{ "data_id": "35590", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL2304405", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL2304405", "version": 11, "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: CHEMBL2304405 (TID: 105568), and it has 109 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 18:27:12", "update_comment": null, "last_update": "2016-07-15 18:27:12", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3562285\/data_52504.arff", "kaggle_url": null, "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL2304405", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL2304405 (TID: 105568), and it has 109 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": 109, "NumberOfFeatures": 65, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 64, "NumberOfSymbolicFeatures": 1, "MaxSkewnessOfNumericAtts": 1.775437371572031, "MinStdDevOfNumericAtts": 0.0026407378575337677, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 0.411124213918298, "MaxStdDevOfNumericAtts": 212.577798966246, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": -0.8729276691921612, "Quartile3StdDevOfNumericAtts": 5.759002952863712, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 1.6232155963302755, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": -0.13226930473534484, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 38.49354501146789, "Quartile1SkewnessOfNumericAtts": -0.7880063085658658, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.14693613202909045, "AutoCorrelation": -0.13957407407407418, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "ClassEntropy": null, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": -0.3223012360215147, "Dimensionality": 0.5963302752293578, "MeanSkewnessOfNumericAtts": -0.14307516569812895, "Quartile2MeansOfNumericAtts": 5.250839449541284, "EquivalentNumberOfAtts": null, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 22.494161550628, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": -0.14408332728204326, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.3147265078030514, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 1.0573783615191354, "MaxKurtosisOfNumericAtts": 2.9527795877043856, "MinMeansOfNumericAtts": -5.344532110091743, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 347.07212844036695, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 0.22005031231084382, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.46153846153847, "Quartile3MeansOfNumericAtts": 10.940490825688073, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -1.387500170988868, "PercentageOfSymbolicFeatures": 1.5384615384615385, "Quartile3MutualInformation": null }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "64", "type": "numeric", "distinct": "84", "missing": "0", "target": "1", "min": "4", "max": "9", "mean": "6", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "109", "missing": "0", "identifier": "1", "distr": [] }, { "name": "GATS7e", "index": "1", "type": "numeric", "distinct": "98", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "CATS2D_06_AL", "index": "2", "type": "numeric", "distinct": "22", "missing": "0", "min": "2", "max": "24", "mean": "12", "stdev": "5" }, { "name": "IC2", "index": "3", "type": "numeric", "distinct": "93", "missing": "0", "min": "4", "max": "5", "mean": "5", "stdev": "0" }, { "name": "JGI6", "index": "4", "type": "numeric", "distinct": "13", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "PW4", "index": "5", "type": "numeric", "distinct": "41", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SpMax2_Bh.s.", "index": "6", "type": "numeric", "distinct": "35", "missing": "0", "min": "5", "max": "8", "mean": "7", "stdev": "1" }, { "name": "SsssCH", "index": "7", "type": "numeric", "distinct": "97", "missing": "0", "min": "-21", "max": "2", "mean": "-5", "stdev": "5" }, { "name": "SpMin1_Bh.i.", "index": "8", "type": "numeric", "distinct": "28", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "SpMin1_Bh.p.", "index": "9", "type": "numeric", "distinct": "38", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "SpMin1_Bh.v.", "index": "10", "type": "numeric", "distinct": "38", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "P_VSA_LogP_4", "index": "11", "type": "numeric", "distinct": "38", "missing": "0", "min": "0", "max": "487", "mean": "207", "stdev": "133" }, { "name": "P_VSA_p_2", "index": "12", "type": "numeric", "distinct": "64", "missing": "0", "min": "21", "max": "780", "mean": "346", "stdev": "213" }, { "name": "P_VSA_v_2", "index": "13", "type": "numeric", "distinct": "67", "missing": "0", "min": "21", "max": "780", "mean": "347", "stdev": "211" }, { "name": "TPSA.NO.", "index": "14", "type": "numeric", "distinct": "64", "missing": "0", "min": "15", "max": "519", "mean": "234", "stdev": "140" }, { "name": "TPSA.Tot.", "index": "15", "type": "numeric", "distinct": "69", "missing": "0", "min": "15", "max": "544", "mean": "237", "stdev": "143" }, { "name": "P_VSA_MR_5", "index": "16", "type": "numeric", "distinct": "87", "missing": "0", "min": "17", "max": "470", "mean": "187", "stdev": "101" }, { "name": "CATS2D_09_DL", "index": "17", "type": "numeric", "distinct": "27", "missing": "0", "min": "0", "max": "42", "mean": "15", "stdev": "12" }, { "name": "LLS_01", "index": "18", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "P_VSA_s_3", "index": "19", "type": "numeric", "distinct": "90", "missing": "0", "min": "16", "max": "156", "mean": "61", "stdev": "27" }, { "name": "SAacc", "index": "20", "type": "numeric", "distinct": "63", "missing": "0", "min": "21", "max": "729", "mean": "331", "stdev": "201" }, { "name": "CATS2D_02_DL", "index": "21", "type": "numeric", "distinct": "22", "missing": "0", "min": "0", "max": "22", "mean": "9", "stdev": "6" }, { "name": "PW5", "index": "22", "type": "numeric", "distinct": "39", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "MATS7p", "index": "23", "type": "numeric", "distinct": "69", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "CATS2D_05_LL", "index": "24", "type": "numeric", "distinct": "15", "missing": "0", "min": "0", "max": "23", "mean": "8", "stdev": "6" }, { "name": "CATS2D_06_LL", "index": "25", "type": "numeric", "distinct": "21", "missing": "0", "min": "0", "max": "31", "mean": "11", "stdev": "7" }, { "name": "CATS2D_07_LL", "index": "26", "type": "numeric", "distinct": "24", "missing": "0", "min": "1", "max": "32", "mean": "14", "stdev": "7" }, { "name": "GATS7v", "index": "27", "type": "numeric", "distinct": "79", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "O.", "index": "28", "type": "numeric", "distinct": "51", "missing": "0", "min": "0", "max": "11", "mean": "6", "stdev": "3" }, { "name": "SM05_EA.bo.", "index": "29", "type": "numeric", "distinct": "78", "missing": "0", "min": "7", "max": "9", "mean": "8", "stdev": "1" }, { "name": "X2A", "index": "30", "type": "numeric", "distinct": "44", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "CIC5", "index": "31", "type": "numeric", "distinct": "89", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "Eig06_EA.bo.", "index": "32", "type": "numeric", "distinct": "79", "missing": "0", "min": "2", "max": "3", "mean": "3", "stdev": "0" }, { "name": "SM03_EA.bo.", "index": "33", "type": "numeric", "distinct": "58", "missing": "0", "min": "4", "max": "6", "mean": "5", "stdev": "0" }, { "name": "GATS7p", "index": "34", "type": "numeric", "distinct": "83", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "ATSC7e", "index": "35", "type": "numeric", "distinct": "101", "missing": "0", "min": "0", "max": "4", "mean": "2", "stdev": "1" }, { "name": "GGI6", "index": "36", "type": "numeric", "distinct": "85", "missing": "0", "min": "0", "max": "3", "mean": "2", "stdev": "1" }, { "name": "SIC5", "index": "37", "type": "numeric", "distinct": "63", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "CATS2D_08_DL", "index": "38", "type": "numeric", "distinct": "25", "missing": "0", "min": "0", "max": "35", "mean": "14", "stdev": "10" }, { "name": "IC3", "index": "39", "type": "numeric", "distinct": "94", "missing": "0", "min": "4", "max": "6", "mean": "5", "stdev": "1" }, { "name": "IC4", "index": "40", "type": "numeric", "distinct": "89", "missing": "0", "min": "4", "max": "7", "mean": "6", "stdev": "1" }, { "name": "IC5", "index": "41", "type": "numeric", "distinct": "91", "missing": "0", "min": "4", "max": "7", "mean": "6", "stdev": "1" }, { "name": "P_VSA_s_6", "index": "42", "type": "numeric", "distinct": "56", "missing": "0", "min": "0", "max": "603", "mean": "255", "stdev": "156" }, { "name": "MATS2e", "index": "43", "type": "numeric", "distinct": "67", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "MATS5p", "index": "44", "type": "numeric", "distinct": "64", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SM02_EA.dm.", "index": "45", "type": "numeric", "distinct": "62", "missing": "0", "min": "1", "max": "5", "mean": "3", "stdev": "1" }, { "name": "SM04_EA.dm.", "index": "46", "type": "numeric", "distinct": "64", "missing": "0", "min": "1", "max": "6", "mean": "4", "stdev": "2" }, { "name": "SM06_EA.dm.", "index": "47", "type": "numeric", "distinct": "63", "missing": "0", "min": "0", "max": "8", "mean": "5", "stdev": "2" }, { "name": "SM08_EA.dm.", "index": "48", "type": "numeric", "distinct": "63", "missing": "0", "min": "0", "max": "11", "mean": "7", "stdev": "3" }, { "name": "SM10_EA.dm.", "index": "49", "type": "numeric", "distinct": "61", "missing": "0", "min": "0", "max": "13", "mean": "8", "stdev": "4" }, { "name": "SM12_EA.dm.", "index": "50", "type": "numeric", "distinct": "61", "missing": "0", "min": "0", "max": "16", "mean": "9", "stdev": "4" }, { "name": "SM14_EA.dm.", "index": "51", "type": "numeric", "distinct": "60", "missing": "0", "min": "0", "max": "19", "mean": "10", "stdev": "5" }, { "name": "Eig05_EA.bo.", "index": "52", "type": "numeric", "distinct": "70", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "GGI1", "index": "53", "type": "numeric", "distinct": "34", "missing": "0", "min": "3", "max": "23", "mean": "12", "stdev": "5" }, { "name": "GNar", "index": "54", "type": "numeric", "distinct": "65", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "HNar", "index": "55", "type": "numeric", "distinct": "71", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "nHet", "index": "56", "type": "numeric", "distinct": "23", "missing": "0", "min": "2", "max": "32", "mean": "15", "stdev": "8" }, { "name": "nN", "index": "57", "type": "numeric", "distinct": "15", "missing": "0", "min": "1", "max": "18", "mean": "8", "stdev": "4" }, { "name": "SM15_AEA.ri.", "index": "58", "type": "numeric", "distinct": "70", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "X0A", "index": "59", "type": "numeric", "distinct": "51", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Hy", "index": "60", "type": "numeric", "distinct": "90", "missing": "0", "min": "-1", "max": "15", "mean": "6", "stdev": "5" }, { "name": "Eig01_AEA.dm.", "index": "61", "type": "numeric", "distinct": "50", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "SM03_EA.dm.", "index": "62", "type": "numeric", "distinct": "35", "missing": "0", "min": "0", "max": "4", "mean": "3", "stdev": "1" }, { "name": "SM05_EA.dm.", "index": "63", "type": "numeric", "distinct": "43", "missing": "0", "min": "0", "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 }