distinct": "113", "missing": "0", "min": "0", "max": "1", "mean": "0", "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 }