{ "data_id": "31160", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL2577", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL2577", "version": 9, "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: CHEMBL2577 (TID: 11097), and it has 120 rows and 61 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 06:51:12", "update_comment": null, "last_update": "2016-07-15 06:51:12", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3440330\/data_52212.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL2577", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL2577 (TID: 11097), and it has 120 rows and 61 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": 120, "NumberOfFeatures": 63, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 62, "NumberOfSymbolicFeatures": 1, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.32541262358367296, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.5365211943823913, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxKurtosisOfNumericAtts": 10.252966195666849, "MinMeansOfNumericAtts": 0.18282499999999996, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 1.1287268728522069, "MaxMeansOfNumericAtts": 196.77103333333335, "MinMutualInformation": null, "PercentageOfNumericFeatures": 98.4126984126984, "Quartile3MeansOfNumericAtts": 16.27245, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfSymbolicFeatures": 1.5873015873015872, "Quartile3MutualInformation": null, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -2.0295614764196, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 0.653520648147472, "MaxSkewnessOfNumericAtts": 1.0408514098698072, "MinStdDevOfNumericAtts": 0.0816821463920708, "Quartile1KurtosisOfNumericAtts": -0.9649558356286261, "Quartile3StdDevOfNumericAtts": 0.7605669564003337, "MaxStdDevOfNumericAtts": 65.27632176338416, "MinorityClassPercentage": null, "Quartile1MeansOfNumericAtts": 2.5352395833333334, "StdvNominalAttDistinctValues": null, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MutualInformation": null, "MeanKurtosisOfNumericAtts": 0.16861184899918888, "NumberOfBinaryFeatures": 0, "Quartile1SkewnessOfNumericAtts": 0.0943467645493718, "MeanMeansOfNumericAtts": 17.99438615591398, "Quartile1StdDevOfNumericAtts": 0.27046932767979753, "AutoCorrelation": 0.032386554621848494, "MeanMutualInformation": null, "Quartile2AttributeEntropy": null, "ClassEntropy": null, "MeanNoiseToSignalRatio": null, "Quartile2KurtosisOfNumericAtts": -0.388734979214423, "Dimensionality": 0.525, "MeanNominalAttDistinctValues": null, "Quartile2MeansOfNumericAtts": 7.527666666666667, "EquivalentNumberOfAtts": null, "MeanSkewnessOfNumericAtts": 0.30052327114045396, "Quartile2MutualInformation": null, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 3.524475405222035, "Quartile2SkewnessOfNumericAtts": 0.34925200172886045, "MajorityClassSize": null, "MinAttributeEntropy": null }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "62", "type": "numeric", "distinct": "113", "missing": "0", "target": "1", "min": "5", "max": "10", "mean": "7", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "120", "missing": "0", "identifier": "1", "distr": [] }, { "name": "Eig03_AEA.dm.", "index": "1", "type": "numeric", "distinct": "59", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "Eig05_AEA.dm.", "index": "2", "type": "numeric", "distinct": "88", "missing": "0", "min": "2", "max": "3", "mean": "3", "stdev": "0" }, { "name": "SpMax3_Bh.m.", "index": "3", "type": "numeric", "distinct": "80", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "Eig04_EA.ed.", "index": "4", "type": "numeric", "distinct": "79", "missing": "0", "min": "5", "max": "9", "mean": "7", "stdev": "1" }, { "name": "Eig05_AEA.ri.", "index": "5", "type": "numeric", "distinct": "89", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "Eig05_EA", "index": "6", "type": "numeric", "distinct": "71", "missing": "0", "min": "2", "max": "3", "mean": "2", "stdev": "0" }, { "name": "Eig13_EA.bo.", "index": "7", "type": "numeric", "distinct": "66", "missing": "0", "min": "-1", "max": "2", "mean": "0", "stdev": "1" }, { "name": "SM13_AEA.bo.", "index": "8", "type": "numeric", "distinct": "71", "missing": "0", "min": "2", "max": "3", "mean": "2", "stdev": "0" }, { "name": "SM13_AEA.dm.", "index": "9", "type": "numeric", "distinct": "79", "missing": "0", "min": "5", "max": "9", "mean": "7", "stdev": "1" }, { "name": "GGI6", "index": "10", "type": "numeric", "distinct": "71", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "ATS1m", "index": "11", "type": "numeric", "distinct": "80", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "GATS2v", "index": "12", "type": "numeric", "distinct": "85", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SM09_AEA.ed.", "index": "13", "type": "numeric", "distinct": "72", "missing": "0", "min": "17", "max": "19", "mean": "18", "stdev": "0" }, { "name": "X1v", "index": "14", "type": "numeric", "distinct": "100", "missing": "0", "min": "6", "max": "16", "mean": "10", "stdev": "3" }, { "name": "P_VSA_s_6", "index": "15", "type": "numeric", "distinct": "51", "missing": "0", "min": "81", "max": "237", "mean": "156", "stdev": "34" }, { "name": "ATS4m", "index": "16", "type": "numeric", "distinct": "106", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "ATSC6e", "index": "17", "type": "numeric", "distinct": "107", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "Eig05_AEA.bo.", "index": "18", "type": "numeric", "distinct": "69", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "Eig12_AEA.ed.", "index": "19", "type": "numeric", "distinct": "58", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "1" }, { "name": "ATSC6m", "index": "20", "type": "numeric", "distinct": "112", "missing": "0", "min": "9", "max": "66", "mean": "32", "stdev": "15" }, { "name": "AAC", "index": "21", "type": "numeric", "distinct": "66", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "IC0", "index": "22", "type": "numeric", "distinct": "66", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "Eta_C_A", "index": "23", "type": "numeric", "distinct": "100", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "ATSC5m", "index": "24", "type": "numeric", "distinct": "113", "missing": "0", "min": "13", "max": "64", "mean": "34", "stdev": "15" }, { "name": "TIC1", "index": "25", "type": "numeric", "distinct": "85", "missing": "0", "min": "111", "max": "330", "mean": "197", "stdev": "65" }, { "name": "X2v", "index": "26", "type": "numeric", "distinct": "106", "missing": "0", "min": "4", "max": "12", "mean": "8", "stdev": "2" }, { "name": "ATSC2p", "index": "27", "type": "numeric", "distinct": "93", "missing": "0", "min": "4", "max": "13", "mean": "8", "stdev": "2" }, { "name": "ZM1Mad", "index": "28", "type": "numeric", "distinct": "92", "missing": "0", "min": "111", "max": "309", "mean": "192", "stdev": "55" }, { "name": "ATS1v", "index": "29", "type": "numeric", "distinct": "82", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "ATS2v", "index": "30", "type": "numeric", "distinct": "88", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "Eig13_EA", "index": "31", "type": "numeric", "distinct": "64", "missing": "0", "min": "-1", "max": "1", "mean": "0", "stdev": "1" }, { "name": "Eig13_EA.ri.", "index": "32", "type": "numeric", "distinct": "86", "missing": "0", "min": "-1", "max": "1", "mean": "0", "stdev": "1" }, { "name": "MPC07", "index": "33", "type": "numeric", "distinct": "61", "missing": "0", "min": "4", "max": "5", "mean": "5", "stdev": "0" }, { "name": "MPC09", "index": "34", "type": "numeric", "distinct": "56", "missing": "0", "min": "3", "max": "5", "mean": "5", "stdev": "0" }, { "name": "Psi_i_1", "index": "35", "type": "numeric", "distinct": "100", "missing": "0", "min": "10", "max": "26", "mean": "17", "stdev": "5" }, { "name": "SM07_AEA.dm.", "index": "36", "type": "numeric", "distinct": "64", "missing": "0", "min": "-1", "max": "1", "mean": "0", "stdev": "1" }, { "name": "C.", "index": "37", "type": "numeric", "distinct": "41", "missing": "0", "min": "33", "max": "46", "mean": "40", "stdev": "3" }, { "name": "Eig05_EA.ri.", "index": "38", "type": "numeric", "distinct": "77", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "GGI3", "index": "39", "type": "numeric", "distinct": "49", "missing": "0", "min": "1", "max": "4", "mean": "2", "stdev": "1" }, { "name": "GGI7", "index": "40", "type": "numeric", "distinct": "72", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SM03_EA.ed.", "index": "41", "type": "numeric", "distinct": "51", "missing": "0", "min": "7", "max": "8", "mean": "8", "stdev": "0" }, { "name": "SM04_EA.ed.", "index": "42", "type": "numeric", "distinct": "78", "missing": "0", "min": "10", "max": "11", "mean": "11", "stdev": "0" }, { "name": "SM05_EA.ed.", "index": "43", "type": "numeric", "distinct": "69", "missing": "0", "min": "12", "max": "13", "mean": "12", "stdev": "0" }, { "name": "SM06_AEA.ed.", "index": "44", "type": "numeric", "distinct": "71", "missing": "0", "min": "12", "max": "13", "mean": "13", "stdev": "0" }, { "name": "SM07_AEA.ed.", "index": "45", "type": "numeric", "distinct": "73", "missing": "0", "min": "14", "max": "15", "mean": "14", "stdev": "0" }, { "name": "SM08_AEA.ed.", "index": "46", "type": "numeric", "distinct": "72", "missing": "0", "min": "15", "max": "17", "mean": "16", "stdev": "0" }, { "name": "SM09_EA.ri.", "index": "47", "type": "numeric", "distinct": "97", "missing": "0", "min": "10", "max": "11", "mean": "11", "stdev": "0" }, { "name": "SM10_AEA.ed.", "index": "48", "type": "numeric", "distinct": "75", "missing": "0", "min": "19", "max": "21", "mean": "20", "stdev": "0" }, { "name": "SM10_EA", "index": "49", "type": "numeric", "distinct": "79", "missing": "0", "min": "11", "max": "13", "mean": "12", "stdev": "0" }, { "name": "SM10_EA.ri.", "index": "50", "type": "numeric", "distinct": "102", "missing": "0", "min": "11", "max": "12", "mean": "12", "stdev": "0" }, { "name": "SM11_EA", "index": "51", "type": "numeric", "distinct": "77", "missing": "0", "min": "12", "max": "14", "mean": "13", "stdev": "0" }, { "name": "SM12_EA", "index": "52", "type": "numeric", "distinct": "75", "missing": "0", "min": "13", "max": "16", "mean": "14", "stdev": "0" }, { "name": "SM14_AEA.ed.", "index": "53", "type": "numeric", "distinct": "73", "missing": "0", "min": "26", "max": "29", "mean": "27", "stdev": "0" }, { "name": "SM15_EA", "index": "54", "type": "numeric", "distinct": "75", "missing": "0", "min": "17", "max": "19", "mean": "18", "stdev": "0" }, { "name": "SM06_EA.ed.", "index": "55", "type": "numeric", "distinct": "70", "missing": "0", "min": "14", "max": "16", "mean": "15", "stdev": "0" }, { "name": "SM11_AEA.ed.", "index": "56", "type": "numeric", "distinct": "73", "missing": "0", "min": "21", "max": "23", "mean": "22", "stdev": "0" }, { "name": "SM12_AEA.ed.", "index": "57", "type": "numeric", "distinct": "73", "missing": "0", "min": "23", "max": "25", "mean": "24", "stdev": "0" }, { "name": "SM13_AEA.ed.", "index": "58", "type": "numeric", "distinct": "74", "missing": "0", "min": "24", "max": "27", "mean": "25", "stdev": "0" }, { "name": "SM13_EA", "index": "59", "type": "numeric", "distinct": "75", "missing": "0", "min": "14", "max": "17", "mean": "16", "stdev": "0" }, { "name": "SM14_EA", "index": "60", "type": "numeric", "distinct": "75", "missing": "0", "min": "16", "max": "18", "mean": "17", "stdev": "0" }, { "name": "ATS5m", "index": "61", "type": "numeric", "distinct": "109", "missing": "0", "min": "3", "max": "5", "mean": "4", "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 }