{ "data_id": "33951", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL259", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL259", "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: CHEMBL259 (TID: 10142), and it has 2872 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": "2016-07-15 14:06:35", "update_comment": null, "last_update": "2016-07-15 14:06:35", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3517949\/data_53746.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL259", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL259 (TID: 10142), and it has 2872 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": 2872, "NumberOfFeatures": 73, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 72, "NumberOfSymbolicFeatures": 1, "Quartile3AttributeEntropy": null, "MaxKurtosisOfNumericAtts": 49.86961017194334, "MinMeansOfNumericAtts": 0.07499025069637882, "PercentageOfInstancesWithMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 33.18524281775956, "MaxMeansOfNumericAtts": 796.6923579387186, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3MeansOfNumericAtts": 28.70465128830083, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.63013698630137, "Quartile3MutualInformation": null, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -1.9696113673362239, "PercentageOfSymbolicFeatures": 1.36986301369863, "Quartile3SkewnessOfNumericAtts": 3.9814916027019436, "MaxSkewnessOfNumericAtts": 5.272211451379358, "MinStdDevOfNumericAtts": 0.023454349020812112, "Quartile1AttributeEntropy": null, "Quartile3StdDevOfNumericAtts": 14.428152852411383, "MaxStdDevOfNumericAtts": 421.95568235199516, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": 1.7429601220876794, "StdvNominalAttDistinctValues": null, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 1.2652525243732595, "MeanKurtosisOfNumericAtts": 17.17166323474595, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 49.283095689221604, "Quartile1SkewnessOfNumericAtts": -0.1970552096740777, "AutoCorrelation": -0.04885823754788937, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.3924641362251363, "ClassEntropy": null, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "Dimensionality": 0.02541782729805014, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": 3.7491124906500115, "EquivalentNumberOfAtts": null, "MeanSkewnessOfNumericAtts": 2.0402870987547383, "Quartile2MeansOfNumericAtts": 5.4841622562674095, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 25.9694561720902, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": 2.100168880938157, "Quartile2StdDevOfNumericAtts": 0.7107886840529685, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.046506515292309, "PercentageOfBinaryFeatures": 0 }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "72", "type": "numeric", "distinct": "1057", "missing": "0", "target": "1", "min": "4", "max": "11", "mean": "6", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "2872", "missing": "0", "identifier": "1", "distr": [] }, { "name": "CMC.80", "index": "1", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "Infective.80", "index": "2", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "Neoplastic.80", "index": "3", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "Psychotic.80", "index": "4", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "Hypertens.80", "index": "5", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "VvdwZAZ", "index": "6", "type": "numeric", "distinct": "2054", "missing": "0", "min": "164", "max": "5702", "mean": "586", "stdev": "320" }, { "name": "Inflammat.80", "index": "7", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "SpMax4_Bh.i.", "index": "8", "type": "numeric", "distinct": "549", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "Eig14_EA", "index": "9", "type": "numeric", "distinct": "1092", "missing": "0", "min": "-2", "max": "3", "mean": "1", "stdev": "1" }, { "name": "SM08_AEA.dm.", "index": "10", "type": "numeric", "distinct": "1092", "missing": "0", "min": "-2", "max": "3", "mean": "1", "stdev": "1" }, { "name": "Eig12_AEA.dm.", "index": "11", "type": "numeric", "distinct": "1067", "missing": "0", "min": "-2", "max": "4", "mean": "2", "stdev": "1" }, { "name": "Eta_L", "index": "12", "type": "numeric", "distinct": "2279", "missing": "0", "min": "3", "max": "103", "mean": "12", "stdev": "6" }, { "name": "Eig06_EA.dm.", "index": "13", "type": "numeric", "distinct": "233", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "1" }, { "name": "Eig12_EA.ri.", "index": "14", "type": "numeric", "distinct": "1091", "missing": "0", "min": "-2", "max": "3", "mean": "1", "stdev": "1" }, { "name": "P_VSA_p_1", "index": "15", "type": "numeric", "distinct": "247", "missing": "0", "min": "82", "max": "3143", "mean": "449", "stdev": "205" }, { "name": "Eig12_AEA.ri.", "index": "16", "type": "numeric", "distinct": "1107", "missing": "0", "min": "-1", "max": "4", "mean": "2", "stdev": "1" }, { "name": "ATSC1p", "index": "17", "type": "numeric", "distinct": "1933", "missing": "0", "min": "1", "max": "59", "mean": "8", "stdev": "4" }, { "name": "ATS2e", "index": "18", "type": "numeric", "distinct": "1102", "missing": "0", "min": "4", "max": "7", "mean": "5", "stdev": "0" }, { "name": "ATS2i", "index": "19", "type": "numeric", "distinct": "1116", "missing": "0", "min": "4", "max": "7", "mean": "5", "stdev": "0" }, { "name": "nCsp3", "index": "20", "type": "numeric", "distinct": "65", "missing": "0", "min": "0", "max": "124", "mean": "15", "stdev": "9" }, { "name": "Eig10_EA.ri.", "index": "21", "type": "numeric", "distinct": "1073", "missing": "0", "min": "-1", "max": "3", "mean": "2", "stdev": "1" }, { "name": "SpMaxA_EA.ri.", "index": "22", "type": "numeric", "distinct": "146", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "DLS_05", "index": "23", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SpMaxA_AEA.ed.", "index": "24", "type": "numeric", "distinct": "280", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "ATS1e", "index": "25", "type": "numeric", "distinct": "1061", "missing": "0", "min": "3", "max": "7", "mean": "4", "stdev": "0" }, { "name": "DLS_01", "index": "26", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "X1Kup", "index": "27", "type": "numeric", "distinct": "2305", "missing": "0", "min": "4", "max": "135", "mean": "15", "stdev": "8" }, { "name": "VvdwMG", "index": "28", "type": "numeric", "distinct": "1935", "missing": "0", "min": "99", "max": "2945", "mean": "330", "stdev": "173" }, { "name": "Vx", "index": "29", "type": "numeric", "distinct": "1935", "missing": "0", "min": "233", "max": "7177", "mean": "797", "stdev": "422" }, { "name": "Sv", "index": "30", "type": "numeric", "distinct": "2010", "missing": "0", "min": "14", "max": "477", "mean": "53", "stdev": "28" }, { "name": "X1Per", "index": "31", "type": "numeric", "distinct": "2259", "missing": "0", "min": "3", "max": "110", "mean": "12", "stdev": "6" }, { "name": "X0v", "index": "32", "type": "numeric", "distinct": "2224", "missing": "0", "min": "9", "max": "231", "mean": "26", "stdev": "13" }, { "name": "ATSC6m", "index": "33", "type": "numeric", "distinct": "2596", "missing": "0", "min": "2", "max": "629", "mean": "68", "stdev": "41" }, { "name": "X1MulPer", "index": "34", "type": "numeric", "distinct": "2260", "missing": "0", "min": "3", "max": "133", "mean": "15", "stdev": "8" }, { "name": "S1K", "index": "35", "type": "numeric", "distinct": "1747", "missing": "0", "min": "10", "max": "329", "mean": "34", "stdev": "20" }, { "name": "Mv", "index": "36", "type": "numeric", "distinct": "196", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Eig11_EA", "index": "37", "type": "numeric", "distinct": "992", "missing": "0", "min": "-2", "max": "3", "mean": "1", "stdev": "1" }, { "name": "SM05_AEA.dm.", "index": "38", "type": "numeric", "distinct": "992", "missing": "0", "min": "-2", "max": "3", "mean": "1", "stdev": "1" }, { "name": "ATSC8i", "index": "39", "type": "numeric", "distinct": "1982", "missing": "0", "min": "0", "max": "32", "mean": "3", "stdev": "2" }, { "name": "ATSC7m", "index": "40", "type": "numeric", "distinct": "2614", "missing": "0", "min": "5", "max": "682", "mean": "70", "stdev": "47" }, { "name": "X1v", "index": "41", "type": "numeric", "distinct": "2274", "missing": "0", "min": "5", "max": "137", "mean": "16", "stdev": "8" }, { "name": "ATSC6v", "index": "42", "type": "numeric", "distinct": "2557", "missing": "0", "min": "2", "max": "258", "mean": "30", "stdev": "17" }, { "name": "ATSC8m", "index": "43", "type": "numeric", "distinct": "2600", "missing": "0", "min": "2", "max": "719", "mean": "71", "stdev": "51" }, { "name": "H.", "index": "44", "type": "numeric", "distinct": "245", "missing": "0", "min": "19", "max": "63", "mean": "48", "stdev": "5" }, { "name": "X3v", "index": "45", "type": "numeric", "distinct": "2274", "missing": "0", "min": "2", "max": "69", "mean": "9", "stdev": "4" }, { "name": "ATSC4m", "index": "46", "type": "numeric", "distinct": "2578", "missing": "0", "min": "8", "max": "533", "mean": "62", "stdev": "34" }, { "name": "ATSC7v", "index": "47", "type": "numeric", "distinct": "2556", "missing": "0", "min": "2", "max": "282", "mean": "31", "stdev": "19" }, { "name": "ATSC6p", "index": "48", "type": "numeric", "distinct": "2507", "missing": "0", "min": "2", "max": "170", "mean": "21", "stdev": "11" }, { "name": "ATSC5m", "index": "49", "type": "numeric", "distinct": "2592", "missing": "0", "min": "6", "max": "565", "mean": "64", "stdev": "37" }, { "name": "LLS_02", "index": "50", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SM02_AEA.bo.", "index": "51", "type": "numeric", "distinct": "778", "missing": "0", "min": "4", "max": "8", "mean": "5", "stdev": "0" }, { "name": "DLS_02", "index": "52", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "ATS7i", "index": "53", "type": "numeric", "distinct": "1415", "missing": "0", "min": "3", "max": "8", "mean": "6", "stdev": "1" }, { "name": "ATS6i", "index": "54", "type": "numeric", "distinct": "1325", "missing": "0", "min": "3", "max": "8", "mean": "6", "stdev": "1" }, { "name": "P_VSA_e_3", "index": "55", "type": "numeric", "distinct": "451", "missing": "0", "min": "0", "max": "1940", "mean": "97", "stdev": "122" }, { "name": "Eta_C_A", "index": "56", "type": "numeric", "distinct": "915", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "ATS6e", "index": "57", "type": "numeric", "distinct": "1350", "missing": "0", "min": "3", "max": "8", "mean": "5", "stdev": "1" }, { "name": "ATS7e", "index": "58", "type": "numeric", "distinct": "1415", "missing": "0", "min": "3", "max": "8", "mean": "5", "stdev": "1" }, { "name": "ATS5m", "index": "59", "type": "numeric", "distinct": "1274", "missing": "0", "min": "3", "max": "7", "mean": "4", "stdev": "0" }, { "name": "P_VSA_MR_1", "index": "60", "type": "numeric", "distinct": "184", "missing": "0", "min": "59", "max": "2295", "mean": "357", "stdev": "146" }, { "name": "ATSC7p", "index": "61", "type": "numeric", "distinct": "2501", "missing": "0", "min": "2", "max": "185", "mean": "22", "stdev": "12" }, { "name": "SpMin4_Bh.m.", "index": "62", "type": "numeric", "distinct": "484", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "ATSC3m", "index": "63", "type": "numeric", "distinct": "2496", "missing": "0", "min": "7", "max": "467", "mean": "54", "stdev": "30" }, { "name": "Chi0_EA.bo.", "index": "64", "type": "numeric", "distinct": "2027", "missing": "0", "min": "7", "max": "254", "mean": "27", "stdev": "15" }, { "name": "ATSC5v", "index": "65", "type": "numeric", "distinct": "2560", "missing": "0", "min": "3", "max": "238", "mean": "29", "stdev": "15" }, { "name": "ATSC4p", "index": "66", "type": "numeric", "distinct": "2456", "missing": "0", "min": "4", "max": "144", "mean": "20", "stdev": "9" }, { "name": "ATS5p", "index": "67", "type": "numeric", "distinct": "1245", "missing": "0", "min": "3", "max": "7", "mean": "5", "stdev": "0" }, { "name": "ATS8i", "index": "68", "type": "numeric", "distinct": "1486", "missing": "0", "min": "3", "max": "8", "mean": "6", "stdev": "1" }, { "name": "ATS6p", "index": "69", "type": "numeric", "distinct": "1303", "missing": "0", "min": "3", "max": "7", "mean": "5", "stdev": "0" }, { "name": "C.008", "index": "70", "type": "numeric", "distinct": "21", "missing": "0", "min": "0", "max": "30", "mean": "2", "stdev": "3" }, { "name": "ATSC6i", "index": "71", "type": "numeric", "distinct": "1898", "missing": "0", "min": "0", "max": "27", "mean": "3", "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 }