{ "data_id": "38165", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL5518", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL5518", "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: CHEMBL5518 (TID: 101220), and it has 709 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": "2016-07-16 03:11:32", "update_comment": null, "last_update": "2016-07-16 03:11:32", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3631406\/data_53480.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL5518", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL5518 (TID: 101220), and it has 709 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": 709, "NumberOfFeatures": 71, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 70, "NumberOfSymbolicFeatures": 1, "Quartile3AttributeEntropy": null, "MaxKurtosisOfNumericAtts": 14.86098265673953, "MinMeansOfNumericAtts": 0.05077574047954871, "PercentageOfInstancesWithMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 3.130789321183503, "MaxMeansOfNumericAtts": 172.00361636107192, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3MeansOfNumericAtts": 4.98406311706629, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.59154929577466, "Quartile3MutualInformation": null, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -2.160778297345029, "PercentageOfSymbolicFeatures": 1.4084507042253522, "Quartile3SkewnessOfNumericAtts": 0.41108312265149927, "MaxSkewnessOfNumericAtts": 4.101105886431769, "MinStdDevOfNumericAtts": 0.03294866758520585, "Quartile1AttributeEntropy": null, "Quartile3StdDevOfNumericAtts": 0.805996112061391, "MaxStdDevOfNumericAtts": 74.3925005989013, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": 0.38818992793268003, "StdvNominalAttDistinctValues": null, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 1.400771509167842, "MeanKurtosisOfNumericAtts": 2.152163404158483, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 7.138735381825509, "Quartile1SkewnessOfNumericAtts": -0.859193364443969, "AutoCorrelation": 0.1492627118644063, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.2614103670196302, "ClassEntropy": null, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "Dimensionality": 0.1001410437235543, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": 1.3915939477250157, "EquivalentNumberOfAtts": null, "MeanSkewnessOfNumericAtts": -0.22128384534949175, "Quartile2MeansOfNumericAtts": 3.357117771509168, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 2.648895906846816, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": -0.5011172094970744, "Quartile2StdDevOfNumericAtts": 0.42358020099561366, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.088606590280476, "PercentageOfBinaryFeatures": 0 }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "70", "type": "numeric", "distinct": "70", "missing": "0", "target": "1", "min": "5", "max": "9", "mean": "6", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "709", "missing": "0", "identifier": "1", "distr": [] }, { "name": "SaaNH", "index": "1", "type": "numeric", "distinct": "195", "missing": "0", "min": "0", "max": "6", "mean": "1", "stdev": "2" }, { "name": "nPyrroles", "index": "2", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "Cl.090", "index": "3", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "H.048", "index": "4", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "1" }, { "name": "C.033", "index": "5", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "1" }, { "name": "PCD", "index": "6", "type": "numeric", "distinct": "570", "missing": "0", "min": "1", "max": "7", "mean": "4", "stdev": "1" }, { "name": "IC2", "index": "7", "type": "numeric", "distinct": "504", "missing": "0", "min": "3", "max": "5", "mean": "5", "stdev": "0" }, { "name": "SaaaC", "index": "8", "type": "numeric", "distinct": "407", "missing": "0", "min": "0", "max": "9", "mean": "1", "stdev": "1" }, { "name": "SpMax1_Bh.e.", "index": "9", "type": "numeric", "distinct": "222", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "piPC10", "index": "10", "type": "numeric", "distinct": "554", "missing": "0", "min": "3", "max": "10", "mean": "8", "stdev": "1" }, { "name": "P_VSA_LogP_6", "index": "11", "type": "numeric", "distinct": "188", "missing": "0", "min": "0", "max": "88", "mean": "17", "stdev": "17" }, { "name": "Eig01_EA.bo.", "index": "12", "type": "numeric", "distinct": "335", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SM11_AEA.ri.", "index": "13", "type": "numeric", "distinct": "335", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SpDiam_EA.bo.", "index": "14", "type": "numeric", "distinct": "337", "missing": "0", "min": "6", "max": "8", "mean": "7", "stdev": "0" }, { "name": "SpMax_EA.bo.", "index": "15", "type": "numeric", "distinct": "335", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SpMax2_Bh.i.", "index": "16", "type": "numeric", "distinct": "253", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "Eig09_AEA.ed.", "index": "17", "type": "numeric", "distinct": "476", "missing": "0", "min": "1", "max": "6", "mean": "4", "stdev": "1" }, { "name": "piPC05", "index": "18", "type": "numeric", "distinct": "476", "missing": "0", "min": "5", "max": "7", "mean": "6", "stdev": "0" }, { "name": "piPC08", "index": "19", "type": "numeric", "distinct": "540", "missing": "0", "min": "5", "max": "9", "mean": "7", "stdev": "1" }, { "name": "NaaNH", "index": "20", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "Eig07_EA.bo.", "index": "21", "type": "numeric", "distinct": "468", "missing": "0", "min": "-1", "max": "3", "mean": "2", "stdev": "0" }, { "name": "piPC07", "index": "22", "type": "numeric", "distinct": "534", "missing": "0", "min": "5", "max": "9", "mean": "7", "stdev": "1" }, { "name": "SRW09", "index": "23", "type": "numeric", "distinct": "94", "missing": "0", "min": "0", "max": "9", "mean": "6", "stdev": "3" }, { "name": "nCrs", "index": "24", "type": "numeric", "distinct": "10", "missing": "0", "min": "0", "max": "12", "mean": "1", "stdev": "2" }, { "name": "ATS7m", "index": "25", "type": "numeric", "distinct": "574", "missing": "0", "min": "0", "max": "5", "mean": "4", "stdev": "1" }, { "name": "piPC04", "index": "26", "type": "numeric", "distinct": "479", "missing": "0", "min": "4", "max": "7", "mean": "6", "stdev": "0" }, { "name": "SpMin4_Bh.i.", "index": "27", "type": "numeric", "distinct": "414", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "SpMin4_Bh.p.", "index": "28", "type": "numeric", "distinct": "401", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "SpMax6_Bh.i.", "index": "29", "type": "numeric", "distinct": "399", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "Eig08_EA.ri.", "index": "30", "type": "numeric", "distinct": "477", "missing": "0", "min": "-1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "D.Dtr09", "index": "31", "type": "numeric", "distinct": "397", "missing": "0", "min": "0", "max": "439", "mean": "78", "stdev": "74" }, { "name": "SpMin4_Bh.e.", "index": "32", "type": "numeric", "distinct": "419", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "SpMin7_Bh.p.", "index": "33", "type": "numeric", "distinct": "402", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "Eig09_EA.ed.", "index": "34", "type": "numeric", "distinct": "534", "missing": "0", "min": "-4", "max": "7", "mean": "3", "stdev": "1" }, { "name": "SM04_AEA.ri.", "index": "35", "type": "numeric", "distinct": "534", "missing": "0", "min": "-4", "max": "7", "mean": "3", "stdev": "1" }, { "name": "Eig06_AEA.bo.", "index": "36", "type": "numeric", "distinct": "463", "missing": "0", "min": "1", "max": "4", "mean": "3", "stdev": "0" }, { "name": "nAB", "index": "37", "type": "numeric", "distinct": "20", "missing": "0", "min": "6", "max": "33", "mean": "19", "stdev": "5" }, { "name": "piPC06", "index": "38", "type": "numeric", "distinct": "514", "missing": "0", "min": "4", "max": "8", "mean": "6", "stdev": "0" }, { "name": "Eig08_AEA.ri.", "index": "39", "type": "numeric", "distinct": "481", "missing": "0", "min": "0", "max": "3", "mean": "2", "stdev": "0" }, { "name": "piID", "index": "40", "type": "numeric", "distinct": "597", "missing": "0", "min": "7", "max": "17", "mean": "11", "stdev": "2" }, { "name": "Eig08_AEA.bo.", "index": "41", "type": "numeric", "distinct": "451", "missing": "0", "min": "0", "max": "4", "mean": "3", "stdev": "0" }, { "name": "IC4", "index": "42", "type": "numeric", "distinct": "439", "missing": "0", "min": "3", "max": "6", "mean": "5", "stdev": "0" }, { "name": "SpMax1_Bh.i.", "index": "43", "type": "numeric", "distinct": "218", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "SpMin3_Bh.p.", "index": "44", "type": "numeric", "distinct": "321", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "NaasC", "index": "45", "type": "numeric", "distinct": "12", "missing": "0", "min": "1", "max": "12", "mean": "6", "stdev": "2" }, { "name": "Eig08_EA", "index": "46", "type": "numeric", "distinct": "453", "missing": "0", "min": "-1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "SM02_AEA.dm.", "index": "47", "type": "numeric", "distinct": "453", "missing": "0", "min": "-1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "SpMin5_Bh.e.", "index": "48", "type": "numeric", "distinct": "401", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "Eig02_EA.bo.", "index": "49", "type": "numeric", "distinct": "395", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SM12_AEA.ri.", "index": "50", "type": "numeric", "distinct": "395", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SpMin7_Bh.v.", "index": "51", "type": "numeric", "distinct": "394", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "Eig08_EA.bo.", "index": "52", "type": "numeric", "distinct": "476", "missing": "0", "min": "-2", "max": "3", "mean": "2", "stdev": "1" }, { "name": "IC3", "index": "53", "type": "numeric", "distinct": "459", "missing": "0", "min": "3", "max": "6", "mean": "5", "stdev": "0" }, { "name": "Eig07_AEA.ri.", "index": "54", "type": "numeric", "distinct": "508", "missing": "0", "min": "0", "max": "3", "mean": "3", "stdev": "0" }, { "name": "Eig06_EA.bo.", "index": "55", "type": "numeric", "distinct": "496", "missing": "0", "min": "0", "max": "3", "mean": "2", "stdev": "0" }, { "name": "Eig08_EA.ed.", "index": "56", "type": "numeric", "distinct": "550", "missing": "0", "min": "-3", "max": "8", "mean": "4", "stdev": "1" }, { "name": "SM03_AEA.ri.", "index": "57", "type": "numeric", "distinct": "550", "missing": "0", "min": "-3", "max": "8", "mean": "4", "stdev": "1" }, { "name": "piPC09", "index": "58", "type": "numeric", "distinct": "552", "missing": "0", "min": "4", "max": "10", "mean": "7", "stdev": "1" }, { "name": "SpMin6_Bh.s.", "index": "59", "type": "numeric", "distinct": "387", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "SpMin4_Bh.v.", "index": "60", "type": "numeric", "distinct": "388", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "ATS8m", "index": "61", "type": "numeric", "distinct": "563", "missing": "0", "min": "0", "max": "5", "mean": "3", "stdev": "1" }, { "name": "SpMin5_Bh.s.", "index": "62", "type": "numeric", "distinct": "400", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SpMaxA_AEA.dm.", "index": "63", "type": "numeric", "distinct": "138", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Eig05_EA", "index": "64", "type": "numeric", "distinct": "471", "missing": "0", "min": "1", "max": "3", "mean": "2", "stdev": "0" }, { "name": "SM13_AEA.bo.", "index": "65", "type": "numeric", "distinct": "471", "missing": "0", "min": "1", "max": "3", "mean": "2", "stdev": "0" }, { "name": "Eig10_AEA.ed.", "index": "66", "type": "numeric", "distinct": "461", "missing": "0", "min": "1", "max": "5", "mean": "4", "stdev": "1" }, { "name": "TIC1", "index": "67", "type": "numeric", "distinct": "641", "missing": "0", "min": "41", "max": "335", "mean": "172", "stdev": "50" }, { "name": "IDDE", "index": "68", "type": "numeric", "distinct": "303", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "nCs", "index": "69", "type": "numeric", "distinct": "11", "missing": "0", "min": "0", "max": "13", "mean": "1", "stdev": "2" } ], "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 }