{ "data_id": "29573", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL5413", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL5413", "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: CHEMBL5413 (TID: 100862), and it has 177 rows and 63 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 02:50:16", "update_comment": null, "last_update": "2016-07-15 02:50:16", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3396177\/data_52593.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL5413", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL5413 (TID: 100862), and it has 177 rows and 63 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": 177, "NumberOfFeatures": 65, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 64, "NumberOfSymbolicFeatures": 1, "ClassEntropy": null, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "Dimensionality": 0.3672316384180791, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": 1.094257375054044, "EquivalentNumberOfAtts": null, "MeanSkewnessOfNumericAtts": 0.579258385541039, "Quartile2MeansOfNumericAtts": 3.9604293785310736, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 2.6102230987826966, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": 0.3504880420842144, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.555127893123683, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.2889888465774727, "MaxKurtosisOfNumericAtts": 34.49614040376817, "MinMeansOfNumericAtts": 0.01966101694915255, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 256.4060621468926, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 8.580249530050647, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.46153846153847, "Quartile3MeansOfNumericAtts": 7.291570621468926, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -1.8803953561124793, "PercentageOfSymbolicFeatures": 1.5384615384615385, "Quartile3MutualInformation": null, "MaxSkewnessOfNumericAtts": 4.004836128834498, "MinStdDevOfNumericAtts": 0.004115187898899153, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 1.6524860673298642, "MaxStdDevOfNumericAtts": 110.70908767720915, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": -0.9908292767533325, "Quartile3StdDevOfNumericAtts": 0.7060187256952072, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 1.512539548022599, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": 4.769080622408796, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 9.694092425847456, "Quartile1SkewnessOfNumericAtts": -0.45376671412717473, "AutoCorrelation": 0.0032897727272727714, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.09846494328286973 }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "64", "type": "numeric", "distinct": "136", "missing": "0", "target": "1", "min": "4", "max": "11", "mean": "8", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "177", "missing": "0", "identifier": "1", "distr": [] }, { "name": "Eig01_AEA.ed.", "index": "1", "type": "numeric", "distinct": "25", "missing": "0", "min": "6", "max": "8", "mean": "7", "stdev": "0" }, { "name": "Eig01_EA", "index": "2", "type": "numeric", "distinct": "25", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "Eig01_EA.ed.", "index": "3", "type": "numeric", "distinct": "28", "missing": "0", "min": "9", "max": "14", "mean": "11", "stdev": "1" }, { "name": "SM09_AEA.bo.", "index": "4", "type": "numeric", "distinct": "25", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SM10_AEA.dm.", "index": "5", "type": "numeric", "distinct": "28", "missing": "0", "min": "9", "max": "14", "mean": "11", "stdev": "1" }, { "name": "SpDiam_EA", "index": "6", "type": "numeric", "distinct": "25", "missing": "0", "min": "5", "max": "6", "mean": "5", "stdev": "0" }, { "name": "SpDiam_EA.ed.", "index": "7", "type": "numeric", "distinct": "36", "missing": "0", "min": "16", "max": "23", "mean": "18", "stdev": "1" }, { "name": "SpMax_AEA.ed.", "index": "8", "type": "numeric", "distinct": "25", "missing": "0", "min": "6", "max": "8", "mean": "7", "stdev": "0" }, { "name": "SpMax_EA", "index": "9", "type": "numeric", "distinct": "25", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SpMax_EA.ed.", "index": "10", "type": "numeric", "distinct": "28", "missing": "0", "min": "9", "max": "14", "mean": "11", "stdev": "1" }, { "name": "SpMAD_AEA.dm.", "index": "11", "type": "numeric", "distinct": "71", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "SpMAD_EA.ed.", "index": "12", "type": "numeric", "distinct": "104", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SpMAD_AEA.ed.", "index": "13", "type": "numeric", "distinct": "50", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "X4A", "index": "14", "type": "numeric", "distinct": "17", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SpMAD_AEA.bo.", "index": "15", "type": "numeric", "distinct": "61", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "GATS7e", "index": "16", "type": "numeric", "distinct": "139", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "GATS7s", "index": "17", "type": "numeric", "distinct": "148", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "CATS2D_02_AL", "index": "18", "type": "numeric", "distinct": "11", "missing": "0", "min": "1", "max": "11", "mean": "5", "stdev": "2" }, { "name": "CATS2D_05_LL", "index": "19", "type": "numeric", "distinct": "15", "missing": "0", "min": "3", "max": "20", "mean": "9", "stdev": "3" }, { "name": "piPC08", "index": "20", "type": "numeric", "distinct": "111", "missing": "0", "min": "5", "max": "9", "mean": "7", "stdev": "0" }, { "name": "X5A", "index": "21", "type": "numeric", "distinct": "15", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "piPC07", "index": "22", "type": "numeric", "distinct": "113", "missing": "0", "min": "5", "max": "8", "mean": "7", "stdev": "0" }, { "name": "piPC09", "index": "23", "type": "numeric", "distinct": "120", "missing": "0", "min": "5", "max": "9", "mean": "7", "stdev": "1" }, { "name": "GATS4m", "index": "24", "type": "numeric", "distinct": "115", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SaaaC", "index": "25", "type": "numeric", "distinct": "67", "missing": "0", "min": "0", "max": "6", "mean": "1", "stdev": "1" }, { "name": "SpDiam_AEA.ed.", "index": "26", "type": "numeric", "distinct": "42", "missing": "0", "min": "6", "max": "8", "mean": "6", "stdev": "0" }, { "name": "CATS2D_07_PP", "index": "27", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "GATS7m", "index": "28", "type": "numeric", "distinct": "113", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SaaNH", "index": "29", "type": "numeric", "distinct": "55", "missing": "0", "min": "0", "max": "6", "mean": "2", "stdev": "2" }, { "name": "MATS4m", "index": "30", "type": "numeric", "distinct": "99", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SaaO", "index": "31", "type": "numeric", "distinct": "28", "missing": "0", "min": "0", "max": "5", "mean": "1", "stdev": "2" }, { "name": "PW4", "index": "32", "type": "numeric", "distinct": "38", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SM15_EA.ed.", "index": "33", "type": "numeric", "distinct": "82", "missing": "0", "min": "35", "max": "40", "mean": "36", "stdev": "1" }, { "name": "SM13_EA.ed.", "index": "34", "type": "numeric", "distinct": "90", "missing": "0", "min": "30", "max": "35", "mean": "31", "stdev": "1" }, { "name": "SM14_EA.ed.", "index": "35", "type": "numeric", "distinct": "88", "missing": "0", "min": "33", "max": "37", "mean": "34", "stdev": "1" }, { "name": "Eig01_AEA.dm.", "index": "36", "type": "numeric", "distinct": "21", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SpDiam_AEA.dm.", "index": "37", "type": "numeric", "distinct": "21", "missing": "0", "min": "6", "max": "7", "mean": "6", "stdev": "0" }, { "name": "SpMax_AEA.dm.", "index": "38", "type": "numeric", "distinct": "21", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "Eig02_EA.ed.", "index": "39", "type": "numeric", "distinct": "43", "missing": "0", "min": "9", "max": "12", "mean": "10", "stdev": "1" }, { "name": "SM11_AEA.dm.", "index": "40", "type": "numeric", "distinct": "43", "missing": "0", "min": "9", "max": "12", "mean": "10", "stdev": "1" }, { "name": "GATS2m", "index": "41", "type": "numeric", "distinct": "87", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SpMin1_Bh.p.", "index": "42", "type": "numeric", "distinct": "39", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "GATS6s", "index": "43", "type": "numeric", "distinct": "142", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "SpDiam_AEA.ri.", "index": "44", "type": "numeric", "distinct": "45", "missing": "0", "min": "5", "max": "6", "mean": "5", "stdev": "0" }, { "name": "Eig15_EA.ri.", "index": "45", "type": "numeric", "distinct": "69", "missing": "0", "min": "0", "max": "2", "mean": "2", "stdev": "1" }, { "name": "Eig01_EA.dm.", "index": "46", "type": "numeric", "distinct": "18", "missing": "0", "min": "1", "max": "3", "mean": "2", "stdev": "0" }, { "name": "SpMax_EA.dm.", "index": "47", "type": "numeric", "distinct": "18", "missing": "0", "min": "1", "max": "3", "mean": "2", "stdev": "0" }, { "name": "piID", "index": "48", "type": "numeric", "distinct": "102", "missing": "0", "min": "8", "max": "16", "mean": "11", "stdev": "1" }, { "name": "SsF", "index": "49", "type": "numeric", "distinct": "37", "missing": "0", "min": "0", "max": "70", "mean": "4", "stdev": "8" }, { "name": "Eig09_AEA.dm.", "index": "50", "type": "numeric", "distinct": "74", "missing": "0", "min": "1", "max": "4", "mean": "3", "stdev": "1" }, { "name": "AMR", "index": "51", "type": "numeric", "distinct": "147", "missing": "0", "min": "118", "max": "439", "mean": "256", "stdev": "111" }, { "name": "Eig14_AEA.dm.", "index": "52", "type": "numeric", "distinct": "73", "missing": "0", "min": "0", "max": "4", "mean": "2", "stdev": "1" }, { "name": "SpMax8_Bh.e.", "index": "53", "type": "numeric", "distinct": "83", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "piPC06", "index": "54", "type": "numeric", "distinct": "108", "missing": "0", "min": "5", "max": "7", "mean": "7", "stdev": "0" }, { "name": "X3A", "index": "55", "type": "numeric", "distinct": "21", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "C.008", "index": "56", "type": "numeric", "distinct": "10", "missing": "0", "min": "0", "max": "13", "mean": "5", "stdev": "5" }, { "name": "CATS2D_06_DA", "index": "57", "type": "numeric", "distinct": "14", "missing": "0", "min": "0", "max": "19", "mean": "8", "stdev": "7" }, { "name": "CATS2D_09_DA", "index": "58", "type": "numeric", "distinct": "20", "missing": "0", "min": "0", "max": "23", "mean": "9", "stdev": "7" }, { "name": "Eig04_AEA.dm.", "index": "59", "type": "numeric", "distinct": "62", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "MPC05", "index": "60", "type": "numeric", "distinct": "79", "missing": "0", "min": "4", "max": "6", "mean": "5", "stdev": "0" }, { "name": "SpMin4_Bh.s.", "index": "61", "type": "numeric", "distinct": "72", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Eig15_EA.ed.", "index": "62", "type": "numeric", "distinct": "66", "missing": "0", "min": "-1", "max": "7", "mean": "4", "stdev": "2" }, { "name": "SM10_AEA.ri.", "index": "63", "type": "numeric", "distinct": "66", "missing": "0", "min": "-1", "max": "7", "mean": "4", "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 }