{ "data_id": "34805", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL2181", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL2181", "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: CHEMBL2181 (TID: 10613), and it has 247 rows and 62 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 16:20:21", "update_comment": null, "last_update": "2016-07-15 16:20:21", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3539581\/data_52387.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL2181", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL2181 (TID: 10613), and it has 247 rows and 62 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": 247, "NumberOfFeatures": 64, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 63, "NumberOfSymbolicFeatures": 1, "Quartile2KurtosisOfNumericAtts": -0.4641394788710289, "Dimensionality": 0.2591093117408907, "MeanNominalAttDistinctValues": null, "Quartile2MeansOfNumericAtts": 1.3400809716599194, "EquivalentNumberOfAtts": null, "MeanSkewnessOfNumericAtts": 0.3797579332449494, "Quartile2MutualInformation": null, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 4.186911434852474, "Quartile2SkewnessOfNumericAtts": 0.43143993958748994, "MajorityClassSize": null, "MinAttributeEntropy": null, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.5193976047574607, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.3377407820379967, "MinMeansOfNumericAtts": -0.8851983805668017, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxKurtosisOfNumericAtts": 5.385783367254298, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 0.0689463233813088, "MaxMeansOfNumericAtts": 146.4857125506073, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.4375, "Quartile3MeansOfNumericAtts": 4.162186234817814, "MaxMutualInformation": null, "MinSkewnessOfNumericAtts": -2.0709228591240185, "PercentageOfSymbolicFeatures": 1.5625, "Quartile3MutualInformation": null, "MaxNominalAttDistinctValues": null, "MinStdDevOfNumericAtts": 0.002325910881041981, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 0.7331333208702594, "MaxSkewnessOfNumericAtts": 2.3368542904649092, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": -0.7714048693555098, "Quartile3StdDevOfNumericAtts": 1.2128146291077888, "MaxStdDevOfNumericAtts": 51.39572630120786, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 0.6437246963562749, "StdvNominalAttDistinctValues": null, "MeanAttributeEntropy": null, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanKurtosisOfNumericAtts": -0.05880296752647269, "Quartile1SkewnessOfNumericAtts": -0.035096661571057335, "MeanMeansOfNumericAtts": 9.26885084506137, "Quartile1StdDevOfNumericAtts": 0.08335851000478336, "AutoCorrelation": 0.5884065040650407, "MeanMutualInformation": null, "Quartile2AttributeEntropy": null, "ClassEntropy": null, "MeanNoiseToSignalRatio": null }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "63", "type": "numeric", "distinct": "73", "missing": "0", "target": "1", "min": "5", "max": "8", "mean": "5", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "247", "missing": "0", "identifier": "1", "distr": [] }, { "name": "X5Av", "index": "1", "type": "numeric", "distinct": "53", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "nDB", "index": "2", "type": "numeric", "distinct": "4", "missing": "0", "min": "1", "max": "4", "mean": "3", "stdev": "1" }, { "name": "C.008", "index": "3", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "JGI7", "index": "4", "type": "numeric", "distinct": "10", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "X3Av", "index": "5", "type": "numeric", "distinct": "85", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Chi1_EA.dm.", "index": "6", "type": "numeric", "distinct": "183", "missing": "0", "min": "8", "max": "49", "mean": "24", "stdev": "9" }, { "name": "Chi0_EA.dm.", "index": "7", "type": "numeric", "distinct": "168", "missing": "0", "min": "12", "max": "35", "mean": "22", "stdev": "5" }, { "name": "MATS2i", "index": "8", "type": "numeric", "distinct": "140", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Eig09_EA.ri.", "index": "9", "type": "numeric", "distinct": "148", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "NsCH3", "index": "10", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "6", "mean": "1", "stdev": "1" }, { "name": "P_VSA_LogP_1", "index": "11", "type": "numeric", "distinct": "17", "missing": "0", "min": "0", "max": "53", "mean": "13", "stdev": "13" }, { "name": "SsCH3", "index": "12", "type": "numeric", "distinct": "149", "missing": "0", "min": "0", "max": "13", "mean": "3", "stdev": "3" }, { "name": "Eig02_EA.dm.", "index": "13", "type": "numeric", "distinct": "24", "missing": "0", "min": "0", "max": "4", "mean": "2", "stdev": "1" }, { "name": "PW5", "index": "14", "type": "numeric", "distinct": "45", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "X4Av", "index": "15", "type": "numeric", "distinct": "66", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "CATS2D_05_NL", "index": "16", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "Eig08_EA.ri.", "index": "17", "type": "numeric", "distinct": "170", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "C.016", "index": "18", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "NdsCH", "index": "19", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "nR.Cs", "index": "20", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "DECC", "index": "21", "type": "numeric", "distinct": "123", "missing": "0", "min": "1", "max": "3", "mean": "2", "stdev": "0" }, { "name": "P_VSA_s_6", "index": "22", "type": "numeric", "distinct": "71", "missing": "0", "min": "79", "max": "269", "mean": "146", "stdev": "34" }, { "name": "Eig09_AEA.bo.", "index": "23", "type": "numeric", "distinct": "108", "missing": "0", "min": "2", "max": "3", "mean": "3", "stdev": "0" }, { "name": "JGI4", "index": "24", "type": "numeric", "distinct": "29", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SpMin3_Bh.m.", "index": "25", "type": "numeric", "distinct": "113", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "MATS8m", "index": "26", "type": "numeric", "distinct": "158", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "ATS5v", "index": "27", "type": "numeric", "distinct": "199", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "TPSA.Tot.", "index": "28", "type": "numeric", "distinct": "76", "missing": "0", "min": "42", "max": "185", "mean": "100", "stdev": "31" }, { "name": "GGI5", "index": "29", "type": "numeric", "distinct": "116", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "BLI", "index": "30", "type": "numeric", "distinct": "156", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "X1Av", "index": "31", "type": "numeric", "distinct": "107", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "P_VSA_i_1", "index": "32", "type": "numeric", "distinct": "10", "missing": "0", "min": "0", "max": "97", "mean": "19", "stdev": "27" }, { "name": "P_VSA_MR_8", "index": "33", "type": "numeric", "distinct": "9", "missing": "0", "min": "0", "max": "97", "mean": "19", "stdev": "27" }, { "name": "NsssN", "index": "34", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "SsssN", "index": "35", "type": "numeric", "distinct": "86", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "CATS2D_04_AL", "index": "36", "type": "numeric", "distinct": "17", "missing": "0", "min": "0", "max": "16", "mean": "6", "stdev": "4" }, { "name": "nCrs", "index": "37", "type": "numeric", "distinct": "8", "missing": "0", "min": "0", "max": "7", "mean": "2", "stdev": "2" }, { "name": "CATS2D_06_AA", "index": "38", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "MATS8p", "index": "39", "type": "numeric", "distinct": "154", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "nS", "index": "40", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "GATS2v", "index": "41", "type": "numeric", "distinct": "159", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SpMin2_Bh.p.", "index": "42", "type": "numeric", "distinct": "124", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "SdssC", "index": "43", "type": "numeric", "distinct": "199", "missing": "0", "min": "-2", "max": "0", "mean": "-1", "stdev": "0" }, { "name": "nHM", "index": "44", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "5", "mean": "1", "stdev": "1" }, { "name": "P_VSA_m_4", "index": "45", "type": "numeric", "distinct": "19", "missing": "0", "min": "0", "max": "162", "mean": "28", "stdev": "33" }, { "name": "SpMin3_Bh.p.", "index": "46", "type": "numeric", "distinct": "119", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "SpMin3_Bh.v.", "index": "47", "type": "numeric", "distinct": "129", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "GGI6", "index": "48", "type": "numeric", "distinct": "107", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SssO", "index": "49", "type": "numeric", "distinct": "141", "missing": "0", "min": "0", "max": "18", "mean": "5", "stdev": "5" }, { "name": "SM12_EA.ri.", "index": "50", "type": "numeric", "distinct": "210", "missing": "0", "min": "13", "max": "15", "mean": "14", "stdev": "1" }, { "name": "CATS2D_06_AN", "index": "51", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "P_VSA_MR_6", "index": "52", "type": "numeric", "distinct": "136", "missing": "0", "min": "1", "max": "231", "mean": "96", "stdev": "51" }, { "name": "MATS2p", "index": "53", "type": "numeric", "distinct": "147", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "NssO", "index": "54", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "Eig02_AEA.bo.", "index": "55", "type": "numeric", "distinct": "78", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "SM14_EA.ri.", "index": "56", "type": "numeric", "distinct": "213", "missing": "0", "min": "15", "max": "18", "mean": "16", "stdev": "1" }, { "name": "SM15_EA.ri.", "index": "57", "type": "numeric", "distinct": "216", "missing": "0", "min": "16", "max": "19", "mean": "17", "stdev": "1" }, { "name": "X5A", "index": "58", "type": "numeric", "distinct": "27", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "nArOR", "index": "59", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "BIC3", "index": "60", "type": "numeric", "distinct": "93", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Eta_beta_A", "index": "61", "type": "numeric", "distinct": "137", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SpMAD_EA.bo.", "index": "62", "type": "numeric", "distinct": "109", "missing": "0", "min": "2", "max": "2", "mean": "2", "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 }