{ "data_id": "29088", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4426", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4426", "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: CHEMBL4426 (TID: 12651), and it has 449 rows and 69 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 01:38:10", "update_comment": null, "last_update": "2016-07-15 01:38:10", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3382772\/data_53524.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4426", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL4426 (TID: 12651), and it has 449 rows and 69 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": 449, "NumberOfFeatures": 71, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 70, "NumberOfSymbolicFeatures": 1, "Quartile3AttributeEntropy": null, "MaxKurtosisOfNumericAtts": 30.46678542051277, "MinMeansOfNumericAtts": -0.6534521158129175, "PercentageOfInstancesWithMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 4.606084291268246, "MaxMeansOfNumericAtts": 57.04865478841871, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3MeansOfNumericAtts": 12.077722160356346, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.59154929577466, "Quartile3MutualInformation": null, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -1.9933259444150628, "PercentageOfSymbolicFeatures": 1.4084507042253522, "Quartile3SkewnessOfNumericAtts": 1.2988754195759957, "MaxSkewnessOfNumericAtts": 3.7323291490611936, "MinStdDevOfNumericAtts": 0.01286753074673982, "Quartile1AttributeEntropy": null, "Quartile3StdDevOfNumericAtts": 1.0236940535754113, "MaxStdDevOfNumericAtts": 63.840274838405094, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": 0.2082006870484603, "StdvNominalAttDistinctValues": null, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 0.5030679287305123, "MeanKurtosisOfNumericAtts": 3.1441032309484944, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 7.796804963410755, "Quartile1SkewnessOfNumericAtts": -0.5222490139497098, "AutoCorrelation": 0.33845535714285735, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.3714846129197833, "ClassEntropy": null, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "Dimensionality": 0.15812917594654788, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": 1.8505233777462418, "EquivalentNumberOfAtts": null, "MeanSkewnessOfNumericAtts": 0.22101526481618383, "Quartile2MeansOfNumericAtts": 4.3164008908685965, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 2.403946164599888, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": 0.010299284532581502, "Quartile2StdDevOfNumericAtts": 0.532645432655246, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.074612208129366, "PercentageOfBinaryFeatures": 0 }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "70", "type": "numeric", "distinct": "328", "missing": "0", "target": "1", "min": "4", "max": "9", "mean": "5", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "449", "missing": "0", "identifier": "1", "distr": [] }, { "name": "nRCONH2", "index": "1", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "SpMax1_Bh.i.", "index": "2", "type": "numeric", "distinct": "212", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "SpMax1_Bh.e.", "index": "3", "type": "numeric", "distinct": "221", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "SpMax1_Bh.v.", "index": "4", "type": "numeric", "distinct": "220", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "CATS2D_06_AP", "index": "5", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "4", "mean": "0", "stdev": "0" }, { "name": "CATS2D_05_AP", "index": "6", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "Eig01_EA.bo.", "index": "7", "type": "numeric", "distinct": "301", "missing": "0", "min": "2", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SM11_AEA.ri.", "index": "8", "type": "numeric", "distinct": "301", "missing": "0", "min": "2", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SpDiam_EA.bo.", "index": "9", "type": "numeric", "distinct": "306", "missing": "0", "min": "4", "max": "8", "mean": "7", "stdev": "0" }, { "name": "SpMax_EA.bo.", "index": "10", "type": "numeric", "distinct": "301", "missing": "0", "min": "2", "max": "5", "mean": "4", "stdev": "0" }, { "name": "nPyrroles", "index": "11", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "SdssC", "index": "12", "type": "numeric", "distinct": "365", "missing": "0", "min": "-7", "max": "5", "mean": "-1", "stdev": "1" }, { "name": "CATS2D_07_PL", "index": "13", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "10", "mean": "1", "stdev": "1" }, { "name": "CATS2D_02_AP", "index": "14", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "6", "mean": "0", "stdev": "1" }, { "name": "CATS2D_09_AP", "index": "15", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "SM15_EA.bo.", "index": "16", "type": "numeric", "distinct": "390", "missing": "0", "min": "14", "max": "25", "mean": "22", "stdev": "1" }, { "name": "CATS2D_09_PL", "index": "17", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "5", "mean": "1", "stdev": "1" }, { "name": "SM14_EA.bo.", "index": "18", "type": "numeric", "distinct": "388", "missing": "0", "min": "13", "max": "23", "mean": "21", "stdev": "1" }, { "name": "C.034", "index": "19", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "5", "mean": "1", "stdev": "1" }, { "name": "SM13_EA.bo.", "index": "20", "type": "numeric", "distinct": "388", "missing": "0", "min": "12", "max": "21", "mean": "19", "stdev": "1" }, { "name": "SM12_EA.bo.", "index": "21", "type": "numeric", "distinct": "382", "missing": "0", "min": "11", "max": "20", "mean": "18", "stdev": "1" }, { "name": "ATS6s", "index": "22", "type": "numeric", "distinct": "396", "missing": "0", "min": "4", "max": "7", "mean": "6", "stdev": "0" }, { "name": "ATSC3s", "index": "23", "type": "numeric", "distinct": "447", "missing": "0", "min": "10", "max": "256", "mean": "57", "stdev": "36" }, { "name": "ATS8s", "index": "24", "type": "numeric", "distinct": "401", "missing": "0", "min": "2", "max": "7", "mean": "6", "stdev": "1" }, { "name": "CATS2D_08_PL", "index": "25", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "8", "mean": "1", "stdev": "1" }, { "name": "Eig01_EA.ri.", "index": "26", "type": "numeric", "distinct": "291", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SpDiam_EA.ri.", "index": "27", "type": "numeric", "distinct": "291", "missing": "0", "min": "4", "max": "6", "mean": "5", "stdev": "0" }, { "name": "SpMax_EA.ri.", "index": "28", "type": "numeric", "distinct": "291", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SM11_EA.bo.", "index": "29", "type": "numeric", "distinct": "383", "missing": "0", "min": "10", "max": "18", "mean": "16", "stdev": "1" }, { "name": "SM09_EA.bo.", "index": "30", "type": "numeric", "distinct": "388", "missing": "0", "min": "8", "max": "15", "mean": "14", "stdev": "1" }, { "name": "ATS7s", "index": "31", "type": "numeric", "distinct": "385", "missing": "0", "min": "3", "max": "7", "mean": "6", "stdev": "1" }, { "name": "SM08_EA.bo.", "index": "32", "type": "numeric", "distinct": "374", "missing": "0", "min": "8", "max": "14", "mean": "12", "stdev": "1" }, { "name": "CATS2D_09_DP", "index": "33", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "SM15_EA.ri.", "index": "34", "type": "numeric", "distinct": "406", "missing": "0", "min": "12", "max": "21", "mean": "17", "stdev": "1" }, { "name": "SM10_EA.bo.", "index": "35", "type": "numeric", "distinct": "393", "missing": "0", "min": "9", "max": "17", "mean": "15", "stdev": "1" }, { "name": "GGI5", "index": "36", "type": "numeric", "distinct": "303", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "ATS7e", "index": "37", "type": "numeric", "distinct": "405", "missing": "0", "min": "3", "max": "6", "mean": "5", "stdev": "1" }, { "name": "SM13_EA.ri.", "index": "38", "type": "numeric", "distinct": "399", "missing": "0", "min": "10", "max": "19", "mean": "15", "stdev": "1" }, { "name": "SM14_EA.ri.", "index": "39", "type": "numeric", "distinct": "402", "missing": "0", "min": "12", "max": "20", "mean": "16", "stdev": "1" }, { "name": "Eig01_AEA.ri.", "index": "40", "type": "numeric", "distinct": "293", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SpMax_AEA.ri.", "index": "41", "type": "numeric", "distinct": "293", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SM12_EA.ri.", "index": "42", "type": "numeric", "distinct": "394", "missing": "0", "min": "10", "max": "17", "mean": "14", "stdev": "1" }, { "name": "CATS2D_08_PN", "index": "43", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "D.Dtr09", "index": "44", "type": "numeric", "distinct": "160", "missing": "0", "min": "0", "max": "275", "mean": "49", "stdev": "64" }, { "name": "SM07_EA.bo.", "index": "45", "type": "numeric", "distinct": "373", "missing": "0", "min": "6", "max": "12", "mean": "11", "stdev": "1" }, { "name": "ATS7i", "index": "46", "type": "numeric", "distinct": "397", "missing": "0", "min": "3", "max": "6", "mean": "5", "stdev": "1" }, { "name": "X4A", "index": "47", "type": "numeric", "distinct": "60", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "ATS8i", "index": "48", "type": "numeric", "distinct": "401", "missing": "0", "min": "2", "max": "6", "mean": "5", "stdev": "1" }, { "name": "MATS3p", "index": "49", "type": "numeric", "distinct": "274", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "ATS8e", "index": "50", "type": "numeric", "distinct": "401", "missing": "0", "min": "2", "max": "6", "mean": "5", "stdev": "1" }, { "name": "SM11_EA.ri.", "index": "51", "type": "numeric", "distinct": "386", "missing": "0", "min": "9", "max": "16", "mean": "13", "stdev": "1" }, { "name": "ATS6e", "index": "52", "type": "numeric", "distinct": "394", "missing": "0", "min": "3", "max": "6", "mean": "5", "stdev": "0" }, { "name": "ATSC6i", "index": "53", "type": "numeric", "distinct": "409", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "CATS2D_09_DA", "index": "54", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "8", "mean": "1", "stdev": "1" }, { "name": "ATS6v", "index": "55", "type": "numeric", "distinct": "390", "missing": "0", "min": "2", "max": "5", "mean": "4", "stdev": "0" }, { "name": "ATSC6p", "index": "56", "type": "numeric", "distinct": "439", "missing": "0", "min": "2", "max": "32", "mean": "11", "stdev": "5" }, { "name": "ATSC7p", "index": "57", "type": "numeric", "distinct": "444", "missing": "0", "min": "1", "max": "31", "mean": "10", "stdev": "5" }, { "name": "GGI7", "index": "58", "type": "numeric", "distinct": "306", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "nArCO", "index": "59", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "SpMax1_Bh.p.", "index": "60", "type": "numeric", "distinct": "224", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "ATSC8m", "index": "61", "type": "numeric", "distinct": "444", "missing": "0", "min": "2", "max": "75", "mean": "27", "stdev": "13" }, { "name": "MATS3i", "index": "62", "type": "numeric", "distinct": "270", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "PW5", "index": "63", "type": "numeric", "distinct": "70", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "ATSC8v", "index": "64", "type": "numeric", "distinct": "446", "missing": "0", "min": "1", "max": "40", "mean": "12", "stdev": "7" }, { "name": "SM11_EA.ed.", "index": "65", "type": "numeric", "distinct": "380", "missing": "0", "min": "18", "max": "32", "mean": "27", "stdev": "2" }, { "name": "CATS2D_08_DN", "index": "66", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "SM10_EA.ri.", "index": "67", "type": "numeric", "distinct": "385", "missing": "0", "min": "9", "max": "15", "mean": "12", "stdev": "1" }, { "name": "ATS5v", "index": "68", "type": "numeric", "distinct": "386", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "CATS2D_09_DD", "index": "69", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "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 }