{ "data_id": "31368", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4105", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4105", "version": 10, "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: CHEMBL4105 (TID: 17106), and it has 127 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 07:23:54", "update_comment": null, "last_update": "2016-07-15 07:23:54", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3447064\/data_52245.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4105", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL4105 (TID: 17106), and it has 127 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": 127, "NumberOfFeatures": 63, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 62, "NumberOfSymbolicFeatures": 1, "Quartile3AttributeEntropy": null, "MaxKurtosisOfNumericAtts": 20.18569299261683, "MinMeansOfNumericAtts": -0.04755118110236212, "PercentageOfInstancesWithMissingValues": 0, "Quartile3KurtosisOfNumericAtts": -0.2436268219257457, "MaxMeansOfNumericAtts": 36.18820472440945, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3MeansOfNumericAtts": 11.094425196850393, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.4126984126984, "Quartile3MutualInformation": null, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -1.2069490225007582, "PercentageOfSymbolicFeatures": 1.5873015873015872, "Quartile3SkewnessOfNumericAtts": 0.43181444752786885, "MaxSkewnessOfNumericAtts": 3.396482312974652, "MinStdDevOfNumericAtts": 0.03571768687716939, "Quartile1AttributeEntropy": null, "Quartile3StdDevOfNumericAtts": 1.2608984510762598, "MaxStdDevOfNumericAtts": 32.61336428373747, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": -1.4200681734045517, "StdvNominalAttDistinctValues": null, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 1.6259842519685042, "MeanKurtosisOfNumericAtts": -0.23086082237860064, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 8.62933274066548, "Quartile1SkewnessOfNumericAtts": -0.06911365960562776, "AutoCorrelation": -0.204031746031746, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.255097407578833, "ClassEntropy": null, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "Dimensionality": 0.49606299212598426, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": -0.8566139728860733, "EquivalentNumberOfAtts": null, "MeanSkewnessOfNumericAtts": 0.23660238396480862, "Quartile2MeansOfNumericAtts": 4.681566929133858, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 1.5852646659798688, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": 0.05679178290888154, "Quartile2StdDevOfNumericAtts": 0.6116354653471295, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -2.032000000000001, "PercentageOfBinaryFeatures": 0 }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "62", "type": "numeric", "distinct": "66", "missing": "0", "target": "1", "min": "4", "max": "10", "mean": "6", "stdev": "2" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "127", "missing": "0", "identifier": "1", "distr": [] }, { "name": "NaaNH", "index": "1", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "SaaNH", "index": "2", "type": "numeric", "distinct": "48", "missing": "0", "min": "0", "max": "6", "mean": "2", "stdev": "2" }, { "name": "CATS2D_02_DL", "index": "3", "type": "numeric", "distinct": "8", "missing": "0", "min": "0", "max": "12", "mean": "2", "stdev": "2" }, { "name": "CATS2D_03_DL", "index": "4", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "6", "mean": "2", "stdev": "2" }, { "name": "CATS2D_03_AA", "index": "5", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "5", "mean": "2", "stdev": "2" }, { "name": "SpMin1_Bh.p.", "index": "6", "type": "numeric", "distinct": "56", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "SsssN", "index": "7", "type": "numeric", "distinct": "87", "missing": "0", "min": "0", "max": "10", "mean": "3", "stdev": "2" }, { "name": "nPyrazines", "index": "8", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "1" }, { "name": "Hy", "index": "9", "type": "numeric", "distinct": "74", "missing": "0", "min": "-1", "max": "3", "mean": "0", "stdev": "1" }, { "name": "P_VSA_s_5", "index": "10", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "35", "mean": "10", "stdev": "12" }, { "name": "H.050", "index": "11", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "6", "mean": "1", "stdev": "2" }, { "name": "nHDon", "index": "12", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "6", "mean": "1", "stdev": "2" }, { "name": "SAdon", "index": "13", "type": "numeric", "distinct": "12", "missing": "0", "min": "0", "max": "256", "mean": "22", "stdev": "33" }, { "name": "SpDiam_EA.ed.", "index": "14", "type": "numeric", "distinct": "50", "missing": "0", "min": "16", "max": "20", "mean": "18", "stdev": "1" }, { "name": "C.029", "index": "15", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "1" }, { "name": "N.071", "index": "16", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "1" }, { "name": "nArNR2", "index": "17", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "1" }, { "name": "nCIR", "index": "18", "type": "numeric", "distinct": "10", "missing": "0", "min": "3", "max": "14", "mean": "6", "stdev": "2" }, { "name": "Rbrid", "index": "19", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "2", "stdev": "1" }, { "name": "CATS2D_04_DL", "index": "20", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "9", "mean": "1", "stdev": "1" }, { "name": "SpDiam_AEA.bo.", "index": "21", "type": "numeric", "distinct": "50", "missing": "0", "min": "5", "max": "6", "mean": "6", "stdev": "0" }, { "name": "LOC", "index": "22", "type": "numeric", "distinct": "54", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "Rperim", "index": "23", "type": "numeric", "distinct": "20", "missing": "0", "min": "9", "max": "37", "mean": "20", "stdev": "6" }, { "name": "C.006", "index": "24", "type": "numeric", "distinct": "8", "missing": "0", "min": "0", "max": "10", "mean": "3", "stdev": "2" }, { "name": "SpDiam_AEA.ed.", "index": "25", "type": "numeric", "distinct": "58", "missing": "0", "min": "6", "max": "7", "mean": "6", "stdev": "0" }, { "name": "Eig01_AEA.ed.", "index": "26", "type": "numeric", "distinct": "31", "missing": "0", "min": "6", "max": "7", "mean": "7", "stdev": "0" }, { "name": "Eig01_EA.ed.", "index": "27", "type": "numeric", "distinct": "43", "missing": "0", "min": "10", "max": "12", "mean": "11", "stdev": "1" }, { "name": "SM10_AEA.dm.", "index": "28", "type": "numeric", "distinct": "43", "missing": "0", "min": "10", "max": "12", "mean": "11", "stdev": "1" }, { "name": "SpMax_AEA.ed.", "index": "29", "type": "numeric", "distinct": "31", "missing": "0", "min": "6", "max": "7", "mean": "7", "stdev": "0" }, { "name": "SpMax_EA.ed.", "index": "30", "type": "numeric", "distinct": "43", "missing": "0", "min": "10", "max": "12", "mean": "11", "stdev": "1" }, { "name": "Eig01_AEA.ri.", "index": "31", "type": "numeric", "distinct": "48", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "Eig01_EA", "index": "32", "type": "numeric", "distinct": "46", "missing": "0", "min": "3", "max": "3", "mean": "3", "stdev": "0" }, { "name": "SM09_AEA.bo.", "index": "33", "type": "numeric", "distinct": "46", "missing": "0", "min": "3", "max": "3", "mean": "3", "stdev": "0" }, { "name": "SM10_EA.ed.", "index": "34", "type": "numeric", "distinct": "90", "missing": "0", "min": "23", "max": "26", "mean": "24", "stdev": "1" }, { "name": "SM11_EA.ed.", "index": "35", "type": "numeric", "distinct": "92", "missing": "0", "min": "25", "max": "28", "mean": "27", "stdev": "1" }, { "name": "SM12_EA.ed.", "index": "36", "type": "numeric", "distinct": "90", "missing": "0", "min": "27", "max": "31", "mean": "29", "stdev": "1" }, { "name": "SM13_EA.ed.", "index": "37", "type": "numeric", "distinct": "88", "missing": "0", "min": "30", "max": "33", "mean": "31", "stdev": "1" }, { "name": "SM14_EA.ed.", "index": "38", "type": "numeric", "distinct": "89", "missing": "0", "min": "32", "max": "36", "mean": "34", "stdev": "1" }, { "name": "SM15_EA.ed.", "index": "39", "type": "numeric", "distinct": "85", "missing": "0", "min": "34", "max": "38", "mean": "36", "stdev": "1" }, { "name": "SpDiam_AEA.ri.", "index": "40", "type": "numeric", "distinct": "73", "missing": "0", "min": "5", "max": "5", "mean": "5", "stdev": "0" }, { "name": "SpDiam_EA", "index": "41", "type": "numeric", "distinct": "46", "missing": "0", "min": "5", "max": "5", "mean": "5", "stdev": "0" }, { "name": "SpMax_AEA.ri.", "index": "42", "type": "numeric", "distinct": "48", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "SpMax_EA", "index": "43", "type": "numeric", "distinct": "46", "missing": "0", "min": "3", "max": "3", "mean": "3", "stdev": "0" }, { "name": "SpMin1_Bh.v.", "index": "44", "type": "numeric", "distinct": "61", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "SM11_EA.bo.", "index": "45", "type": "numeric", "distinct": "83", "missing": "0", "min": "15", "max": "18", "mean": "17", "stdev": "0" }, { "name": "piPC04", "index": "46", "type": "numeric", "distinct": "82", "missing": "0", "min": "5", "max": "6", "mean": "6", "stdev": "0" }, { "name": "TRS", "index": "47", "type": "numeric", "distinct": "16", "missing": "0", "min": "11", "max": "41", "mean": "24", "stdev": "6" }, { "name": "MPC06", "index": "48", "type": "numeric", "distinct": "66", "missing": "0", "min": "4", "max": "5", "mean": "5", "stdev": "0" }, { "name": "MPC08", "index": "49", "type": "numeric", "distinct": "79", "missing": "0", "min": "3", "max": "6", "mean": "5", "stdev": "0" }, { "name": "RBF", "index": "50", "type": "numeric", "distinct": "60", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "nCIC", "index": "51", "type": "numeric", "distinct": "6", "missing": "0", "min": "2", "max": "7", "mean": "4", "stdev": "1" }, { "name": "piPC05", "index": "52", "type": "numeric", "distinct": "91", "missing": "0", "min": "5", "max": "7", "mean": "6", "stdev": "0" }, { "name": "MCD", "index": "53", "type": "numeric", "distinct": "48", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "MPC07", "index": "54", "type": "numeric", "distinct": "70", "missing": "0", "min": "3", "max": "6", "mean": "5", "stdev": "0" }, { "name": "C.002", "index": "55", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "5", "mean": "1", "stdev": "1" }, { "name": "SM08_EA.ed.", "index": "56", "type": "numeric", "distinct": "93", "missing": "0", "min": "18", "max": "21", "mean": "20", "stdev": "1" }, { "name": "SM09_EA.ed.", "index": "57", "type": "numeric", "distinct": "94", "missing": "0", "min": "21", "max": "23", "mean": "22", "stdev": "1" }, { "name": "SM15_AEA.ed.", "index": "58", "type": "numeric", "distinct": "93", "missing": "0", "min": "28", "max": "30", "mean": "29", "stdev": "1" }, { "name": "Eig12_AEA.ed.", "index": "59", "type": "numeric", "distinct": "72", "missing": "0", "min": "1", "max": "5", "mean": "3", "stdev": "1" }, { "name": "MPC04", "index": "60", "type": "numeric", "distinct": "49", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "piPC08", "index": "61", "type": "numeric", "distinct": "91", "missing": "0", "min": "6", "max": "8", "mean": "7", "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 }