{ "data_id": "38370", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL1841", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL1841", "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: CHEMBL1841 (TID: 11755), and it has 1089 rows and 70 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 03:56:47", "update_comment": null, "last_update": "2016-07-16 03:56:47", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3638409\/data_53691.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL1841", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL1841 (TID: 11755), and it has 1089 rows and 70 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": 1089, "NumberOfFeatures": 72, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 71, "NumberOfSymbolicFeatures": 1, "Quartile2KurtosisOfNumericAtts": 6.322330352511621, "Dimensionality": 0.06611570247933884, "MeanNominalAttDistinctValues": null, "Quartile2MeansOfNumericAtts": 4.007742424242425, "EquivalentNumberOfAtts": null, "MeanSkewnessOfNumericAtts": 0.247745861906304, "Quartile2MutualInformation": null, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 1036.4636573003818, "Quartile2SkewnessOfNumericAtts": -0.7591801676194214, "MajorityClassSize": null, "MinAttributeEntropy": null, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.7102663087394774, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -0.028317940314745993, "MinMeansOfNumericAtts": 0.18365472910927436, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxKurtosisOfNumericAtts": 396.1751196969144, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 14.72641452781423, "MaxMeansOfNumericAtts": 39302.0817263544, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.61111111111111, "Quartile3MeansOfNumericAtts": 9.809777777777779, "MaxMutualInformation": null, "MinSkewnessOfNumericAtts": -3.290969132457682, "PercentageOfSymbolicFeatures": 1.3888888888888888, "Quartile3MutualInformation": null, "MaxNominalAttDistinctValues": null, "MinStdDevOfNumericAtts": 0.04683737959013405, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 1.351144872637138, "MaxSkewnessOfNumericAtts": 17.865774675589403, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": 2.6911090625567025, "Quartile3StdDevOfNumericAtts": 2.805334210984154, "MaxStdDevOfNumericAtts": 73215.04468942668, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 2.164885215794307, "StdvNominalAttDistinctValues": null, "MeanAttributeEntropy": null, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanKurtosisOfNumericAtts": 17.158017579631213, "Quartile1SkewnessOfNumericAtts": -1.3462115532796899, "MeanMeansOfNumericAtts": 566.6465627724098, "Quartile1StdDevOfNumericAtts": 0.4223947365934259, "AutoCorrelation": 0.18254963235294255, "MeanMutualInformation": null, "Quartile2AttributeEntropy": null, "ClassEntropy": null, "MeanNoiseToSignalRatio": null }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "71", "type": "numeric", "distinct": "216", "missing": "0", "target": "1", "min": "4", "max": "10", "mean": "6", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "1089", "missing": "0", "identifier": "1", "distr": [] }, { "name": "CATS2D_08_DP", "index": "1", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "8", "mean": "0", "stdev": "1" }, { "name": "Eig08_EA.ed.", "index": "2", "type": "numeric", "distinct": "809", "missing": "0", "min": "-6", "max": "10", "mean": "4", "stdev": "2" }, { "name": "SM03_AEA.ri.", "index": "3", "type": "numeric", "distinct": "809", "missing": "0", "min": "-6", "max": "10", "mean": "4", "stdev": "2" }, { "name": "X5sol", "index": "4", "type": "numeric", "distinct": "905", "missing": "0", "min": "0", "max": "30", "mean": "7", "stdev": "2" }, { "name": "SM04_EA.bo.", "index": "5", "type": "numeric", "distinct": "627", "missing": "0", "min": "4", "max": "9", "mean": "7", "stdev": "0" }, { "name": "Eig08_EA.ri.", "index": "6", "type": "numeric", "distinct": "683", "missing": "0", "min": "-2", "max": "3", "mean": "1", "stdev": "1" }, { "name": "Eig08_AEA.ri.", "index": "7", "type": "numeric", "distinct": "696", "missing": "0", "min": "-1", "max": "4", "mean": "2", "stdev": "1" }, { "name": "D.Dtr09", "index": "8", "type": "numeric", "distinct": "565", "missing": "0", "min": "0", "max": "557", "mean": "80", "stdev": "87" }, { "name": "X1sol", "index": "9", "type": "numeric", "distinct": "840", "missing": "0", "min": "2", "max": "57", "mean": "14", "stdev": "4" }, { "name": "ATS1m", "index": "10", "type": "numeric", "distinct": "624", "missing": "0", "min": "2", "max": "5", "mean": "4", "stdev": "0" }, { "name": "Eig08_EA", "index": "11", "type": "numeric", "distinct": "629", "missing": "0", "min": "-2", "max": "3", "mean": "1", "stdev": "1" }, { "name": "SM02_AEA.dm.", "index": "12", "type": "numeric", "distinct": "629", "missing": "0", "min": "-2", "max": "3", "mean": "1", "stdev": "1" }, { "name": "X2sol", "index": "13", "type": "numeric", "distinct": "917", "missing": "0", "min": "2", "max": "56", "mean": "13", "stdev": "4" }, { "name": "Eig07_EA.bo.", "index": "14", "type": "numeric", "distinct": "657", "missing": "0", "min": "-2", "max": "4", "mean": "2", "stdev": "1" }, { "name": "X3sol", "index": "15", "type": "numeric", "distinct": "921", "missing": "0", "min": "0", "max": "48", "mean": "11", "stdev": "3" }, { "name": "Eig07_EA.ed.", "index": "16", "type": "numeric", "distinct": "831", "missing": "0", "min": "-4", "max": "11", "mean": "4", "stdev": "2" }, { "name": "SM02_AEA.ri.", "index": "17", "type": "numeric", "distinct": "831", "missing": "0", "min": "-4", "max": "11", "mean": "4", "stdev": "2" }, { "name": "AECC", "index": "18", "type": "numeric", "distinct": "780", "missing": "0", "min": "2", "max": "25", "mean": "11", "stdev": "3" }, { "name": "Eig09_EA.ed.", "index": "19", "type": "numeric", "distinct": "794", "missing": "0", "min": "-7", "max": "10", "mean": "3", "stdev": "2" }, { "name": "SM04_AEA.ri.", "index": "20", "type": "numeric", "distinct": "794", "missing": "0", "min": "-7", "max": "10", "mean": "3", "stdev": "2" }, { "name": "Eig09_AEA.ed.", "index": "21", "type": "numeric", "distinct": "685", "missing": "0", "min": "0", "max": "6", "mean": "4", "stdev": "1" }, { "name": "HVcpx", "index": "22", "type": "numeric", "distinct": "696", "missing": "0", "min": "1", "max": "5", "mean": "3", "stdev": "0" }, { "name": "ICR", "index": "23", "type": "numeric", "distinct": "563", "missing": "0", "min": "1", "max": "4", "mean": "3", "stdev": "0" }, { "name": "XMOD", "index": "24", "type": "numeric", "distinct": "1026", "missing": "0", "min": "12", "max": "373", "mean": "90", "stdev": "27" }, { "name": "Eig08_AEA.ed.", "index": "25", "type": "numeric", "distinct": "704", "missing": "0", "min": "0", "max": "7", "mean": "4", "stdev": "1" }, { "name": "SM06_EA.bo.", "index": "26", "type": "numeric", "distinct": "658", "missing": "0", "min": "6", "max": "11", "mean": "10", "stdev": "0" }, { "name": "IDE", "index": "27", "type": "numeric", "distinct": "713", "missing": "0", "min": "1", "max": "5", "mean": "4", "stdev": "0" }, { "name": "ATS2m", "index": "28", "type": "numeric", "distinct": "653", "missing": "0", "min": "2", "max": "6", "mean": "4", "stdev": "0" }, { "name": "X4sol", "index": "29", "type": "numeric", "distinct": "926", "missing": "0", "min": "0", "max": "36", "mean": "9", "stdev": "3" }, { "name": "GMTIV", "index": "30", "type": "numeric", "distinct": "1058", "missing": "0", "min": "130", "max": "1837350", "mean": "39302", "stdev": "73215" }, { "name": "UNIP", "index": "31", "type": "numeric", "distinct": "242", "missing": "0", "min": "3", "max": "1326", "mean": "124", "stdev": "77" }, { "name": "Eig09_AEA.dm.", "index": "32", "type": "numeric", "distinct": "685", "missing": "0", "min": "-2", "max": "4", "mean": "1", "stdev": "1" }, { "name": "MSD", "index": "33", "type": "numeric", "distinct": "904", "missing": "0", "min": "2", "max": "15", "mean": "7", "stdev": "2" }, { "name": "X4v", "index": "34", "type": "numeric", "distinct": "942", "missing": "0", "min": "0", "max": "15", "mean": "4", "stdev": "1" }, { "name": "X0sol", "index": "35", "type": "numeric", "distinct": "615", "missing": "0", "min": "4", "max": "89", "mean": "20", "stdev": "6" }, { "name": "Eig01_EA.bo.", "index": "36", "type": "numeric", "distinct": "486", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SM11_AEA.ri.", "index": "37", "type": "numeric", "distinct": "486", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SpDiam_EA.bo.", "index": "38", "type": "numeric", "distinct": "486", "missing": "0", "min": "4", "max": "8", "mean": "7", "stdev": "0" }, { "name": "SpMax_EA.bo.", "index": "39", "type": "numeric", "distinct": "486", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SpMax6_Bh.m.", "index": "40", "type": "numeric", "distinct": "622", "missing": "0", "min": "0", "max": "4", "mean": "3", "stdev": "0" }, { "name": "Eig09_EA.bo.", "index": "41", "type": "numeric", "distinct": "698", "missing": "0", "min": "-3", "max": "4", "mean": "2", "stdev": "1" }, { "name": "Eta_betaP", "index": "42", "type": "numeric", "distinct": "64", "missing": "0", "min": "0", "max": "90", "mean": "20", "stdev": "6" }, { "name": "Eig08_AEA.dm.", "index": "43", "type": "numeric", "distinct": "687", "missing": "0", "min": "-2", "max": "4", "mean": "2", "stdev": "1" }, { "name": "SpMax3_Bh.m.", "index": "44", "type": "numeric", "distinct": "457", "missing": "0", "min": "2", "max": "7", "mean": "4", "stdev": "0" }, { "name": "Eig07_AEA.ed.", "index": "45", "type": "numeric", "distinct": "723", "missing": "0", "min": "0", "max": "7", "mean": "4", "stdev": "1" }, { "name": "P_VSA_e_3", "index": "46", "type": "numeric", "distinct": "349", "missing": "0", "min": "0", "max": "433", "mean": "74", "stdev": "34" }, { "name": "X1v", "index": "47", "type": "numeric", "distinct": "991", "missing": "0", "min": "1", "max": "40", "mean": "10", "stdev": "3" }, { "name": "P_VSA_m_2", "index": "48", "type": "numeric", "distinct": "1009", "missing": "0", "min": "10", "max": "615", "mean": "196", "stdev": "55" }, { "name": "DECC", "index": "49", "type": "numeric", "distinct": "718", "missing": "0", "min": "0", "max": "4", "mean": "2", "stdev": "1" }, { "name": "SpMin1_Bh.p.", "index": "50", "type": "numeric", "distinct": "199", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "SpMax4_Bh.m.", "index": "51", "type": "numeric", "distinct": "569", "missing": "0", "min": "0", "max": "7", "mean": "3", "stdev": "0" }, { "name": "SpMin1_Bh.v.", "index": "52", "type": "numeric", "distinct": "203", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "Chi0_EA.dm.", "index": "53", "type": "numeric", "distinct": "931", "missing": "0", "min": "0", "max": "92", "mean": "20", "stdev": "10" }, { "name": "Eta_alpha", "index": "54", "type": "numeric", "distinct": "648", "missing": "0", "min": "2", "max": "53", "mean": "14", "stdev": "4" }, { "name": "X3v", "index": "55", "type": "numeric", "distinct": "975", "missing": "0", "min": "0", "max": "21", "mean": "5", "stdev": "2" }, { "name": "ATS4m", "index": "56", "type": "numeric", "distinct": "727", "missing": "0", "min": "0", "max": "6", "mean": "4", "stdev": "0" }, { "name": "X1", "index": "57", "type": "numeric", "distinct": "765", "missing": "0", "min": "2", "max": "57", "mean": "14", "stdev": "4" }, { "name": "Eig10_EA", "index": "58", "type": "numeric", "distinct": "640", "missing": "0", "min": "-2", "max": "3", "mean": "1", "stdev": "1" }, { "name": "SM04_AEA.dm.", "index": "59", "type": "numeric", "distinct": "640", "missing": "0", "min": "-2", "max": "3", "mean": "1", "stdev": "1" }, { "name": "Eig09_EA", "index": "60", "type": "numeric", "distinct": "632", "missing": "0", "min": "-2", "max": "3", "mean": "1", "stdev": "1" }, { "name": "SM03_AEA.dm.", "index": "61", "type": "numeric", "distinct": "632", "missing": "0", "min": "-2", "max": "3", "mean": "1", "stdev": "1" }, { "name": "CATS2D_02_DL", "index": "62", "type": "numeric", "distinct": "16", "missing": "0", "min": "0", "max": "17", "mean": "3", "stdev": "2" }, { "name": "X4", "index": "63", "type": "numeric", "distinct": "938", "missing": "0", "min": "0", "max": "36", "mean": "9", "stdev": "3" }, { "name": "SM08_EA.bo.", "index": "64", "type": "numeric", "distinct": "700", "missing": "0", "min": "8", "max": "14", "mean": "13", "stdev": "0" }, { "name": "Eig09_AEA.ri.", "index": "65", "type": "numeric", "distinct": "688", "missing": "0", "min": "-1", "max": "4", "mean": "2", "stdev": "1" }, { "name": "piPC10", "index": "66", "type": "numeric", "distinct": "806", "missing": "0", "min": "0", "max": "10", "mean": "8", "stdev": "1" }, { "name": "Eig06_EA.bo.", "index": "67", "type": "numeric", "distinct": "655", "missing": "0", "min": "-2", "max": "4", "mean": "2", "stdev": "1" }, { "name": "Hy", "index": "68", "type": "numeric", "distinct": "514", "missing": "0", "min": "-1", "max": "17", "mean": "1", "stdev": "1" }, { "name": "SM10_EA.bo.", "index": "69", "type": "numeric", "distinct": "770", "missing": "0", "min": "9", "max": "17", "mean": "15", "stdev": "1" }, { "name": "SpMin7_Bh.e.", "index": "70", "type": "numeric", "distinct": "528", "missing": "0", "min": "0", "max": "2", "mean": "1", "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 }