{ "data_id": "35275", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL2414", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL2414", "version": 11, "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: CHEMBL2414 (TID: 10579), and it has 388 rows and 67 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 17:36:14", "update_comment": null, "last_update": "2016-07-15 17:36:14", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3553148\/data_53177.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL2414", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL2414 (TID: 10579), and it has 388 rows and 67 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": 388, "NumberOfFeatures": 69, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 68, "NumberOfSymbolicFeatures": 1, "ClassEntropy": null, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "Dimensionality": 0.17783505154639176, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": 0.8347254010160607, "EquivalentNumberOfAtts": null, "MeanSkewnessOfNumericAtts": 0.19464113476467382, "Quartile2MeansOfNumericAtts": 3.840868556701031, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 1.257706981067353, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": -0.38189629469141845, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -0.9365939400998586, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.39637004418636357, "MaxKurtosisOfNumericAtts": 243.5477045082806, "MinMeansOfNumericAtts": -1.1588943298969079, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 91.55046391752578, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 4.230295107995818, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.55072463768117, "Quartile3MeansOfNumericAtts": 6.354059922680412, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -2.598751996475002, "PercentageOfSymbolicFeatures": 1.4492753623188406, "Quartile3MutualInformation": null, "MaxSkewnessOfNumericAtts": 13.868476497824817, "MinStdDevOfNumericAtts": 0.004815991259403433, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 0.7499767946425624, "MaxStdDevOfNumericAtts": 33.12598499599324, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": 0.14481341304502582, "Quartile3StdDevOfNumericAtts": 0.674967887891432, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 0.6198453608247418, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": 7.308705078992478, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 5.7311445952092175, "Quartile1SkewnessOfNumericAtts": -0.7921995643640363, "AutoCorrelation": 0.1884521963824292, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.1540893702296346 }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "68", "type": "numeric", "distinct": "198", "missing": "0", "target": "1", "min": "4", "max": "8", "mean": "6", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "388", "missing": "0", "identifier": "1", "distr": [] }, { "name": "piPC09", "index": "1", "type": "numeric", "distinct": "272", "missing": "0", "min": "2", "max": "8", "mean": "7", "stdev": "1" }, { "name": "piPC07", "index": "2", "type": "numeric", "distinct": "266", "missing": "0", "min": "3", "max": "7", "mean": "6", "stdev": "1" }, { "name": "piPC06", "index": "3", "type": "numeric", "distinct": "262", "missing": "0", "min": "3", "max": "7", "mean": "6", "stdev": "0" }, { "name": "piPC10", "index": "4", "type": "numeric", "distinct": "278", "missing": "0", "min": "0", "max": "9", "mean": "7", "stdev": "1" }, { "name": "piPC08", "index": "5", "type": "numeric", "distinct": "268", "missing": "0", "min": "2", "max": "8", "mean": "7", "stdev": "1" }, { "name": "piPC05", "index": "6", "type": "numeric", "distinct": "250", "missing": "0", "min": "3", "max": "6", "mean": "6", "stdev": "0" }, { "name": "SM09_EA.bo.", "index": "7", "type": "numeric", "distinct": "254", "missing": "0", "min": "11", "max": "15", "mean": "14", "stdev": "1" }, { "name": "SM10_EA.bo.", "index": "8", "type": "numeric", "distinct": "258", "missing": "0", "min": "12", "max": "17", "mean": "15", "stdev": "1" }, { "name": "SpMax1_Bh.i.", "index": "9", "type": "numeric", "distinct": "154", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "Eig02_EA.bo.", "index": "10", "type": "numeric", "distinct": "158", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SM05_EA.bo.", "index": "11", "type": "numeric", "distinct": "227", "missing": "0", "min": "6", "max": "9", "mean": "8", "stdev": "0" }, { "name": "SM12_AEA.ri.", "index": "12", "type": "numeric", "distinct": "158", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "Eig02_AEA.bo.", "index": "13", "type": "numeric", "distinct": "188", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SpMax3_Bh.m.", "index": "14", "type": "numeric", "distinct": "215", "missing": "0", "min": "3", "max": "11", "mean": "4", "stdev": "0" }, { "name": "SM04_EA.bo.", "index": "15", "type": "numeric", "distinct": "247", "missing": "0", "min": "6", "max": "8", "mean": "7", "stdev": "0" }, { "name": "CATS2D_04_AA", "index": "16", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "6", "mean": "1", "stdev": "1" }, { "name": "C.035", "index": "17", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "Cl.090", "index": "18", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "P_VSA_LogP_6", "index": "19", "type": "numeric", "distinct": "42", "missing": "0", "min": "0", "max": "59", "mean": "13", "stdev": "15" }, { "name": "nPyrazoles", "index": "20", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "SpMax1_Bh.m.", "index": "21", "type": "numeric", "distinct": "139", "missing": "0", "min": "4", "max": "11", "mean": "4", "stdev": "1" }, { "name": "piPC04", "index": "22", "type": "numeric", "distinct": "239", "missing": "0", "min": "3", "max": "6", "mean": "5", "stdev": "0" }, { "name": "MPC10", "index": "23", "type": "numeric", "distinct": "169", "missing": "0", "min": "0", "max": "6", "mean": "5", "stdev": "1" }, { "name": "PCD", "index": "24", "type": "numeric", "distinct": "274", "missing": "0", "min": "0", "max": "5", "mean": "3", "stdev": "1" }, { "name": "SpMax2_Bh.v.", "index": "25", "type": "numeric", "distinct": "169", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "CATS2D_02_DA", "index": "26", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "6", "mean": "2", "stdev": "1" }, { "name": "C.029", "index": "27", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "0" }, { "name": "GATS4m", "index": "28", "type": "numeric", "distinct": "252", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "MPC09", "index": "29", "type": "numeric", "distinct": "164", "missing": "0", "min": "2", "max": "6", "mean": "5", "stdev": "0" }, { "name": "piID", "index": "30", "type": "numeric", "distinct": "275", "missing": "0", "min": "5", "max": "14", "mean": "11", "stdev": "1" }, { "name": "nThiophenes", "index": "31", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "Eig05_AEA.bo.", "index": "32", "type": "numeric", "distinct": "216", "missing": "0", "min": "2", "max": "4", "mean": "4", "stdev": "0" }, { "name": "CATS2D_09_DD", "index": "33", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "Eig05_EA.bo.", "index": "34", "type": "numeric", "distinct": "197", "missing": "0", "min": "1", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SM15_AEA.ri.", "index": "35", "type": "numeric", "distinct": "197", "missing": "0", "min": "1", "max": "4", "mean": "3", "stdev": "0" }, { "name": "GATS3i", "index": "36", "type": "numeric", "distinct": "253", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SM03_EA.bo.", "index": "37", "type": "numeric", "distinct": "85", "missing": "0", "min": "4", "max": "6", "mean": "5", "stdev": "0" }, { "name": "MATS2m", "index": "38", "type": "numeric", "distinct": "193", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "X5A", "index": "39", "type": "numeric", "distinct": "27", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SpMax3_Bh.e.", "index": "40", "type": "numeric", "distinct": "177", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "CATS2D_03_DL", "index": "41", "type": "numeric", "distinct": "8", "missing": "0", "min": "0", "max": "7", "mean": "2", "stdev": "1" }, { "name": "IC1", "index": "42", "type": "numeric", "distinct": "291", "missing": "0", "min": "2", "max": "4", "mean": "4", "stdev": "0" }, { "name": "MATS2p", "index": "43", "type": "numeric", "distinct": "204", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "MATS3i", "index": "44", "type": "numeric", "distinct": "244", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "SpMax2_Bh.e.", "index": "45", "type": "numeric", "distinct": "156", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "nS", "index": "46", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "SM13_EA.bo.", "index": "47", "type": "numeric", "distinct": "249", "missing": "0", "min": "15", "max": "21", "mean": "20", "stdev": "1" }, { "name": "TPSA.Tot.", "index": "48", "type": "numeric", "distinct": "146", "missing": "0", "min": "18", "max": "165", "mean": "92", "stdev": "33" }, { "name": "SM07_EA.bo.", "index": "49", "type": "numeric", "distinct": "261", "missing": "0", "min": "9", "max": "12", "mean": "11", "stdev": "1" }, { "name": "MPC08", "index": "50", "type": "numeric", "distinct": "151", "missing": "0", "min": "2", "max": "6", "mean": "5", "stdev": "0" }, { "name": "SM08_AEA.bo.", "index": "51", "type": "numeric", "distinct": "259", "missing": "0", "min": "12", "max": "14", "mean": "13", "stdev": "0" }, { "name": "SM06_EA.bo.", "index": "52", "type": "numeric", "distinct": "267", "missing": "0", "min": "8", "max": "10", "mean": "10", "stdev": "0" }, { "name": "SM08_EA.bo.", "index": "53", "type": "numeric", "distinct": "260", "missing": "0", "min": "10", "max": "13", "mean": "12", "stdev": "1" }, { "name": "X4A", "index": "54", "type": "numeric", "distinct": "36", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "GATS4p", "index": "55", "type": "numeric", "distinct": "257", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "NaaS", "index": "56", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "MATS8e", "index": "57", "type": "numeric", "distinct": "263", "missing": "0", "min": "-1", "max": "0", "mean": "0", "stdev": "0" }, { "name": "N.073", "index": "58", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "SddssS", "index": "59", "type": "numeric", "distinct": "96", "missing": "0", "min": "-7", "max": "0", "mean": "-1", "stdev": "2" }, { "name": "nAB", "index": "60", "type": "numeric", "distinct": "12", "missing": "0", "min": "0", "max": "28", "mean": "16", "stdev": "4" }, { "name": "SpMax1_Bh.e.", "index": "61", "type": "numeric", "distinct": "131", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "SaaN", "index": "62", "type": "numeric", "distinct": "201", "missing": "0", "min": "0", "max": "15", "mean": "4", "stdev": "4" }, { "name": "X3A", "index": "63", "type": "numeric", "distinct": "41", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SpMax3_Bh.p.", "index": "64", "type": "numeric", "distinct": "190", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "C.005", "index": "65", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "GATS2p", "index": "66", "type": "numeric", "distinct": "228", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Ui", "index": "67", "type": "numeric", "distinct": "24", "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 }