{ "data_id": "6346", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL1952", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL1952", "version": 1, "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: CHEMBL1952 (TID: CHEMBL1952), and it has 559 rows and 43 features (including IDs and class feature: molecule_id and pXC50). The features represent Molecular Descriptors which were generated from SMILES strings (with imputation of missing values if they exist).", "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": "2016-04-04 17:36:41", "update_comment": null, "last_update": "2016-04-04 17:36:41", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/1859467\/data_33980.arff", "kaggle_url": null, "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 0, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL1952", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL1952 (TID: CHEMBL1952), and it has 559 rows and 43 features (including IDs and class feature: molecule_id and pXC50). The features represent Molecular Descriptors which were generated from SMILES strings (with imputation of missing values if they exist). " ], "weight": 5 }, "qualities": { "NumberOfInstances": 559, "NumberOfFeatures": 45, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 44, "NumberOfSymbolicFeatures": 1, "MaxKurtosisOfNumericAtts": 75.55464980915133, "MinMeansOfNumericAtts": 0, "Quartile2MutualInformation": null, "REPTreeDepth3ErrRate": null, "DecisionStumpErrRate": null, "MaxMeansOfNumericAtts": 402.0777996422182, "MinMutualInformation": null, "Quartile2SkewnessOfNumericAtts": 0.8375439276776431, "REPTreeDepth3Kappa": null, "DecisionStumpKappa": null, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 2.915339850176488, "RandomTreeDepth1AUC": null, "Dimensionality": 0.08050089445438283, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -0.8843135329123565, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "RandomTreeDepth1ErrRate": null, "EquivalentNumberOfAtts": null, "J48.00001.AUC": null, "MaxSkewnessOfNumericAtts": 8.791151241391656, "MinStdDevOfNumericAtts": 0, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 2.559702932714535, "AutoCorrelation": -0.03912903225806442, "RandomTreeDepth1Kappa": null, "J48.00001.ErrRate": null, "MaxStdDevOfNumericAtts": 117.06802334826307, "MinorityClassPercentage": null, "PercentageOfNumericFeatures": 97.77777777777777, "Quartile3MeansOfNumericAtts": 29.900715563506264, "CfsSubsetEval_DecisionStumpAUC": null, "RandomTreeDepth2AUC": null, "J48.00001.Kappa": null, "MeanAttributeEntropy": null, "MinorityClassSize": null, "PercentageOfSymbolicFeatures": 2.2222222222222223, "Quartile3MutualInformation": null, "CfsSubsetEval_DecisionStumpErrRate": null, "RandomTreeDepth2ErrRate": null, "RandomTreeDepth2Kappa": null, "J48.0001.AUC": null, "MeanKurtosisOfNumericAtts": 5.584384459708708, "NaiveBayesAUC": null, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 1.2683293138215184, "CfsSubsetEval_DecisionStumpKappa": null, "RandomTreeDepth3AUC": null, "J48.0001.ErrRate": null, "MeanMeansOfNumericAtts": 22.558735851357945, "NaiveBayesErrRate": null, "Quartile1KurtosisOfNumericAtts": 0.9114229517058203, "Quartile3StdDevOfNumericAtts": 6.749892212920875, "CfsSubsetEval_NaiveBayesAUC": null, "RandomTreeDepth3ErrRate": null, "J48.0001.Kappa": null, "MeanMutualInformation": null, "NaiveBayesKappa": null, "Quartile1MeansOfNumericAtts": 0.5215062611806798, "REPTreeDepth1AUC": null, "CfsSubsetEval_NaiveBayesErrRate": null, "RandomTreeDepth3Kappa": null, "J48.001.AUC": null, "MeanNoiseToSignalRatio": null, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "REPTreeDepth1ErrRate": null, "CfsSubsetEval_NaiveBayesKappa": null, "StdvNominalAttDistinctValues": null, "J48.001.ErrRate": null, "MeanNominalAttDistinctValues": null, "Quartile1SkewnessOfNumericAtts": 0.5767414574152656, "REPTreeDepth1Kappa": null, "CfsSubsetEval_kNN1NAUC": null, "kNN1NAUC": null, "J48.001.Kappa": null, "MeanSkewnessOfNumericAtts": 1.2834247248759827, "Quartile1StdDevOfNumericAtts": 0.5037145546816209, "REPTreeDepth2AUC": null, "CfsSubsetEval_kNN1NErrRate": null, "kNN1NErrRate": null, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 6.833436722603094, "Quartile2AttributeEntropy": null, "REPTreeDepth2ErrRate": null, "CfsSubsetEval_kNN1NKappa": null, "kNN1NKappa": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2KurtosisOfNumericAtts": 1.8405593358557053, "REPTreeDepth2Kappa": null, "ClassEntropy": null, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.012139762742191, "Quartile2MeansOfNumericAtts": 5.863134168157418, "REPTreeDepth3AUC": null, "DecisionStumpAUC": null }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "44", "type": "numeric", "distinct": "367", "missing": "0", "target": "1", "min": "4", "max": "10", "mean": "6", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "559", "missing": "0", "identifier": "1", "distr": [] }, { "name": "AMW", "index": "1", "type": "numeric", "distinct": "383", "missing": "0", "min": "7", "max": "16", "mean": "9", "stdev": "1" }, { "name": "C.", "index": "2", "type": "numeric", "distinct": "132", "missing": "0", "min": "14", "max": "58", "mean": "42", "stdev": "5" }, { "name": "H.", "index": "3", "type": "numeric", "distinct": "128", "missing": "0", "min": "21", "max": "49", "mean": "38", "stdev": "5" }, { "name": "Me", "index": "4", "type": "numeric", "distinct": "77", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Mi", "index": "5", "type": "numeric", "distinct": "69", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Mp", "index": "6", "type": "numeric", "distinct": "148", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Mv", "index": "7", "type": "numeric", "distinct": "140", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "MW", "index": "8", "type": "numeric", "distinct": "413", "missing": "0", "min": "170", "max": "994", "mean": "402", "stdev": "117" }, { "name": "N.", "index": "9", "type": "numeric", "distinct": "106", "missing": "0", "min": "0", "max": "19", "mean": "9", "stdev": "3" }, { "name": "nAB", "index": "10", "type": "numeric", "distinct": "15", "missing": "0", "min": "0", "max": "34", "mean": "15", "stdev": "5" }, { "name": "nAT", "index": "11", "type": "numeric", "distinct": "63", "missing": "0", "min": "19", "max": "122", "mean": "46", "stdev": "15" }, { "name": "nB", "index": "12", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "nBM", "index": "13", "type": "numeric", "distinct": "29", "missing": "0", "min": "2", "max": "40", "mean": "18", "stdev": "5" }, { "name": "nBO", "index": "14", "type": "numeric", "distinct": "46", "missing": "0", "min": "10", "max": "73", "mean": "30", "stdev": "9" }, { "name": "nBR", "index": "15", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "4", "mean": "0", "stdev": "0" }, { "name": "nBT", "index": "16", "type": "numeric", "distinct": "64", "missing": "0", "min": "20", "max": "124", "mean": "49", "stdev": "16" }, { "name": "nC", "index": "17", "type": "numeric", "distinct": "30", "missing": "0", "min": "3", "max": "44", "mean": "19", "stdev": "6" }, { "name": "nCL", "index": "18", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "4", "mean": "0", "stdev": "0" }, { "name": "nCsp", "index": "19", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "nCsp2", "index": "20", "type": "numeric", "distinct": "21", "missing": "0", "min": "0", "max": "34", "mean": "15", "stdev": "4" }, { "name": "nCsp3", "index": "21", "type": "numeric", "distinct": "17", "missing": "0", "min": "0", "max": "17", "mean": "4", "stdev": "3" }, { "name": "nDB", "index": "22", "type": "numeric", "distinct": "12", "missing": "0", "min": "0", "max": "11", "mean": "3", "stdev": "2" }, { "name": "nF", "index": "23", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "6", "mean": "0", "stdev": "1" }, { "name": "nH", "index": "24", "type": "numeric", "distinct": "35", "missing": "0", "min": "5", "max": "51", "mean": "18", "stdev": "7" }, { "name": "nHet", "index": "25", "type": "numeric", "distinct": "20", "missing": "0", "min": "1", "max": "27", "mean": "9", "stdev": "4" }, { "name": "nHM", "index": "26", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "nI", "index": "27", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "nN", "index": "28", "type": "numeric", "distinct": "10", "missing": "0", "min": "0", "max": "9", "mean": "4", "stdev": "2" }, { "name": "nO", "index": "29", "type": "numeric", "distinct": "16", "missing": "0", "min": "0", "max": "18", "mean": "4", "stdev": "3" }, { "name": "nP", "index": "30", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "nS", "index": "31", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "1" }, { "name": "nSK", "index": "32", "type": "numeric", "distinct": "41", "missing": "0", "min": "11", "max": "71", "mean": "28", "stdev": "9" }, { "name": "nTB", "index": "33", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "nX", "index": "34", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "6", "mean": "0", "stdev": "1" }, { "name": "O.", "index": "35", "type": "numeric", "distinct": "117", "missing": "0", "min": "0", "max": "29", "mean": "8", "stdev": "5" }, { "name": "RBF", "index": "36", "type": "numeric", "distinct": "130", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "RBN", "index": "37", "type": "numeric", "distinct": "23", "missing": "0", "min": "0", "max": "30", "mean": "6", "stdev": "4" }, { "name": "SCBO", "index": "38", "type": "numeric", "distinct": "90", "missing": "0", "min": "12", "max": "95", "mean": "41", "stdev": "12" }, { "name": "Se", "index": "39", "type": "numeric", "distinct": "413", "missing": "0", "min": "19", "max": "126", "mean": "47", "stdev": "16" }, { "name": "Si", "index": "40", "type": "numeric", "distinct": "413", "missing": "0", "min": "20", "max": "139", "mean": "52", "stdev": "17" }, { "name": "Sp", "index": "41", "type": "numeric", "distinct": "405", "missing": "0", "min": "14", "max": "77", "mean": "32", "stdev": "9" }, { "name": "Sv", "index": "42", "type": "numeric", "distinct": "409", "missing": "0", "min": "12", "max": "77", "mean": "31", "stdev": "9" }, { "name": "X.", "index": "43", "type": "numeric", "distinct": "43", "missing": "0", "min": "0", "max": "16", "mean": "1", "stdev": "2" } ], "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 }