DEVELOPMENT... { "data_id": "32084", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL2304404", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL2304404", "version": 12, "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: CHEMBL2304404 (TID: 105567), and it has 318 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 09:16:38", "update_comment": null, "last_update": "2016-07-15 09:16:38", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3469720\/data_52970.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL2304404", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL2304404 (TID: 105567), and it has 318 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": 318, "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": -0.6417693815535342, "Quartile1MeansOfNumericAtts": 0.5987908805031447, "StdvNominalAttDistinctValues": null, "Quartile1SkewnessOfNumericAtts": 0.117315424580008, "Quartile1StdDevOfNumericAtts": 0.12292825303479214, "Quartile2AttributeEntropy": null, "Quartile2KurtosisOfNumericAtts": -0.14020284943806893, "Quartile2MeansOfNumericAtts": 1.1415487421383648, "Quartile2MutualInformation": null, "Quartile2SkewnessOfNumericAtts": 0.4356448820856388, "Quartile2StdDevOfNumericAtts": 0.39804006846202555, "Quartile3AttributeEntropy": null, "Quartile3KurtosisOfNumericAtts": 1.2068441261953313, "Quartile3MeansOfNumericAtts": 2.9559748427672963, "Quartile3MutualInformation": null, "Quartile3SkewnessOfNumericAtts": 0.8923796013379137, "Quartile3StdDevOfNumericAtts": 2.2095861523943245, "AutoCorrelation": -0.3435205047318618, "MeanMeansOfNumericAtts": 6.321972031637124, "ClassEntropy": null, "Dimensionality": 0.21069182389937108, "EquivalentNumberOfAtts": null, "MajorityClassPercentage": null, "MajorityClassSize": null, "MaxAttributeEntropy": null, "MaxKurtosisOfNumericAtts": 35.803468449464056, "MaxMeansOfNumericAtts": 145.94749371069182, "MaxMutualInformation": null, "MaxNominalAttDistinctValues": null, "MaxSkewnessOfNumericAtts": 4.637621094338537, "MaxStdDevOfNumericAtts": 78.83476866596789, "MeanAttributeEntropy": null, "MeanKurtosisOfNumericAtts": 1.305384353890781, "NumberOfBinaryFeatures": 0, "MeanMutualInformation": null, "MeanNoiseToSignalRatio": null, "MeanNominalAttDistinctValues": null, "MeanSkewnessOfNumericAtts": 0.5005686019094152, "MeanStdDevOfNumericAtts": 3.110345847658792, "MinAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.7363074672524557, "MinMeansOfNumericAtts": -1.4881477987421379, "MinMutualInformation": null, "MinNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -1.5417010319861435, "MinStdDevOfNumericAtts": 0.006977551790872349, "MinorityClassPercentage": null, "MinorityClassSize": null }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "66", "type": "numeric", "distinct": "225", "missing": "0", "target": "1", "min": "4", "max": "9", "mean": "6", "stdev": "1" }, { "name": "MATS8e", "index": "49", "type": "numeric", "distinct": "199", "missing": "0", "min": "-1", "max": "1", "mean": "0", "stdev": "0" }, { "name": "GATS2e", "index": "34", "type": "numeric", "distinct": "214", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "MATS7e", "index": "48", "type": "numeric", "distinct": "213", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "X2Av", "index": "47", "type": "numeric", "distinct": "68", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SpMin7_Bh.s.", "index": "46", "type": "numeric", "distinct": "159", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "GATS2s", "index": "45", "type": "numeric", "distinct": "224", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "PCR", "index": "44", "type": "numeric", "distinct": "166", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "X4Av", "index": "43", "type": "numeric", "distinct": "31", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "MATS7m", "index": "42", "type": "numeric", "distinct": "221", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "BIC1", "index": "41", "type": "numeric", "distinct": "176", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "CATS2D_09_LL", "index": "40", "type": "numeric", "distinct": "19", "missing": "0", "min": "0", "max": "24", "mean": "3", "stdev": "4" }, { "name": "CATS2D_07_LL", "index": "39", "type": "numeric", "distinct": "11", "missing": "0", "min": "0", "max": "12", "mean": "2", "stdev": "3" }, { "name": "CATS2D_06_AL", "index": "38", "type": "numeric", "distinct": "21", "missing": "0", "min": "0", "max": "21", "mean": "7", "stdev": "4" }, { "name": "ALOGP", "index": "37", "type": "numeric", "distinct": "273", "missing": "0", "min": "-2", "max": "6", "mean": "2", "stdev": "2" }, { "name": "ALOGP2", "index": "36", "type": "numeric", "distinct": "261", "missing": "0", "min": "0", "max": "36", "mean": "6", "stdev": "7" }, { "name": "CIC1", "index": "35", "type": "numeric", "distinct": "242", "missing": "0", "min": "0", "max": "4", "mean": "2", "stdev": "1" }, { "name": "X3Av", "index": "33", "type": "numeric", "distinct": "43", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "nCsp3", "index": "50", "type": "numeric", "distinct": "19", "missing": "0", "min": "0", "max": "19", "mean": "9", "stdev": "3" }, { "name": "SIC1", "index": "51", "type": "numeric", "distinct": "175", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "GATS7m", "index": "52", "type": "numeric", "distinct": "237", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "H.049", "index": "53", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "O.", "index": "54", "type": "numeric", "distinct": "86", "missing": "0", "min": "0", "max": "16", "mean": "7", "stdev": "3" }, { "name": "CATS2D_02_AP", "index": "55", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "SpMin3_Bh.m.", "index": "56", "type": "numeric", "distinct": "139", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "P_VSA_LogP_4", "index": "57", "type": "numeric", "distinct": "47", "missing": "0", "min": "47", "max": "200", "mean": "94", "stdev": "24" }, { "name": "SsNH2", "index": "58", "type": "numeric", "distinct": "88", "missing": "0", "min": "0", "max": "11", "mean": "2", "stdev": "3" }, { "name": "Eta_C_A", "index": "59", "type": "numeric", "distinct": "226", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "CATS2D_07_DP", "index": "60", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "SIC2", "index": "61", "type": "numeric", "distinct": "165", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "CIC5", "index": "62", "type": "numeric", "distinct": "211", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "P_VSA_s_6", "index": "63", "type": "numeric", "distinct": "68", "missing": "0", "min": "59", "max": "307", "mean": "146", "stdev": "79" }, { "name": "AMW", "index": "64", "type": "numeric", "distinct": "198", "missing": "0", "min": "6", "max": "11", "mean": "7", "stdev": "1" }, { "name": "CATS2D_04_AP", "index": "65", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "Eig03_EA.ed.", "index": "8", "type": "numeric", "distinct": "152", "missing": "0", "min": "6", "max": "10", "mean": "8", "stdev": "1" }, { "name": "Eta_betaP_A", "index": "16", "type": "numeric", "distinct": "105", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "Eta_beta_A", "index": "15", "type": "numeric", "distinct": "171", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "SpMin3_Bh.s.", "index": "14", "type": "numeric", "distinct": "159", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Eig03_AEA.ed.", "index": "13", "type": "numeric", "distinct": "126", "missing": "0", "min": "5", "max": "7", "mean": "6", "stdev": "0" }, { "name": "Eta_FL_A", "index": "12", "type": "numeric", "distinct": "122", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SssCH2", "index": "11", "type": "numeric", "distinct": "277", "missing": "0", "min": "-1", "max": "16", "mean": "3", "stdev": "3" }, { "name": "GATS7e", "index": "10", "type": "numeric", "distinct": "256", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "SM12_AEA.dm.", "index": "9", "type": "numeric", "distinct": "152", "missing": "0", "min": "6", "max": "10", "mean": "8", "stdev": "1" }, { "name": "ARR", "index": "17", "type": "numeric", "distinct": "68", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "SsssCH", "index": "7", "type": "numeric", "distinct": "188", "missing": "0", "min": "-6", "max": "4", "mean": "-1", "stdev": "2" }, { "name": "Eta_F_A", "index": "6", "type": "numeric", "distinct": "225", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SaaNH", "index": "5", "type": "numeric", "distinct": "117", "missing": "0", "min": "0", "max": "5", "mean": "1", "stdev": "2" }, { "name": "SpMin2_Bh.s.", "index": "4", "type": "numeric", "distinct": "122", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "CATS2D_03_DL", "index": "3", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "6", "mean": "1", "stdev": "1" }, { "name": "P_VSA_MR_6", "index": "2", "type": "numeric", "distinct": "108", "missing": "0", "min": "2", "max": "125", "mean": "44", "stdev": "33" }, { "name": "CATS2D_02_DL", "index": "1", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "6", "mean": "1", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "318", "missing": "0", "identifier": "1", "distr": [] }, { "name": "Psi_e_A", "index": "18", "type": "numeric", "distinct": "200", "missing": "0", "min": "7", "max": "9", "mean": "8", "stdev": "0" }, { "name": "Psi_i_A", "index": "19", "type": "numeric", "distinct": "200", "missing": "0", "min": "2", "max": "3", "mean": "2", "stdev": "0" }, { "name": "NaaCH", "index": "20", "type": "numeric", "distinct": "13", "missing": "0", "min": "0", "max": "13", "mean": "3", "stdev": "3" }, { "name": "SaaCH", "index": "21", "type": "numeric", "distinct": "220", "missing": "0", "min": "0", "max": "25", "mean": "4", "stdev": "5" }, { "name": "H.052", "index": "22", "type": "numeric", "distinct": "12", "missing": "0", "min": "0", "max": "12", "mean": "3", "stdev": "2" }, { "name": "Eta_epsi_A", "index": "23", "type": "numeric", "distinct": "127", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Eta_L_A", "index": "24", "type": "numeric", "distinct": "129", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "CATS2D_08_PL", "index": "25", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "1" }, { "name": "Me", "index": "26", "type": "numeric", "distinct": "54", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "AAC", "index": "27", "type": "numeric", "distinct": "159", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "IC0", "index": "28", "type": "numeric", "distinct": "159", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "CATS2D_04_DL", "index": "29", "type": "numeric", "distinct": "8", "missing": "0", "min": "0", "max": "7", "mean": "1", "stdev": "2" }, { "name": "CATS2D_08_LL", "index": "30", "type": "numeric", "distinct": "17", "missing": "0", "min": "0", "max": "16", "mean": "3", "stdev": "4" }, { "name": "C.002", "index": "31", "type": "numeric", "distinct": "11", "missing": "0", "min": "0", "max": "12", "mean": "3", "stdev": "2" }, { "name": "MAXDN", "index": "32", "type": "numeric", "distinct": "206", "missing": "0", "min": "1", "max": "6", "mean": "2", "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 }