{ "data_id": "26225", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4398", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4398", "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: CHEMBL4398 (TID: 11907), and it has 270 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": "2016-07-14 18:45:09", "update_comment": null, "last_update": "2016-07-14 18:45:09", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3296526\/data_53186.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4398", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL4398 (TID: 11907), and it has 270 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": 270, "NumberOfFeatures": 69, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 68, "NumberOfSymbolicFeatures": 1, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 1.0918925925925926, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": 0.5430936461584756, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 48.24884074074074, "Quartile1SkewnessOfNumericAtts": -0.47032022889314856, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.16441788827342646, "AutoCorrelation": 0.06815985130111496, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "ClassEntropy": null, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": -0.15695106320772223, "Dimensionality": 0.25555555555555554, "MeanSkewnessOfNumericAtts": 0.04410411370833001, "Quartile2MeansOfNumericAtts": 3.8648148148148147, "EquivalentNumberOfAtts": null, "MeanStdDevOfNumericAtts": 22.241099532255653, "Quartile2MutualInformation": null, "MajorityClassPercentage": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": 0.040419092023459925, "MajorityClassSize": null, "MinKurtosisOfNumericAtts": -0.8279966796788556, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 1.2022589258938245, "MaxAttributeEntropy": null, "MaxKurtosisOfNumericAtts": 10.693244799045688, "MinMeansOfNumericAtts": -0.28024444444444446, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 406.359062962963, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 0.392174961207549, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.55072463768117, "Quartile3MeansOfNumericAtts": 12.957407407407405, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -2.398985763517165, "PercentageOfSymbolicFeatures": 1.4492753623188406, "Quartile3MutualInformation": null, "MaxSkewnessOfNumericAtts": 2.099537197914244, "MinStdDevOfNumericAtts": 0.009493869990493481, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 0.4352426941171207, "MaxStdDevOfNumericAtts": 191.59860738847814, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": -0.4554238031481257, "Quartile3StdDevOfNumericAtts": 5.749866019447286 }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "68", "type": "numeric", "distinct": "192", "missing": "0", "target": "1", "min": "4", "max": "9", "mean": "6", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "270", "missing": "0", "identifier": "1", "distr": [] }, { "name": "CATS2D_03_DN", "index": "1", "type": "numeric", "distinct": "12", "missing": "0", "min": "0", "max": "12", "mean": "4", "stdev": "2" }, { "name": "CATS2D_04_DD", "index": "2", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "6", "mean": "2", "stdev": "1" }, { "name": "SsOH", "index": "3", "type": "numeric", "distinct": "245", "missing": "0", "min": "0", "max": "109", "mean": "50", "stdev": "23" }, { "name": "ATSC3s", "index": "4", "type": "numeric", "distinct": "257", "missing": "0", "min": "24", "max": "727", "mean": "293", "stdev": "139" }, { "name": "MATS6e", "index": "5", "type": "numeric", "distinct": "186", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "GATS6e", "index": "6", "type": "numeric", "distinct": "197", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "CATS2D_05_DN", "index": "7", "type": "numeric", "distinct": "11", "missing": "0", "min": "0", "max": "12", "mean": "3", "stdev": "2" }, { "name": "ATSC4s", "index": "8", "type": "numeric", "distinct": "257", "missing": "0", "min": "34", "max": "970", "mean": "406", "stdev": "192" }, { "name": "Eta_C_A", "index": "9", "type": "numeric", "distinct": "202", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "MATS6s", "index": "10", "type": "numeric", "distinct": "189", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "CATS2D_02_NN", "index": "11", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "6", "mean": "2", "stdev": "1" }, { "name": "MAXDN", "index": "12", "type": "numeric", "distinct": "223", "missing": "0", "min": "2", "max": "8", "mean": "6", "stdev": "1" }, { "name": "GATS4e", "index": "13", "type": "numeric", "distinct": "199", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "nO", "index": "14", "type": "numeric", "distinct": "28", "missing": "0", "min": "1", "max": "32", "mean": "14", "stdev": "6" }, { "name": "X5Av", "index": "15", "type": "numeric", "distinct": "39", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "CATS2D_03_AN", "index": "16", "type": "numeric", "distinct": "17", "missing": "0", "min": "0", "max": "24", "mean": "6", "stdev": "5" }, { "name": "Eta_sh_x", "index": "17", "type": "numeric", "distinct": "141", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "P_VSA_s_1", "index": "18", "type": "numeric", "distinct": "31", "missing": "0", "min": "0", "max": "69", "mean": "20", "stdev": "14" }, { "name": "MATS4e", "index": "19", "type": "numeric", "distinct": "200", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "MCD", "index": "20", "type": "numeric", "distinct": "97", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "GATS2p", "index": "21", "type": "numeric", "distinct": "179", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "ATSC1s", "index": "22", "type": "numeric", "distinct": "235", "missing": "0", "min": "6", "max": "291", "mean": "122", "stdev": "53" }, { "name": "CATS2D_04_DA", "index": "23", "type": "numeric", "distinct": "24", "missing": "0", "min": "0", "max": "30", "mean": "10", "stdev": "6" }, { "name": "O.056", "index": "24", "type": "numeric", "distinct": "12", "missing": "0", "min": "0", "max": "11", "mean": "5", "stdev": "2" }, { "name": "nPO4", "index": "25", "type": "numeric", "distinct": "8", "missing": "0", "min": "0", "max": "7", "mean": "2", "stdev": "1" }, { "name": "P.117", "index": "26", "type": "numeric", "distinct": "8", "missing": "0", "min": "0", "max": "7", "mean": "2", "stdev": "2" }, { "name": "D.Dtr05", "index": "27", "type": "numeric", "distinct": "150", "missing": "0", "min": "0", "max": "877", "mean": "153", "stdev": "155" }, { "name": "SpMax7_Bh.s.", "index": "28", "type": "numeric", "distinct": "80", "missing": "0", "min": "4", "max": "7", "mean": "6", "stdev": "1" }, { "name": "ATSC2e", "index": "29", "type": "numeric", "distinct": "221", "missing": "0", "min": "0", "max": "4", "mean": "2", "stdev": "1" }, { "name": "MATS2p", "index": "30", "type": "numeric", "distinct": "162", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "MATS3e", "index": "31", "type": "numeric", "distinct": "173", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "CATS2D_04_NN", "index": "32", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "5", "mean": "1", "stdev": "1" }, { "name": "P_VSA_e_5", "index": "33", "type": "numeric", "distinct": "106", "missing": "0", "min": "25", "max": "726", "mean": "334", "stdev": "128" }, { "name": "P_VSA_m_3", "index": "34", "type": "numeric", "distinct": "121", "missing": "0", "min": "25", "max": "726", "mean": "336", "stdev": "128" }, { "name": "ATSC2s", "index": "35", "type": "numeric", "distinct": "245", "missing": "0", "min": "24", "max": "521", "mean": "223", "stdev": "80" }, { "name": "nROH", "index": "36", "type": "numeric", "distinct": "12", "missing": "0", "min": "0", "max": "11", "mean": "5", "stdev": "2" }, { "name": "X2Av", "index": "37", "type": "numeric", "distinct": "82", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "MATS4s", "index": "38", "type": "numeric", "distinct": "204", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "ATS4s", "index": "39", "type": "numeric", "distinct": "230", "missing": "0", "min": "6", "max": "8", "mean": "7", "stdev": "0" }, { "name": "ATSC5e", "index": "40", "type": "numeric", "distinct": "252", "missing": "0", "min": "0", "max": "6", "mean": "3", "stdev": "1" }, { "name": "O.059", "index": "41", "type": "numeric", "distinct": "12", "missing": "0", "min": "0", "max": "11", "mean": "4", "stdev": "3" }, { "name": "MATS1p", "index": "42", "type": "numeric", "distinct": "167", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SpMax8_Bh.s.", "index": "43", "type": "numeric", "distinct": "87", "missing": "0", "min": "4", "max": "7", "mean": "6", "stdev": "1" }, { "name": "NssO", "index": "44", "type": "numeric", "distinct": "12", "missing": "0", "min": "0", "max": "11", "mean": "4", "stdev": "3" }, { "name": "SssO", "index": "45", "type": "numeric", "distinct": "224", "missing": "0", "min": "0", "max": "58", "mean": "17", "stdev": "11" }, { "name": "ATSC6s", "index": "46", "type": "numeric", "distinct": "257", "missing": "0", "min": "38", "max": "1043", "mean": "392", "stdev": "181" }, { "name": "CATS2D_01_AN", "index": "47", "type": "numeric", "distinct": "18", "missing": "0", "min": "0", "max": "21", "mean": "7", "stdev": "4" }, { "name": "CATS2D_07_DN", "index": "48", "type": "numeric", "distinct": "9", "missing": "0", "min": "0", "max": "10", "mean": "1", "stdev": "2" }, { "name": "SpMax6_Bh.s.", "index": "49", "type": "numeric", "distinct": "49", "missing": "0", "min": "4", "max": "8", "mean": "7", "stdev": "1" }, { "name": "CATS2D_08_DD", "index": "50", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "6", "mean": "1", "stdev": "1" }, { "name": "BAC", "index": "51", "type": "numeric", "distinct": "82", "missing": "0", "min": "21", "max": "662", "mean": "138", "stdev": "81" }, { "name": "P_VSA_LogP_3", "index": "52", "type": "numeric", "distinct": "88", "missing": "0", "min": "85", "max": "451", "mean": "246", "stdev": "71" }, { "name": "Eig05_EA", "index": "53", "type": "numeric", "distinct": "124", "missing": "0", "min": "2", "max": "3", "mean": "3", "stdev": "0" }, { "name": "SM13_AEA.bo.", "index": "54", "type": "numeric", "distinct": "124", "missing": "0", "min": "2", "max": "3", "mean": "3", "stdev": "0" }, { "name": "Eig05_AEA.ri.", "index": "55", "type": "numeric", "distinct": "149", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "Eig05_EA.ed.", "index": "56", "type": "numeric", "distinct": "144", "missing": "0", "min": "5", "max": "12", "mean": "9", "stdev": "1" }, { "name": "SM14_AEA.dm.", "index": "57", "type": "numeric", "distinct": "144", "missing": "0", "min": "5", "max": "12", "mean": "9", "stdev": "1" }, { "name": "P_VSA_i_1", "index": "58", "type": "numeric", "distinct": "48", "missing": "0", "min": "0", "max": "130", "mean": "27", "stdev": "21" }, { "name": "DBI", "index": "59", "type": "numeric", "distinct": "65", "missing": "0", "min": "3", "max": "8", "mean": "5", "stdev": "1" }, { "name": "MATS5p", "index": "60", "type": "numeric", "distinct": "147", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "ATSC8s", "index": "61", "type": "numeric", "distinct": "256", "missing": "0", "min": "28", "max": "869", "mean": "316", "stdev": "165" }, { "name": "ATS6s", "index": "62", "type": "numeric", "distinct": "226", "missing": "0", "min": "6", "max": "8", "mean": "7", "stdev": "0" }, { "name": "Eig03_AEA.ri.", "index": "63", "type": "numeric", "distinct": "143", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "Eig03_EA", "index": "64", "type": "numeric", "distinct": "121", "missing": "0", "min": "3", "max": "3", "mean": "3", "stdev": "0" }, { "name": "SM11_AEA.bo.", "index": "65", "type": "numeric", "distinct": "121", "missing": "0", "min": "3", "max": "3", "mean": "3", "stdev": "0" }, { "name": "ATSC3m", "index": "66", "type": "numeric", "distinct": "244", "missing": "0", "min": "10", "max": "80", "mean": "35", "stdev": "13" }, { "name": "Eig02_EA.ri.", "index": "67", "type": "numeric", "distinct": "114", "missing": "0", "min": "3", "max": "3", "mean": "3", "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 }