{ "data_id": "38792", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4471", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4471", "version": 12, "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: CHEMBL4471 (TID: 10403), and it has 935 rows and 70 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": "2016-07-16 05:31:20", "update_comment": null, "last_update": "2016-07-16 05:31:20", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3652799\/data_53702.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4471", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL4471 (TID: 10403), and it has 935 rows and 70 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": 935, "NumberOfFeatures": 72, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 71, "NumberOfSymbolicFeatures": 1, "Quartile3AttributeEntropy": null, "MaxKurtosisOfNumericAtts": 39.64060233246144, "MinMeansOfNumericAtts": -1.174286631016044, "PercentageOfInstancesWithMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 10.248156404087396, "MaxMeansOfNumericAtts": 285.4992106951872, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3MeansOfNumericAtts": 23.9361807486631, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.61111111111111, "Quartile3MutualInformation": null, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -5.991971816627668, "PercentageOfSymbolicFeatures": 1.3888888888888888, "Quartile3SkewnessOfNumericAtts": 0.9135355209386008, "MaxSkewnessOfNumericAtts": 5.419613867652436, "MinStdDevOfNumericAtts": 0.12226233743813328, "Quartile1AttributeEntropy": null, "Quartile3StdDevOfNumericAtts": 1.7239313927376712, "MaxStdDevOfNumericAtts": 173.97720022495804, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": 0.38129778267664527, "StdvNominalAttDistinctValues": null, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 1.460962566844917, "MeanKurtosisOfNumericAtts": 7.5123110082277895, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 18.34329396701062, "Quartile1SkewnessOfNumericAtts": -0.7131398176654192, "AutoCorrelation": 0.0154635974304072, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.2275325630724073, "ClassEntropy": null, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "Dimensionality": 0.07700534759358289, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": 0.9251243503456332, "EquivalentNumberOfAtts": null, "MeanSkewnessOfNumericAtts": 0.6024376591158933, "Quartile2MeansOfNumericAtts": 3.707531550802139, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 10.815742961827969, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": -0.44950652151696735, "Quartile2StdDevOfNumericAtts": 0.6405004214033084, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.5959172768360148, "PercentageOfBinaryFeatures": 0 }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "71", "type": "numeric", "distinct": "529", "missing": "0", "target": "1", "min": "4", "max": "9", "mean": "5", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "935", "missing": "0", "identifier": "1", "distr": [] }, { "name": "nRCONR2", "index": "1", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "CATS2D_02_DD", "index": "2", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "ATS8p", "index": "3", "type": "numeric", "distinct": "684", "missing": "0", "min": "1", "max": "6", "mean": "4", "stdev": "1" }, { "name": "SpMin2_Bh.s.", "index": "4", "type": "numeric", "distinct": "366", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "CATS2D_09_DA", "index": "5", "type": "numeric", "distinct": "19", "missing": "0", "min": "0", "max": "43", "mean": "3", "stdev": "4" }, { "name": "CATS2D_07_DD", "index": "6", "type": "numeric", "distinct": "8", "missing": "0", "min": "0", "max": "7", "mean": "1", "stdev": "1" }, { "name": "SsssCH", "index": "7", "type": "numeric", "distinct": "477", "missing": "0", "min": "-40", "max": "1", "mean": "-1", "stdev": "4" }, { "name": "CATS2D_04_PL", "index": "8", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "8", "mean": "1", "stdev": "1" }, { "name": "SpMax5_Bh.v.", "index": "9", "type": "numeric", "distinct": "482", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "ATSC7s", "index": "10", "type": "numeric", "distinct": "887", "missing": "0", "min": "4", "max": "2019", "mean": "144", "stdev": "174" }, { "name": "CATS2D_07_DP", "index": "11", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "ATS7m", "index": "12", "type": "numeric", "distinct": "685", "missing": "0", "min": "1", "max": "6", "mean": "4", "stdev": "1" }, { "name": "SpMax6_Bh.v.", "index": "13", "type": "numeric", "distinct": "486", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SpMin4_Bh.v.", "index": "14", "type": "numeric", "distinct": "376", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "CATS2D_08_DA", "index": "15", "type": "numeric", "distinct": "18", "missing": "0", "min": "0", "max": "35", "mean": "3", "stdev": "4" }, { "name": "GATS1m", "index": "16", "type": "numeric", "distinct": "373", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "CATS2D_05_AA", "index": "17", "type": "numeric", "distinct": "15", "missing": "0", "min": "0", "max": "28", "mean": "3", "stdev": "3" }, { "name": "NsssCH", "index": "18", "type": "numeric", "distinct": "11", "missing": "0", "min": "0", "max": "23", "mean": "1", "stdev": "2" }, { "name": "C.008", "index": "19", "type": "numeric", "distinct": "10", "missing": "0", "min": "0", "max": "21", "mean": "1", "stdev": "2" }, { "name": "SpMax5_Bh.e.", "index": "20", "type": "numeric", "distinct": "454", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "N.067", "index": "21", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "1" }, { "name": "SpMin5_Bh.s.", "index": "22", "type": "numeric", "distinct": "441", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "MAXDN", "index": "23", "type": "numeric", "distinct": "673", "missing": "0", "min": "1", "max": "6", "mean": "4", "stdev": "1" }, { "name": "SpMax5_Bh.i.", "index": "24", "type": "numeric", "distinct": "451", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SpDiam_AEA.bo.", "index": "25", "type": "numeric", "distinct": "424", "missing": "0", "min": "5", "max": "6", "mean": "6", "stdev": "0" }, { "name": "SdO", "index": "26", "type": "numeric", "distinct": "794", "missing": "0", "min": "0", "max": "447", "mean": "39", "stdev": "37" }, { "name": "ATS4s", "index": "27", "type": "numeric", "distinct": "617", "missing": "0", "min": "5", "max": "8", "mean": "6", "stdev": "0" }, { "name": "SpMin6_Bh.v.", "index": "28", "type": "numeric", "distinct": "434", "missing": "0", "min": "0", "max": "2", "mean": "2", "stdev": "0" }, { "name": "SpMin4_Bh.p.", "index": "29", "type": "numeric", "distinct": "386", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "S1K", "index": "30", "type": "numeric", "distinct": "662", "missing": "0", "min": "7", "max": "157", "mean": "25", "stdev": "12" }, { "name": "ATSC1s", "index": "31", "type": "numeric", "distinct": "839", "missing": "0", "min": "2", "max": "258", "mean": "25", "stdev": "24" }, { "name": "S2K", "index": "32", "type": "numeric", "distinct": "716", "missing": "0", "min": "3", "max": "79", "mean": "11", "stdev": "6" }, { "name": "Eig01_AEA.ed.", "index": "33", "type": "numeric", "distinct": "361", "missing": "0", "min": "5", "max": "9", "mean": "7", "stdev": "0" }, { "name": "SpMax_AEA.ed.", "index": "34", "type": "numeric", "distinct": "361", "missing": "0", "min": "5", "max": "9", "mean": "7", "stdev": "0" }, { "name": "Eig03_EA.ri.", "index": "35", "type": "numeric", "distinct": "474", "missing": "0", "min": "1", "max": "3", "mean": "3", "stdev": "0" }, { "name": "P_VSA_LogP_7", "index": "36", "type": "numeric", "distinct": "151", "missing": "0", "min": "47", "max": "1413", "mean": "285", "stdev": "142" }, { "name": "Eig01_EA.ed.", "index": "37", "type": "numeric", "distinct": "440", "missing": "0", "min": "7", "max": "17", "mean": "12", "stdev": "1" }, { "name": "SM10_AEA.dm.", "index": "38", "type": "numeric", "distinct": "440", "missing": "0", "min": "7", "max": "17", "mean": "12", "stdev": "1" }, { "name": "SpMax_EA.ed.", "index": "39", "type": "numeric", "distinct": "440", "missing": "0", "min": "7", "max": "17", "mean": "12", "stdev": "1" }, { "name": "SM15_AEA.ed.", "index": "40", "type": "numeric", "distinct": "616", "missing": "0", "min": "26", "max": "33", "mean": "30", "stdev": "1" }, { "name": "ATSC2s", "index": "41", "type": "numeric", "distinct": "872", "missing": "0", "min": "6", "max": "691", "mean": "69", "stdev": "62" }, { "name": "SpMin5_Bh.i.", "index": "42", "type": "numeric", "distinct": "455", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "Eig01_EA", "index": "43", "type": "numeric", "distinct": "353", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SM09_AEA.bo.", "index": "44", "type": "numeric", "distinct": "353", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SpDiam_EA", "index": "45", "type": "numeric", "distinct": "353", "missing": "0", "min": "5", "max": "6", "mean": "5", "stdev": "0" }, { "name": "SpMax_EA", "index": "46", "type": "numeric", "distinct": "353", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "ATSC5e", "index": "47", "type": "numeric", "distinct": "663", "missing": "0", "min": "0", "max": "11", "mean": "1", "stdev": "1" }, { "name": "SM15_EA.ed.", "index": "48", "type": "numeric", "distinct": "602", "missing": "0", "min": "30", "max": "43", "mean": "37", "stdev": "2" }, { "name": "SM05_EA", "index": "49", "type": "numeric", "distinct": "137", "missing": "0", "min": "5", "max": "8", "mean": "7", "stdev": "0" }, { "name": "SM14_AEA.ed.", "index": "50", "type": "numeric", "distinct": "621", "missing": "0", "min": "25", "max": "30", "mean": "28", "stdev": "1" }, { "name": "SpMin6_Bh.i.", "index": "51", "type": "numeric", "distinct": "463", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "Eig03_AEA.ri.", "index": "52", "type": "numeric", "distinct": "468", "missing": "0", "min": "2", "max": "4", "mean": "4", "stdev": "0" }, { "name": "SM14_EA.ed.", "index": "53", "type": "numeric", "distinct": "613", "missing": "0", "min": "28", "max": "40", "mean": "35", "stdev": "2" }, { "name": "SM13_EA.ed.", "index": "54", "type": "numeric", "distinct": "603", "missing": "0", "min": "26", "max": "37", "mean": "32", "stdev": "1" }, { "name": "SpMin1_Bh.s.", "index": "55", "type": "numeric", "distinct": "322", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "GATS1p", "index": "56", "type": "numeric", "distinct": "485", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "SM11_EA.ed.", "index": "57", "type": "numeric", "distinct": "629", "missing": "0", "min": "22", "max": "31", "mean": "27", "stdev": "1" }, { "name": "Eta_B", "index": "58", "type": "numeric", "distinct": "360", "missing": "0", "min": "0", "max": "6", "mean": "1", "stdev": "0" }, { "name": "SpMin6_Bh.m.", "index": "59", "type": "numeric", "distinct": "391", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "SM12_EA.ed.", "index": "60", "type": "numeric", "distinct": "606", "missing": "0", "min": "24", "max": "34", "mean": "30", "stdev": "1" }, { "name": "ATSC3s", "index": "61", "type": "numeric", "distinct": "873", "missing": "0", "min": "7", "max": "1119", "mean": "83", "stdev": "94" }, { "name": "SpDiam_EA.ed.", "index": "62", "type": "numeric", "distinct": "525", "missing": "0", "min": "13", "max": "27", "mean": "19", "stdev": "2" }, { "name": "SpMax8_Bh.p.", "index": "63", "type": "numeric", "distinct": "461", "missing": "0", "min": "1", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SM03_EA.ed.", "index": "64", "type": "numeric", "distinct": "374", "missing": "0", "min": "6", "max": "9", "mean": "8", "stdev": "0" }, { "name": "ATSC6s", "index": "65", "type": "numeric", "distinct": "887", "missing": "0", "min": "9", "max": "1801", "mean": "127", "stdev": "153" }, { "name": "X0", "index": "66", "type": "numeric", "distinct": "418", "missing": "0", "min": "9", "max": "136", "mean": "24", "stdev": "10" }, { "name": "SM13_AEA.ed.", "index": "67", "type": "numeric", "distinct": "617", "missing": "0", "min": "23", "max": "28", "mean": "26", "stdev": "1" }, { "name": "SM07_EA", "index": "68", "type": "numeric", "distinct": "486", "missing": "0", "min": "7", "max": "11", "mean": "9", "stdev": "0" }, { "name": "SM08_EA", "index": "69", "type": "numeric", "distinct": "584", "missing": "0", "min": "9", "max": "12", "mean": "10", "stdev": "0" }, { "name": "SM12_AEA.ed.", "index": "70", "type": "numeric", "distinct": "615", "missing": "0", "min": "21", "max": "26", "mean": "24", "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 }