{ "data_id": "33840", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3490", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3490", "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: CHEMBL3490 (TID: 100610), and it has 273 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": "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 13:49:20", "update_comment": null, "last_update": "2016-07-15 13:49:20", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3515182\/data_53007.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3490", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL3490 (TID: 100610), and it has 273 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": 273, "NumberOfFeatures": 67, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 66, "NumberOfSymbolicFeatures": 1, "PercentageOfNumericFeatures": 98.50746268656717, "Quartile3MeansOfNumericAtts": 6.026525641025641, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfSymbolicFeatures": 1.4925373134328357, "Quartile3MutualInformation": null, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -0.6752492695885778, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 0.7969655269980753, "MaxSkewnessOfNumericAtts": 1.2435249168167686, "MinStdDevOfNumericAtts": 0.012178791557494741, "Quartile1KurtosisOfNumericAtts": -0.9006062954755542, "Quartile3StdDevOfNumericAtts": 1.818261581288719, "MaxStdDevOfNumericAtts": 159.62798973199392, "MinorityClassPercentage": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 0.6227106227106225, "StdvNominalAttDistinctValues": null, "MeanAttributeEntropy": null, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanKurtosisOfNumericAtts": -0.2353432084590011, "Quartile1SkewnessOfNumericAtts": -0.11267950506488708, "MeanMeansOfNumericAtts": 9.131518870018871, "Quartile1StdDevOfNumericAtts": 0.5468296187818464, "AutoCorrelation": 0.6800661764705884, "MeanMutualInformation": null, "Quartile2AttributeEntropy": null, "ClassEntropy": null, "MeanNoiseToSignalRatio": null, "Quartile2KurtosisOfNumericAtts": -0.4988249616444753, "Dimensionality": 0.2454212454212454, "MeanNominalAttDistinctValues": null, "Quartile2MeansOfNumericAtts": 1.542124542124542, "EquivalentNumberOfAtts": null, "MeanSkewnessOfNumericAtts": 0.33873037836094017, "Quartile2MutualInformation": null, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 5.47039972655572, "Quartile2SkewnessOfNumericAtts": 0.21928878248199823, "MajorityClassSize": null, "MinAttributeEntropy": null, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 1.1255011572575766, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.9299348549041067, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxKurtosisOfNumericAtts": 4.710497440169089, "MinMeansOfNumericAtts": -5.770183150183151, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 0.07273682716036023, "MaxMeansOfNumericAtts": 134.57009157509162, "MinMutualInformation": null }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "66", "type": "numeric", "distinct": "43", "missing": "0", "target": "1", "min": "4", "max": "7", "mean": "5", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "273", "missing": "0", "identifier": "1", "distr": [] }, { "name": "C.043", "index": "1", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "nTriazoles", "index": "2", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "NaasN", "index": "3", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "1" }, { "name": "SaaN", "index": "4", "type": "numeric", "distinct": "193", "missing": "0", "min": "0", "max": "19", "mean": "7", "stdev": "5" }, { "name": "N.075", "index": "5", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "2", "stdev": "1" }, { "name": "NaaN", "index": "6", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "2", "stdev": "1" }, { "name": "CATS2D_01_AA", "index": "7", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "1" }, { "name": "nCt", "index": "8", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "5", "mean": "2", "stdev": "2" }, { "name": "N.073", "index": "9", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "1" }, { "name": "nCrt", "index": "10", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "5", "mean": "2", "stdev": "2" }, { "name": "C.003", "index": "11", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "5", "mean": "1", "stdev": "2" }, { "name": "SsssCH", "index": "12", "type": "numeric", "distinct": "124", "missing": "0", "min": "-3", "max": "4", "mean": "0", "stdev": "1" }, { "name": "N.072", "index": "13", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "C.008", "index": "14", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "DLS_01", "index": "15", "type": "numeric", "distinct": "3", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Eig03_EA.dm.", "index": "16", "type": "numeric", "distinct": "30", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "1" }, { "name": "CATS2D_02_AA", "index": "17", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "7", "mean": "2", "stdev": "1" }, { "name": "CATS2D_02_DA", "index": "18", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "5", "mean": "1", "stdev": "1" }, { "name": "nRCONHR", "index": "19", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "piPC10", "index": "20", "type": "numeric", "distinct": "181", "missing": "0", "min": "5", "max": "9", "mean": "7", "stdev": "1" }, { "name": "CATS2D_07_LL", "index": "21", "type": "numeric", "distinct": "29", "missing": "0", "min": "0", "max": "33", "mean": "13", "stdev": "6" }, { "name": "CATS2D_02_DL", "index": "22", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "6", "mean": "1", "stdev": "2" }, { "name": "C.025", "index": "23", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "Eig04_EA.dm.", "index": "24", "type": "numeric", "distinct": "16", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "NssNH", "index": "25", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "1" }, { "name": "piPC06", "index": "26", "type": "numeric", "distinct": "180", "missing": "0", "min": "5", "max": "7", "mean": "6", "stdev": "0" }, { "name": "DLS_03", "index": "27", "type": "numeric", "distinct": "3", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "DLS_06", "index": "28", "type": "numeric", "distinct": "3", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "nCIR", "index": "29", "type": "numeric", "distinct": "13", "missing": "0", "min": "2", "max": "17", "mean": "6", "stdev": "2" }, { "name": "CATS2D_03_DA", "index": "30", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "piID", "index": "31", "type": "numeric", "distinct": "177", "missing": "0", "min": "7", "max": "13", "mean": "10", "stdev": "1" }, { "name": "C.011", "index": "32", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "piPC03", "index": "33", "type": "numeric", "distinct": "141", "missing": "0", "min": "4", "max": "5", "mean": "5", "stdev": "0" }, { "name": "nR05", "index": "34", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "1" }, { "name": "D.Dtr08", "index": "35", "type": "numeric", "distinct": "102", "missing": "0", "min": "0", "max": "512", "mean": "135", "stdev": "160" }, { "name": "P_VSA_LogP_2", "index": "36", "type": "numeric", "distinct": "84", "missing": "0", "min": "7", "max": "84", "mean": "30", "stdev": "20" }, { "name": "MSD", "index": "37", "type": "numeric", "distinct": "188", "missing": "0", "min": "4", "max": "10", "mean": "7", "stdev": "1" }, { "name": "ATSC3m", "index": "38", "type": "numeric", "distinct": "249", "missing": "0", "min": "21", "max": "69", "mean": "37", "stdev": "10" }, { "name": "P_VSA_m_3", "index": "39", "type": "numeric", "distinct": "66", "missing": "0", "min": "0", "max": "197", "mean": "56", "stdev": "42" }, { "name": "nAB", "index": "40", "type": "numeric", "distinct": "11", "missing": "0", "min": "0", "max": "27", "mean": "12", "stdev": "7" }, { "name": "HVcpx", "index": "41", "type": "numeric", "distinct": "176", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "ICR", "index": "42", "type": "numeric", "distinct": "149", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "IDE", "index": "43", "type": "numeric", "distinct": "170", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "nHAcc", "index": "44", "type": "numeric", "distinct": "9", "missing": "0", "min": "2", "max": "10", "mean": "5", "stdev": "2" }, { "name": "CATS2D_03_AA", "index": "45", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "piPC04", "index": "46", "type": "numeric", "distinct": "162", "missing": "0", "min": "4", "max": "6", "mean": "5", "stdev": "0" }, { "name": "CATS2D_04_AL", "index": "47", "type": "numeric", "distinct": "24", "missing": "0", "min": "2", "max": "29", "mean": "13", "stdev": "6" }, { "name": "nDB", "index": "48", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "5", "mean": "1", "stdev": "1" }, { "name": "NdO", "index": "49", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "5", "mean": "1", "stdev": "1" }, { "name": "O.058", "index": "50", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "5", "mean": "1", "stdev": "1" }, { "name": "X4Av", "index": "51", "type": "numeric", "distinct": "47", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "GATS3m", "index": "52", "type": "numeric", "distinct": "185", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "RBN", "index": "53", "type": "numeric", "distinct": "9", "missing": "0", "min": "1", "max": "9", "mean": "5", "stdev": "1" }, { "name": "UNIP", "index": "54", "type": "numeric", "distinct": "101", "missing": "0", "min": "50", "max": "239", "mean": "119", "stdev": "35" }, { "name": "SpMax4_Bh.s.", "index": "55", "type": "numeric", "distinct": "146", "missing": "0", "min": "4", "max": "8", "mean": "5", "stdev": "1" }, { "name": "BLTA96", "index": "56", "type": "numeric", "distinct": "166", "missing": "0", "min": "-9", "max": "0", "mean": "-6", "stdev": "1" }, { "name": "BLTD48", "index": "57", "type": "numeric", "distinct": "162", "missing": "0", "min": "-9", "max": "0", "mean": "-6", "stdev": "1" }, { "name": "MLOGP", "index": "58", "type": "numeric", "distinct": "196", "missing": "0", "min": "2", "max": "8", "mean": "5", "stdev": "1" }, { "name": "MLOGP2", "index": "59", "type": "numeric", "distinct": "199", "missing": "0", "min": "3", "max": "60", "mean": "23", "stdev": "13" }, { "name": "SRW05", "index": "60", "type": "numeric", "distinct": "9", "missing": "0", "min": "0", "max": "5", "mean": "2", "stdev": "1" }, { "name": "BLTF96", "index": "61", "type": "numeric", "distinct": "161", "missing": "0", "min": "-8", "max": "0", "mean": "-5", "stdev": "1" }, { "name": "CATS2D_06_LL", "index": "62", "type": "numeric", "distinct": "23", "missing": "0", "min": "0", "max": "42", "mean": "12", "stdev": "5" }, { "name": "NaasC", "index": "63", "type": "numeric", "distinct": "10", "missing": "0", "min": "0", "max": "9", "mean": "4", "stdev": "2" }, { "name": "H.", "index": "64", "type": "numeric", "distinct": "95", "missing": "0", "min": "35", "max": "59", "mean": "47", "stdev": "5" }, { "name": "ATSC3e", "index": "65", "type": "numeric", "distinct": "209", "missing": "0", "min": "0", "max": "2", "mean": "0", "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 }