DEVELOPMENT... { "data_id": "28688", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL2626", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL2626", "version": 7, "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: CHEMBL2626 (TID: 10075), and it has 161 rows and 65 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": "unknown", "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 00:37:34", "update_comment": null, "last_update": "2016-07-15 00:37:34", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3369280\/data_52814.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL2626", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL2626 (TID: 10075), and it has 161 rows and 65 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": 161, "NumberOfFeatures": 67, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 66, "NumberOfSymbolicFeatures": 1, "Quartile1MutualInformation": null, "PercentageOfBinaryFeatures": 0, "PercentageOfInstancesWithMissingValues": 0, "PercentageOfMissingValues": 0, "PercentageOfNumericFeatures": 98.50746268656717, "PercentageOfSymbolicFeatures": 1.4925373134328357, "Quartile1AttributeEntropy": null, "Quartile1KurtosisOfNumericAtts": -0.5814922077709884, "Quartile1MeansOfNumericAtts": 2.614722049689441, "StdvNominalAttDistinctValues": null, "Quartile1SkewnessOfNumericAtts": -0.74192348838423, "Quartile1StdDevOfNumericAtts": 0.30835078076743544, "Quartile2AttributeEntropy": null, "Quartile2KurtosisOfNumericAtts": 0.12299634888786692, "Quartile2MeansOfNumericAtts": 5.269118012422361, "Quartile2MutualInformation": null, "Quartile2SkewnessOfNumericAtts": -0.3202505951060632, "Quartile2StdDevOfNumericAtts": 0.44166621015218654, "Quartile3AttributeEntropy": null, "Quartile3KurtosisOfNumericAtts": 0.8742867458426828, "Quartile3MeansOfNumericAtts": 8.021585403726709, "Quartile3MutualInformation": null, "Quartile3SkewnessOfNumericAtts": 0.3393798932357128, "Quartile3StdDevOfNumericAtts": 0.7068554687970662, "AutoCorrelation": -0.12138749999999998, "MeanMeansOfNumericAtts": 10.557833427442123, "ClassEntropy": null, "Dimensionality": 0.4161490683229814, "EquivalentNumberOfAtts": null, "MajorityClassPercentage": null, "MajorityClassSize": null, "MaxAttributeEntropy": null, "MaxKurtosisOfNumericAtts": 60.00786454885491, "MaxMeansOfNumericAtts": 114.68143478260869, "MaxMutualInformation": null, "MaxNominalAttDistinctValues": null, "MaxSkewnessOfNumericAtts": 7.345093235730298, "MaxStdDevOfNumericAtts": 36.112988926905274, "MeanAttributeEntropy": null, "MeanKurtosisOfNumericAtts": 1.4707885773671012, "NumberOfBinaryFeatures": 0, "MeanMutualInformation": null, "MeanNoiseToSignalRatio": null, "MeanNominalAttDistinctValues": null, "MeanSkewnessOfNumericAtts": -0.08228851921848165, "MeanStdDevOfNumericAtts": 2.3329956100623, "MinAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.527884466585988, "MinMeansOfNumericAtts": 0.04314906832298137, "MinMutualInformation": null, "MinNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -1.2987292012599387, "MinStdDevOfNumericAtts": 0.036922251282276296, "MinorityClassPercentage": null, "MinorityClassSize": null }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "66", "type": "numeric", "distinct": "113", "missing": "0", "target": "1", "min": "2", "max": "8", "mean": "6", "stdev": "1" }, { "name": "BBI", "index": "49", "type": "numeric", "distinct": "31", "missing": "0", "min": "11", "max": "61", "mean": "26", "stdev": "7" }, { "name": "Eig07_AEA.ed.", "index": "34", "type": "numeric", "distinct": "98", "missing": "0", "min": "1", "max": "5", "mean": "3", "stdev": "1" }, { "name": "Eig12_AEA.ed.", "index": "48", "type": "numeric", "distinct": "67", "missing": "0", "min": "0", "max": "4", "mean": "2", "stdev": "1" }, { "name": "MPC07", "index": "47", "type": "numeric", "distinct": "42", "missing": "0", "min": "0", "max": "5", "mean": "3", "stdev": "1" }, { "name": "SM03_AEA.bo.", "index": "46", "type": "numeric", "distinct": "94", "missing": "0", "min": "5", "max": "7", "mean": "6", "stdev": "0" }, { "name": "ZM2Mad", "index": "45", "type": "numeric", "distinct": "132", "missing": "0", "min": "50", "max": "290", "mean": "115", "stdev": "36" }, { "name": "nCq", "index": "44", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "1" }, { "name": "C.004", "index": "43", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "1" }, { "name": "SpMax2_Bh.v.", "index": "42", "type": "numeric", "distinct": "112", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "ZM2", "index": "41", "type": "numeric", "distinct": "72", "missing": "0", "min": "41", "max": "250", "mean": "99", "stdev": "28" }, { "name": "MWC03", "index": "40", "type": "numeric", "distinct": "72", "missing": "0", "min": "4", "max": "6", "mean": "5", "stdev": "0" }, { "name": "SM04_EA.bo.", "index": "39", "type": "numeric", "distinct": "100", "missing": "0", "min": "5", "max": "8", "mean": "6", "stdev": "0" }, { "name": "Eig08_AEA.ed.", "index": "38", "type": "numeric", "distinct": "88", "missing": "0", "min": "1", "max": "5", "mean": "3", "stdev": "1" }, { "name": "SpMax2_Bh.p.", "index": "37", "type": "numeric", "distinct": "118", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "SM06_EA.bo.", "index": "36", "type": "numeric", "distinct": "115", "missing": "0", "min": "8", "max": "10", "mean": "8", "stdev": "0" }, { "name": "SpMax1_Bh.p.", "index": "35", "type": "numeric", "distinct": "81", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "nCrq", "index": "33", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "1" }, { "name": "MPC02", "index": "50", "type": "numeric", "distinct": "31", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SM02_EA", "index": "51", "type": "numeric", "distinct": "31", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "GGI1", "index": "52", "type": "numeric", "distinct": "13", "missing": "0", "min": "3", "max": "10", "mean": "5", "stdev": "1" }, { "name": "Eig11_AEA.ed.", "index": "53", "type": "numeric", "distinct": "81", "missing": "0", "min": "0", "max": "4", "mean": "2", "stdev": "1" }, { "name": "Eig01_EA.bo.", "index": "54", "type": "numeric", "distinct": "48", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "SM11_AEA.ri.", "index": "55", "type": "numeric", "distinct": "48", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "SpMax_EA.bo.", "index": "56", "type": "numeric", "distinct": "48", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "Eig13_AEA.ed.", "index": "57", "type": "numeric", "distinct": "52", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "Eig04_AEA.dm.", "index": "58", "type": "numeric", "distinct": "87", "missing": "0", "min": "1", "max": "4", "mean": "3", "stdev": "1" }, { "name": "Eig09_AEA.ed.", "index": "59", "type": "numeric", "distinct": "78", "missing": "0", "min": "0", "max": "5", "mean": "2", "stdev": "1" }, { "name": "SM14_EA.ed.", "index": "60", "type": "numeric", "distinct": "61", "missing": "0", "min": "29", "max": "38", "mean": "34", "stdev": "3" }, { "name": "SM15_EA.ed.", "index": "61", "type": "numeric", "distinct": "58", "missing": "0", "min": "31", "max": "41", "mean": "37", "stdev": "3" }, { "name": "C.003", "index": "62", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "nCt", "index": "63", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "NsssCH", "index": "64", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "SpMax2_Bh.m.", "index": "65", "type": "numeric", "distinct": "104", "missing": "0", "min": "3", "max": "7", "mean": "4", "stdev": "0" }, { "name": "MWC06", "index": "8", "type": "numeric", "distinct": "99", "missing": "0", "min": "7", "max": "9", "mean": "8", "stdev": "0" }, { "name": "SM05_AEA.bo.", "index": "16", "type": "numeric", "distinct": "119", "missing": "0", "min": "7", "max": "9", "mean": "8", "stdev": "0" }, { "name": "SM04_AEA.bo.", "index": "15", "type": "numeric", "distinct": "112", "missing": "0", "min": "6", "max": "8", "mean": "7", "stdev": "0" }, { "name": "SM03_AEA.ed.", "index": "14", "type": "numeric", "distinct": "100", "missing": "0", "min": "6", "max": "8", "mean": "7", "stdev": "0" }, { "name": "SM02_EA.ed.", "index": "13", "type": "numeric", "distinct": "86", "missing": "0", "min": "5", "max": "7", "mean": "6", "stdev": "0" }, { "name": "MWC10", "index": "12", "type": "numeric", "distinct": "100", "missing": "0", "min": "10", "max": "13", "mean": "11", "stdev": "1" }, { "name": "MWC09", "index": "11", "type": "numeric", "distinct": "103", "missing": "0", "min": "9", "max": "12", "mean": "10", "stdev": "1" }, { "name": "MWC08", "index": "10", "type": "numeric", "distinct": "102", "missing": "0", "min": "8", "max": "11", "mean": "9", "stdev": "0" }, { "name": "MWC07", "index": "9", "type": "numeric", "distinct": "102", "missing": "0", "min": "7", "max": "10", "mean": "9", "stdev": "0" }, { "name": "TWC", "index": "17", "type": "numeric", "distinct": "96", "missing": "0", "min": "10", "max": "13", "mean": "12", "stdev": "1" }, { "name": "SRW05", "index": "7", "type": "numeric", "distinct": "10", "missing": "0", "min": "0", "max": "5", "mean": "3", "stdev": "2" }, { "name": "SpDiam_AEA.ri.", "index": "6", "type": "numeric", "distinct": "90", "missing": "0", "min": "5", "max": "6", "mean": "5", "stdev": "0" }, { "name": "SM06_AEA.bo.", "index": "5", "type": "numeric", "distinct": "117", "missing": "0", "min": "9", "max": "11", "mean": "10", "stdev": "0" }, { "name": "SM04_EA", "index": "4", "type": "numeric", "distinct": "79", "missing": "0", "min": "5", "max": "6", "mean": "6", "stdev": "0" }, { "name": "D.Dtr03", "index": "3", "type": "numeric", "distinct": "62", "missing": "0", "min": "0", "max": "164", "mean": "34", "stdev": "26" }, { "name": "SpDiam_EA", "index": "2", "type": "numeric", "distinct": "72", "missing": "0", "min": "5", "max": "6", "mean": "5", "stdev": "0" }, { "name": "SpDiam_AEA.bo.", "index": "1", "type": "numeric", "distinct": "65", "missing": "0", "min": "5", "max": "6", "mean": "5", "stdev": "0" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "161", "missing": "0", "identifier": "1", "distr": [] }, { "name": "SpDiam_AEA.ed.", "index": "18", "type": "numeric", "distinct": "90", "missing": "0", "min": "5", "max": "8", "mean": "7", "stdev": "1" }, { "name": "MWC05", "index": "19", "type": "numeric", "distinct": "99", "missing": "0", "min": "6", "max": "8", "mean": "7", "stdev": "0" }, { "name": "SRW08", "index": "20", "type": "numeric", "distinct": "103", "missing": "0", "min": "7", "max": "9", "mean": "8", "stdev": "0" }, { "name": "SRW10", "index": "21", "type": "numeric", "distinct": "104", "missing": "0", "min": "8", "max": "11", "mean": "10", "stdev": "0" }, { "name": "MWC04", "index": "22", "type": "numeric", "distinct": "87", "missing": "0", "min": "5", "max": "7", "mean": "6", "stdev": "0" }, { "name": "nR03", "index": "23", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "SpMax1_Bh.e.", "index": "24", "type": "numeric", "distinct": "78", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "SRW03", "index": "25", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "GGI2", "index": "26", "type": "numeric", "distinct": "24", "missing": "0", "min": "1", "max": "5", "mean": "3", "stdev": "1" }, { "name": "SM02_AEA.ed.", "index": "27", "type": "numeric", "distinct": "73", "missing": "0", "min": "4", "max": "6", "mean": "5", "stdev": "0" }, { "name": "SRW06", "index": "28", "type": "numeric", "distinct": "91", "missing": "0", "min": "6", "max": "7", "mean": "6", "stdev": "0" }, { "name": "Eta_sh_x", "index": "29", "type": "numeric", "distinct": "42", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "IVDE", "index": "30", "type": "numeric", "distinct": "65", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "NssssC", "index": "31", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "1" }, { "name": "SpAD_EA.ed.", "index": "32", "type": "numeric", "distinct": "106", "missing": "0", "min": "32", "max": "188", "mean": "77", "stdev": "23" } ], "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 }