{ "data_id": "26482", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4033", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4033", "version": 7, "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: CHEMBL4033 (TID: 11346), and it has 133 rows and 60 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": "2016-07-14 19:20:55", "update_comment": null, "last_update": "2016-07-14 19:20:55", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3303901\/data_52031.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4033", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL4033 (TID: 11346), and it has 133 rows and 60 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": 133, "NumberOfFeatures": 62, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 61, "NumberOfSymbolicFeatures": 1, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 3.8326654135338347, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": 11.834570463050841, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 14.292196474793542, "Quartile1SkewnessOfNumericAtts": -0.4478336661981882, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.10418465968327531, "AutoCorrelation": 0.40450000000000025, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "ClassEntropy": null, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": 0.3554252217259086, "Dimensionality": 0.46616541353383456, "MeanSkewnessOfNumericAtts": -1.1773614260604206, "Quartile2MeansOfNumericAtts": 5.894451127819549, "EquivalentNumberOfAtts": null, "MeanStdDevOfNumericAtts": 1.3002715902311128, "Quartile2MutualInformation": null, "MajorityClassPercentage": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": -0.08491187902761, "MajorityClassSize": null, "MinKurtosisOfNumericAtts": -1.3546495744131883, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.1955916665473872, "MaxAttributeEntropy": null, "MaxKurtosisOfNumericAtts": 114.51472037257227, "MinMeansOfNumericAtts": 0.5555864661654135, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 162.92466165413535, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 2.1345918208062082, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.38709677419355, "Quartile3MeansOfNumericAtts": 12.089669172932332, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -10.502153014852063, "PercentageOfSymbolicFeatures": 1.6129032258064515, "Quartile3MutualInformation": null, "MaxSkewnessOfNumericAtts": 3.5606763198339095, "MinStdDevOfNumericAtts": 0.0181247229533905, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 0.182049593344037, "MaxStdDevOfNumericAtts": 23.107739015476657, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": -0.10366579673872378, "Quartile3StdDevOfNumericAtts": 0.6156948703580369 }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "61", "type": "numeric", "distinct": "68", "missing": "0", "target": "1", "min": "5", "max": "8", "mean": "7", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "133", "missing": "0", "identifier": "1", "distr": [] }, { "name": "SpMax1_Bh.v.", "index": "1", "type": "numeric", "distinct": "45", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "piPC06", "index": "2", "type": "numeric", "distinct": "77", "missing": "0", "min": "6", "max": "7", "mean": "6", "stdev": "0" }, { "name": "piPC07", "index": "3", "type": "numeric", "distinct": "74", "missing": "0", "min": "6", "max": "7", "mean": "7", "stdev": "0" }, { "name": "Eta_betaP", "index": "4", "type": "numeric", "distinct": "12", "missing": "0", "min": "14", "max": "26", "mean": "19", "stdev": "3" }, { "name": "Eta_F", "index": "5", "type": "numeric", "distinct": "133", "missing": "0", "min": "22", "max": "45", "mean": "31", "stdev": "4" }, { "name": "piPC09", "index": "6", "type": "numeric", "distinct": "78", "missing": "0", "min": "6", "max": "8", "mean": "8", "stdev": "0" }, { "name": "piPC10", "index": "7", "type": "numeric", "distinct": "80", "missing": "0", "min": "6", "max": "9", "mean": "8", "stdev": "0" }, { "name": "Ui", "index": "8", "type": "numeric", "distinct": "10", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SpMax1_Bh.p.", "index": "9", "type": "numeric", "distinct": "19", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "piPC08", "index": "10", "type": "numeric", "distinct": "78", "missing": "0", "min": "6", "max": "8", "mean": "7", "stdev": "0" }, { "name": "SpMax2_Bh.m.", "index": "11", "type": "numeric", "distinct": "77", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "AMR", "index": "12", "type": "numeric", "distinct": "125", "missing": "0", "min": "68", "max": "124", "mean": "97", "stdev": "9" }, { "name": "ATS4v", "index": "13", "type": "numeric", "distinct": "118", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "SpMax2_Bh.p.", "index": "14", "type": "numeric", "distinct": "82", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "Eta_beta", "index": "15", "type": "numeric", "distinct": "39", "missing": "0", "min": "28", "max": "47", "mean": "36", "stdev": "4" }, { "name": "Eta_FL", "index": "16", "type": "numeric", "distinct": "114", "missing": "0", "min": "5", "max": "10", "mean": "7", "stdev": "1" }, { "name": "PCD", "index": "17", "type": "numeric", "distinct": "61", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "1" }, { "name": "piPC03", "index": "18", "type": "numeric", "distinct": "53", "missing": "0", "min": "5", "max": "5", "mean": "5", "stdev": "0" }, { "name": "piPC04", "index": "19", "type": "numeric", "distinct": "66", "missing": "0", "min": "5", "max": "6", "mean": "5", "stdev": "0" }, { "name": "piPC05", "index": "20", "type": "numeric", "distinct": "73", "missing": "0", "min": "6", "max": "6", "mean": "6", "stdev": "0" }, { "name": "Eig07_AEA.bo.", "index": "21", "type": "numeric", "distinct": "69", "missing": "0", "min": "3", "max": "3", "mean": "3", "stdev": "0" }, { "name": "Eig07_EA.bo.", "index": "22", "type": "numeric", "distinct": "78", "missing": "0", "min": "2", "max": "3", "mean": "2", "stdev": "0" }, { "name": "P_VSA_m_2", "index": "23", "type": "numeric", "distinct": "115", "missing": "0", "min": "109", "max": "219", "mean": "163", "stdev": "23" }, { "name": "SM03_AEA.bo.", "index": "24", "type": "numeric", "distinct": "59", "missing": "0", "min": "6", "max": "7", "mean": "6", "stdev": "0" }, { "name": "Eig11_AEA.dm.", "index": "25", "type": "numeric", "distinct": "56", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "GGI8", "index": "26", "type": "numeric", "distinct": "67", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Chi0_EA.ri.", "index": "27", "type": "numeric", "distinct": "129", "missing": "0", "min": "14", "max": "23", "mean": "18", "stdev": "2" }, { "name": "Eig01_EA.ri.", "index": "28", "type": "numeric", "distinct": "75", "missing": "0", "min": "3", "max": "3", "mean": "3", "stdev": "0" }, { "name": "Eta_alpha", "index": "29", "type": "numeric", "distinct": "68", "missing": "0", "min": "9", "max": "16", "mean": "13", "stdev": "1" }, { "name": "SpDiam_EA.ri.", "index": "30", "type": "numeric", "distinct": "76", "missing": "0", "min": "5", "max": "5", "mean": "5", "stdev": "0" }, { "name": "SpMax_EA.ri.", "index": "31", "type": "numeric", "distinct": "75", "missing": "0", "min": "3", "max": "3", "mean": "3", "stdev": "0" }, { "name": "S0K", "index": "32", "type": "numeric", "distinct": "44", "missing": "0", "min": "78", "max": "164", "mean": "124", "stdev": "15" }, { "name": "NaasC", "index": "33", "type": "numeric", "distinct": "7", "missing": "0", "min": "2", "max": "8", "mean": "6", "stdev": "1" }, { "name": "SM06_EA.bo.", "index": "34", "type": "numeric", "distinct": "67", "missing": "0", "min": "9", "max": "10", "mean": "10", "stdev": "0" }, { "name": "Eig04_AEA.ed.", "index": "35", "type": "numeric", "distinct": "64", "missing": "0", "min": "5", "max": "7", "mean": "6", "stdev": "0" }, { "name": "Eig01_EA.bo.", "index": "36", "type": "numeric", "distinct": "5", "missing": "0", "min": "4", "max": "5", "mean": "5", "stdev": "0" }, { "name": "Eig02_EA.bo.", "index": "37", "type": "numeric", "distinct": "42", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "SM11_AEA.ri.", "index": "38", "type": "numeric", "distinct": "5", "missing": "0", "min": "4", "max": "5", "mean": "5", "stdev": "0" }, { "name": "SM12_AEA.ri.", "index": "39", "type": "numeric", "distinct": "42", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "SpAD_AEA.dm.", "index": "40", "type": "numeric", "distinct": "123", "missing": "0", "min": "35", "max": "59", "mean": "48", "stdev": "5" }, { "name": "SpDiam_EA.bo.", "index": "41", "type": "numeric", "distinct": "5", "missing": "0", "min": "7", "max": "8", "mean": "8", "stdev": "0" }, { "name": "SpMax7_Bh.m.", "index": "42", "type": "numeric", "distinct": "82", "missing": "0", "min": "3", "max": "3", "mean": "3", "stdev": "0" }, { "name": "SpMax_EA.bo.", "index": "43", "type": "numeric", "distinct": "5", "missing": "0", "min": "4", "max": "5", "mean": "5", "stdev": "0" }, { "name": "X0sol", "index": "44", "type": "numeric", "distinct": "53", "missing": "0", "min": "14", "max": "22", "mean": "18", "stdev": "1" }, { "name": "Eta_betaP_A", "index": "45", "type": "numeric", "distinct": "30", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "piID", "index": "46", "type": "numeric", "distinct": "65", "missing": "0", "min": "9", "max": "12", "mean": "10", "stdev": "1" }, { "name": "SM05_EA.bo.", "index": "47", "type": "numeric", "distinct": "53", "missing": "0", "min": "7", "max": "9", "mean": "8", "stdev": "0" }, { "name": "SpMAD_AEA.dm.", "index": "48", "type": "numeric", "distinct": "92", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "ATS5v", "index": "49", "type": "numeric", "distinct": "115", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "SM11_EA.ri.", "index": "50", "type": "numeric", "distinct": "119", "missing": "0", "min": "13", "max": "14", "mean": "13", "stdev": "0" }, { "name": "SM12_EA.ri.", "index": "51", "type": "numeric", "distinct": "123", "missing": "0", "min": "14", "max": "15", "mean": "14", "stdev": "0" }, { "name": "SM13_EA.ri.", "index": "52", "type": "numeric", "distinct": "118", "missing": "0", "min": "15", "max": "16", "mean": "15", "stdev": "0" }, { "name": "SM14_EA.ri.", "index": "53", "type": "numeric", "distinct": "117", "missing": "0", "min": "16", "max": "17", "mean": "16", "stdev": "0" }, { "name": "SM15_EA.ri.", "index": "54", "type": "numeric", "distinct": "125", "missing": "0", "min": "17", "max": "18", "mean": "17", "stdev": "0" }, { "name": "SpMax8_Bh.m.", "index": "55", "type": "numeric", "distinct": "61", "missing": "0", "min": "2", "max": "3", "mean": "3", "stdev": "0" }, { "name": "X1v", "index": "56", "type": "numeric", "distinct": "127", "missing": "0", "min": "7", "max": "12", "mean": "10", "stdev": "1" }, { "name": "Eig12_AEA.dm.", "index": "57", "type": "numeric", "distinct": "58", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Eig10_AEA.bo.", "index": "58", "type": "numeric", "distinct": "44", "missing": "0", "min": "1", "max": "3", "mean": "2", "stdev": "0" }, { "name": "SM02_AEA.bo.", "index": "59", "type": "numeric", "distinct": "52", "missing": "0", "min": "5", "max": "5", "mean": "5", "stdev": "0" }, { "name": "SM07_EA.bo.", "index": "60", "type": "numeric", "distinct": "61", "missing": "0", "min": "10", "max": "12", "mean": "11", "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 }