{ "data_id": "26160", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL2129", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL2129", "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: CHEMBL2129 (TID: 10959), and it has 90 rows and 60 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 18:36:07", "update_comment": null, "last_update": "2016-07-14 18:36:07", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3294709\/data_52158.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL2129", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL2129 (TID: 10959), and it has 90 rows and 60 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": 90, "NumberOfFeatures": 62, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 61, "NumberOfSymbolicFeatures": 1, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 1.9631, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": 1.464904853044538, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 14.78398670309654, "Quartile1SkewnessOfNumericAtts": -0.9605379279730131, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.3083823653312965, "AutoCorrelation": 0.30995505617977537, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "ClassEntropy": null, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": -0.028926563574800834, "Dimensionality": 0.6888888888888889, "MeanSkewnessOfNumericAtts": -0.46152749397760673, "Quartile2MeansOfNumericAtts": 3.817388888888889, "EquivalentNumberOfAtts": null, "MeanStdDevOfNumericAtts": 3.699338562785899, "Quartile2MutualInformation": null, "MajorityClassPercentage": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": -0.6346529156453853, "MajorityClassSize": null, "MinKurtosisOfNumericAtts": -1.7243480848961001, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.7914759083403271, "MaxAttributeEntropy": null, "MaxKurtosisOfNumericAtts": 10.98318438159311, "MinMeansOfNumericAtts": -0.7726555555555555, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 227.58587777777777, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 3.128871885197043, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.38709677419355, "Quartile3MeansOfNumericAtts": 9.215811111111112, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -2.8449813756948092, "PercentageOfSymbolicFeatures": 1.6129032258064515, "Quartile3MutualInformation": null, "MaxSkewnessOfNumericAtts": 2.1652720039909155, "MinStdDevOfNumericAtts": 0.0485248575242917, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 0.12203799357662316, "MaxStdDevOfNumericAtts": 42.522760952575, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": -0.7699565414648091, "Quartile3StdDevOfNumericAtts": 2.5622617716030662 }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "61", "type": "numeric", "distinct": "59", "missing": "0", "target": "1", "min": "4", "max": "9", "mean": "6", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "90", "missing": "0", "identifier": "1", "distr": [] }, { "name": "SdssC", "index": "1", "type": "numeric", "distinct": "81", "missing": "0", "min": "-2", "max": "2", "mean": "-1", "stdev": "1" }, { "name": "Chi1_EA.dm.", "index": "2", "type": "numeric", "distinct": "58", "missing": "0", "min": "12", "max": "34", "mean": "25", "stdev": "5" }, { "name": "CATS2D_07_DL", "index": "3", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "3", "stdev": "1" }, { "name": "Eig08_AEA.dm.", "index": "4", "type": "numeric", "distinct": "67", "missing": "0", "min": "0", "max": "3", "mean": "2", "stdev": "1" }, { "name": "HVcpx", "index": "5", "type": "numeric", "distinct": "60", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "P_VSA_p_2", "index": "6", "type": "numeric", "distinct": "21", "missing": "0", "min": "21", "max": "180", "mean": "109", "stdev": "28" }, { "name": "Eig07_AEA.dm.", "index": "7", "type": "numeric", "distinct": "60", "missing": "0", "min": "1", "max": "3", "mean": "2", "stdev": "0" }, { "name": "CATS2D_02_DA", "index": "8", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "2", "stdev": "1" }, { "name": "DECC", "index": "9", "type": "numeric", "distinct": "56", "missing": "0", "min": "1", "max": "4", "mean": "2", "stdev": "1" }, { "name": "Eig04_EA", "index": "10", "type": "numeric", "distinct": "47", "missing": "0", "min": "2", "max": "3", "mean": "3", "stdev": "0" }, { "name": "SM12_AEA.bo.", "index": "11", "type": "numeric", "distinct": "47", "missing": "0", "min": "2", "max": "3", "mean": "3", "stdev": "0" }, { "name": "TPSA.Tot.", "index": "12", "type": "numeric", "distinct": "23", "missing": "0", "min": "47", "max": "120", "mean": "90", "stdev": "23" }, { "name": "X4v", "index": "13", "type": "numeric", "distinct": "81", "missing": "0", "min": "2", "max": "6", "mean": "5", "stdev": "1" }, { "name": "AECC", "index": "14", "type": "numeric", "distinct": "58", "missing": "0", "min": "7", "max": "26", "mean": "13", "stdev": "3" }, { "name": "IDE", "index": "15", "type": "numeric", "distinct": "56", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "Eig07_AEA.ed.", "index": "16", "type": "numeric", "distinct": "46", "missing": "0", "min": "2", "max": "5", "mean": "5", "stdev": "1" }, { "name": "CATS2D_06_DL", "index": "17", "type": "numeric", "distinct": "8", "missing": "0", "min": "0", "max": "7", "mean": "4", "stdev": "2" }, { "name": "Eig01_AEA.dm.", "index": "18", "type": "numeric", "distinct": "21", "missing": "0", "min": "3", "max": "5", "mean": "5", "stdev": "1" }, { "name": "nRSR", "index": "19", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "1" }, { "name": "NssS", "index": "20", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "1" }, { "name": "SM04_EA.dm.", "index": "21", "type": "numeric", "distinct": "26", "missing": "0", "min": "2", "max": "8", "mean": "5", "stdev": "2" }, { "name": "SpDiam_AEA.dm.", "index": "22", "type": "numeric", "distinct": "21", "missing": "0", "min": "5", "max": "7", "mean": "7", "stdev": "1" }, { "name": "SpDiam_EA.dm.", "index": "23", "type": "numeric", "distinct": "13", "missing": "0", "min": "3", "max": "10", "mean": "6", "stdev": "2" }, { "name": "SpMax_AEA.dm.", "index": "24", "type": "numeric", "distinct": "21", "missing": "0", "min": "3", "max": "5", "mean": "5", "stdev": "1" }, { "name": "SssS", "index": "25", "type": "numeric", "distinct": "44", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "SpMax2_Bh.v.", "index": "26", "type": "numeric", "distinct": "43", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "SAdon", "index": "27", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "85", "mean": "55", "stdev": "14" }, { "name": "Eig03_AEA.dm.", "index": "28", "type": "numeric", "distinct": "42", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "NNRS", "index": "29", "type": "numeric", "distinct": "3", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Rbrid", "index": "30", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "RCI", "index": "31", "type": "numeric", "distinct": "4", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "RFD", "index": "32", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Eig09_AEA.dm.", "index": "33", "type": "numeric", "distinct": "61", "missing": "0", "min": "0", "max": "3", "mean": "2", "stdev": "1" }, { "name": "ZM2Mad", "index": "34", "type": "numeric", "distinct": "78", "missing": "0", "min": "96", "max": "299", "mean": "228", "stdev": "43" }, { "name": "ICR", "index": "35", "type": "numeric", "distinct": "55", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "TPSA.NO.", "index": "36", "type": "numeric", "distinct": "21", "missing": "0", "min": "15", "max": "112", "mean": "68", "stdev": "18" }, { "name": "X3sol", "index": "37", "type": "numeric", "distinct": "64", "missing": "0", "min": "5", "max": "17", "mean": "11", "stdev": "2" }, { "name": "Eig08_AEA.ed.", "index": "38", "type": "numeric", "distinct": "45", "missing": "0", "min": "2", "max": "5", "mean": "4", "stdev": "1" }, { "name": "X3v", "index": "39", "type": "numeric", "distinct": "80", "missing": "0", "min": "2", "max": "9", "mean": "6", "stdev": "1" }, { "name": "SpMax2_Bh.e.", "index": "40", "type": "numeric", "distinct": "43", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "Vindex", "index": "41", "type": "numeric", "distinct": "43", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Xindex", "index": "42", "type": "numeric", "distinct": "43", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "Yindex", "index": "43", "type": "numeric", "distinct": "56", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "CATS2D_02_NL", "index": "44", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "2", "stdev": "1" }, { "name": "Eig03_EA.dm.", "index": "45", "type": "numeric", "distinct": "13", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "SM02_EA.dm.", "index": "46", "type": "numeric", "distinct": "26", "missing": "0", "min": "2", "max": "5", "mean": "3", "stdev": "1" }, { "name": "Eig01_EA.dm.", "index": "47", "type": "numeric", "distinct": "12", "missing": "0", "min": "1", "max": "6", "mean": "3", "stdev": "1" }, { "name": "SM06_EA.dm.", "index": "48", "type": "numeric", "distinct": "23", "missing": "0", "min": "3", "max": "11", "mean": "7", "stdev": "2" }, { "name": "SM08_EA.dm.", "index": "49", "type": "numeric", "distinct": "22", "missing": "0", "min": "4", "max": "14", "mean": "9", "stdev": "3" }, { "name": "SM10_EA.dm.", "index": "50", "type": "numeric", "distinct": "20", "missing": "0", "min": "4", "max": "18", "mean": "12", "stdev": "4" }, { "name": "SM12_EA.dm.", "index": "51", "type": "numeric", "distinct": "18", "missing": "0", "min": "5", "max": "21", "mean": "14", "stdev": "5" }, { "name": "SM13_EA.dm.", "index": "52", "type": "numeric", "distinct": "15", "missing": "0", "min": "0", "max": "23", "mean": "13", "stdev": "7" }, { "name": "SM14_EA.dm.", "index": "53", "type": "numeric", "distinct": "18", "missing": "0", "min": "6", "max": "25", "mean": "16", "stdev": "6" }, { "name": "SM15_EA.dm.", "index": "54", "type": "numeric", "distinct": "15", "missing": "0", "min": "0", "max": "27", "mean": "15", "stdev": "8" }, { "name": "SpMax_EA.dm.", "index": "55", "type": "numeric", "distinct": "12", "missing": "0", "min": "1", "max": "6", "mean": "3", "stdev": "1" }, { "name": "MATS4i", "index": "56", "type": "numeric", "distinct": "67", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "P_VSA_LogP_4", "index": "57", "type": "numeric", "distinct": "15", "missing": "0", "min": "0", "max": "159", "mean": "88", "stdev": "25" }, { "name": "LLS_01", "index": "58", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "SpMax2_Bh.i.", "index": "59", "type": "numeric", "distinct": "42", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "SsOH", "index": "60", "type": "numeric", "distinct": "70", "missing": "0", "min": "0", "max": "19", "mean": "9", "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 }