{ "data_id": "33741", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL326", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL326", "version": 9, "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: CHEMBL326 (TID: 12742), and it has 737 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 13:34:11", "update_comment": null, "last_update": "2016-07-15 13:34:11", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3512907\/data_53279.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL326", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL326 (TID: 12742), and it has 737 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": 737, "NumberOfFeatures": 69, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 68, "NumberOfSymbolicFeatures": 1, "ClassEntropy": null, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "Dimensionality": 0.09362279511533243, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": 17.37009692577242, "EquivalentNumberOfAtts": null, "MeanSkewnessOfNumericAtts": 2.2678632910207077, "Quartile2MeansOfNumericAtts": 14.995147218453187, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 2959.3842558778265, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": 2.5218459694596245, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -0.5997914645961724, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 4.076590022558659, "MaxKurtosisOfNumericAtts": 123.91496434042818, "MinMeansOfNumericAtts": 0.10455766621438263, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 30776.303914518332, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 21.084622889667518, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.55072463768117, "Quartile3MeansOfNumericAtts": 27.315860583446405, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -2.929064921446073, "PercentageOfSymbolicFeatures": 1.4492753623188406, "Quartile3MutualInformation": null, "MaxSkewnessOfNumericAtts": 10.8940748289039, "MinStdDevOfNumericAtts": 0.028953575077413723, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 2.9854229927823166, "MaxStdDevOfNumericAtts": 85047.36485823452, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": 6.020023517978796, "Quartile3StdDevOfNumericAtts": 8.822886663753788, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 1.4970244233378562, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": 24.47507316628446, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 1305.1736077101139, "Quartile1SkewnessOfNumericAtts": -0.663279501506516, "AutoCorrelation": -0.14031521739130334, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.5192907678981826 }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "68", "type": "numeric", "distinct": "515", "missing": "0", "target": "1", "min": "4", "max": "11", "mean": "7", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "737", "missing": "0", "identifier": "1", "distr": [] }, { "name": "Chi1_EA.bo.", "index": "1", "type": "numeric", "distinct": "537", "missing": "0", "min": "2", "max": "40", "mean": "13", "stdev": "4" }, { "name": "ATS3e", "index": "2", "type": "numeric", "distinct": "439", "missing": "0", "min": "3", "max": "6", "mean": "5", "stdev": "0" }, { "name": "SpMax8_Bh.m.", "index": "3", "type": "numeric", "distinct": "339", "missing": "0", "min": "0", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SpMin6_Bh.s.", "index": "4", "type": "numeric", "distinct": "298", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "TIC5", "index": "5", "type": "numeric", "distinct": "467", "missing": "0", "min": "26", "max": "1140", "mean": "287", "stdev": "104" }, { "name": "ATSC1v", "index": "6", "type": "numeric", "distinct": "510", "missing": "0", "min": "1", "max": "27", "mean": "7", "stdev": "2" }, { "name": "nH", "index": "7", "type": "numeric", "distinct": "45", "missing": "0", "min": "5", "max": "108", "mean": "27", "stdev": "10" }, { "name": "TIC3", "index": "8", "type": "numeric", "distinct": "549", "missing": "0", "min": "43", "max": "1014", "mean": "276", "stdev": "96" }, { "name": "P_VSA_LogP_7", "index": "9", "type": "numeric", "distinct": "90", "missing": "0", "min": "24", "max": "1177", "mean": "301", "stdev": "111" }, { "name": "ATS3i", "index": "10", "type": "numeric", "distinct": "448", "missing": "0", "min": "3", "max": "6", "mean": "5", "stdev": "0" }, { "name": "UNIP", "index": "11", "type": "numeric", "distinct": "194", "missing": "0", "min": "11", "max": "1673", "mean": "138", "stdev": "131" }, { "name": "ATSC1p", "index": "12", "type": "numeric", "distinct": "509", "missing": "0", "min": "1", "max": "18", "mean": "5", "stdev": "2" }, { "name": "Eig08_EA", "index": "13", "type": "numeric", "distinct": "354", "missing": "0", "min": "-1", "max": "3", "mean": "1", "stdev": "0" }, { "name": "SM02_AEA.dm.", "index": "14", "type": "numeric", "distinct": "354", "missing": "0", "min": "-1", "max": "3", "mean": "1", "stdev": "0" }, { "name": "SNar", "index": "15", "type": "numeric", "distinct": "190", "missing": "0", "min": "3", "max": "63", "mean": "22", "stdev": "6" }, { "name": "Xt", "index": "16", "type": "numeric", "distinct": "117", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "RDCHI", "index": "17", "type": "numeric", "distinct": "457", "missing": "0", "min": "2", "max": "10", "mean": "4", "stdev": "1" }, { "name": "Chi0_EA.bo.", "index": "18", "type": "numeric", "distinct": "501", "missing": "0", "min": "4", "max": "57", "mean": "18", "stdev": "5" }, { "name": "Eta_betaS", "index": "19", "type": "numeric", "distinct": "93", "missing": "0", "min": "4", "max": "58", "mean": "19", "stdev": "5" }, { "name": "Eta_L", "index": "20", "type": "numeric", "distinct": "595", "missing": "0", "min": "2", "max": "26", "mean": "7", "stdev": "2" }, { "name": "GMTI", "index": "21", "type": "numeric", "distinct": "527", "missing": "0", "min": "130", "max": "433871", "mean": "15338", "stdev": "33426" }, { "name": "SMTI", "index": "22", "type": "numeric", "distinct": "526", "missing": "0", "min": "188", "max": "412058", "mean": "14512", "stdev": "31437" }, { "name": "Eig08_AEA.ri.", "index": "23", "type": "numeric", "distinct": "402", "missing": "0", "min": "0", "max": "4", "mean": "2", "stdev": "0" }, { "name": "Chi1_EA.ri.", "index": "24", "type": "numeric", "distinct": "647", "missing": "0", "min": "3", "max": "49", "mean": "17", "stdev": "5" }, { "name": "Psi_i_0", "index": "25", "type": "numeric", "distinct": "550", "missing": "0", "min": "4", "max": "66", "mean": "21", "stdev": "6" }, { "name": "ATSC4m", "index": "26", "type": "numeric", "distinct": "677", "missing": "0", "min": "5", "max": "137", "mean": "37", "stdev": "14" }, { "name": "SpMaxA_AEA.ed.", "index": "27", "type": "numeric", "distinct": "171", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "IDMT", "index": "28", "type": "numeric", "distinct": "533", "missing": "0", "min": "218", "max": "1131670", "mean": "30776", "stdev": "85047" }, { "name": "Xu", "index": "29", "type": "numeric", "distinct": "525", "missing": "0", "min": "7", "max": "73", "mean": "28", "stdev": "6" }, { "name": "CSI", "index": "30", "type": "numeric", "distinct": "406", "missing": "0", "min": "47", "max": "9724", "mean": "824", "stdev": "769" }, { "name": "Eig08_EA.ri.", "index": "31", "type": "numeric", "distinct": "416", "missing": "0", "min": "-1", "max": "3", "mean": "1", "stdev": "0" }, { "name": "ATS4i", "index": "32", "type": "numeric", "distinct": "479", "missing": "0", "min": "3", "max": "7", "mean": "5", "stdev": "0" }, { "name": "SMTIV", "index": "33", "type": "numeric", "distinct": "656", "missing": "0", "min": "512", "max": "617646", "mean": "23115", "stdev": "47507" }, { "name": "Eig10_EA", "index": "34", "type": "numeric", "distinct": "349", "missing": "0", "min": "-2", "max": "2", "mean": "1", "stdev": "1" }, { "name": "SM04_AEA.dm.", "index": "35", "type": "numeric", "distinct": "349", "missing": "0", "min": "-2", "max": "2", "mean": "1", "stdev": "1" }, { "name": "Psi_i_1", "index": "36", "type": "numeric", "distinct": "604", "missing": "0", "min": "3", "max": "52", "mean": "17", "stdev": "5" }, { "name": "ECC", "index": "37", "type": "numeric", "distinct": "311", "missing": "0", "min": "29", "max": "4598", "mean": "381", "stdev": "359" }, { "name": "ATS4e", "index": "38", "type": "numeric", "distinct": "478", "missing": "0", "min": "3", "max": "6", "mean": "5", "stdev": "0" }, { "name": "Eig10_AEA.ri.", "index": "39", "type": "numeric", "distinct": "425", "missing": "0", "min": "-1", "max": "3", "mean": "2", "stdev": "1" }, { "name": "SpMaxA_AEA.ri.", "index": "40", "type": "numeric", "distinct": "135", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "Eig14_AEA.ri.", "index": "41", "type": "numeric", "distinct": "441", "missing": "0", "min": "-1", "max": "3", "mean": "1", "stdev": "1" }, { "name": "Eig10_EA.ri.", "index": "42", "type": "numeric", "distinct": "415", "missing": "0", "min": "-2", "max": "2", "mean": "1", "stdev": "1" }, { "name": "Chi1_AEA.bo.", "index": "43", "type": "numeric", "distinct": "481", "missing": "0", "min": "3", "max": "47", "mean": "16", "stdev": "4" }, { "name": "Chi1_AEA.dm.", "index": "44", "type": "numeric", "distinct": "481", "missing": "0", "min": "3", "max": "47", "mean": "16", "stdev": "4" }, { "name": "Chi1_AEA.ed.", "index": "45", "type": "numeric", "distinct": "481", "missing": "0", "min": "3", "max": "47", "mean": "16", "stdev": "4" }, { "name": "Chi1_AEA.ri.", "index": "46", "type": "numeric", "distinct": "481", "missing": "0", "min": "3", "max": "47", "mean": "16", "stdev": "4" }, { "name": "Chi1_EA", "index": "47", "type": "numeric", "distinct": "481", "missing": "0", "min": "3", "max": "47", "mean": "16", "stdev": "4" }, { "name": "SpMaxA_EA.ri.", "index": "48", "type": "numeric", "distinct": "112", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "ATSC3m", "index": "49", "type": "numeric", "distinct": "642", "missing": "0", "min": "4", "max": "112", "mean": "33", "stdev": "11" }, { "name": "Chi1_EA.ed.", "index": "50", "type": "numeric", "distinct": "500", "missing": "0", "min": "1", "max": "18", "mean": "5", "stdev": "2" }, { "name": "IDET", "index": "51", "type": "numeric", "distinct": "530", "missing": "0", "min": "46", "max": "23392", "mean": "1729", "stdev": "1908" }, { "name": "Eig08_AEA.dm.", "index": "52", "type": "numeric", "distinct": "467", "missing": "0", "min": "-1", "max": "3", "mean": "2", "stdev": "1" }, { "name": "Eig14_AEA.dm.", "index": "53", "type": "numeric", "distinct": "360", "missing": "0", "min": "-2", "max": "2", "mean": "1", "stdev": "1" }, { "name": "TIC2", "index": "54", "type": "numeric", "distinct": "597", "missing": "0", "min": "43", "max": "892", "mean": "245", "stdev": "84" }, { "name": "Eta_C", "index": "55", "type": "numeric", "distinct": "682", "missing": "0", "min": "3", "max": "137", "mean": "28", "stdev": "12" }, { "name": "Chi0_AEA.bo.", "index": "56", "type": "numeric", "distinct": "407", "missing": "0", "min": "4", "max": "62", "mean": "20", "stdev": "5" }, { "name": "Chi0_AEA.dm.", "index": "57", "type": "numeric", "distinct": "407", "missing": "0", "min": "4", "max": "62", "mean": "20", "stdev": "5" }, { "name": "Chi0_AEA.ed.", "index": "58", "type": "numeric", "distinct": "407", "missing": "0", "min": "4", "max": "62", "mean": "20", "stdev": "5" }, { "name": "Chi0_AEA.ri.", "index": "59", "type": "numeric", "distinct": "407", "missing": "0", "min": "4", "max": "62", "mean": "20", "stdev": "5" }, { "name": "Chi0_EA", "index": "60", "type": "numeric", "distinct": "407", "missing": "0", "min": "4", "max": "62", "mean": "20", "stdev": "5" }, { "name": "P_VSA_MR_1", "index": "61", "type": "numeric", "distinct": "71", "missing": "0", "min": "24", "max": "942", "mean": "276", "stdev": "95" }, { "name": "Eig11_EA", "index": "62", "type": "numeric", "distinct": "322", "missing": "0", "min": "-2", "max": "2", "mean": "1", "stdev": "1" }, { "name": "SM05_AEA.dm.", "index": "63", "type": "numeric", "distinct": "322", "missing": "0", "min": "-2", "max": "2", "mean": "1", "stdev": "1" }, { "name": "SpMaxA_EA.bo.", "index": "64", "type": "numeric", "distinct": "130", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "CID", "index": "65", "type": "numeric", "distinct": "315", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "Eig14_EA.ri.", "index": "66", "type": "numeric", "distinct": "461", "missing": "0", "min": "-2", "max": "2", "mean": "0", "stdev": "1" }, { "name": "X1", "index": "67", "type": "numeric", "distinct": "425", "missing": "0", "min": "3", "max": "44", "mean": "14", "stdev": "4" } ], "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 }