{ "data_id": "24414", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4772", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4772", "version": 8, "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: CHEMBL4772 (TID: 12608), and it has 123 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": "2016-07-14 14:36:05", "update_comment": null, "last_update": "2016-07-14 14:36:05", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3245873\/data_52441.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4772", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL4772 (TID: 12608), and it has 123 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": 123, "NumberOfFeatures": 64, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 63, "NumberOfSymbolicFeatures": 1, "PercentageOfSymbolicFeatures": 1.5625, "Quartile3MutualInformation": null, "CfsSubsetEval_DecisionStumpErrRate": null, "RandomTreeDepth2ErrRate": null, "J48.00001.Kappa": null, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 0.3511830167858088, "CfsSubsetEval_DecisionStumpKappa": null, "RandomTreeDepth2Kappa": null, "J48.0001.AUC": null, "MeanKurtosisOfNumericAtts": 1.8378852041217486, "NaiveBayesAUC": null, "Quartile1KurtosisOfNumericAtts": -0.39275578155603696, "Quartile3StdDevOfNumericAtts": 0.35179025964148286, "CfsSubsetEval_NaiveBayesAUC": null, "RandomTreeDepth3AUC": null, "J48.0001.ErrRate": null, "MeanMeansOfNumericAtts": 360.4565723964382, "NaiveBayesErrRate": null, "Quartile1MeansOfNumericAtts": 2.866878048780488, "REPTreeDepth1AUC": null, "CfsSubsetEval_NaiveBayesErrRate": null, "RandomTreeDepth3ErrRate": null, "J48.0001.Kappa": null, "MeanMutualInformation": null, "NaiveBayesKappa": null, "Quartile1MutualInformation": null, "REPTreeDepth1ErrRate": null, "CfsSubsetEval_NaiveBayesKappa": null, "RandomTreeDepth3Kappa": null, "J48.001.AUC": null, "MeanNoiseToSignalRatio": null, "NumberOfBinaryFeatures": 0, "Quartile1SkewnessOfNumericAtts": -0.13165800905180736, "REPTreeDepth1Kappa": null, "CfsSubsetEval_kNN1NAUC": null, "StdvNominalAttDistinctValues": null, "J48.001.ErrRate": null, "MeanNominalAttDistinctValues": null, "Quartile1StdDevOfNumericAtts": 0.09734801630655762, "REPTreeDepth2AUC": null, "CfsSubsetEval_kNN1NErrRate": null, "kNN1NAUC": null, "J48.001.Kappa": null, "MeanSkewnessOfNumericAtts": 0.19904524006031848, "Quartile2AttributeEntropy": null, "REPTreeDepth2ErrRate": null, "CfsSubsetEval_kNN1NKappa": null, "kNN1NErrRate": null, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 99.60442518202251, "Quartile2KurtosisOfNumericAtts": 0.09949479400213779, "REPTreeDepth2Kappa": null, "ClassEntropy": null, "kNN1NKappa": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2MeansOfNumericAtts": 3.8821463414634145, "REPTreeDepth3AUC": null, "DecisionStumpAUC": null, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.1337431354726222, "Quartile2MutualInformation": null, "REPTreeDepth3ErrRate": null, "DecisionStumpErrRate": null, "MaxKurtosisOfNumericAtts": 13.813277629297556, "MinMeansOfNumericAtts": -0.07182926829268292, "Quartile2SkewnessOfNumericAtts": 0.10235328560483596, "REPTreeDepth3Kappa": null, "DecisionStumpKappa": null, "MaxMeansOfNumericAtts": 22098.186991869916, "MinMutualInformation": null, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.12249778875568865, "RandomTreeDepth1AUC": null, "Dimensionality": 0.5203252032520326, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "RandomTreeDepth1ErrRate": null, "EquivalentNumberOfAtts": null, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -1.9322605985587944, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 2.006541390253387, "AutoCorrelation": -0.14251639344262249, "RandomTreeDepth1Kappa": null, "J48.00001.AUC": null, "MaxSkewnessOfNumericAtts": 3.468222011086393, "MinStdDevOfNumericAtts": 0.014799580702317693, "PercentageOfNumericFeatures": 98.4375, "Quartile3MeansOfNumericAtts": 5.521512195121951, "CfsSubsetEval_DecisionStumpAUC": null, "RandomTreeDepth2AUC": null, "J48.00001.ErrRate": null, "MaxStdDevOfNumericAtts": 6181.3357505856875, "MinorityClassPercentage": null }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "63", "type": "numeric", "distinct": "84", "missing": "0", "target": "1", "min": "4", "max": "8", "mean": "6", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "123", "missing": "0", "identifier": "1", "distr": [] }, { "name": "Eig04_AEA.dm.", "index": "1", "type": "numeric", "distinct": "67", "missing": "0", "min": "2", "max": "3", "mean": "3", "stdev": "0" }, { "name": "Eig07_AEA.bo.", "index": "2", "type": "numeric", "distinct": "45", "missing": "0", "min": "3", "max": "3", "mean": "3", "stdev": "0" }, { "name": "GMTIV", "index": "3", "type": "numeric", "distinct": "103", "missing": "0", "min": "5953", "max": "39417", "mean": "22098", "stdev": "6181" }, { "name": "Eta_beta", "index": "4", "type": "numeric", "distinct": "40", "missing": "0", "min": "25", "max": "40", "mean": "34", "stdev": "3" }, { "name": "Eta_betaP", "index": "5", "type": "numeric", "distinct": "13", "missing": "0", "min": "15", "max": "23", "mean": "19", "stdev": "2" }, { "name": "GATS3i", "index": "6", "type": "numeric", "distinct": "97", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SpMax7_Bh.m.", "index": "7", "type": "numeric", "distinct": "85", "missing": "0", "min": "2", "max": "3", "mean": "3", "stdev": "0" }, { "name": "ATSC1s", "index": "8", "type": "numeric", "distinct": "104", "missing": "0", "min": "4", "max": "46", "mean": "11", "stdev": "8" }, { "name": "Eig05_AEA.dm.", "index": "9", "type": "numeric", "distinct": "73", "missing": "0", "min": "2", "max": "3", "mean": "2", "stdev": "0" }, { "name": "MATS2m", "index": "10", "type": "numeric", "distinct": "70", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "ATS8m", "index": "11", "type": "numeric", "distinct": "107", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SpMin6_Bh.s.", "index": "12", "type": "numeric", "distinct": "53", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "SpMAD_EA.ri.", "index": "13", "type": "numeric", "distinct": "73", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "P_VSA_m_2", "index": "14", "type": "numeric", "distinct": "100", "missing": "0", "min": "126", "max": "265", "mean": "180", "stdev": "29" }, { "name": "MATS1m", "index": "15", "type": "numeric", "distinct": "43", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "nBM", "index": "16", "type": "numeric", "distinct": "7", "missing": "0", "min": "16", "max": "23", "mean": "18", "stdev": "1" }, { "name": "Uc", "index": "17", "type": "numeric", "distinct": "7", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "MATS6i", "index": "18", "type": "numeric", "distinct": "97", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Eig06_AEA.bo.", "index": "19", "type": "numeric", "distinct": "43", "missing": "0", "min": "3", "max": "3", "mean": "3", "stdev": "0" }, { "name": "GATS1p", "index": "20", "type": "numeric", "distinct": "88", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "ATSC8s", "index": "21", "type": "numeric", "distinct": "121", "missing": "0", "min": "8", "max": "144", "mean": "36", "stdev": "17" }, { "name": "Eig09_EA.bo.", "index": "22", "type": "numeric", "distinct": "27", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "ALOGP", "index": "23", "type": "numeric", "distinct": "101", "missing": "0", "min": "3", "max": "6", "mean": "5", "stdev": "1" }, { "name": "ALOGP2", "index": "24", "type": "numeric", "distinct": "104", "missing": "0", "min": "10", "max": "41", "mean": "23", "stdev": "7" }, { "name": "Eig13_AEA.bo.", "index": "25", "type": "numeric", "distinct": "46", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "SpMax3_Bh.m.", "index": "26", "type": "numeric", "distinct": "86", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "Eig11_AEA.dm.", "index": "27", "type": "numeric", "distinct": "69", "missing": "0", "min": "-1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "P_VSA_LogP_1", "index": "28", "type": "numeric", "distinct": "14", "missing": "0", "min": "0", "max": "31", "mean": "11", "stdev": "7" }, { "name": "SpMax4_Bh.s.", "index": "29", "type": "numeric", "distinct": "79", "missing": "0", "min": "4", "max": "7", "mean": "5", "stdev": "1" }, { "name": "Eta_sh_y", "index": "30", "type": "numeric", "distinct": "62", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "AAC", "index": "31", "type": "numeric", "distinct": "81", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "AECC", "index": "32", "type": "numeric", "distinct": "44", "missing": "0", "min": "7", "max": "12", "mean": "10", "stdev": "1" }, { "name": "AMR", "index": "33", "type": "numeric", "distinct": "104", "missing": "0", "min": "74", "max": "118", "mean": "95", "stdev": "9" }, { "name": "AMW", "index": "34", "type": "numeric", "distinct": "95", "missing": "0", "min": "8", "max": "12", "mean": "9", "stdev": "1" }, { "name": "ARR", "index": "35", "type": "numeric", "distinct": "19", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "ATS1e", "index": "36", "type": "numeric", "distinct": "89", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "ATS1i", "index": "37", "type": "numeric", "distinct": "89", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "ATS1m", "index": "38", "type": "numeric", "distinct": "84", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "ATS1p", "index": "39", "type": "numeric", "distinct": "87", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "ATS1s", "index": "40", "type": "numeric", "distinct": "93", "missing": "0", "min": "5", "max": "5", "mean": "5", "stdev": "0" }, { "name": "ATS1v", "index": "41", "type": "numeric", "distinct": "83", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "ATS2e", "index": "42", "type": "numeric", "distinct": "94", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "ATS2i", "index": "43", "type": "numeric", "distinct": "93", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "ATS2m", "index": "44", "type": "numeric", "distinct": "88", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "ATS2p", "index": "45", "type": "numeric", "distinct": "95", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "ATS2s", "index": "46", "type": "numeric", "distinct": "105", "missing": "0", "min": "5", "max": "6", "mean": "6", "stdev": "0" }, { "name": "ATS2v", "index": "47", "type": "numeric", "distinct": "86", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "ATS3e", "index": "48", "type": "numeric", "distinct": "99", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "ATS3i", "index": "49", "type": "numeric", "distinct": "101", "missing": "0", "min": "4", "max": "5", "mean": "5", "stdev": "0" }, { "name": "ATS3m", "index": "50", "type": "numeric", "distinct": "95", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "ATS3p", "index": "51", "type": "numeric", "distinct": "104", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "ATS3s", "index": "52", "type": "numeric", "distinct": "98", "missing": "0", "min": "5", "max": "6", "mean": "6", "stdev": "0" }, { "name": "ATS3v", "index": "53", "type": "numeric", "distinct": "98", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "ATS4e", "index": "54", "type": "numeric", "distinct": "103", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "ATS4i", "index": "55", "type": "numeric", "distinct": "107", "missing": "0", "min": "4", "max": "5", "mean": "5", "stdev": "0" }, { "name": "ATS4m", "index": "56", "type": "numeric", "distinct": "110", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "ATS4p", "index": "57", "type": "numeric", "distinct": "112", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "ATS4s", "index": "58", "type": "numeric", "distinct": "106", "missing": "0", "min": "5", "max": "6", "mean": "6", "stdev": "0" }, { "name": "ATS4v", "index": "59", "type": "numeric", "distinct": "107", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "ATS5e", "index": "60", "type": "numeric", "distinct": "108", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "ATS5i", "index": "61", "type": "numeric", "distinct": "113", "missing": "0", "min": "4", "max": "5", "mean": "5", "stdev": "0" }, { "name": "ATS5m", "index": "62", "type": "numeric", "distinct": "107", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" } ], "nr_of_issues": 0, "nr_of_downvotes": 0, "nr_of_likes": 0, "nr_of_downloads": 0, "total_downloads": 0, "reach": 0, "reuse": 11, "impact_of_reuse": 0, "reach_of_reuse": 0, "impact": 11 }