{ "data_id": "33815", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4909", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4909", "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: CHEMBL4909 (TID: 100427), and it has 77 rows and 59 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 13:45:40", "update_comment": null, "last_update": "2016-07-15 13:45:40", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3514657\/data_51938.arff", "kaggle_url": null, "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4909", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL4909 (TID: 100427), and it has 77 rows and 59 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": 77, "NumberOfFeatures": 61, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 60, "NumberOfSymbolicFeatures": 1, "MaxSkewnessOfNumericAtts": 1.2145340074006823, "MinStdDevOfNumericAtts": 0.0028606864559606094, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 0.21978027927657107, "MaxStdDevOfNumericAtts": 31.788126122909716, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": -0.70935165315342, "Quartile3StdDevOfNumericAtts": 0.7835511875936019, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 1.9325162337662338, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": -0.1900682993870957, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 7.853864285714286, "Quartile1SkewnessOfNumericAtts": -0.6242663125698371, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.2547271689760529, "AutoCorrelation": 0.43640789473684205, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "ClassEntropy": null, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": -0.27840533500264386, "Dimensionality": 0.7922077922077922, "MeanSkewnessOfNumericAtts": -0.14070476468564252, "Quartile2MeansOfNumericAtts": 4.000584415584416, "EquivalentNumberOfAtts": null, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 2.109830842473601, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": -0.34598169511084265, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.4538114942678013, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.32959487732569703, "MaxKurtosisOfNumericAtts": 3.2305476825783224, "MinMeansOfNumericAtts": 0.010025974025974027, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 155.57142857142858, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 0.09667938404808618, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.36065573770492, "Quartile3MeansOfNumericAtts": 5.481444805194806, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -0.9868677545186072, "PercentageOfSymbolicFeatures": 1.639344262295082, "Quartile3MutualInformation": null }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "60", "type": "numeric", "distinct": "45", "missing": "0", "target": "1", "min": "5", "max": "8", "mean": "6", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "77", "missing": "0", "identifier": "1", "distr": [] }, { "name": "Eig08_EA", "index": "1", "type": "numeric", "distinct": "47", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "Eig08_EA.ed.", "index": "2", "type": "numeric", "distinct": "45", "missing": "0", "min": "1", "max": "6", "mean": "4", "stdev": "1" }, { "name": "SM02_AEA.dm.", "index": "3", "type": "numeric", "distinct": "47", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "SM03_AEA.ri.", "index": "4", "type": "numeric", "distinct": "45", "missing": "0", "min": "1", "max": "6", "mean": "4", "stdev": "1" }, { "name": "SpMin5_Bh.s.", "index": "5", "type": "numeric", "distinct": "60", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SpDiam_AEA.ri.", "index": "6", "type": "numeric", "distinct": "45", "missing": "0", "min": "5", "max": "6", "mean": "5", "stdev": "0" }, { "name": "nS", "index": "7", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "P_VSA_i_1", "index": "8", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "95", "mean": "22", "stdev": "27" }, { "name": "Eig01_EA", "index": "9", "type": "numeric", "distinct": "27", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SM09_AEA.bo.", "index": "10", "type": "numeric", "distinct": "27", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SpDiam_EA", "index": "11", "type": "numeric", "distinct": "29", "missing": "0", "min": "5", "max": "6", "mean": "5", "stdev": "0" }, { "name": "SpMax_EA", "index": "12", "type": "numeric", "distinct": "27", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SpMax1_Bh.m.", "index": "13", "type": "numeric", "distinct": "35", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "Eig08_AEA.ed.", "index": "14", "type": "numeric", "distinct": "46", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "1" }, { "name": "Eig07_EA", "index": "15", "type": "numeric", "distinct": "50", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "Eig08_AEA.ri.", "index": "16", "type": "numeric", "distinct": "64", "missing": "0", "min": "2", "max": "3", "mean": "2", "stdev": "0" }, { "name": "Eig09_EA", "index": "17", "type": "numeric", "distinct": "37", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "SM03_AEA.dm.", "index": "18", "type": "numeric", "distinct": "37", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "SM15_AEA.bo.", "index": "19", "type": "numeric", "distinct": "50", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "nHM", "index": "20", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "P_VSA_m_4", "index": "21", "type": "numeric", "distinct": "12", "missing": "0", "min": "0", "max": "134", "mean": "26", "stdev": "31" }, { "name": "CATS2D_02_AL", "index": "22", "type": "numeric", "distinct": "9", "missing": "0", "min": "2", "max": "10", "mean": "6", "stdev": "2" }, { "name": "SpMin3_Bh.m.", "index": "23", "type": "numeric", "distinct": "52", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "Eig04_AEA.ri.", "index": "24", "type": "numeric", "distinct": "52", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "Eig04_EA", "index": "25", "type": "numeric", "distinct": "45", "missing": "0", "min": "2", "max": "3", "mean": "2", "stdev": "0" }, { "name": "Eig05_EA.ed.", "index": "26", "type": "numeric", "distinct": "44", "missing": "0", "min": "3", "max": "7", "mean": "6", "stdev": "1" }, { "name": "Eig08_EA.ri.", "index": "27", "type": "numeric", "distinct": "63", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "Eig09_AEA.ri.", "index": "28", "type": "numeric", "distinct": "56", "missing": "0", "min": "1", "max": "3", "mean": "2", "stdev": "0" }, { "name": "Eig09_EA.ri.", "index": "29", "type": "numeric", "distinct": "52", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "GGI3", "index": "30", "type": "numeric", "distinct": "41", "missing": "0", "min": "1", "max": "3", "mean": "2", "stdev": "1" }, { "name": "MPC07", "index": "31", "type": "numeric", "distinct": "43", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "Psi_e_1", "index": "32", "type": "numeric", "distinct": "71", "missing": "0", "min": "3", "max": "6", "mean": "5", "stdev": "1" }, { "name": "SM04_AEA.bo.", "index": "33", "type": "numeric", "distinct": "54", "missing": "0", "min": "7", "max": "8", "mean": "7", "stdev": "0" }, { "name": "SM12_AEA.bo.", "index": "34", "type": "numeric", "distinct": "45", "missing": "0", "min": "2", "max": "3", "mean": "2", "stdev": "0" }, { "name": "SM14_AEA.dm.", "index": "35", "type": "numeric", "distinct": "44", "missing": "0", "min": "3", "max": "7", "mean": "6", "stdev": "1" }, { "name": "SRW10", "index": "36", "type": "numeric", "distinct": "54", "missing": "0", "min": "9", "max": "11", "mean": "10", "stdev": "0" }, { "name": "VAR", "index": "37", "type": "numeric", "distinct": "40", "missing": "0", "min": "98", "max": "225", "mean": "156", "stdev": "32" }, { "name": "Eig07_AEA.ri.", "index": "38", "type": "numeric", "distinct": "66", "missing": "0", "min": "2", "max": "3", "mean": "3", "stdev": "0" }, { "name": "Eig12_AEA.dm.", "index": "39", "type": "numeric", "distinct": "50", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "S1K", "index": "40", "type": "numeric", "distinct": "61", "missing": "0", "min": "21", "max": "28", "mean": "24", "stdev": "2" }, { "name": "SpMin5_Bh.m.", "index": "41", "type": "numeric", "distinct": "55", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "Eig01_AEA.bo.", "index": "42", "type": "numeric", "distinct": "34", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SpMax_AEA.bo.", "index": "43", "type": "numeric", "distinct": "34", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "JGI8", "index": "44", "type": "numeric", "distinct": "13", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "BBI", "index": "45", "type": "numeric", "distinct": "30", "missing": "0", "min": "26", "max": "61", "mean": "44", "stdev": "9" }, { "name": "Eig06_AEA.ed.", "index": "46", "type": "numeric", "distinct": "41", "missing": "0", "min": "4", "max": "5", "mean": "5", "stdev": "0" }, { "name": "Eig06_EA.ed.", "index": "47", "type": "numeric", "distinct": "45", "missing": "0", "min": "3", "max": "7", "mean": "5", "stdev": "1" }, { "name": "Eig07_AEA.ed.", "index": "48", "type": "numeric", "distinct": "47", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "1" }, { "name": "Eig07_EA.ed.", "index": "49", "type": "numeric", "distinct": "50", "missing": "0", "min": "2", "max": "6", "mean": "4", "stdev": "1" }, { "name": "Eig12_AEA.ed.", "index": "50", "type": "numeric", "distinct": "41", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "1" }, { "name": "MPC02", "index": "51", "type": "numeric", "distinct": "30", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "MPC03", "index": "52", "type": "numeric", "distinct": "38", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "MPC04", "index": "53", "type": "numeric", "distinct": "39", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "MWC03", "index": "54", "type": "numeric", "distinct": "46", "missing": "0", "min": "5", "max": "6", "mean": "6", "stdev": "0" }, { "name": "MWC04", "index": "55", "type": "numeric", "distinct": "53", "missing": "0", "min": "6", "max": "7", "mean": "7", "stdev": "0" }, { "name": "MWC05", "index": "56", "type": "numeric", "distinct": "57", "missing": "0", "min": "7", "max": "8", "mean": "7", "stdev": "0" }, { "name": "piPC03", "index": "57", "type": "numeric", "distinct": "50", "missing": "0", "min": "3", "max": "5", "mean": "5", "stdev": "0" }, { "name": "piPC04", "index": "58", "type": "numeric", "distinct": "54", "missing": "0", "min": "3", "max": "6", "mean": "5", "stdev": "1" }, { "name": "piPC07", "index": "59", "type": "numeric", "distinct": "58", "missing": "0", "min": "3", "max": "7", "mean": "6", "stdev": "1" } ], "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 }