{ "data_id": "6380", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL301", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL301", "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: CHEMBL301 (TID: CHEMBL301), and it has 2577 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 17:38:48", "update_comment": null, "last_update": "2016-04-04 17:38:48", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/1859505\/data_34937.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-CHEMBL301", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL301 (TID: CHEMBL301), and it has 2577 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": 2577, "NumberOfFeatures": 45, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 44, "NumberOfSymbolicFeatures": 1, "REPTreeDepth3AUC": null, "DecisionStumpAUC": null, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -0.5723672166632157, "Quartile2MeansOfNumericAtts": 4.547729918509897, "REPTreeDepth3ErrRate": null, "DecisionStumpErrRate": null, "MaxKurtosisOfNumericAtts": 1285.9968922990315, "MinMeansOfNumericAtts": 0, "Quartile2MutualInformation": null, "REPTreeDepth3Kappa": null, "DecisionStumpKappa": null, "MaxMeansOfNumericAtts": 385.5730112533954, "MinMutualInformation": null, "Quartile2SkewnessOfNumericAtts": 0.6597810767525053, "RandomTreeDepth1AUC": null, "Dimensionality": 0.017462165308498253, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 2.174803763684734, "RandomTreeDepth1ErrRate": null, "EquivalentNumberOfAtts": null, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -0.3157570338891922, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "RandomTreeDepth1Kappa": null, "J48.00001.AUC": null, "MaxSkewnessOfNumericAtts": 35.87476599579857, "MinStdDevOfNumericAtts": 0, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 3.5370645351829086, "AutoCorrelation": -0.059421972049689055, "RandomTreeDepth2AUC": null, "J48.00001.ErrRate": null, "MaxStdDevOfNumericAtts": 78.60773799297964, "MinorityClassPercentage": null, "PercentageOfNumericFeatures": 97.77777777777777, "Quartile3MeansOfNumericAtts": 29.536670547147846, "CfsSubsetEval_DecisionStumpAUC": null, "RandomTreeDepth2ErrRate": null, "J48.00001.Kappa": null, "MeanAttributeEntropy": null, "MinorityClassSize": null, "PercentageOfSymbolicFeatures": 2.2222222222222223, "Quartile3MutualInformation": null, "CfsSubsetEval_DecisionStumpErrRate": null, "RandomTreeDepth2Kappa": null, "J48.0001.AUC": null, "MeanKurtosisOfNumericAtts": 33.94871981770199, "NaiveBayesAUC": null, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 1.330112745267966, "CfsSubsetEval_DecisionStumpKappa": null, "CfsSubsetEval_NaiveBayesAUC": null, "RandomTreeDepth3AUC": null, "J48.0001.ErrRate": null, "MeanMeansOfNumericAtts": 22.17406142625322, "NaiveBayesErrRate": null, "Quartile1KurtosisOfNumericAtts": 0.5236336280741267, "Quartile3StdDevOfNumericAtts": 5.579057272350876, "CfsSubsetEval_NaiveBayesErrRate": null, "RandomTreeDepth3ErrRate": null, "J48.0001.Kappa": null, "MeanMutualInformation": null, "NaiveBayesKappa": null, "Quartile1MeansOfNumericAtts": 0.6481802483507955, "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": 0.32672230596959645, "REPTreeDepth1Kappa": null, "REPTreeDepth2AUC": null, "CfsSubsetEval_kNN1NErrRate": null, "kNN1NAUC": null, "J48.001.Kappa": null, "MeanSkewnessOfNumericAtts": 1.9479075306408264, "Quartile1StdDevOfNumericAtts": 0.34133859264405525, "REPTreeDepth2ErrRate": null, "CfsSubsetEval_kNN1NKappa": null, "kNN1NErrRate": null, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 5.030302529374811, "Quartile2AttributeEntropy": null, "REPTreeDepth2Kappa": null, "ClassEntropy": null, "kNN1NKappa": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2KurtosisOfNumericAtts": 0.8675519234568903 }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "44", "type": "numeric", "distinct": "563", "missing": "0", "target": "1", "min": "4", "max": "10", "mean": "6", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "2577", "missing": "0", "identifier": "1", "distr": [] }, { "name": "AMW", "index": "1", "type": "numeric", "distinct": "1450", "missing": "0", "min": "6", "max": "15", "mean": "8", "stdev": "1" }, { "name": "C.", "index": "2", "type": "numeric", "distinct": "179", "missing": "0", "min": "24", "max": "56", "mean": "43", "stdev": "4" }, { "name": "H.", "index": "3", "type": "numeric", "distinct": "219", "missing": "0", "min": "20", "max": "57", "mean": "40", "stdev": "6" }, { "name": "Me", "index": "4", "type": "numeric", "distinct": "89", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Mi", "index": "5", "type": "numeric", "distinct": "81", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Mp", "index": "6", "type": "numeric", "distinct": "192", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Mv", "index": "7", "type": "numeric", "distinct": "190", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "MW", "index": "8", "type": "numeric", "distinct": "1870", "missing": "0", "min": "144", "max": "776", "mean": "386", "stdev": "79" }, { "name": "N.", "index": "9", "type": "numeric", "distinct": "166", "missing": "0", "min": "0", "max": "35", "mean": "10", "stdev": "4" }, { "name": "nAB", "index": "10", "type": "numeric", "distinct": "28", "missing": "0", "min": "0", "max": "35", "mean": "18", "stdev": "5" }, { "name": "nAT", "index": "11", "type": "numeric", "distinct": "73", "missing": "0", "min": "14", "max": "109", "mean": "46", "stdev": "11" }, { "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": "32", "missing": "0", "min": "4", "max": "37", "mean": "19", "stdev": "5" }, { "name": "nBO", "index": "14", "type": "numeric", "distinct": "44", "missing": "0", "min": "11", "max": "57", "mean": "30", "stdev": "6" }, { "name": "nBR", "index": "15", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "nBT", "index": "16", "type": "numeric", "distinct": "74", "missing": "0", "min": "15", "max": "110", "mean": "49", "stdev": "12" }, { "name": "nC", "index": "17", "type": "numeric", "distinct": "34", "missing": "0", "min": "4", "max": "39", "mean": "20", "stdev": "4" }, { "name": "nCL", "index": "18", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "0" }, { "name": "nCsp", "index": "19", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "0" }, { "name": "nCsp2", "index": "20", "type": "numeric", "distinct": "32", "missing": "0", "min": "3", "max": "35", "mean": "16", "stdev": "4" }, { "name": "nCsp3", "index": "21", "type": "numeric", "distinct": "17", "missing": "0", "min": "0", "max": "16", "mean": "4", "stdev": "3" }, { "name": "nDB", "index": "22", "type": "numeric", "distinct": "8", "missing": "0", "min": "0", "max": "10", "mean": "1", "stdev": "1" }, { "name": "nF", "index": "23", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "6", "mean": "0", "stdev": "1" }, { "name": "nH", "index": "24", "type": "numeric", "distinct": "43", "missing": "0", "min": "3", "max": "53", "mean": "19", "stdev": "6" }, { "name": "nHet", "index": "25", "type": "numeric", "distinct": "18", "missing": "0", "min": "3", "max": "23", "mean": "8", "stdev": "2" }, { "name": "nHM", "index": "26", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "6", "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": "14", "missing": "0", "min": "0", "max": "21", "mean": "5", "stdev": "2" }, { "name": "nO", "index": "29", "type": "numeric", "distinct": "10", "missing": "0", "min": "0", "max": "9", "mean": "2", "stdev": "1" }, { "name": "nP", "index": "30", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "nS", "index": "31", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "0", "stdev": "1" }, { "name": "nSK", "index": "32", "type": "numeric", "distinct": "41", "missing": "0", "min": "10", "max": "56", "mean": "27", "stdev": "6" }, { "name": "nTB", "index": "33", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "nX", "index": "34", "type": "numeric", "distinct": "8", "missing": "0", "min": "0", "max": "7", "mean": "1", "stdev": "1" }, { "name": "O.", "index": "35", "type": "numeric", "distinct": "128", "missing": "0", "min": "0", "max": "22", "mean": "4", "stdev": "3" }, { "name": "RBF", "index": "36", "type": "numeric", "distinct": "156", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "RBN", "index": "37", "type": "numeric", "distinct": "18", "missing": "0", "min": "0", "max": "18", "mean": "5", "stdev": "2" }, { "name": "SCBO", "index": "38", "type": "numeric", "distinct": "105", "missing": "0", "min": "15", "max": "75", "mean": "41", "stdev": "8" }, { "name": "Se", "index": "39", "type": "numeric", "distinct": "1841", "missing": "0", "min": "15", "max": "110", "mean": "47", "stdev": "11" }, { "name": "Si", "index": "40", "type": "numeric", "distinct": "1930", "missing": "0", "min": "16", "max": "127", "mean": "52", "stdev": "13" }, { "name": "Sp", "index": "41", "type": "numeric", "distinct": "1715", "missing": "0", "min": "10", "max": "67", "mean": "32", "stdev": "7" }, { "name": "Sv", "index": "42", "type": "numeric", "distinct": "1938", "missing": "0", "min": "10", "max": "64", "mean": "31", "stdev": "7" }, { "name": "X.", "index": "43", "type": "numeric", "distinct": "94", "missing": "0", "min": "0", "max": "18", "mean": "2", "stdev": "3" } ], "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 }