{ "data_id": "35476", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3106", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3106", "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: CHEMBL3106 (TID: 11723), and it has 118 rows and 66 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 18:08:52", "update_comment": null, "last_update": "2016-07-15 18:08:52", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3559241\/data_53037.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3106", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL3106 (TID: 11723), and it has 118 rows and 66 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": 118, "NumberOfFeatures": 68, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 67, "NumberOfSymbolicFeatures": 1, "ClassEntropy": null, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "Dimensionality": 0.576271186440678, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": 0.10298961685372277, "EquivalentNumberOfAtts": null, "MeanSkewnessOfNumericAtts": 0.5483890585526222, "Quartile2MeansOfNumericAtts": 1.2403474576271185, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 5.059584930742804, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": 0.3466792503738071, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.8637732742331876, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.6666886871634857, "MaxKurtosisOfNumericAtts": 16.028755864731302, "MinMeansOfNumericAtts": -0.27749152542372885, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 75.21856779661017, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 1.5104366328135197, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.52941176470588, "Quartile3MeansOfNumericAtts": 4.185110169491526, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -1.3966273199947647, "PercentageOfSymbolicFeatures": 1.4705882352941175, "Quartile3MutualInformation": null, "MaxSkewnessOfNumericAtts": 2.912499705800588, "MinStdDevOfNumericAtts": 0.010582639072863016, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 1.1389170580872525, "MaxStdDevOfNumericAtts": 64.13096259729845, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": -0.3758533752860851, "Quartile3StdDevOfNumericAtts": 1.0271167126910201, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 0.16101694915254255, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": 1.1934862395136656, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 8.030867062990133, "Quartile1SkewnessOfNumericAtts": -0.11574925174870217, "AutoCorrelation": 0.17235897435897446, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.2444691321999167 }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "67", "type": "numeric", "distinct": "98", "missing": "0", "target": "1", "min": "3", "max": "8", "mean": "5", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "118", "missing": "0", "identifier": "1", "distr": [] }, { "name": "H.054", "index": "1", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "MATS3m", "index": "2", "type": "numeric", "distinct": "101", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "P_VSA_e_2", "index": "3", "type": "numeric", "distinct": "98", "missing": "0", "min": "5", "max": "240", "mean": "66", "stdev": "64" }, { "name": "C.029", "index": "4", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "P_VSA_MR_5", "index": "5", "type": "numeric", "distinct": "70", "missing": "0", "min": "0", "max": "108", "mean": "36", "stdev": "22" }, { "name": "P_VSA_MR_6", "index": "6", "type": "numeric", "distinct": "62", "missing": "0", "min": "5", "max": "216", "mean": "54", "stdev": "59" }, { "name": "P_VSA_s_4", "index": "7", "type": "numeric", "distinct": "53", "missing": "0", "min": "0", "max": "212", "mean": "46", "stdev": "59" }, { "name": "CATS2D_04_DA", "index": "8", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "6", "mean": "2", "stdev": "1" }, { "name": "N.071", "index": "9", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "nArNR2", "index": "10", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "GATS3s", "index": "11", "type": "numeric", "distinct": "99", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "X4A", "index": "12", "type": "numeric", "distinct": "31", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "GATS3m", "index": "13", "type": "numeric", "distinct": "94", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "MATS6p", "index": "14", "type": "numeric", "distinct": "103", "missing": "0", "min": "-1", "max": "1", "mean": "0", "stdev": "0" }, { "name": "SM09_EA.bo.", "index": "15", "type": "numeric", "distinct": "75", "missing": "0", "min": "11", "max": "14", "mean": "13", "stdev": "1" }, { "name": "CATS2D_02_DD", "index": "16", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "CATS2D_06_DD", "index": "17", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "0" }, { "name": "GATS6v", "index": "18", "type": "numeric", "distinct": "103", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "Eig01_AEA.bo.", "index": "19", "type": "numeric", "distinct": "55", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SpMax_AEA.bo.", "index": "20", "type": "numeric", "distinct": "55", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "MATS3s", "index": "21", "type": "numeric", "distinct": "99", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "BIC2", "index": "22", "type": "numeric", "distinct": "76", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SM10_EA.bo.", "index": "23", "type": "numeric", "distinct": "78", "missing": "0", "min": "13", "max": "16", "mean": "14", "stdev": "1" }, { "name": "SM11_EA.bo.", "index": "24", "type": "numeric", "distinct": "76", "missing": "0", "min": "14", "max": "17", "mean": "15", "stdev": "1" }, { "name": "GATS6s", "index": "25", "type": "numeric", "distinct": "113", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "MATS8e", "index": "26", "type": "numeric", "distinct": "99", "missing": "0", "min": "-2", "max": "1", "mean": "0", "stdev": "1" }, { "name": "GATS8e", "index": "27", "type": "numeric", "distinct": "99", "missing": "0", "min": "0", "max": "5", "mean": "1", "stdev": "1" }, { "name": "MATS8s", "index": "28", "type": "numeric", "distinct": "103", "missing": "0", "min": "-2", "max": "1", "mean": "0", "stdev": "1" }, { "name": "SsssN", "index": "29", "type": "numeric", "distinct": "54", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "MATS3e", "index": "30", "type": "numeric", "distinct": "104", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SRW07", "index": "31", "type": "numeric", "distinct": "9", "missing": "0", "min": "0", "max": "6", "mean": "3", "stdev": "2" }, { "name": "SM13_EA.bo.", "index": "32", "type": "numeric", "distinct": "75", "missing": "0", "min": "16", "max": "20", "mean": "18", "stdev": "1" }, { "name": "MATS6v", "index": "33", "type": "numeric", "distinct": "98", "missing": "0", "min": "-1", "max": "2", "mean": "0", "stdev": "0" }, { "name": "GATS3e", "index": "34", "type": "numeric", "distinct": "105", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "GATS8s", "index": "35", "type": "numeric", "distinct": "97", "missing": "0", "min": "0", "max": "6", "mean": "2", "stdev": "1" }, { "name": "SM12_EA.bo.", "index": "36", "type": "numeric", "distinct": "78", "missing": "0", "min": "15", "max": "19", "mean": "17", "stdev": "1" }, { "name": "SM14_EA.bo.", "index": "37", "type": "numeric", "distinct": "76", "missing": "0", "min": "17", "max": "22", "mean": "20", "stdev": "1" }, { "name": "SM15_EA.bo.", "index": "38", "type": "numeric", "distinct": "73", "missing": "0", "min": "18", "max": "23", "mean": "21", "stdev": "1" }, { "name": "Eig01_EA.bo.", "index": "39", "type": "numeric", "distinct": "58", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SM11_AEA.ri.", "index": "40", "type": "numeric", "distinct": "58", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SpMax_EA.bo.", "index": "41", "type": "numeric", "distinct": "58", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "GATS6m", "index": "42", "type": "numeric", "distinct": "109", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "P_VSA_i_2", "index": "43", "type": "numeric", "distinct": "98", "missing": "0", "min": "6", "max": "240", "mean": "72", "stdev": "61" }, { "name": "Eig06_AEA.ri.", "index": "44", "type": "numeric", "distinct": "76", "missing": "0", "min": "0", "max": "3", "mean": "2", "stdev": "1" }, { "name": "X2A", "index": "45", "type": "numeric", "distinct": "45", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Eig11_AEA.dm.", "index": "46", "type": "numeric", "distinct": "79", "missing": "0", "min": "-2", "max": "2", "mean": "0", "stdev": "1" }, { "name": "Ui", "index": "47", "type": "numeric", "distinct": "15", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "1" }, { "name": "P_VSA_MR_2", "index": "48", "type": "numeric", "distinct": "29", "missing": "0", "min": "0", "max": "171", "mean": "75", "stdev": "37" }, { "name": "Eig06_EA.bo.", "index": "49", "type": "numeric", "distinct": "80", "missing": "0", "min": "-1", "max": "3", "mean": "1", "stdev": "1" }, { "name": "SpMin5_Bh.e.", "index": "50", "type": "numeric", "distinct": "76", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "MATS5m", "index": "51", "type": "numeric", "distinct": "103", "missing": "0", "min": "-1", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Eig06_AEA.ed.", "index": "52", "type": "numeric", "distinct": "48", "missing": "0", "min": "2", "max": "6", "mean": "4", "stdev": "1" }, { "name": "Eig12_AEA.dm.", "index": "53", "type": "numeric", "distinct": "84", "missing": "0", "min": "-2", "max": "2", "mean": "0", "stdev": "1" }, { "name": "IC2", "index": "54", "type": "numeric", "distinct": "80", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "MATS6e", "index": "55", "type": "numeric", "distinct": "106", "missing": "0", "min": "-1", "max": "1", "mean": "0", "stdev": "0" }, { "name": "nArX", "index": "56", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "JGI5", "index": "57", "type": "numeric", "distinct": "33", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "MATS6m", "index": "58", "type": "numeric", "distinct": "99", "missing": "0", "min": "-1", "max": "1", "mean": "0", "stdev": "0" }, { "name": "GATS6e", "index": "59", "type": "numeric", "distinct": "106", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "Eig01_EA.dm.", "index": "60", "type": "numeric", "distinct": "24", "missing": "0", "min": "0", "max": "4", "mean": "2", "stdev": "1" }, { "name": "SpDiam_EA.dm.", "index": "61", "type": "numeric", "distinct": "28", "missing": "0", "min": "0", "max": "5", "mean": "3", "stdev": "1" }, { "name": "SpMax_EA.dm.", "index": "62", "type": "numeric", "distinct": "24", "missing": "0", "min": "0", "max": "4", "mean": "2", "stdev": "1" }, { "name": "SpMAD_EA.ri.", "index": "63", "type": "numeric", "distinct": "81", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SM03_EA.dm.", "index": "64", "type": "numeric", "distinct": "19", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "SM05_EA.dm.", "index": "65", "type": "numeric", "distinct": "24", "missing": "0", "min": "0", "max": "7", "mean": "2", "stdev": "2" }, { "name": "Eig13_AEA.ri.", "index": "66", "type": "numeric", "distinct": "74", "missing": "0", "min": "-1", "max": "2", "mean": "0", "stdev": "1" } ], "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 }