{ "data_id": "32635", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4068", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4068", "version": 8, "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: CHEMBL4068 (TID: 10074), and it has 377 rows and 67 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 10:43:45", "update_comment": null, "last_update": "2016-07-15 10:43:45", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3486055\/data_53280.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4068", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL4068 (TID: 10074), and it has 377 rows and 67 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": 377, "NumberOfFeatures": 69, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 68, "NumberOfSymbolicFeatures": 1, "ClassEntropy": null, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "Dimensionality": 0.1830238726790451, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": 0.5141880605439997, "EquivalentNumberOfAtts": null, "MeanSkewnessOfNumericAtts": 0.5469822832739086, "Quartile2MeansOfNumericAtts": 5.931791777188328, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 236.54549248790784, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": 0.6131426760145666, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.7209340323566178, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 1.6941864697929279, "MaxKurtosisOfNumericAtts": 41.00467183608802, "MinMeansOfNumericAtts": 0.12581432360742706, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 17635.416445623352, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 1.7483630488423316, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.55072463768117, "Quartile3MeansOfNumericAtts": 55.323171750663136, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -1.0816183618762312, "PercentageOfSymbolicFeatures": 1.4492753623188406, "Quartile3MutualInformation": null, "MaxSkewnessOfNumericAtts": 4.318851015245986, "MinStdDevOfNumericAtts": 0.0161522348087363, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 0.9239689057266443, "MaxStdDevOfNumericAtts": 14736.324328939954, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": -0.7458354243569503, "Quartile3StdDevOfNumericAtts": 15.011363657865827, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 2.889303050397878, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": 1.590004757239727, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 319.2201873147139, "Quartile1SkewnessOfNumericAtts": -0.026184607669318648, "AutoCorrelation": -0.06630851063829807, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.4276535370015039 }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "68", "type": "numeric", "distinct": "259", "missing": "0", "target": "1", "min": "4", "max": "9", "mean": "6", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "377", "missing": "0", "identifier": "1", "distr": [] }, { "name": "SpMax8_Bh.s.", "index": "1", "type": "numeric", "distinct": "211", "missing": "0", "min": "3", "max": "7", "mean": "5", "stdev": "1" }, { "name": "ATS3s", "index": "2", "type": "numeric", "distinct": "310", "missing": "0", "min": "5", "max": "7", "mean": "6", "stdev": "0" }, { "name": "Eta_alpha_A", "index": "3", "type": "numeric", "distinct": "68", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "DELS", "index": "4", "type": "numeric", "distinct": "357", "missing": "0", "min": "17", "max": "181", "mean": "60", "stdev": "25" }, { "name": "NdssC", "index": "5", "type": "numeric", "distinct": "10", "missing": "0", "min": "0", "max": "11", "mean": "4", "stdev": "2" }, { "name": "SpMax7_Bh.s.", "index": "6", "type": "numeric", "distinct": "229", "missing": "0", "min": "4", "max": "7", "mean": "5", "stdev": "1" }, { "name": "ATS2s", "index": "7", "type": "numeric", "distinct": "284", "missing": "0", "min": "5", "max": "7", "mean": "6", "stdev": "0" }, { "name": "ATSC6i", "index": "8", "type": "numeric", "distinct": "333", "missing": "0", "min": "0", "max": "6", "mean": "2", "stdev": "1" }, { "name": "CATS2D_03_DA", "index": "9", "type": "numeric", "distinct": "9", "missing": "0", "min": "0", "max": "10", "mean": "2", "stdev": "2" }, { "name": "Psi_e_0", "index": "10", "type": "numeric", "distinct": "343", "missing": "0", "min": "6", "max": "32", "mean": "13", "stdev": "4" }, { "name": "Eta_F", "index": "11", "type": "numeric", "distinct": "355", "missing": "0", "min": "14", "max": "107", "mean": "39", "stdev": "14" }, { "name": "X0", "index": "12", "type": "numeric", "distinct": "193", "missing": "0", "min": "11", "max": "63", "mean": "25", "stdev": "7" }, { "name": "ATSC3e", "index": "13", "type": "numeric", "distinct": "295", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "1" }, { "name": "IDDE", "index": "14", "type": "numeric", "distinct": "185", "missing": "0", "min": "2", "max": "6", "mean": "5", "stdev": "0" }, { "name": "SM06_AEA.bo.", "index": "15", "type": "numeric", "distinct": "225", "missing": "0", "min": "10", "max": "11", "mean": "10", "stdev": "0" }, { "name": "MW", "index": "16", "type": "numeric", "distinct": "281", "missing": "0", "min": "210", "max": "1175", "mean": "486", "stdev": "122" }, { "name": "Eig15_EA.ed.", "index": "17", "type": "numeric", "distinct": "196", "missing": "0", "min": "-5", "max": "5", "mean": "0", "stdev": "2" }, { "name": "SM10_AEA.ri.", "index": "18", "type": "numeric", "distinct": "196", "missing": "0", "min": "-5", "max": "5", "mean": "0", "stdev": "2" }, { "name": "Eig10_EA.bo.", "index": "19", "type": "numeric", "distinct": "200", "missing": "0", "min": "-1", "max": "3", "mean": "2", "stdev": "1" }, { "name": "Chi1_EA.bo.", "index": "20", "type": "numeric", "distinct": "279", "missing": "0", "min": "6", "max": "37", "mean": "14", "stdev": "4" }, { "name": "Eig06_EA.ed.", "index": "21", "type": "numeric", "distinct": "247", "missing": "0", "min": "2", "max": "11", "mean": "6", "stdev": "1" }, { "name": "SM15_AEA.dm.", "index": "22", "type": "numeric", "distinct": "247", "missing": "0", "min": "2", "max": "11", "mean": "6", "stdev": "1" }, { "name": "MAXDN", "index": "23", "type": "numeric", "distinct": "317", "missing": "0", "min": "2", "max": "6", "mean": "4", "stdev": "2" }, { "name": "nDB", "index": "24", "type": "numeric", "distinct": "10", "missing": "0", "min": "0", "max": "11", "mean": "4", "stdev": "2" }, { "name": "Eig07_AEA.ri.", "index": "25", "type": "numeric", "distinct": "267", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "ATS6v", "index": "26", "type": "numeric", "distinct": "319", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "ATSC5s", "index": "27", "type": "numeric", "distinct": "358", "missing": "0", "min": "19", "max": "784", "mean": "175", "stdev": "108" }, { "name": "Psi_i_s", "index": "28", "type": "numeric", "distinct": "274", "missing": "0", "min": "41", "max": "219", "mean": "90", "stdev": "26" }, { "name": "SPI", "index": "29", "type": "numeric", "distinct": "271", "missing": "0", "min": "6", "max": "77", "mean": "21", "stdev": "8" }, { "name": "X2", "index": "30", "type": "numeric", "distinct": "268", "missing": "0", "min": "7", "max": "36", "mean": "15", "stdev": "4" }, { "name": "Eig07_EA.ri.", "index": "31", "type": "numeric", "distinct": "256", "missing": "0", "min": "1", "max": "3", "mean": "2", "stdev": "0" }, { "name": "SpMax6_Bh.e.", "index": "32", "type": "numeric", "distinct": "236", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "Dz", "index": "33", "type": "numeric", "distinct": "166", "missing": "0", "min": "34", "max": "187", "mean": "76", "stdev": "21" }, { "name": "RDSQ", "index": "34", "type": "numeric", "distinct": "272", "missing": "0", "min": "99", "max": "1006", "mean": "323", "stdev": "124" }, { "name": "SpAD_AEA.ed.", "index": "35", "type": "numeric", "distinct": "274", "missing": "0", "min": "25", "max": "135", "mean": "57", "stdev": "15" }, { "name": "SpAD_EA", "index": "36", "type": "numeric", "distinct": "273", "missing": "0", "min": "25", "max": "125", "mean": "55", "stdev": "15" }, { "name": "SpAD_EA.ri.", "index": "37", "type": "numeric", "distinct": "343", "missing": "0", "min": "25", "max": "122", "mean": "53", "stdev": "14" }, { "name": "TPSA.NO.", "index": "38", "type": "numeric", "distinct": "140", "missing": "0", "min": "34", "max": "352", "mean": "115", "stdev": "46" }, { "name": "SpMax5_Bh.s.", "index": "39", "type": "numeric", "distinct": "134", "missing": "0", "min": "4", "max": "7", "mean": "6", "stdev": "1" }, { "name": "ATS1s", "index": "40", "type": "numeric", "distinct": "269", "missing": "0", "min": "5", "max": "6", "mean": "5", "stdev": "0" }, { "name": "IDDM", "index": "41", "type": "numeric", "distinct": "172", "missing": "0", "min": "4", "max": "6", "mean": "5", "stdev": "0" }, { "name": "SM02_EA.ri.", "index": "42", "type": "numeric", "distinct": "247", "missing": "0", "min": "4", "max": "5", "mean": "5", "stdev": "0" }, { "name": "SpMin5_Bh.m.", "index": "43", "type": "numeric", "distinct": "207", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "Eig12_AEA.ri.", "index": "44", "type": "numeric", "distinct": "238", "missing": "0", "min": "0", "max": "3", "mean": "2", "stdev": "1" }, { "name": "Eig12_EA.ri.", "index": "45", "type": "numeric", "distinct": "226", "missing": "0", "min": "-1", "max": "2", "mean": "1", "stdev": "1" }, { "name": "SpAD_AEA.bo.", "index": "46", "type": "numeric", "distinct": "285", "missing": "0", "min": "26", "max": "128", "mean": "56", "stdev": "15" }, { "name": "SpAD_AEA.ri.", "index": "47", "type": "numeric", "distinct": "344", "missing": "0", "min": "25", "max": "125", "mean": "55", "stdev": "15" }, { "name": "CID", "index": "48", "type": "numeric", "distinct": "191", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SMTI", "index": "49", "type": "numeric", "distinct": "272", "missing": "0", "min": "2154", "max": "181673", "mean": "17635", "stdev": "14736" }, { "name": "VvdwMG", "index": "50", "type": "numeric", "distinct": "280", "missing": "0", "min": "115", "max": "636", "mean": "239", "stdev": "64" }, { "name": "VvdwZAZ", "index": "51", "type": "numeric", "distinct": "283", "missing": "0", "min": "212", "max": "1179", "mean": "428", "stdev": "122" }, { "name": "Vx", "index": "52", "type": "numeric", "distinct": "280", "missing": "0", "min": "272", "max": "1545", "mean": "574", "stdev": "156" }, { "name": "SM04_EA.ri.", "index": "53", "type": "numeric", "distinct": "274", "missing": "0", "min": "5", "max": "7", "mean": "6", "stdev": "0" }, { "name": "Psi_e_1", "index": "54", "type": "numeric", "distinct": "338", "missing": "0", "min": "2", "max": "14", "mean": "6", "stdev": "2" }, { "name": "UNIP", "index": "55", "type": "numeric", "distinct": "161", "missing": "0", "min": "47", "max": "789", "mean": "150", "stdev": "73" }, { "name": "Eig14_AEA.ed.", "index": "56", "type": "numeric", "distinct": "214", "missing": "0", "min": "1", "max": "5", "mean": "3", "stdev": "1" }, { "name": "ATSC5i", "index": "57", "type": "numeric", "distinct": "328", "missing": "0", "min": "0", "max": "5", "mean": "2", "stdev": "1" }, { "name": "SpAD_EA.ed.", "index": "58", "type": "numeric", "distinct": "274", "missing": "0", "min": "65", "max": "359", "mean": "161", "stdev": "44" }, { "name": "GGI9", "index": "59", "type": "numeric", "distinct": "183", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "IDM", "index": "60", "type": "numeric", "distinct": "251", "missing": "0", "min": "7", "max": "11", "mean": "9", "stdev": "1" }, { "name": "Eig14_EA.ed.", "index": "61", "type": "numeric", "distinct": "222", "missing": "0", "min": "-5", "max": "5", "mean": "1", "stdev": "2" }, { "name": "SM09_AEA.ri.", "index": "62", "type": "numeric", "distinct": "222", "missing": "0", "min": "-5", "max": "5", "mean": "1", "stdev": "2" }, { "name": "ECC", "index": "63", "type": "numeric", "distinct": "213", "missing": "0", "min": "120", "max": "2200", "mean": "431", "stdev": "209" }, { "name": "MWC02", "index": "64", "type": "numeric", "distinct": "82", "missing": "0", "min": "4", "max": "6", "mean": "5", "stdev": "0" }, { "name": "ZM1", "index": "65", "type": "numeric", "distinct": "82", "missing": "0", "min": "78", "max": "402", "mean": "177", "stdev": "47" }, { "name": "Eta_epsi", "index": "66", "type": "numeric", "distinct": "275", "missing": "0", "min": "16", "max": "102", "mean": "37", "stdev": "11" }, { "name": "SpMaxA_EA.bo.", "index": "67", "type": "numeric", "distinct": "100", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" } ], "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 }