{ "data_id": "35227", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL245", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL245", "version": 12, "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: CHEMBL245 (TID: 219), and it has 1584 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 17:28:38", "update_comment": null, "last_update": "2016-07-15 17:28:38", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3551834\/data_53499.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL245", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL245 (TID: 219), and it has 1584 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": 1584, "NumberOfFeatures": 71, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 70, "NumberOfSymbolicFeatures": 1, "Quartile2KurtosisOfNumericAtts": 2.1091068626725713, "Dimensionality": 0.04482323232323232, "MeanNominalAttDistinctValues": null, "Quartile2MeansOfNumericAtts": 4.928850378787878, "EquivalentNumberOfAtts": null, "MeanSkewnessOfNumericAtts": 0.13827594530105417, "Quartile2MutualInformation": null, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 14.596514107986156, "Quartile2SkewnessOfNumericAtts": 0.4204971122149941, "MajorityClassSize": null, "MinAttributeEntropy": null, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.787169554051528, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.1916953952644935, "MinMeansOfNumericAtts": 0.13510101010100986, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxKurtosisOfNumericAtts": 13.700794755140832, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 2.949184408251757, "MaxMeansOfNumericAtts": 518.1601357323232, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.59154929577466, "Quartile3MeansOfNumericAtts": 13.569633996212122, "MaxMutualInformation": null, "MinSkewnessOfNumericAtts": -2.8537712939345137, "PercentageOfSymbolicFeatures": 1.4084507042253522, "Quartile3MutualInformation": null, "MaxNominalAttDistinctValues": null, "MinStdDevOfNumericAtts": 0.14102267332751803, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 0.8018758298871018, "MaxSkewnessOfNumericAtts": 3.112376446532678, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": 0.7838453495219206, "Quartile3StdDevOfNumericAtts": 6.275384420962293, "MaxStdDevOfNumericAtts": 148.88256535380793, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 2.5569236111111113, "StdvNominalAttDistinctValues": null, "MeanAttributeEntropy": null, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanKurtosisOfNumericAtts": 2.2199217372207416, "Quartile1SkewnessOfNumericAtts": -0.8195234552825373, "MeanMeansOfNumericAtts": 45.51625203823954, "Quartile1StdDevOfNumericAtts": 0.39642836488148936, "AutoCorrelation": -0.19376247631080035, "MeanMutualInformation": null, "Quartile2AttributeEntropy": null, "ClassEntropy": null, "MeanNoiseToSignalRatio": null }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "70", "type": "numeric", "distinct": "784", "missing": "0", "target": "1", "min": "3", "max": "11", "mean": "7", "stdev": "2" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "1584", "missing": "0", "identifier": "1", "distr": [] }, { "name": "Eig01_AEA.dm.", "index": "1", "type": "numeric", "distinct": "494", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SpMax_AEA.dm.", "index": "2", "type": "numeric", "distinct": "494", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "Eig09_EA.bo.", "index": "3", "type": "numeric", "distinct": "661", "missing": "0", "min": "-2", "max": "3", "mean": "1", "stdev": "1" }, { "name": "Eig01_AEA.bo.", "index": "4", "type": "numeric", "distinct": "459", "missing": "0", "min": "4", "max": "5", "mean": "5", "stdev": "0" }, { "name": "SpMax_AEA.bo.", "index": "5", "type": "numeric", "distinct": "459", "missing": "0", "min": "4", "max": "5", "mean": "5", "stdev": "0" }, { "name": "Eig01_AEA.ed.", "index": "6", "type": "numeric", "distinct": "412", "missing": "0", "min": "5", "max": "9", "mean": "7", "stdev": "1" }, { "name": "SpMax_AEA.ed.", "index": "7", "type": "numeric", "distinct": "412", "missing": "0", "min": "5", "max": "9", "mean": "7", "stdev": "1" }, { "name": "CATS2D_08_PL", "index": "8", "type": "numeric", "distinct": "8", "missing": "0", "min": "0", "max": "8", "mean": "1", "stdev": "1" }, { "name": "ATSC8p", "index": "9", "type": "numeric", "distinct": "1381", "missing": "0", "min": "0", "max": "50", "mean": "12", "stdev": "6" }, { "name": "ATSC2p", "index": "10", "type": "numeric", "distinct": "1213", "missing": "0", "min": "2", "max": "24", "mean": "10", "stdev": "3" }, { "name": "SpMin6_Bh.i.", "index": "11", "type": "numeric", "distinct": "565", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "SpMax6_Bh.v.", "index": "12", "type": "numeric", "distinct": "601", "missing": "0", "min": "1", "max": "4", "mean": "3", "stdev": "0" }, { "name": "ATS1p", "index": "13", "type": "numeric", "distinct": "663", "missing": "0", "min": "2", "max": "5", "mean": "4", "stdev": "0" }, { "name": "ATS7e", "index": "14", "type": "numeric", "distinct": "904", "missing": "0", "min": "1", "max": "7", "mean": "5", "stdev": "1" }, { "name": "ATSC3v", "index": "15", "type": "numeric", "distinct": "1342", "missing": "0", "min": "2", "max": "48", "mean": "18", "stdev": "6" }, { "name": "ATSC8v", "index": "16", "type": "numeric", "distinct": "1394", "missing": "0", "min": "0", "max": "71", "mean": "17", "stdev": "8" }, { "name": "ATSC1v", "index": "17", "type": "numeric", "distinct": "1084", "missing": "0", "min": "1", "max": "20", "mean": "8", "stdev": "2" }, { "name": "ATS8s", "index": "18", "type": "numeric", "distinct": "959", "missing": "0", "min": "0", "max": "8", "mean": "6", "stdev": "1" }, { "name": "SpMax6_Bh.p.", "index": "19", "type": "numeric", "distinct": "567", "missing": "0", "min": "1", "max": "4", "mean": "3", "stdev": "0" }, { "name": "ATS6m", "index": "20", "type": "numeric", "distinct": "901", "missing": "0", "min": "0", "max": "6", "mean": "4", "stdev": "1" }, { "name": "SpDiam_AEA.dm.", "index": "21", "type": "numeric", "distinct": "524", "missing": "0", "min": "5", "max": "7", "mean": "6", "stdev": "0" }, { "name": "Eig01_EA.dm.", "index": "22", "type": "numeric", "distinct": "138", "missing": "0", "min": "0", "max": "6", "mean": "2", "stdev": "1" }, { "name": "SpMax_EA.dm.", "index": "23", "type": "numeric", "distinct": "138", "missing": "0", "min": "0", "max": "6", "mean": "2", "stdev": "1" }, { "name": "LLS_01", "index": "24", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "Eig03_AEA.ri.", "index": "25", "type": "numeric", "distinct": "631", "missing": "0", "min": "2", "max": "4", "mean": "4", "stdev": "0" }, { "name": "Sv", "index": "26", "type": "numeric", "distinct": "1048", "missing": "0", "min": "11", "max": "98", "mean": "35", "stdev": "10" }, { "name": "SM08_EA.dm.", "index": "27", "type": "numeric", "distinct": "410", "missing": "0", "min": "0", "max": "14", "mean": "5", "stdev": "3" }, { "name": "ATS1v", "index": "28", "type": "numeric", "distinct": "681", "missing": "0", "min": "2", "max": "5", "mean": "4", "stdev": "0" }, { "name": "ATSC6i", "index": "29", "type": "numeric", "distinct": "1065", "missing": "0", "min": "0", "max": "6", "mean": "2", "stdev": "1" }, { "name": "nBT", "index": "30", "type": "numeric", "distinct": "104", "missing": "0", "min": "19", "max": "168", "mean": "61", "stdev": "17" }, { "name": "Eig03_EA.ri.", "index": "31", "type": "numeric", "distinct": "623", "missing": "0", "min": "1", "max": "3", "mean": "2", "stdev": "0" }, { "name": "ATS7s", "index": "32", "type": "numeric", "distinct": "940", "missing": "0", "min": "1", "max": "8", "mean": "6", "stdev": "1" }, { "name": "ISIZ", "index": "33", "type": "numeric", "distinct": "101", "missing": "0", "min": "75", "max": "1172", "mean": "342", "stdev": "123" }, { "name": "nAT", "index": "34", "type": "numeric", "distinct": "101", "missing": "0", "min": "18", "max": "160", "mean": "58", "stdev": "17" }, { "name": "VvdwZAZ", "index": "35", "type": "numeric", "distinct": "1102", "missing": "0", "min": "111", "max": "1072", "mean": "379", "stdev": "111" }, { "name": "Se", "index": "36", "type": "numeric", "distinct": "1061", "missing": "0", "min": "19", "max": "160", "mean": "58", "stdev": "17" }, { "name": "CATS2D_06_AP", "index": "37", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "0" }, { "name": "VvdwMG", "index": "38", "type": "numeric", "distinct": "1042", "missing": "0", "min": "69", "max": "600", "mean": "216", "stdev": "61" }, { "name": "Vx", "index": "39", "type": "numeric", "distinct": "1042", "missing": "0", "min": "161", "max": "1456", "mean": "518", "stdev": "149" }, { "name": "ATSC6v", "index": "40", "type": "numeric", "distinct": "1393", "missing": "0", "min": "1", "max": "64", "mean": "19", "stdev": "8" }, { "name": "CATS2D_06_LL", "index": "41", "type": "numeric", "distinct": "40", "missing": "0", "min": "0", "max": "45", "mean": "11", "stdev": "7" }, { "name": "Eig02_EA.ed.", "index": "42", "type": "numeric", "distinct": "663", "missing": "0", "min": "4", "max": "18", "mean": "10", "stdev": "2" }, { "name": "SM11_AEA.dm.", "index": "43", "type": "numeric", "distinct": "663", "missing": "0", "min": "4", "max": "18", "mean": "10", "stdev": "2" }, { "name": "ATSC4i", "index": "44", "type": "numeric", "distinct": "1055", "missing": "0", "min": "0", "max": "5", "mean": "2", "stdev": "1" }, { "name": "SM05_EA.dm.", "index": "45", "type": "numeric", "distinct": "220", "missing": "0", "min": "0", "max": "9", "mean": "3", "stdev": "2" }, { "name": "TIC5", "index": "46", "type": "numeric", "distinct": "1048", "missing": "0", "min": "69", "max": "925", "mean": "292", "stdev": "106" }, { "name": "Eig03_AEA.ed.", "index": "47", "type": "numeric", "distinct": "565", "missing": "0", "min": "3", "max": "7", "mean": "6", "stdev": "1" }, { "name": "ATSC5i", "index": "48", "type": "numeric", "distinct": "1084", "missing": "0", "min": "0", "max": "6", "mean": "2", "stdev": "1" }, { "name": "TIC3", "index": "49", "type": "numeric", "distinct": "1189", "missing": "0", "min": "69", "max": "844", "mean": "281", "stdev": "100" }, { "name": "SM10_EA.dm.", "index": "50", "type": "numeric", "distinct": "367", "missing": "0", "min": "0", "max": "18", "mean": "6", "stdev": "4" }, { "name": "TIC4", "index": "51", "type": "numeric", "distinct": "1084", "missing": "0", "min": "69", "max": "886", "mean": "290", "stdev": "104" }, { "name": "SM09_EA.dm.", "index": "52", "type": "numeric", "distinct": "207", "missing": "0", "min": "0", "max": "16", "mean": "5", "stdev": "4" }, { "name": "Eig03_EA", "index": "53", "type": "numeric", "distinct": "559", "missing": "0", "min": "1", "max": "3", "mean": "3", "stdev": "0" }, { "name": "SM11_AEA.bo.", "index": "54", "type": "numeric", "distinct": "559", "missing": "0", "min": "1", "max": "3", "mean": "3", "stdev": "0" }, { "name": "AMR", "index": "55", "type": "numeric", "distinct": "1319", "missing": "0", "min": "36", "max": "322", "mean": "114", "stdev": "32" }, { "name": "SpDiam_AEA.bo.", "index": "56", "type": "numeric", "distinct": "484", "missing": "0", "min": "5", "max": "6", "mean": "6", "stdev": "0" }, { "name": "CATS2D_05_AP", "index": "57", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "0" }, { "name": "ATSC2i", "index": "58", "type": "numeric", "distinct": "853", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "0" }, { "name": "SpDiam_EA.dm.", "index": "59", "type": "numeric", "distinct": "172", "missing": "0", "min": "0", "max": "10", "mean": "3", "stdev": "1" }, { "name": "SpMaxA_EA.ed.", "index": "60", "type": "numeric", "distinct": "402", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "ATS6e", "index": "61", "type": "numeric", "distinct": "902", "missing": "0", "min": "2", "max": "6", "mean": "5", "stdev": "1" }, { "name": "CATS2D_09_PL", "index": "62", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "8", "mean": "0", "stdev": "1" }, { "name": "ATSC4v", "index": "63", "type": "numeric", "distinct": "1391", "missing": "0", "min": "2", "max": "53", "mean": "20", "stdev": "7" }, { "name": "SM07_EA.dm.", "index": "64", "type": "numeric", "distinct": "215", "missing": "0", "min": "0", "max": "12", "mean": "4", "stdev": "3" }, { "name": "SpDiam_EA.ri.", "index": "65", "type": "numeric", "distinct": "476", "missing": "0", "min": "4", "max": "6", "mean": "5", "stdev": "0" }, { "name": "ATS8p", "index": "66", "type": "numeric", "distinct": "935", "missing": "0", "min": "0", "max": "6", "mean": "4", "stdev": "1" }, { "name": "SpMin5_Bh.e.", "index": "67", "type": "numeric", "distinct": "544", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "ATS4p", "index": "68", "type": "numeric", "distinct": "843", "missing": "0", "min": "2", "max": "5", "mean": "4", "stdev": "0" }, { "name": "TIC2", "index": "69", "type": "numeric", "distinct": "1291", "missing": "0", "min": "69", "max": "724", "mean": "248", "stdev": "85" } ], "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 }