{ "data_id": "38181", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3157", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3157", "version": 10, "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: CHEMBL3157 (TID: 10034), and it has 574 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": "2016-07-16 03:14:54", "update_comment": null, "last_update": "2016-07-16 03:14:54", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3631818\/data_53362.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3157", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL3157 (TID: 10034), and it has 574 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": 574, "NumberOfFeatures": 70, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 69, "NumberOfSymbolicFeatures": 1, "Quartile3AttributeEntropy": null, "MaxKurtosisOfNumericAtts": 182.8161174835333, "MinMeansOfNumericAtts": -0.14054006968641114, "PercentageOfInstancesWithMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 5.971868172192814, "MaxMeansOfNumericAtts": 82224.00696864112, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3MeansOfNumericAtts": 16.559855400696865, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.57142857142858, "Quartile3MutualInformation": null, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -1.3647171318060969, "PercentageOfSymbolicFeatures": 1.4285714285714286, "Quartile3SkewnessOfNumericAtts": 2.123025569721291, "MaxSkewnessOfNumericAtts": 10.75972200094739, "MinStdDevOfNumericAtts": 0.019997868248395365, "Quartile1AttributeEntropy": null, "Quartile3StdDevOfNumericAtts": 6.970584901248737, "MaxStdDevOfNumericAtts": 120419.28321228792, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": 1.3996156124645234, "StdvNominalAttDistinctValues": null, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 1.7377700348432055, "MeanKurtosisOfNumericAtts": 8.559843278996057, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 1284.3775815785489, "Quartile1SkewnessOfNumericAtts": -0.3880499628592735, "AutoCorrelation": -0.3351710296684109, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.35681898533191764, "ClassEntropy": null, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "Dimensionality": 0.12195121951219512, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": 2.871754679821399, "EquivalentNumberOfAtts": null, "MeanSkewnessOfNumericAtts": 1.001070100418293, "Quartile2MeansOfNumericAtts": 3.5421324041811846, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 1795.807820889564, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": 0.4510224932382984, "Quartile2StdDevOfNumericAtts": 0.7478981102121091, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.099640898643289, "PercentageOfBinaryFeatures": 0 }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "69", "type": "numeric", "distinct": "354", "missing": "0", "target": "1", "min": "4", "max": "10", "mean": "7", "stdev": "2" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "574", "missing": "0", "identifier": "1", "distr": [] }, { "name": "IDE", "index": "1", "type": "numeric", "distinct": "332", "missing": "0", "min": "3", "max": "6", "mean": "4", "stdev": "0" }, { "name": "AECC", "index": "2", "type": "numeric", "distinct": "368", "missing": "0", "min": "7", "max": "47", "mean": "17", "stdev": "5" }, { "name": "HVcpx", "index": "3", "type": "numeric", "distinct": "322", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "MSD", "index": "4", "type": "numeric", "distinct": "383", "missing": "0", "min": "4", "max": "28", "mean": "10", "stdev": "3" }, { "name": "SPI", "index": "5", "type": "numeric", "distinct": "392", "missing": "0", "min": "6", "max": "147", "mean": "28", "stdev": "14" }, { "name": "CATS2D_08_AA", "index": "6", "type": "numeric", "distinct": "15", "missing": "0", "min": "0", "max": "19", "mean": "2", "stdev": "3" }, { "name": "IC3", "index": "7", "type": "numeric", "distinct": "400", "missing": "0", "min": "3", "max": "7", "mean": "6", "stdev": "0" }, { "name": "MW", "index": "8", "type": "numeric", "distinct": "460", "missing": "0", "min": "212", "max": "2244", "mean": "663", "stdev": "211" }, { "name": "MATS8m", "index": "9", "type": "numeric", "distinct": "247", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Eig13_AEA.ed.", "index": "10", "type": "numeric", "distinct": "267", "missing": "0", "min": "1", "max": "6", "mean": "4", "stdev": "1" }, { "name": "Eig07_AEA.ri.", "index": "11", "type": "numeric", "distinct": "287", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "CATS2D_03_DA", "index": "12", "type": "numeric", "distinct": "14", "missing": "0", "min": "0", "max": "20", "mean": "2", "stdev": "3" }, { "name": "Eig06_AEA.ri.", "index": "13", "type": "numeric", "distinct": "274", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SpMaxA_AEA.ed.", "index": "14", "type": "numeric", "distinct": "135", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "GATS8v", "index": "15", "type": "numeric", "distinct": "272", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "Eig06_EA.dm.", "index": "16", "type": "numeric", "distinct": "71", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "H.051", "index": "17", "type": "numeric", "distinct": "11", "missing": "0", "min": "0", "max": "12", "mean": "3", "stdev": "2" }, { "name": "nRCONR2", "index": "18", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "Eig15_AEA.ed.", "index": "19", "type": "numeric", "distinct": "257", "missing": "0", "min": "1", "max": "6", "mean": "4", "stdev": "1" }, { "name": "Eig07_EA.dm.", "index": "20", "type": "numeric", "distinct": "48", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "Eig11_AEA.dm.", "index": "21", "type": "numeric", "distinct": "261", "missing": "0", "min": "-1", "max": "4", "mean": "2", "stdev": "1" }, { "name": "nDB", "index": "22", "type": "numeric", "distinct": "16", "missing": "0", "min": "0", "max": "24", "mean": "4", "stdev": "3" }, { "name": "Eig08_AEA.ri.", "index": "23", "type": "numeric", "distinct": "318", "missing": "0", "min": "1", "max": "4", "mean": "3", "stdev": "0" }, { "name": "Eta_betaS", "index": "24", "type": "numeric", "distinct": "122", "missing": "0", "min": "9", "max": "99", "mean": "29", "stdev": "10" }, { "name": "Eig08_EA.ri.", "index": "25", "type": "numeric", "distinct": "317", "missing": "0", "min": "0", "max": "3", "mean": "2", "stdev": "0" }, { "name": "Eig04_EA.dm.", "index": "26", "type": "numeric", "distinct": "85", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "1" }, { "name": "VvdwZAZ", "index": "27", "type": "numeric", "distinct": "463", "missing": "0", "min": "210", "max": "2167", "mean": "595", "stdev": "207" }, { "name": "Eig13_AEA.dm.", "index": "28", "type": "numeric", "distinct": "256", "missing": "0", "min": "-1", "max": "4", "mean": "2", "stdev": "1" }, { "name": "Eig08_EA", "index": "29", "type": "numeric", "distinct": "253", "missing": "0", "min": "0", "max": "3", "mean": "2", "stdev": "0" }, { "name": "SM02_AEA.dm.", "index": "30", "type": "numeric", "distinct": "253", "missing": "0", "min": "0", "max": "3", "mean": "2", "stdev": "0" }, { "name": "Eig14_EA.ed.", "index": "31", "type": "numeric", "distinct": "306", "missing": "0", "min": "-4", "max": "8", "mean": "3", "stdev": "2" }, { "name": "SM09_AEA.ri.", "index": "32", "type": "numeric", "distinct": "306", "missing": "0", "min": "-4", "max": "8", "mean": "3", "stdev": "2" }, { "name": "VAR", "index": "33", "type": "numeric", "distinct": "227", "missing": "0", "min": "44", "max": "2404", "mean": "330", "stdev": "226" }, { "name": "CATS2D_05_AA", "index": "34", "type": "numeric", "distinct": "16", "missing": "0", "min": "0", "max": "20", "mean": "4", "stdev": "3" }, { "name": "SMTIV", "index": "35", "type": "numeric", "distinct": "531", "missing": "0", "min": "3120", "max": "2018350", "mean": "82224", "stdev": "120419" }, { "name": "X1Mad", "index": "36", "type": "numeric", "distinct": "511", "missing": "0", "min": "8", "max": "70", "mean": "20", "stdev": "7" }, { "name": "ECC", "index": "37", "type": "numeric", "distinct": "317", "missing": "0", "min": "130", "max": "7447", "mean": "862", "stdev": "610" }, { "name": "SpMaxA_EA", "index": "38", "type": "numeric", "distinct": "87", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "CSI", "index": "39", "type": "numeric", "distinct": "359", "missing": "0", "min": "261", "max": "14895", "mean": "1828", "stdev": "1252" }, { "name": "SpMaxA_AEA.bo.", "index": "40", "type": "numeric", "distinct": "103", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Eig11_EA", "index": "41", "type": "numeric", "distinct": "245", "missing": "0", "min": "-1", "max": "3", "mean": "2", "stdev": "0" }, { "name": "SM05_AEA.dm.", "index": "42", "type": "numeric", "distinct": "245", "missing": "0", "min": "-1", "max": "3", "mean": "2", "stdev": "0" }, { "name": "Uindex", "index": "43", "type": "numeric", "distinct": "393", "missing": "0", "min": "26", "max": "1187", "mean": "89", "stdev": "61" }, { "name": "SpAD_EA.dm.", "index": "44", "type": "numeric", "distinct": "246", "missing": "0", "min": "0", "max": "107", "mean": "16", "stdev": "13" }, { "name": "ATS3s", "index": "45", "type": "numeric", "distinct": "404", "missing": "0", "min": "5", "max": "8", "mean": "6", "stdev": "0" }, { "name": "Eig14_EA.bo.", "index": "46", "type": "numeric", "distinct": "244", "missing": "0", "min": "-2", "max": "3", "mean": "1", "stdev": "1" }, { "name": "MPC03", "index": "47", "type": "numeric", "distinct": "103", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "TPSA.Tot.", "index": "48", "type": "numeric", "distinct": "249", "missing": "0", "min": "0", "max": "1036", "mean": "145", "stdev": "129" }, { "name": "S0K", "index": "49", "type": "numeric", "distinct": "268", "missing": "0", "min": "40", "max": "1125", "mean": "244", "stdev": "109" }, { "name": "CATS2D_03_AA", "index": "50", "type": "numeric", "distinct": "8", "missing": "0", "min": "0", "max": "7", "mean": "2", "stdev": "1" }, { "name": "SM04_EA.ri.", "index": "51", "type": "numeric", "distinct": "397", "missing": "0", "min": "5", "max": "8", "mean": "6", "stdev": "0" }, { "name": "ZM1V", "index": "52", "type": "numeric", "distinct": "232", "missing": "0", "min": "162", "max": "2262", "mean": "679", "stdev": "227" }, { "name": "MATS1i", "index": "53", "type": "numeric", "distinct": "263", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "S2K", "index": "54", "type": "numeric", "distinct": "430", "missing": "0", "min": "5", "max": "77", "mean": "16", "stdev": "7" }, { "name": "Eig09_EA.ri.", "index": "55", "type": "numeric", "distinct": "300", "missing": "0", "min": "0", "max": "3", "mean": "2", "stdev": "0" }, { "name": "nArOR", "index": "56", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "Eig13_EA.ed.", "index": "57", "type": "numeric", "distinct": "277", "missing": "0", "min": "-4", "max": "8", "mean": "3", "stdev": "1" }, { "name": "SM08_AEA.ri.", "index": "58", "type": "numeric", "distinct": "277", "missing": "0", "min": "-4", "max": "8", "mean": "3", "stdev": "1" }, { "name": "ATS1s", "index": "59", "type": "numeric", "distinct": "376", "missing": "0", "min": "5", "max": "7", "mean": "6", "stdev": "0" }, { "name": "TPSA.NO.", "index": "60", "type": "numeric", "distinct": "232", "missing": "0", "min": "0", "max": "1010", "mean": "138", "stdev": "122" }, { "name": "Eig10_EA", "index": "61", "type": "numeric", "distinct": "240", "missing": "0", "min": "-1", "max": "3", "mean": "2", "stdev": "0" }, { "name": "SM04_AEA.dm.", "index": "62", "type": "numeric", "distinct": "240", "missing": "0", "min": "-1", "max": "3", "mean": "2", "stdev": "0" }, { "name": "Pol", "index": "63", "type": "numeric", "distinct": "89", "missing": "0", "min": "22", "max": "234", "mean": "75", "stdev": "23" }, { "name": "TIC3", "index": "64", "type": "numeric", "distinct": "477", "missing": "0", "min": "104", "max": "2054", "mean": "475", "stdev": "212" }, { "name": "Eig11_AEA.ed.", "index": "65", "type": "numeric", "distinct": "231", "missing": "0", "min": "2", "max": "6", "mean": "4", "stdev": "1" }, { "name": "Ram", "index": "66", "type": "numeric", "distinct": "31", "missing": "0", "min": "4", "max": "49", "mean": "16", "stdev": "5" }, { "name": "Eig06_AEA.bo.", "index": "67", "type": "numeric", "distinct": "222", "missing": "0", "min": "2", "max": "4", "mean": "4", "stdev": "0" }, { "name": "DECC", "index": "68", "type": "numeric", "distinct": "346", "missing": "0", "min": "1", "max": "8", "mean": "3", "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 }