{ "data_id": "29846", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL209", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL209", "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: CHEMBL209 (TID: 42), and it has 1302 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": "2016-07-15 03:31:32", "update_comment": null, "last_update": "2016-07-15 03:31:32", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3403784\/data_53656.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL209", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL209 (TID: 42), and it has 1302 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": 1302, "NumberOfFeatures": 72, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 71, "NumberOfSymbolicFeatures": 1, "ClassEntropy": null, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "Dimensionality": 0.055299539170506916, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": 1.7444221271251465, "EquivalentNumberOfAtts": null, "MeanSkewnessOfNumericAtts": 0.6580759464523697, "Quartile2MeansOfNumericAtts": 1.2486935483870965, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 4.165083008686539, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": 0.3764861504737926, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.0860205968416152, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.5426561650539262, "MaxKurtosisOfNumericAtts": 124.08129880311881, "MinMeansOfNumericAtts": -0.07552380952380952, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 147.30724884792627, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 5.165361776684877, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.61111111111111, "Quartile3MeansOfNumericAtts": 6.935215053763441, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -6.910030281767099, "PercentageOfSymbolicFeatures": 1.3888888888888888, "Quartile3MutualInformation": null, "MaxSkewnessOfNumericAtts": 6.596628354251712, "MinStdDevOfNumericAtts": 0.0018519910354423549, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 1.8089815642222784, "MaxStdDevOfNumericAtts": 45.03772200443949, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": 0.21900840484549766, "Quartile3StdDevOfNumericAtts": 1.720584894007901, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 0.28033794162826436, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": 6.7406776419139565, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 10.355757783258692, "Quartile1SkewnessOfNumericAtts": -0.3478149950806111, "AutoCorrelation": -0.2653274404304378, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.23359562123231734 }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "71", "type": "numeric", "distinct": "522", "missing": "0", "target": "1", "min": "-6", "max": "11", "mean": "6", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "1302", "missing": "0", "identifier": "1", "distr": [] }, { "name": "GATS5m", "index": "1", "type": "numeric", "distinct": "457", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "N.066", "index": "2", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "5", "mean": "1", "stdev": "1" }, { "name": "nRNH2", "index": "3", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "5", "mean": "1", "stdev": "1" }, { "name": "CATS2D_00_DD", "index": "4", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "5", "mean": "1", "stdev": "1" }, { "name": "CATS2D_00_DP", "index": "5", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "5", "mean": "1", "stdev": "1" }, { "name": "CATS2D_00_PP", "index": "6", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "5", "mean": "1", "stdev": "1" }, { "name": "NsNH2", "index": "7", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "5", "mean": "1", "stdev": "1" }, { "name": "CATS2D_04_PL", "index": "8", "type": "numeric", "distinct": "8", "missing": "0", "min": "0", "max": "7", "mean": "2", "stdev": "1" }, { "name": "GATS5p", "index": "9", "type": "numeric", "distinct": "397", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "nArCONHR", "index": "10", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "SM05_EA.dm.", "index": "11", "type": "numeric", "distinct": "257", "missing": "0", "min": "0", "max": "8", "mean": "3", "stdev": "2" }, { "name": "P_VSA_p_3", "index": "12", "type": "numeric", "distinct": "1012", "missing": "0", "min": "15", "max": "348", "mean": "147", "stdev": "42" }, { "name": "P_VSA_v_3", "index": "13", "type": "numeric", "distinct": "1012", "missing": "0", "min": "15", "max": "348", "mean": "147", "stdev": "42" }, { "name": "GATS5v", "index": "14", "type": "numeric", "distinct": "338", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "B.112", "index": "15", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "nB", "index": "16", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "NsssB", "index": "17", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "SsssB", "index": "18", "type": "numeric", "distinct": "53", "missing": "0", "min": "-2", "max": "0", "mean": "0", "stdev": "0" }, { "name": "CATS2D_07_AP", "index": "19", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "4", "mean": "0", "stdev": "1" }, { "name": "MATS7e", "index": "20", "type": "numeric", "distinct": "472", "missing": "0", "min": "-2", "max": "1", "mean": "0", "stdev": "0" }, { "name": "RCI", "index": "21", "type": "numeric", "distinct": "42", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "MATS5p", "index": "22", "type": "numeric", "distinct": "336", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "C.009", "index": "23", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "RFD", "index": "24", "type": "numeric", "distinct": "42", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SM09_EA.dm.", "index": "25", "type": "numeric", "distinct": "281", "missing": "0", "min": "0", "max": "15", "mean": "6", "stdev": "3" }, { "name": "Eig01_AEA.ed.", "index": "26", "type": "numeric", "distinct": "387", "missing": "0", "min": "5", "max": "9", "mean": "7", "stdev": "1" }, { "name": "SpMax_AEA.ed.", "index": "27", "type": "numeric", "distinct": "387", "missing": "0", "min": "5", "max": "9", "mean": "7", "stdev": "1" }, { "name": "SsNH2", "index": "28", "type": "numeric", "distinct": "750", "missing": "0", "min": "0", "max": "28", "mean": "7", "stdev": "4" }, { "name": "SdNH", "index": "29", "type": "numeric", "distinct": "489", "missing": "0", "min": "0", "max": "16", "mean": "5", "stdev": "5" }, { "name": "Eig01_EA.ed.", "index": "30", "type": "numeric", "distinct": "508", "missing": "0", "min": "7", "max": "18", "mean": "12", "stdev": "2" }, { "name": "SM10_AEA.dm.", "index": "31", "type": "numeric", "distinct": "508", "missing": "0", "min": "7", "max": "18", "mean": "12", "stdev": "2" }, { "name": "SpMax_EA.ed.", "index": "32", "type": "numeric", "distinct": "508", "missing": "0", "min": "7", "max": "18", "mean": "12", "stdev": "2" }, { "name": "Cl.089", "index": "33", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "Eig01_EA", "index": "34", "type": "numeric", "distinct": "403", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SM09_AEA.bo.", "index": "35", "type": "numeric", "distinct": "403", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SpMax_EA", "index": "36", "type": "numeric", "distinct": "403", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SpDiam_EA.bo.", "index": "37", "type": "numeric", "distinct": "391", "missing": "0", "min": "4", "max": "8", "mean": "7", "stdev": "1" }, { "name": "Eig01_EA.bo.", "index": "38", "type": "numeric", "distinct": "382", "missing": "0", "min": "2", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SM11_AEA.ri.", "index": "39", "type": "numeric", "distinct": "382", "missing": "0", "min": "2", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SpMax_EA.bo.", "index": "40", "type": "numeric", "distinct": "382", "missing": "0", "min": "2", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SpDiam_EA", "index": "41", "type": "numeric", "distinct": "404", "missing": "0", "min": "4", "max": "6", "mean": "5", "stdev": "0" }, { "name": "NdNH", "index": "42", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "1" }, { "name": "nArX", "index": "43", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "SsCl", "index": "44", "type": "numeric", "distinct": "164", "missing": "0", "min": "0", "max": "13", "mean": "1", "stdev": "3" }, { "name": "CATS2D_02_PL", "index": "45", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "5", "mean": "1", "stdev": "1" }, { "name": "SM03_EA.dm.", "index": "46", "type": "numeric", "distinct": "151", "missing": "0", "min": "0", "max": "5", "mean": "2", "stdev": "1" }, { "name": "CATS2D_07_DP", "index": "47", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "5", "mean": "0", "stdev": "1" }, { "name": "P_VSA_e_4", "index": "48", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "78", "mean": "8", "stdev": "21" }, { "name": "nCL", "index": "49", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "NsCl", "index": "50", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "SAdon", "index": "51", "type": "numeric", "distinct": "129", "missing": "0", "min": "0", "max": "291", "mean": "97", "stdev": "45" }, { "name": "P_VSA_e_3", "index": "52", "type": "numeric", "distinct": "265", "missing": "0", "min": "0", "max": "324", "mean": "104", "stdev": "40" }, { "name": "Eta_alpha_A", "index": "53", "type": "numeric", "distinct": "76", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "DECC", "index": "54", "type": "numeric", "distinct": "621", "missing": "0", "min": "1", "max": "5", "mean": "2", "stdev": "0" }, { "name": "P_VSA_MR_7", "index": "55", "type": "numeric", "distinct": "124", "missing": "0", "min": "0", "max": "134", "mean": "22", "stdev": "25" }, { "name": "SpDiam_EA.ed.", "index": "56", "type": "numeric", "distinct": "588", "missing": "0", "min": "12", "max": "28", "mean": "19", "stdev": "2" }, { "name": "AECC", "index": "57", "type": "numeric", "distinct": "737", "missing": "0", "min": "4", "max": "28", "mean": "13", "stdev": "3" }, { "name": "HVcpx", "index": "58", "type": "numeric", "distinct": "530", "missing": "0", "min": "2", "max": "5", "mean": "4", "stdev": "0" }, { "name": "IDE", "index": "59", "type": "numeric", "distinct": "547", "missing": "0", "min": "2", "max": "5", "mean": "4", "stdev": "0" }, { "name": "MSD", "index": "60", "type": "numeric", "distinct": "840", "missing": "0", "min": "3", "max": "16", "mean": "8", "stdev": "2" }, { "name": "GATS2m", "index": "61", "type": "numeric", "distinct": "424", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "CATS2D_02_PP", "index": "62", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "GATS7e", "index": "63", "type": "numeric", "distinct": "709", "missing": "0", "min": "0", "max": "8", "mean": "1", "stdev": "0" }, { "name": "P_VSA_LogP_8", "index": "64", "type": "numeric", "distinct": "13", "missing": "0", "min": "0", "max": "123", "mean": "9", "stdev": "22" }, { "name": "JGI10", "index": "65", "type": "numeric", "distinct": "14", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "MATS3i", "index": "66", "type": "numeric", "distinct": "388", "missing": "0", "min": "-1", "max": "0", "mean": "0", "stdev": "0" }, { "name": "CATS2D_02_DP", "index": "67", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "GATS5i", "index": "68", "type": "numeric", "distinct": "375", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SM15_EA.dm.", "index": "69", "type": "numeric", "distinct": "242", "missing": "0", "min": "0", "max": "25", "mean": "9", "stdev": "5" }, { "name": "SM12_EA.dm.", "index": "70", "type": "numeric", "distinct": "373", "missing": "0", "min": "0", "max": "20", "mean": "8", "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 }