{ "data_id": "27904", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4223", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4223", "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: CHEMBL4223 (TID: 30012), and it has 559 rows and 68 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 22:40:39", "update_comment": null, "last_update": "2016-07-14 22:40:39", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3343864\/data_53405.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4223", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL4223 (TID: 30012), and it has 559 rows and 68 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": 559, "NumberOfFeatures": 70, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 69, "NumberOfSymbolicFeatures": 1, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 1.8406779964221824, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": 2.9682694576603814, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 1110.680052215395, "Quartile1SkewnessOfNumericAtts": -0.6234393207642912, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.3507883212205476, "AutoCorrelation": 0.17453942652329735, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "ClassEntropy": null, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": 0.5588172668339468, "Dimensionality": 0.1252236135957066, "MeanSkewnessOfNumericAtts": 0.14230042847792956, "Quartile2MeansOfNumericAtts": 3.229726296958855, "EquivalentNumberOfAtts": null, "MeanStdDevOfNumericAtts": 1671.350167128974, "Quartile2MutualInformation": null, "MajorityClassPercentage": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": -0.06447591323992392, "MajorityClassSize": null, "MinKurtosisOfNumericAtts": -0.6496196432619143, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.5775907626949136, "MaxAttributeEntropy": null, "MaxKurtosisOfNumericAtts": 139.1679929505268, "MinMeansOfNumericAtts": 0.1466905187835421, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 37242.55277280859, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 1.7904959268561518, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.57142857142858, "Quartile3MeansOfNumericAtts": 6.307846153846153, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -1.6623333126293494, "PercentageOfSymbolicFeatures": 1.4285714285714286, "Quartile3MutualInformation": null, "MaxSkewnessOfNumericAtts": 10.754711751447529, "MinStdDevOfNumericAtts": 0.04997698074251999, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 0.6784579881045985, "MaxStdDevOfNumericAtts": 89998.63892529355, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": -0.08372422460204976, "Quartile3StdDevOfNumericAtts": 2.3531418180994805 }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "69", "type": "numeric", "distinct": "83", "missing": "0", "target": "1", "min": "5", "max": "10", "mean": "6", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "559", "missing": "0", "identifier": "1", "distr": [] }, { "name": "CATS2D_08_DP", "index": "1", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "0" }, { "name": "DECC", "index": "2", "type": "numeric", "distinct": "414", "missing": "0", "min": "1", "max": "4", "mean": "2", "stdev": "0" }, { "name": "Yindex", "index": "3", "type": "numeric", "distinct": "330", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Chi0_EA.dm.", "index": "4", "type": "numeric", "distinct": "489", "missing": "0", "min": "0", "max": "46", "mean": "18", "stdev": "8" }, { "name": "Eta_betaP", "index": "5", "type": "numeric", "distinct": "46", "missing": "0", "min": "9", "max": "35", "mean": "20", "stdev": "4" }, { "name": "Xindex", "index": "6", "type": "numeric", "distinct": "222", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "CATS2D_08_DD", "index": "7", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "Eig07_AEA.bo.", "index": "8", "type": "numeric", "distinct": "390", "missing": "0", "min": "1", "max": "4", "mean": "3", "stdev": "0" }, { "name": "IDE", "index": "9", "type": "numeric", "distinct": "420", "missing": "0", "min": "2", "max": "4", "mean": "4", "stdev": "0" }, { "name": "AECC", "index": "10", "type": "numeric", "distinct": "434", "missing": "0", "min": "5", "max": "20", "mean": "11", "stdev": "3" }, { "name": "Eig08_EA.bo.", "index": "11", "type": "numeric", "distinct": "398", "missing": "0", "min": "0", "max": "3", "mean": "2", "stdev": "1" }, { "name": "SpMax6_Bh.m.", "index": "12", "type": "numeric", "distinct": "386", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "MSD", "index": "13", "type": "numeric", "distinct": "488", "missing": "0", "min": "3", "max": "11", "mean": "7", "stdev": "1" }, { "name": "Vindex", "index": "14", "type": "numeric", "distinct": "187", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Eig06_EA", "index": "15", "type": "numeric", "distinct": "376", "missing": "0", "min": "1", "max": "3", "mean": "2", "stdev": "0" }, { "name": "SM14_AEA.bo.", "index": "16", "type": "numeric", "distinct": "376", "missing": "0", "min": "1", "max": "3", "mean": "2", "stdev": "0" }, { "name": "Eig07_EA.bo.", "index": "17", "type": "numeric", "distinct": "396", "missing": "0", "min": "0", "max": "3", "mean": "2", "stdev": "0" }, { "name": "Eig10_EA.ed.", "index": "18", "type": "numeric", "distinct": "417", "missing": "0", "min": "-3", "max": "6", "mean": "2", "stdev": "1" }, { "name": "SM05_AEA.ri.", "index": "19", "type": "numeric", "distinct": "417", "missing": "0", "min": "-3", "max": "6", "mean": "2", "stdev": "1" }, { "name": "SpMax4_Bh.m.", "index": "20", "type": "numeric", "distinct": "383", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "UNIP", "index": "21", "type": "numeric", "distinct": "170", "missing": "0", "min": "32", "max": "309", "mean": "113", "stdev": "47" }, { "name": "X2sol", "index": "22", "type": "numeric", "distinct": "492", "missing": "0", "min": "7", "max": "22", "mean": "12", "stdev": "3" }, { "name": "Chi1_EA.dm.", "index": "23", "type": "numeric", "distinct": "497", "missing": "0", "min": "0", "max": "77", "mean": "24", "stdev": "14" }, { "name": "CATS2D_04_PL", "index": "24", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "5", "mean": "1", "stdev": "1" }, { "name": "Eta_beta", "index": "25", "type": "numeric", "distinct": "134", "missing": "0", "min": "19", "max": "65", "mean": "38", "stdev": "8" }, { "name": "SMTIV", "index": "26", "type": "numeric", "distinct": "536", "missing": "0", "min": "2896", "max": "71800", "mean": "17685", "stdev": "10658" }, { "name": "Eig06_EA.bo.", "index": "27", "type": "numeric", "distinct": "410", "missing": "0", "min": "1", "max": "3", "mean": "2", "stdev": "0" }, { "name": "Eig09_AEA.dm.", "index": "28", "type": "numeric", "distinct": "408", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "0" }, { "name": "SpMax3_Bh.i.", "index": "29", "type": "numeric", "distinct": "291", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "Eig07_EA", "index": "30", "type": "numeric", "distinct": "377", "missing": "0", "min": "0", "max": "2", "mean": "2", "stdev": "0" }, { "name": "SM15_AEA.bo.", "index": "31", "type": "numeric", "distinct": "377", "missing": "0", "min": "0", "max": "2", "mean": "2", "stdev": "0" }, { "name": "Eig09_EA", "index": "32", "type": "numeric", "distinct": "352", "missing": "0", "min": "-1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "SM03_AEA.dm.", "index": "33", "type": "numeric", "distinct": "352", "missing": "0", "min": "-1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "SpMax3_Bh.m.", "index": "34", "type": "numeric", "distinct": "301", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "CATS2D_05_DL", "index": "35", "type": "numeric", "distinct": "15", "missing": "0", "min": "0", "max": "16", "mean": "3", "stdev": "3" }, { "name": "SpMin3_Bh.v.", "index": "36", "type": "numeric", "distinct": "287", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "Eig07_AEA.ri.", "index": "37", "type": "numeric", "distinct": "431", "missing": "0", "min": "1", "max": "3", "mean": "3", "stdev": "0" }, { "name": "Eig09_AEA.ri.", "index": "38", "type": "numeric", "distinct": "386", "missing": "0", "min": "0", "max": "3", "mean": "2", "stdev": "0" }, { "name": "Eig10_AEA.bo.", "index": "39", "type": "numeric", "distinct": "362", "missing": "0", "min": "0", "max": "3", "mean": "2", "stdev": "1" }, { "name": "HVcpx", "index": "40", "type": "numeric", "distinct": "407", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SpMin3_Bh.p.", "index": "41", "type": "numeric", "distinct": "283", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "ATS1m", "index": "42", "type": "numeric", "distinct": "380", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "X4sol", "index": "43", "type": "numeric", "distinct": "494", "missing": "0", "min": "4", "max": "19", "mean": "9", "stdev": "2" }, { "name": "SssNH", "index": "44", "type": "numeric", "distinct": "382", "missing": "0", "min": "0", "max": "11", "mean": "3", "stdev": "3" }, { "name": "Eig10_EA.bo.", "index": "45", "type": "numeric", "distinct": "380", "missing": "0", "min": "-1", "max": "3", "mean": "1", "stdev": "1" }, { "name": "SpMax4_Bh.i.", "index": "46", "type": "numeric", "distinct": "377", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "XMOD", "index": "47", "type": "numeric", "distinct": "532", "missing": "0", "min": "48", "max": "143", "mean": "87", "stdev": "18" }, { "name": "Eig10_AEA.ed.", "index": "48", "type": "numeric", "distinct": "372", "missing": "0", "min": "2", "max": "5", "mean": "4", "stdev": "1" }, { "name": "Eig10_AEA.ri.", "index": "49", "type": "numeric", "distinct": "397", "missing": "0", "min": "0", "max": "3", "mean": "2", "stdev": "1" }, { "name": "MW", "index": "50", "type": "numeric", "distinct": "497", "missing": "0", "min": "211", "max": "642", "mean": "386", "stdev": "81" }, { "name": "CATS2D_04_DL", "index": "51", "type": "numeric", "distinct": "14", "missing": "0", "min": "0", "max": "14", "mean": "4", "stdev": "3" }, { "name": "P_VSA_s_3", "index": "52", "type": "numeric", "distinct": "497", "missing": "0", "min": "8", "max": "97", "mean": "39", "stdev": "17" }, { "name": "Eig10_EA", "index": "53", "type": "numeric", "distinct": "357", "missing": "0", "min": "-1", "max": "2", "mean": "1", "stdev": "1" }, { "name": "SM04_AEA.dm.", "index": "54", "type": "numeric", "distinct": "357", "missing": "0", "min": "-1", "max": "2", "mean": "1", "stdev": "1" }, { "name": "CATS2D_02_DA", "index": "55", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "6", "mean": "2", "stdev": "1" }, { "name": "Eig07_EA.ed.", "index": "56", "type": "numeric", "distinct": "463", "missing": "0", "min": "0", "max": "8", "mean": "4", "stdev": "1" }, { "name": "SM02_AEA.ri.", "index": "57", "type": "numeric", "distinct": "463", "missing": "0", "min": "0", "max": "8", "mean": "4", "stdev": "1" }, { "name": "CSI", "index": "58", "type": "numeric", "distinct": "399", "missing": "0", "min": "154", "max": "2039", "mean": "690", "stdev": "303" }, { "name": "NssNH", "index": "59", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "Eig06_AEA.ri.", "index": "60", "type": "numeric", "distinct": "427", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "Eig06_AEA.bo.", "index": "61", "type": "numeric", "distinct": "391", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "Eig08_EA.ed.", "index": "62", "type": "numeric", "distinct": "439", "missing": "0", "min": "-1", "max": "8", "mean": "4", "stdev": "1" }, { "name": "SM03_AEA.ri.", "index": "63", "type": "numeric", "distinct": "439", "missing": "0", "min": "-1", "max": "8", "mean": "4", "stdev": "1" }, { "name": "Wap", "index": "64", "type": "numeric", "distinct": "486", "missing": "0", "min": "1081", "max": "1325540", "mean": "37243", "stdev": "89999" }, { "name": "IDMT", "index": "65", "type": "numeric", "distinct": "511", "missing": "0", "min": "2088", "max": "94747", "mean": "20123", "stdev": "14121" }, { "name": "TPC", "index": "66", "type": "numeric", "distinct": "432", "missing": "0", "min": "5", "max": "11", "mean": "8", "stdev": "1" }, { "name": "RDCHI", "index": "67", "type": "numeric", "distinct": "448", "missing": "0", "min": "3", "max": "6", "mean": "4", "stdev": "1" }, { "name": "Eig06_EA.ed.", "index": "68", "type": "numeric", "distinct": "470", "missing": "0", "min": "1", "max": "9", "mean": "5", "stdev": "1" } ], "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 }