{ "data_id": "23548", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL1892", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL1892", "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: CHEMBL1892 (TID: 184), and it has 224 rows and 67 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": "2016-07-14 12:42:13", "update_comment": null, "last_update": "2016-07-14 12:42:13", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3228009\/data_53200.arff", "kaggle_url": null, "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL1892", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL1892 (TID: 184), and it has 224 rows and 67 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": 224, "NumberOfFeatures": 69, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 68, "NumberOfSymbolicFeatures": 1, "REPTreeDepth3AUC": null, "DecisionStumpAUC": null, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.0517786298273828, "Quartile2MeansOfNumericAtts": 4.888859375, "REPTreeDepth3ErrRate": null, "DecisionStumpErrRate": null, "MaxKurtosisOfNumericAtts": 19.44000396539827, "MinMeansOfNumericAtts": -3.462982142857143, "Quartile2MutualInformation": null, "REPTreeDepth3Kappa": null, "DecisionStumpKappa": null, "MaxMeansOfNumericAtts": 248.66872767857143, "MinMutualInformation": null, "Quartile2SkewnessOfNumericAtts": 2.50924733019549, "RandomTreeDepth1AUC": null, "Dimensionality": 0.3080357142857143, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 2.337350805024102, "RandomTreeDepth1ErrRate": null, "EquivalentNumberOfAtts": null, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -2.85430641031026, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "RandomTreeDepth1Kappa": null, "J48.00001.AUC": null, "MaxSkewnessOfNumericAtts": 4.170309019820069, "MinStdDevOfNumericAtts": 0.03864178696944779, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 13.523716972530314, "AutoCorrelation": -0.1474484304932734, "RandomTreeDepth2AUC": null, "J48.00001.ErrRate": null, "MaxStdDevOfNumericAtts": 242.2597371414179, "MinorityClassPercentage": null, "PercentageOfNumericFeatures": 98.55072463768117, "Quartile3MeansOfNumericAtts": 43.777218749999996, "CfsSubsetEval_DecisionStumpAUC": null, "RandomTreeDepth2ErrRate": null, "J48.00001.Kappa": null, "MeanAttributeEntropy": null, "MinorityClassSize": null, "PercentageOfSymbolicFeatures": 1.4492753623188406, "Quartile3MutualInformation": null, "CfsSubsetEval_DecisionStumpErrRate": null, "RandomTreeDepth2Kappa": null, "J48.0001.AUC": null, "MeanKurtosisOfNumericAtts": 8.183622531515718, "NaiveBayesAUC": null, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 3.2959963331405002, "CfsSubsetEval_DecisionStumpKappa": null, "CfsSubsetEval_NaiveBayesAUC": null, "RandomTreeDepth3AUC": null, "J48.0001.ErrRate": null, "MeanMeansOfNumericAtts": 49.50465670955882, "NaiveBayesErrRate": null, "Quartile1KurtosisOfNumericAtts": 1.8698579111963713, "Quartile3StdDevOfNumericAtts": 39.14479330310201, "CfsSubsetEval_NaiveBayesErrRate": null, "RandomTreeDepth3ErrRate": null, "J48.0001.Kappa": null, "MeanMutualInformation": null, "NaiveBayesKappa": null, "Quartile1MeansOfNumericAtts": 1.0355256696428572, "REPTreeDepth1AUC": null, "CfsSubsetEval_NaiveBayesKappa": null, "RandomTreeDepth3Kappa": null, "J48.001.AUC": null, "MeanNoiseToSignalRatio": null, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "REPTreeDepth1ErrRate": null, "CfsSubsetEval_kNN1NAUC": null, "StdvNominalAttDistinctValues": null, "J48.001.ErrRate": null, "MeanNominalAttDistinctValues": null, "Quartile1SkewnessOfNumericAtts": 0.5346825059883448, "REPTreeDepth1Kappa": null, "REPTreeDepth2AUC": null, "CfsSubsetEval_kNN1NErrRate": null, "kNN1NAUC": null, "J48.001.Kappa": null, "MeanSkewnessOfNumericAtts": 1.8831149772523426, "Quartile1StdDevOfNumericAtts": 0.8512442341166817, "REPTreeDepth2ErrRate": null, "CfsSubsetEval_kNN1NKappa": null, "kNN1NErrRate": null, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 40.12694421626481, "Quartile2AttributeEntropy": null, "REPTreeDepth2Kappa": null, "ClassEntropy": null, "kNN1NKappa": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2KurtosisOfNumericAtts": 8.95004885195039 }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "68", "type": "numeric", "distinct": "173", "missing": "0", "target": "1", "min": "4", "max": "11", "mean": "7", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "224", "missing": "0", "identifier": "1", "distr": [] }, { "name": "ATSC3s", "index": "1", "type": "numeric", "distinct": "209", "missing": "0", "min": "14", "max": "903", "mean": "151", "stdev": "132" }, { "name": "CATS2D_04_DN", "index": "2", "type": "numeric", "distinct": "8", "missing": "0", "min": "0", "max": "9", "mean": "2", "stdev": "2" }, { "name": "ATSC3e", "index": "3", "type": "numeric", "distinct": "185", "missing": "0", "min": "0", "max": "5", "mean": "1", "stdev": "1" }, { "name": "GATS7e", "index": "4", "type": "numeric", "distinct": "191", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "MATS7m", "index": "5", "type": "numeric", "distinct": "145", "missing": "0", "min": "-1", "max": "0", "mean": "0", "stdev": "0" }, { "name": "ATSC2s", "index": "6", "type": "numeric", "distinct": "207", "missing": "0", "min": "29", "max": "860", "mean": "121", "stdev": "110" }, { "name": "ATSC1e", "index": "7", "type": "numeric", "distinct": "153", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "ATSC5s", "index": "8", "type": "numeric", "distinct": "209", "missing": "0", "min": "26", "max": "1432", "mean": "230", "stdev": "202" }, { "name": "GATS7m", "index": "9", "type": "numeric", "distinct": "172", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "nHAcc", "index": "10", "type": "numeric", "distinct": "26", "missing": "0", "min": "2", "max": "48", "mean": "9", "stdev": "6" }, { "name": "ATSC2e", "index": "11", "type": "numeric", "distinct": "168", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "TPSA.NO.", "index": "12", "type": "numeric", "distinct": "91", "missing": "0", "min": "37", "max": "826", "mean": "149", "stdev": "108" }, { "name": "nHDon", "index": "13", "type": "numeric", "distinct": "17", "missing": "0", "min": "0", "max": "21", "mean": "4", "stdev": "3" }, { "name": "CATS2D_07_DA", "index": "14", "type": "numeric", "distinct": "13", "missing": "0", "min": "0", "max": "13", "mean": "2", "stdev": "2" }, { "name": "ATSC8e", "index": "15", "type": "numeric", "distinct": "195", "missing": "0", "min": "0", "max": "7", "mean": "1", "stdev": "1" }, { "name": "ATSC4s", "index": "16", "type": "numeric", "distinct": "209", "missing": "0", "min": "17", "max": "1167", "mean": "191", "stdev": "164" }, { "name": "SpMax5_Bh.s.", "index": "17", "type": "numeric", "distinct": "90", "missing": "0", "min": "3", "max": "8", "mean": "6", "stdev": "1" }, { "name": "CATS2D_07_DD", "index": "18", "type": "numeric", "distinct": "8", "missing": "0", "min": "0", "max": "7", "mean": "1", "stdev": "1" }, { "name": "nHet", "index": "19", "type": "numeric", "distinct": "26", "missing": "0", "min": "3", "max": "56", "mean": "10", "stdev": "7" }, { "name": "MATS7s", "index": "20", "type": "numeric", "distinct": "175", "missing": "0", "min": "-1", "max": "1", "mean": "0", "stdev": "0" }, { "name": "ATSC1s", "index": "21", "type": "numeric", "distinct": "195", "missing": "0", "min": "8", "max": "277", "mean": "46", "stdev": "40" }, { "name": "ATSC8s", "index": "22", "type": "numeric", "distinct": "207", "missing": "0", "min": "1", "max": "1304", "mean": "178", "stdev": "191" }, { "name": "ATSC4e", "index": "23", "type": "numeric", "distinct": "196", "missing": "0", "min": "0", "max": "7", "mean": "1", "stdev": "1" }, { "name": "CATS2D_04_DL", "index": "24", "type": "numeric", "distinct": "21", "missing": "0", "min": "0", "max": "28", "mean": "5", "stdev": "4" }, { "name": "SsOH", "index": "25", "type": "numeric", "distinct": "197", "missing": "0", "min": "0", "max": "161", "mean": "25", "stdev": "21" }, { "name": "SsssCH", "index": "26", "type": "numeric", "distinct": "164", "missing": "0", "min": "-11", "max": "5", "mean": "-2", "stdev": "2" }, { "name": "P_VSA_e_5", "index": "27", "type": "numeric", "distinct": "67", "missing": "0", "min": "68", "max": "1253", "mean": "220", "stdev": "159" }, { "name": "GATS7s", "index": "28", "type": "numeric", "distinct": "180", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "P_VSA_MR_2", "index": "29", "type": "numeric", "distinct": "85", "missing": "0", "min": "68", "max": "1221", "mean": "239", "stdev": "166" }, { "name": "nHM", "index": "30", "type": "numeric", "distinct": "8", "missing": "0", "min": "0", "max": "7", "mean": "1", "stdev": "1" }, { "name": "CATS2D_02_DL", "index": "31", "type": "numeric", "distinct": "16", "missing": "0", "min": "0", "max": "20", "mean": "3", "stdev": "3" }, { "name": "CATS2D_05_DN", "index": "32", "type": "numeric", "distinct": "11", "missing": "0", "min": "0", "max": "12", "mean": "2", "stdev": "2" }, { "name": "SpMax3_Bh.s.", "index": "33", "type": "numeric", "distinct": "42", "missing": "0", "min": "4", "max": "8", "mean": "7", "stdev": "1" }, { "name": "SpMax8_Bh.s.", "index": "34", "type": "numeric", "distinct": "151", "missing": "0", "min": "1", "max": "7", "mean": "5", "stdev": "1" }, { "name": "S3K", "index": "35", "type": "numeric", "distinct": "187", "missing": "0", "min": "2", "max": "39", "mean": "8", "stdev": "5" }, { "name": "MATS7e", "index": "36", "type": "numeric", "distinct": "178", "missing": "0", "min": "-1", "max": "1", "mean": "0", "stdev": "0" }, { "name": "ATSC6s", "index": "37", "type": "numeric", "distinct": "209", "missing": "0", "min": "30", "max": "1676", "mean": "229", "stdev": "242" }, { "name": "SpMax4_Bh.s.", "index": "38", "type": "numeric", "distinct": "51", "missing": "0", "min": "4", "max": "8", "mean": "7", "stdev": "1" }, { "name": "TIE", "index": "39", "type": "numeric", "distinct": "209", "missing": "0", "min": "16", "max": "1402", "mean": "157", "stdev": "200" }, { "name": "Hy", "index": "40", "type": "numeric", "distinct": "152", "missing": "0", "min": "-1", "max": "13", "mean": "2", "stdev": "2" }, { "name": "CATS2D_05_DD", "index": "41", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "6", "mean": "1", "stdev": "1" }, { "name": "Uindex", "index": "42", "type": "numeric", "distinct": "178", "missing": "0", "min": "19", "max": "389", "mean": "79", "stdev": "59" }, { "name": "SdssC", "index": "43", "type": "numeric", "distinct": "197", "missing": "0", "min": "-17", "max": "1", "mean": "-3", "stdev": "2" }, { "name": "P_VSA_p_4", "index": "44", "type": "numeric", "distinct": "11", "missing": "0", "min": "0", "max": "57", "mean": "11", "stdev": "21" }, { "name": "CATS2D_01_AN", "index": "45", "type": "numeric", "distinct": "15", "missing": "0", "min": "0", "max": "20", "mean": "3", "stdev": "3" }, { "name": "CATS2D_01_DN", "index": "46", "type": "numeric", "distinct": "13", "missing": "0", "min": "0", "max": "16", "mean": "3", "stdev": "2" }, { "name": "CATS2D_03_AL", "index": "47", "type": "numeric", "distinct": "26", "missing": "0", "min": "0", "max": "46", "mean": "6", "stdev": "6" }, { "name": "P_VSA_LogP_4", "index": "48", "type": "numeric", "distinct": "74", "missing": "0", "min": "80", "max": "1017", "mean": "208", "stdev": "134" }, { "name": "ATSC6e", "index": "49", "type": "numeric", "distinct": "196", "missing": "0", "min": "0", "max": "9", "mean": "1", "stdev": "1" }, { "name": "BLI", "index": "50", "type": "numeric", "distinct": "159", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "X1Av", "index": "51", "type": "numeric", "distinct": "109", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "CATS2D_02_NL", "index": "52", "type": "numeric", "distinct": "14", "missing": "0", "min": "0", "max": "22", "mean": "3", "stdev": "3" }, { "name": "NdssC", "index": "53", "type": "numeric", "distinct": "16", "missing": "0", "min": "1", "max": "19", "mean": "4", "stdev": "3" }, { "name": "P_VSA_LogP_2", "index": "54", "type": "numeric", "distinct": "93", "missing": "0", "min": "1", "max": "204", "mean": "37", "stdev": "37" }, { "name": "DLS_cons", "index": "55", "type": "numeric", "distinct": "47", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SpMax7_Bh.s.", "index": "56", "type": "numeric", "distinct": "120", "missing": "0", "min": "2", "max": "7", "mean": "5", "stdev": "1" }, { "name": "SpMax1_Bh.s.", "index": "57", "type": "numeric", "distinct": "29", "missing": "0", "min": "7", "max": "8", "mean": "8", "stdev": "0" }, { "name": "P_VSA_m_3", "index": "58", "type": "numeric", "distinct": "71", "missing": "0", "min": "68", "max": "1253", "mean": "221", "stdev": "159" }, { "name": "SpMax6_Bh.s.", "index": "59", "type": "numeric", "distinct": "92", "missing": "0", "min": "2", "max": "7", "mean": "6", "stdev": "1" }, { "name": "DLS_06", "index": "60", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "CATS2D_06_DA", "index": "61", "type": "numeric", "distinct": "14", "missing": "0", "min": "0", "max": "15", "mean": "2", "stdev": "3" }, { "name": "DLS_03", "index": "62", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SM06_EA.bo.", "index": "63", "type": "numeric", "distinct": "176", "missing": "0", "min": "6", "max": "11", "mean": "9", "stdev": "1" }, { "name": "SpMax1_Bh.m.", "index": "64", "type": "numeric", "distinct": "130", "missing": "0", "min": "4", "max": "11", "mean": "5", "stdev": "3" }, { "name": "P_VSA_s_6", "index": "65", "type": "numeric", "distinct": "86", "missing": "0", "min": "86", "max": "1253", "mean": "234", "stdev": "153" }, { "name": "P_VSA_v_2", "index": "66", "type": "numeric", "distinct": "98", "missing": "0", "min": "68", "max": "1348", "mean": "249", "stdev": "174" }, { "name": "SAacc", "index": "67", "type": "numeric", "distinct": "93", "missing": "0", "min": "68", "max": "1346", "mean": "248", "stdev": "174" } ], "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 }