{ "data_id": "29359", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL5973", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL5973", "version": 9, "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: CHEMBL5973 (TID: 101402), and it has 97 rows and 65 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 02:18:24", "update_comment": null, "last_update": "2016-07-15 02:18:24", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3390445\/data_52881.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL5973", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL5973 (TID: 101402), and it has 97 rows and 65 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": 97, "NumberOfFeatures": 67, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 66, "NumberOfSymbolicFeatures": 1, "ClassEntropy": null, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "Dimensionality": 0.6907216494845361, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": 3.8777922680935912, "EquivalentNumberOfAtts": null, "MeanSkewnessOfNumericAtts": -1.750138065186603, "Quartile2MeansOfNumericAtts": 11.59791237113402, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 4.54712462918853, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": -1.8950417612187718, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.3092990993164417, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 2.0041392294132385, "MaxKurtosisOfNumericAtts": 11.179659112060301, "MinMeansOfNumericAtts": -2.2017731958762883, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 124.06118556701031, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 8.493236404017845, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.50746268656717, "Quartile3MeansOfNumericAtts": 19.326894329896906, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -3.2100892677590136, "PercentageOfSymbolicFeatures": 1.4925373134328357, "Quartile3MutualInformation": null, "MaxSkewnessOfNumericAtts": 2.6251001335818755, "MinStdDevOfNumericAtts": 0.14217060485515184, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": -1.4613815058764401, "MaxStdDevOfNumericAtts": 60.99525751754698, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": 2.6007482516224543, "Quartile3StdDevOfNumericAtts": 3.1260576201574573, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 5.843353092783506, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": 4.696717584406403, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 15.587568728522337, "Quartile1SkewnessOfNumericAtts": -2.7251850290058273, "AutoCorrelation": -0.06546874999999996, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 1.1283183379035244 }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "66", "type": "numeric", "distinct": "84", "missing": "0", "target": "1", "min": "4", "max": "8", "mean": "6", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "97", "missing": "0", "identifier": "1", "distr": [] }, { "name": "SM03_EA.bo.", "index": "1", "type": "numeric", "distinct": "44", "missing": "0", "min": "0", "max": "5", "mean": "4", "stdev": "1" }, { "name": "SpMax2_Bh.m.", "index": "2", "type": "numeric", "distinct": "92", "missing": "0", "min": "2", "max": "5", "mean": "4", "stdev": "1" }, { "name": "SM05_EA.bo.", "index": "3", "type": "numeric", "distinct": "69", "missing": "0", "min": "0", "max": "9", "mean": "7", "stdev": "2" }, { "name": "SM15_EA", "index": "4", "type": "numeric", "distinct": "75", "missing": "0", "min": "0", "max": "20", "mean": "16", "stdev": "4" }, { "name": "SM09_EA.ed.", "index": "5", "type": "numeric", "distinct": "77", "missing": "0", "min": "0", "max": "24", "mean": "20", "stdev": "5" }, { "name": "SM10_EA.ed.", "index": "6", "type": "numeric", "distinct": "81", "missing": "0", "min": "13", "max": "27", "mean": "23", "stdev": "3" }, { "name": "SM11_EA", "index": "7", "type": "numeric", "distinct": "76", "missing": "0", "min": "0", "max": "15", "mean": "12", "stdev": "3" }, { "name": "SM11_EA.ed.", "index": "8", "type": "numeric", "distinct": "77", "missing": "0", "min": "0", "max": "30", "mean": "25", "stdev": "7" }, { "name": "SM12_EA", "index": "9", "type": "numeric", "distinct": "79", "missing": "0", "min": "8", "max": "16", "mean": "14", "stdev": "2" }, { "name": "SM12_EA.ed.", "index": "10", "type": "numeric", "distinct": "80", "missing": "0", "min": "15", "max": "33", "mean": "28", "stdev": "4" }, { "name": "SM13_AEA.ed.", "index": "11", "type": "numeric", "distinct": "80", "missing": "0", "min": "17", "max": "27", "mean": "25", "stdev": "2" }, { "name": "SM13_EA", "index": "12", "type": "numeric", "distinct": "74", "missing": "0", "min": "0", "max": "17", "mean": "14", "stdev": "4" }, { "name": "SM13_EA.ed.", "index": "13", "type": "numeric", "distinct": "76", "missing": "0", "min": "0", "max": "35", "mean": "29", "stdev": "8" }, { "name": "SM14_AEA.ed.", "index": "14", "type": "numeric", "distinct": "80", "missing": "0", "min": "18", "max": "30", "mean": "26", "stdev": "2" }, { "name": "SM14_EA", "index": "15", "type": "numeric", "distinct": "82", "missing": "0", "min": "9", "max": "19", "mean": "16", "stdev": "2" }, { "name": "SM14_EA.ed.", "index": "16", "type": "numeric", "distinct": "81", "missing": "0", "min": "18", "max": "38", "mean": "32", "stdev": "4" }, { "name": "SM15_AEA.ed.", "index": "17", "type": "numeric", "distinct": "80", "missing": "0", "min": "20", "max": "32", "mean": "28", "stdev": "2" }, { "name": "SM15_EA.ed.", "index": "18", "type": "numeric", "distinct": "77", "missing": "0", "min": "0", "max": "41", "mean": "33", "stdev": "9" }, { "name": "SM06_EA.bo.", "index": "19", "type": "numeric", "distinct": "80", "missing": "0", "min": "4", "max": "10", "mean": "9", "stdev": "1" }, { "name": "SM05_EA", "index": "20", "type": "numeric", "distinct": "54", "missing": "0", "min": "0", "max": "7", "mean": "6", "stdev": "2" }, { "name": "SM08_AEA.bo.", "index": "21", "type": "numeric", "distinct": "78", "missing": "0", "min": "8", "max": "14", "mean": "12", "stdev": "1" }, { "name": "SM06_AEA.bo.", "index": "22", "type": "numeric", "distinct": "80", "missing": "0", "min": "6", "max": "11", "mean": "10", "stdev": "1" }, { "name": "SM07_AEA.bo.", "index": "23", "type": "numeric", "distinct": "81", "missing": "0", "min": "7", "max": "12", "mean": "11", "stdev": "1" }, { "name": "SM07_EA", "index": "24", "type": "numeric", "distinct": "69", "missing": "0", "min": "0", "max": "10", "mean": "8", "stdev": "2" }, { "name": "ZM1Mad", "index": "25", "type": "numeric", "distinct": "90", "missing": "0", "min": "23", "max": "257", "mean": "124", "stdev": "61" }, { "name": "X2v", "index": "26", "type": "numeric", "distinct": "96", "missing": "0", "min": "1", "max": "10", "mean": "5", "stdev": "2" }, { "name": "SM07_EA.ed.", "index": "27", "type": "numeric", "distinct": "75", "missing": "0", "min": "0", "max": "19", "mean": "16", "stdev": "4" }, { "name": "SM08_EA.ed.", "index": "28", "type": "numeric", "distinct": "81", "missing": "0", "min": "11", "max": "22", "mean": "19", "stdev": "2" }, { "name": "SM10_EA", "index": "29", "type": "numeric", "distinct": "81", "missing": "0", "min": "7", "max": "14", "mean": "12", "stdev": "1" }, { "name": "SpDiam_EA.ed.", "index": "30", "type": "numeric", "distinct": "81", "missing": "0", "min": "7", "max": "24", "mean": "17", "stdev": "4" }, { "name": "MATS2v", "index": "31", "type": "numeric", "distinct": "81", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "nHet", "index": "32", "type": "numeric", "distinct": "13", "missing": "0", "min": "1", "max": "14", "mean": "6", "stdev": "3" }, { "name": "SM08_EA.bo.", "index": "33", "type": "numeric", "distinct": "78", "missing": "0", "min": "5", "max": "13", "mean": "12", "stdev": "2" }, { "name": "SM11_AEA.ed.", "index": "34", "type": "numeric", "distinct": "80", "missing": "0", "min": "15", "max": "23", "mean": "21", "stdev": "2" }, { "name": "SM12_AEA.ed.", "index": "35", "type": "numeric", "distinct": "78", "missing": "0", "min": "16", "max": "25", "mean": "23", "stdev": "2" }, { "name": "SM07_EA.bo.", "index": "36", "type": "numeric", "distinct": "70", "missing": "0", "min": "0", "max": "12", "mean": "10", "stdev": "3" }, { "name": "X3v", "index": "37", "type": "numeric", "distinct": "92", "missing": "0", "min": "0", "max": "8", "mean": "3", "stdev": "2" }, { "name": "SM09_EA.bo.", "index": "38", "type": "numeric", "distinct": "74", "missing": "0", "min": "0", "max": "15", "mean": "12", "stdev": "3" }, { "name": "SM10_EA.bo.", "index": "39", "type": "numeric", "distinct": "82", "missing": "0", "min": "7", "max": "16", "mean": "14", "stdev": "2" }, { "name": "Eig02_EA.bo.", "index": "40", "type": "numeric", "distinct": "81", "missing": "0", "min": "-1", "max": "5", "mean": "3", "stdev": "1" }, { "name": "SM12_AEA.ri.", "index": "41", "type": "numeric", "distinct": "81", "missing": "0", "min": "-1", "max": "5", "mean": "3", "stdev": "1" }, { "name": "SM08_EA", "index": "42", "type": "numeric", "distinct": "81", "missing": "0", "min": "5", "max": "11", "mean": "9", "stdev": "1" }, { "name": "SpDiam_AEA.ri.", "index": "43", "type": "numeric", "distinct": "81", "missing": "0", "min": "4", "max": "6", "mean": "5", "stdev": "0" }, { "name": "SM09_EA", "index": "44", "type": "numeric", "distinct": "73", "missing": "0", "min": "0", "max": "12", "mean": "10", "stdev": "3" }, { "name": "Eig02_AEA.ri.", "index": "45", "type": "numeric", "distinct": "88", "missing": "0", "min": "0", "max": "4", "mean": "3", "stdev": "1" }, { "name": "Eig01_EA", "index": "46", "type": "numeric", "distinct": "67", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SM09_AEA.bo.", "index": "47", "type": "numeric", "distinct": "67", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SM10_AEA.ed.", "index": "48", "type": "numeric", "distinct": "79", "missing": "0", "min": "13", "max": "21", "mean": "19", "stdev": "2" }, { "name": "SpMax_EA", "index": "49", "type": "numeric", "distinct": "67", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "ATSC6s", "index": "50", "type": "numeric", "distinct": "95", "missing": "0", "min": "0", "max": "334", "mean": "52", "stdev": "53" }, { "name": "ATSC2s", "index": "51", "type": "numeric", "distinct": "96", "missing": "0", "min": "3", "max": "244", "mean": "55", "stdev": "41" }, { "name": "SddssS", "index": "52", "type": "numeric", "distinct": "45", "missing": "0", "min": "-9", "max": "0", "mean": "-2", "stdev": "3" }, { "name": "ATS1m", "index": "53", "type": "numeric", "distinct": "85", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SM06_EA.ed.", "index": "54", "type": "numeric", "distinct": "80", "missing": "0", "min": "8", "max": "17", "mean": "14", "stdev": "2" }, { "name": "SM05_EA.ed.", "index": "55", "type": "numeric", "distinct": "73", "missing": "0", "min": "0", "max": "14", "mean": "11", "stdev": "3" }, { "name": "SM07_AEA.ed.", "index": "56", "type": "numeric", "distinct": "81", "missing": "0", "min": "9", "max": "15", "mean": "14", "stdev": "1" }, { "name": "Eig01_AEA.ed.", "index": "57", "type": "numeric", "distinct": "70", "missing": "0", "min": "4", "max": "8", "mean": "7", "stdev": "1" }, { "name": "Eig01_EA.ed.", "index": "58", "type": "numeric", "distinct": "75", "missing": "0", "min": "3", "max": "15", "mean": "10", "stdev": "2" }, { "name": "SM10_AEA.dm.", "index": "59", "type": "numeric", "distinct": "75", "missing": "0", "min": "3", "max": "15", "mean": "10", "stdev": "2" }, { "name": "SpMax_AEA.ed.", "index": "60", "type": "numeric", "distinct": "70", "missing": "0", "min": "4", "max": "8", "mean": "7", "stdev": "1" }, { "name": "SpMax_EA.ed.", "index": "61", "type": "numeric", "distinct": "75", "missing": "0", "min": "3", "max": "15", "mean": "10", "stdev": "2" }, { "name": "SM04_EA.ed.", "index": "62", "type": "numeric", "distinct": "80", "missing": "0", "min": "6", "max": "12", "mean": "10", "stdev": "1" }, { "name": "SM08_AEA.ed.", "index": "63", "type": "numeric", "distinct": "79", "missing": "0", "min": "11", "max": "17", "mean": "15", "stdev": "1" }, { "name": "SM09_AEA.ed.", "index": "64", "type": "numeric", "distinct": "78", "missing": "0", "min": "12", "max": "19", "mean": "17", "stdev": "2" }, { "name": "SM15_EA.bo.", "index": "65", "type": "numeric", "distinct": "74", "missing": "0", "min": "0", "max": "24", "mean": "21", "stdev": "6" } ], "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 }