{ "data_id": "27586", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3710", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3710", "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: CHEMBL3710 (TID: 10329), and it has 669 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 21:55:36", "update_comment": null, "last_update": "2016-07-14 21:55:36", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3334580\/data_53066.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3710", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL3710 (TID: 10329), and it has 669 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": 669, "NumberOfFeatures": 68, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 67, "NumberOfSymbolicFeatures": 1, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 0.8829910313901346, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": 1.1160122816795304, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 54.21947161055708, "Quartile1SkewnessOfNumericAtts": -0.3714601965184216, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.2179875549780126, "AutoCorrelation": 0.031850299401197366, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "ClassEntropy": null, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": 0.13729552704513903, "Dimensionality": 0.10164424514200299, "MeanSkewnessOfNumericAtts": 0.36744537537068606, "Quartile2MeansOfNumericAtts": 4.01245889387145, "EquivalentNumberOfAtts": null, "MeanStdDevOfNumericAtts": 17.979531104097973, "Quartile2MutualInformation": null, "MajorityClassPercentage": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": 0.3905554823384879, "MajorityClassSize": null, "MinKurtosisOfNumericAtts": -1.7582517402203566, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.966766077402477, "MaxAttributeEntropy": null, "MaxKurtosisOfNumericAtts": 10.44217530278532, "MinMeansOfNumericAtts": 0.09614499252615843, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 594.7798295964126, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 1.808978018832303, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.52941176470588, "Quartile3MeansOfNumericAtts": 13.75890284005979, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -2.0140808646682227, "PercentageOfSymbolicFeatures": 1.4705882352941175, "Quartile3MutualInformation": null, "MaxSkewnessOfNumericAtts": 3.3116125280118998, "MinStdDevOfNumericAtts": 0.01025636473378063, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 0.8744072939800966, "MaxStdDevOfNumericAtts": 170.34634550210657, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": -0.2691798724775256, "Quartile3StdDevOfNumericAtts": 7.03790114216976 }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "67", "type": "numeric", "distinct": "415", "missing": "0", "target": "1", "min": "4", "max": "9", "mean": "7", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "669", "missing": "0", "identifier": "1", "distr": [] }, { "name": "SpMin3_Bh.s.", "index": "1", "type": "numeric", "distinct": "254", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SpMin2_Bh.s.", "index": "2", "type": "numeric", "distinct": "207", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "P_VSA_MR_2", "index": "3", "type": "numeric", "distinct": "132", "missing": "0", "min": "24", "max": "256", "mean": "102", "stdev": "41" }, { "name": "nCsp3", "index": "4", "type": "numeric", "distinct": "21", "missing": "0", "min": "0", "max": "21", "mean": "4", "stdev": "4" }, { "name": "nCs", "index": "5", "type": "numeric", "distinct": "17", "missing": "0", "min": "0", "max": "16", "mean": "2", "stdev": "4" }, { "name": "NssCH2", "index": "6", "type": "numeric", "distinct": "15", "missing": "0", "min": "0", "max": "14", "mean": "3", "stdev": "3" }, { "name": "DLS_05", "index": "7", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "SpMAD_EA.bo.", "index": "8", "type": "numeric", "distinct": "283", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "PW5", "index": "9", "type": "numeric", "distinct": "54", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "PDI", "index": "10", "type": "numeric", "distinct": "167", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Eta_beta_A", "index": "11", "type": "numeric", "distinct": "256", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "Eta_betaP_A", "index": "12", "type": "numeric", "distinct": "206", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "C.008", "index": "13", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "1" }, { "name": "P_VSA_s_2", "index": "14", "type": "numeric", "distinct": "60", "missing": "0", "min": "94", "max": "494", "mean": "233", "stdev": "72" }, { "name": "Eig02_AEA.bo.", "index": "15", "type": "numeric", "distinct": "245", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "ATSC2v", "index": "16", "type": "numeric", "distinct": "527", "missing": "0", "min": "4", "max": "19", "mean": "10", "stdev": "3" }, { "name": "nH", "index": "17", "type": "numeric", "distinct": "34", "missing": "0", "min": "10", "max": "43", "mean": "21", "stdev": "6" }, { "name": "SpMin5_Bh.s.", "index": "18", "type": "numeric", "distinct": "294", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SpMin4_Bh.s.", "index": "19", "type": "numeric", "distinct": "287", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "NsssCH", "index": "20", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "5", "mean": "1", "stdev": "1" }, { "name": "nOHs", "index": "21", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "1" }, { "name": "GATS2v", "index": "22", "type": "numeric", "distinct": "322", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "ON1V", "index": "23", "type": "numeric", "distinct": "440", "missing": "0", "min": "2", "max": "5", "mean": "3", "stdev": "1" }, { "name": "P_VSA_p_1", "index": "24", "type": "numeric", "distinct": "95", "missing": "0", "min": "94", "max": "494", "mean": "245", "stdev": "70" }, { "name": "O.056", "index": "25", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "0", "stdev": "1" }, { "name": "ATSC1v", "index": "26", "type": "numeric", "distinct": "493", "missing": "0", "min": "2", "max": "11", "mean": "6", "stdev": "2" }, { "name": "P_VSA_e_1", "index": "27", "type": "numeric", "distinct": "34", "missing": "0", "min": "94", "max": "494", "mean": "232", "stdev": "72" }, { "name": "P_VSA_m_1", "index": "28", "type": "numeric", "distinct": "32", "missing": "0", "min": "94", "max": "494", "mean": "232", "stdev": "72" }, { "name": "P_VSA_v_1", "index": "29", "type": "numeric", "distinct": "32", "missing": "0", "min": "94", "max": "494", "mean": "232", "stdev": "72" }, { "name": "P_VSA_LogP_7", "index": "30", "type": "numeric", "distinct": "88", "missing": "0", "min": "102", "max": "494", "mean": "240", "stdev": "72" }, { "name": "ATSC3v", "index": "31", "type": "numeric", "distinct": "598", "missing": "0", "min": "6", "max": "27", "mean": "13", "stdev": "4" }, { "name": "Eta_FL_A", "index": "32", "type": "numeric", "distinct": "141", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "ATS3i", "index": "33", "type": "numeric", "distinct": "401", "missing": "0", "min": "4", "max": "6", "mean": "5", "stdev": "0" }, { "name": "C.002", "index": "34", "type": "numeric", "distinct": "14", "missing": "0", "min": "0", "max": "13", "mean": "2", "stdev": "3" }, { "name": "ATSC1m", "index": "35", "type": "numeric", "distinct": "511", "missing": "0", "min": "1", "max": "20", "mean": "9", "stdev": "4" }, { "name": "P_VSA_MR_3", "index": "36", "type": "numeric", "distinct": "12", "missing": "0", "min": "0", "max": "165", "mean": "11", "stdev": "30" }, { "name": "SsOH", "index": "37", "type": "numeric", "distinct": "185", "missing": "0", "min": "0", "max": "40", "mean": "5", "stdev": "10" }, { "name": "piPC09", "index": "38", "type": "numeric", "distinct": "451", "missing": "0", "min": "4", "max": "8", "mean": "7", "stdev": "1" }, { "name": "CMC.80", "index": "39", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "SpMax1_Bh.v.", "index": "40", "type": "numeric", "distinct": "230", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "SsssN", "index": "41", "type": "numeric", "distinct": "213", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "Eig08_EA.bo.", "index": "42", "type": "numeric", "distinct": "343", "missing": "0", "min": "1", "max": "3", "mean": "2", "stdev": "0" }, { "name": "nROH", "index": "43", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "nArX", "index": "44", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "6", "mean": "1", "stdev": "2" }, { "name": "P_VSA_i_3", "index": "45", "type": "numeric", "distinct": "361", "missing": "0", "min": "188", "max": "643", "mean": "359", "stdev": "86" }, { "name": "Eta_F_A", "index": "46", "type": "numeric", "distinct": "391", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "D.Dtr09", "index": "47", "type": "numeric", "distinct": "239", "missing": "0", "min": "0", "max": "335", "mean": "77", "stdev": "82" }, { "name": "NsOH", "index": "48", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "ZM1MulPer", "index": "49", "type": "numeric", "distinct": "582", "missing": "0", "min": "265", "max": "1154", "mean": "595", "stdev": "170" }, { "name": "nBM", "index": "50", "type": "numeric", "distinct": "34", "missing": "0", "min": "1", "max": "40", "mean": "22", "stdev": "7" }, { "name": "Uc", "index": "51", "type": "numeric", "distinct": "34", "missing": "0", "min": "1", "max": "5", "mean": "4", "stdev": "1" }, { "name": "Eig07_EA.bo.", "index": "52", "type": "numeric", "distinct": "343", "missing": "0", "min": "1", "max": "3", "mean": "2", "stdev": "0" }, { "name": "ATS7i", "index": "53", "type": "numeric", "distinct": "474", "missing": "0", "min": "4", "max": "6", "mean": "5", "stdev": "0" }, { "name": "DLS_01", "index": "54", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SpDiam_EA.bo.", "index": "55", "type": "numeric", "distinct": "214", "missing": "0", "min": "5", "max": "8", "mean": "7", "stdev": "1" }, { "name": "Eig09_AEA.bo.", "index": "56", "type": "numeric", "distinct": "302", "missing": "0", "min": "1", "max": "4", "mean": "3", "stdev": "0" }, { "name": "P_VSA_m_4", "index": "57", "type": "numeric", "distinct": "51", "missing": "0", "min": "0", "max": "226", "mean": "49", "stdev": "53" }, { "name": "ATSC4v", "index": "58", "type": "numeric", "distinct": "632", "missing": "0", "min": "5", "max": "29", "mean": "14", "stdev": "4" }, { "name": "RBF", "index": "59", "type": "numeric", "distinct": "128", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "ATS3m", "index": "60", "type": "numeric", "distinct": "464", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "ZM1V", "index": "61", "type": "numeric", "distinct": "232", "missing": "0", "min": "246", "max": "1064", "mean": "548", "stdev": "154" }, { "name": "ATS2m", "index": "62", "type": "numeric", "distinct": "415", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "ZM2Mad", "index": "63", "type": "numeric", "distinct": "583", "missing": "0", "min": "106", "max": "450", "mean": "266", "stdev": "80" }, { "name": "nAB", "index": "64", "type": "numeric", "distinct": "24", "missing": "0", "min": "0", "max": "36", "mean": "18", "stdev": "7" }, { "name": "CATS2D_02_DA", "index": "65", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "5", "mean": "2", "stdev": "1" }, { "name": "DLS_cons", "index": "66", "type": "numeric", "distinct": "46", "missing": "0", "min": "0", "max": "1", "mean": "1", "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 }