{ "data_id": "40309", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL1741171", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL1741171", "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: CHEMBL1741171 (TID: 103967), and it has 1875 rows and 71 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": "2016-07-16 11:00:42", "update_comment": null, "last_update": "2016-07-16 11:00:42", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3693138\/data_53748.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL1741171", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL1741171 (TID: 103967), and it has 1875 rows and 71 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": 1875, "NumberOfFeatures": 73, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 72, "NumberOfSymbolicFeatures": 1, "ClassEntropy": null, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "Dimensionality": 0.038933333333333334, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": 1.8841511887841, "EquivalentNumberOfAtts": null, "MeanSkewnessOfNumericAtts": 1.2869606993288674, "Quartile2MeansOfNumericAtts": 1.2763474666666659, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 3.1639166735818334, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": 1.0124069913844447, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -0.8119338151691458, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.6204276626957428, "MaxKurtosisOfNumericAtts": 37.22433588375427, "MinMeansOfNumericAtts": -0.029261333333333334, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 78.60656586666667, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 5.1376508716562626, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.63013698630137, "Quartile3MeansOfNumericAtts": 4.012788933333333, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -1.1588795192338404, "PercentageOfSymbolicFeatures": 1.36986301369863, "Quartile3MutualInformation": null, "MaxSkewnessOfNumericAtts": 5.689707384462373, "MinStdDevOfNumericAtts": 0.043331727548169455, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 2.367136904184389, "MaxStdDevOfNumericAtts": 39.40934283820889, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": 0.625539829802818, "Quartile3StdDevOfNumericAtts": 2.002171693729366, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 0.23560000000000042, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": 4.030210043140812, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 5.112785122222222, "Quartile1SkewnessOfNumericAtts": 0.3156002703813731, "AutoCorrelation": 0.3049028815368192, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.31870424246592527 }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "72", "type": "numeric", "distinct": "1029", "missing": "0", "target": "1", "min": "4", "max": "8", "mean": "5", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "1875", "missing": "0", "identifier": "1", "distr": [] }, { "name": "CATS2D_04_DL", "index": "1", "type": "numeric", "distinct": "15", "missing": "0", "min": "0", "max": "20", "mean": "2", "stdev": "3" }, { "name": "CATS2D_06_DD", "index": "2", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "8", "mean": "0", "stdev": "1" }, { "name": "CATS2D_06_DA", "index": "3", "type": "numeric", "distinct": "9", "missing": "0", "min": "0", "max": "9", "mean": "1", "stdev": "1" }, { "name": "NaaNH", "index": "4", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "NaasC", "index": "5", "type": "numeric", "distinct": "13", "missing": "0", "min": "0", "max": "12", "mean": "4", "stdev": "2" }, { "name": "CATS2D_03_DD", "index": "6", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "0", "stdev": "0" }, { "name": "CATS2D_06_DL", "index": "7", "type": "numeric", "distinct": "13", "missing": "0", "min": "0", "max": "12", "mean": "2", "stdev": "2" }, { "name": "CATS2D_01_DA", "index": "8", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "N.073", "index": "9", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "1" }, { "name": "nPyrazoles", "index": "10", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "SsOH", "index": "11", "type": "numeric", "distinct": "490", "missing": "0", "min": "0", "max": "65", "mean": "4", "stdev": "7" }, { "name": "C.029", "index": "12", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "4", "mean": "0", "stdev": "1" }, { "name": "StsC", "index": "13", "type": "numeric", "distinct": "249", "missing": "0", "min": "0", "max": "8", "mean": "0", "stdev": "1" }, { "name": "nArOH", "index": "14", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "6", "mean": "0", "stdev": "1" }, { "name": "C.025", "index": "15", "type": "numeric", "distinct": "10", "missing": "0", "min": "0", "max": "9", "mean": "2", "stdev": "1" }, { "name": "Eig03_EA.bo.", "index": "16", "type": "numeric", "distinct": "895", "missing": "0", "min": "2", "max": "5", "mean": "3", "stdev": "0" }, { "name": "SM13_AEA.ri.", "index": "17", "type": "numeric", "distinct": "895", "missing": "0", "min": "2", "max": "5", "mean": "3", "stdev": "0" }, { "name": "StN", "index": "18", "type": "numeric", "distinct": "286", "missing": "0", "min": "0", "max": "39", "mean": "2", "stdev": "5" }, { "name": "Eig03_EA.dm.", "index": "19", "type": "numeric", "distinct": "240", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "nRCN", "index": "20", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "0", "stdev": "0" }, { "name": "CATS2D_02_DL", "index": "21", "type": "numeric", "distinct": "10", "missing": "0", "min": "0", "max": "12", "mean": "2", "stdev": "2" }, { "name": "P_VSA_MR_5", "index": "22", "type": "numeric", "distinct": "1190", "missing": "0", "min": "0", "max": "184", "mean": "43", "stdev": "30" }, { "name": "CATS2D_07_DA", "index": "23", "type": "numeric", "distinct": "8", "missing": "0", "min": "0", "max": "8", "mean": "0", "stdev": "1" }, { "name": "SAdon", "index": "24", "type": "numeric", "distinct": "88", "missing": "0", "min": "0", "max": "256", "mean": "33", "stdev": "34" }, { "name": "SM08_EA.dm.", "index": "25", "type": "numeric", "distinct": "725", "missing": "0", "min": "0", "max": "14", "mean": "6", "stdev": "4" }, { "name": "MATS1i", "index": "26", "type": "numeric", "distinct": "557", "missing": "0", "min": "-1", "max": "0", "mean": "0", "stdev": "0" }, { "name": "O.057", "index": "27", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "6", "mean": "0", "stdev": "1" }, { "name": "NtN", "index": "28", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "0", "stdev": "1" }, { "name": "SM06_EA.dm.", "index": "29", "type": "numeric", "distinct": "767", "missing": "0", "min": "0", "max": "11", "mean": "5", "stdev": "3" }, { "name": "CATS2D_05_DL", "index": "30", "type": "numeric", "distinct": "11", "missing": "0", "min": "0", "max": "10", "mean": "2", "stdev": "2" }, { "name": "nCsp", "index": "31", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "0", "stdev": "1" }, { "name": "nTB", "index": "32", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "0", "stdev": "1" }, { "name": "NtsC", "index": "33", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "0", "stdev": "1" }, { "name": "SM04_EA.dm.", "index": "34", "type": "numeric", "distinct": "815", "missing": "0", "min": "0", "max": "7", "mean": "4", "stdev": "2" }, { "name": "SpDiam_EA.dm.", "index": "35", "type": "numeric", "distinct": "316", "missing": "0", "min": "0", "max": "10", "mean": "4", "stdev": "2" }, { "name": "H.051", "index": "36", "type": "numeric", "distinct": "11", "missing": "0", "min": "0", "max": "10", "mean": "1", "stdev": "2" }, { "name": "H.050", "index": "37", "type": "numeric", "distinct": "8", "missing": "0", "min": "0", "max": "9", "mean": "1", "stdev": "1" }, { "name": "nHDon", "index": "38", "type": "numeric", "distinct": "8", "missing": "0", "min": "0", "max": "9", "mean": "1", "stdev": "1" }, { "name": "SaaNH", "index": "39", "type": "numeric", "distinct": "249", "missing": "0", "min": "0", "max": "7", "mean": "1", "stdev": "1" }, { "name": "SpDiam_EA.ri.", "index": "40", "type": "numeric", "distinct": "716", "missing": "0", "min": "4", "max": "6", "mean": "5", "stdev": "0" }, { "name": "GATS4s", "index": "41", "type": "numeric", "distinct": "822", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "P_VSA_i_4", "index": "42", "type": "numeric", "distinct": "463", "missing": "0", "min": "0", "max": "160", "mean": "47", "stdev": "33" }, { "name": "SpMAD_EA.dm.", "index": "43", "type": "numeric", "distinct": "635", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "SpMax3_Bh.e.", "index": "44", "type": "numeric", "distinct": "606", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "Eta_sh_y", "index": "45", "type": "numeric", "distinct": "299", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "MATS5m", "index": "46", "type": "numeric", "distinct": "533", "missing": "0", "min": "-1", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Eig01_EA.ri.", "index": "47", "type": "numeric", "distinct": "711", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SpMax_EA.ri.", "index": "48", "type": "numeric", "distinct": "711", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "NsOH", "index": "49", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "6", "mean": "0", "stdev": "1" }, { "name": "CATS2D_08_DA", "index": "50", "type": "numeric", "distinct": "8", "missing": "0", "min": "0", "max": "10", "mean": "0", "stdev": "1" }, { "name": "Hy", "index": "51", "type": "numeric", "distinct": "585", "missing": "0", "min": "-1", "max": "6", "mean": "0", "stdev": "1" }, { "name": "SpMaxA_EA.dm.", "index": "52", "type": "numeric", "distinct": "187", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Eig02_EA.ri.", "index": "53", "type": "numeric", "distinct": "703", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "ATSC7m", "index": "54", "type": "numeric", "distinct": "1817", "missing": "0", "min": "0", "max": "86", "mean": "21", "stdev": "12" }, { "name": "C.020", "index": "55", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "SM10_EA.dm.", "index": "56", "type": "numeric", "distinct": "633", "missing": "0", "min": "0", "max": "18", "mean": "8", "stdev": "4" }, { "name": "N.066", "index": "57", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "nRNH2", "index": "58", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "GGI6", "index": "59", "type": "numeric", "distinct": "775", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "Eig01_AEA.ri.", "index": "60", "type": "numeric", "distinct": "701", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SpMax_AEA.ri.", "index": "61", "type": "numeric", "distinct": "701", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "LLS_01", "index": "62", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "SpDiam_EA.ed.", "index": "63", "type": "numeric", "distinct": "1314", "missing": "0", "min": "13", "max": "32", "mean": "19", "stdev": "2" }, { "name": "SpMAD_EA.ed.", "index": "64", "type": "numeric", "distinct": "886", "missing": "0", "min": "3", "max": "6", "mean": "4", "stdev": "0" }, { "name": "Eig02_EA.dm.", "index": "65", "type": "numeric", "distinct": "288", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "GNar", "index": "66", "type": "numeric", "distinct": "300", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "SM12_EA.dm.", "index": "67", "type": "numeric", "distinct": "586", "missing": "0", "min": "0", "max": "21", "mean": "9", "stdev": "5" }, { "name": "SM14_EA.dm.", "index": "68", "type": "numeric", "distinct": "551", "missing": "0", "min": "0", "max": "25", "mean": "10", "stdev": "6" }, { "name": "C.017", "index": "69", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "0" }, { "name": "nR.Ct", "index": "70", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "0" }, { "name": "P_VSA_LogP_4", "index": "71", "type": "numeric", "distinct": "716", "missing": "0", "min": "0", "max": "317", "mean": "79", "stdev": "39" } ], "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 }