{ "data_id": "33010", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4789", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4789", "version": 8, "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: CHEMBL4789 (TID: 11042), and it has 207 rows and 68 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 11:40:42", "update_comment": null, "last_update": "2016-07-15 11:40:42", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3494538\/data_53301.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4789", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL4789 (TID: 11042), and it has 207 rows and 68 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": 207, "NumberOfFeatures": 70, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 69, "NumberOfSymbolicFeatures": 1, "ClassEntropy": null, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "Dimensionality": 0.33816425120772947, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": 4.407201246570589, "EquivalentNumberOfAtts": null, "MeanSkewnessOfNumericAtts": -1.5659430720158616, "Quartile2MeansOfNumericAtts": 7.55251690821256, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 4.563315062705321, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": -1.597357877743866, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.1479750428977353, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 1.3126937091973572, "MaxKurtosisOfNumericAtts": 21.55448235341544, "MinMeansOfNumericAtts": -3.1375748792270532, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 170.00041062801932, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 9.752487581665894, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.57142857142858, "Quartile3MeansOfNumericAtts": 16.445152173913044, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -4.520755127020889, "PercentageOfSymbolicFeatures": 1.4285714285714286, "Quartile3MutualInformation": null, "MaxSkewnessOfNumericAtts": 2.589145125230224, "MinStdDevOfNumericAtts": 0.08533240389690122, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": -0.6732205536471882, "MaxStdDevOfNumericAtts": 77.52187949449942, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": 0.5895800725498244, "Quartile3StdDevOfNumericAtts": 2.5367083541106217, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 3.666782608695652, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": 6.4158890587078625, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 13.826474690191137, "Quartile1SkewnessOfNumericAtts": -2.7244507806083718, "AutoCorrelation": 0.07148543689320429, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.4415398113032332 }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "69", "type": "numeric", "distinct": "184", "missing": "0", "target": "1", "min": "4", "max": "8", "mean": "6", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "207", "missing": "0", "identifier": "1", "distr": [] }, { "name": "SM05_EA.bo.", "index": "1", "type": "numeric", "distinct": "135", "missing": "0", "min": "0", "max": "9", "mean": "8", "stdev": "1" }, { "name": "SM07_EA.bo.", "index": "2", "type": "numeric", "distinct": "150", "missing": "0", "min": "0", "max": "12", "mean": "10", "stdev": "2" }, { "name": "SM08_EA.bo.", "index": "3", "type": "numeric", "distinct": "158", "missing": "0", "min": "5", "max": "13", "mean": "12", "stdev": "1" }, { "name": "SM08_AEA.bo.", "index": "4", "type": "numeric", "distinct": "159", "missing": "0", "min": "8", "max": "14", "mean": "13", "stdev": "1" }, { "name": "SM06_EA.bo.", "index": "5", "type": "numeric", "distinct": "162", "missing": "0", "min": "4", "max": "10", "mean": "9", "stdev": "1" }, { "name": "SpDiam_AEA.bo.", "index": "6", "type": "numeric", "distinct": "152", "missing": "0", "min": "4", "max": "6", "mean": "5", "stdev": "0" }, { "name": "SpMax2_Bh.p.", "index": "7", "type": "numeric", "distinct": "159", "missing": "0", "min": "2", "max": "4", "mean": "4", "stdev": "0" }, { "name": "SpMax3_Bh.e.", "index": "8", "type": "numeric", "distinct": "173", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SM13_EA.bo.", "index": "9", "type": "numeric", "distinct": "154", "missing": "0", "min": "0", "max": "21", "mean": "19", "stdev": "4" }, { "name": "SM14_EA.bo.", "index": "10", "type": "numeric", "distinct": "158", "missing": "0", "min": "9", "max": "23", "mean": "21", "stdev": "2" }, { "name": "SM15_EA.bo.", "index": "11", "type": "numeric", "distinct": "151", "missing": "0", "min": "0", "max": "24", "mean": "22", "stdev": "4" }, { "name": "SM12_EA.bo.", "index": "12", "type": "numeric", "distinct": "154", "missing": "0", "min": "8", "max": "20", "mean": "18", "stdev": "2" }, { "name": "SM09_EA.bo.", "index": "13", "type": "numeric", "distinct": "153", "missing": "0", "min": "0", "max": "15", "mean": "13", "stdev": "2" }, { "name": "SM11_EA.bo.", "index": "14", "type": "numeric", "distinct": "154", "missing": "0", "min": "0", "max": "18", "mean": "16", "stdev": "3" }, { "name": "SM10_EA.bo.", "index": "15", "type": "numeric", "distinct": "163", "missing": "0", "min": "7", "max": "16", "mean": "15", "stdev": "2" }, { "name": "Eig03_EA.bo.", "index": "16", "type": "numeric", "distinct": "151", "missing": "0", "min": "-1", "max": "5", "mean": "3", "stdev": "1" }, { "name": "SM13_AEA.ri.", "index": "17", "type": "numeric", "distinct": "151", "missing": "0", "min": "-1", "max": "5", "mean": "3", "stdev": "1" }, { "name": "Eig03_AEA.bo.", "index": "18", "type": "numeric", "distinct": "155", "missing": "0", "min": "0", "max": "5", "mean": "4", "stdev": "1" }, { "name": "SpMax3_Bh.i.", "index": "19", "type": "numeric", "distinct": "172", "missing": "0", "min": "2", "max": "4", "mean": "4", "stdev": "0" }, { "name": "SpMax3_Bh.p.", "index": "20", "type": "numeric", "distinct": "163", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SpMax3_Bh.v.", "index": "21", "type": "numeric", "distinct": "165", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SpMax3_Bh.m.", "index": "22", "type": "numeric", "distinct": "176", "missing": "0", "min": "2", "max": "4", "mean": "4", "stdev": "0" }, { "name": "SpMax4_Bh.m.", "index": "23", "type": "numeric", "distinct": "165", "missing": "0", "min": "1", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SM04_EA.bo.", "index": "24", "type": "numeric", "distinct": "153", "missing": "0", "min": "3", "max": "8", "mean": "7", "stdev": "1" }, { "name": "SM09_EA", "index": "25", "type": "numeric", "distinct": "152", "missing": "0", "min": "0", "max": "13", "mean": "11", "stdev": "2" }, { "name": "SpMax4_Bh.p.", "index": "26", "type": "numeric", "distinct": "154", "missing": "0", "min": "1", "max": "4", "mean": "3", "stdev": "0" }, { "name": "GATS1e", "index": "27", "type": "numeric", "distinct": "147", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "X1v", "index": "28", "type": "numeric", "distinct": "185", "missing": "0", "min": "1", "max": "17", "mean": "7", "stdev": "3" }, { "name": "SM06_AEA.bo.", "index": "29", "type": "numeric", "distinct": "155", "missing": "0", "min": "6", "max": "11", "mean": "10", "stdev": "1" }, { "name": "SM10_EA", "index": "30", "type": "numeric", "distinct": "161", "missing": "0", "min": "7", "max": "14", "mean": "12", "stdev": "1" }, { "name": "SpMax1_Bh.e.", "index": "31", "type": "numeric", "distinct": "132", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "SdO", "index": "32", "type": "numeric", "distinct": "179", "missing": "0", "min": "0", "max": "61", "mean": "26", "stdev": "15" }, { "name": "SddssS", "index": "33", "type": "numeric", "distinct": "124", "missing": "0", "min": "-9", "max": "0", "mean": "-3", "stdev": "3" }, { "name": "P_VSA_e_3", "index": "34", "type": "numeric", "distinct": "64", "missing": "0", "min": "0", "max": "127", "mean": "49", "stdev": "34" }, { "name": "P_VSA_i_4", "index": "35", "type": "numeric", "distinct": "73", "missing": "0", "min": "0", "max": "162", "mean": "52", "stdev": "37" }, { "name": "Eig01_AEA.bo.", "index": "36", "type": "numeric", "distinct": "107", "missing": "0", "min": "3", "max": "5", "mean": "5", "stdev": "0" }, { "name": "SpMax_AEA.bo.", "index": "37", "type": "numeric", "distinct": "107", "missing": "0", "min": "3", "max": "5", "mean": "5", "stdev": "0" }, { "name": "D.Dtr05", "index": "38", "type": "numeric", "distinct": "73", "missing": "0", "min": "0", "max": "338", "mean": "33", "stdev": "52" }, { "name": "ATS1m", "index": "39", "type": "numeric", "distinct": "163", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SpMax2_Bh.e.", "index": "40", "type": "numeric", "distinct": "159", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "X2v", "index": "41", "type": "numeric", "distinct": "195", "missing": "0", "min": "0", "max": "15", "mean": "6", "stdev": "3" }, { "name": "X2sol", "index": "42", "type": "numeric", "distinct": "172", "missing": "0", "min": "2", "max": "24", "mean": "10", "stdev": "4" }, { "name": "SM08_EA", "index": "43", "type": "numeric", "distinct": "158", "missing": "0", "min": "5", "max": "11", "mean": "10", "stdev": "1" }, { "name": "SpMax4_Bh.e.", "index": "44", "type": "numeric", "distinct": "163", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SpMax4_Bh.v.", "index": "45", "type": "numeric", "distinct": "156", "missing": "0", "min": "1", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SM05_AEA.bo.", "index": "46", "type": "numeric", "distinct": "154", "missing": "0", "min": "5", "max": "10", "mean": "8", "stdev": "1" }, { "name": "SpDiam_AEA.ed.", "index": "47", "type": "numeric", "distinct": "140", "missing": "0", "min": "4", "max": "8", "mean": "7", "stdev": "1" }, { "name": "SpMax1_Bh.i.", "index": "48", "type": "numeric", "distinct": "138", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "SpMax1_Bh.v.", "index": "49", "type": "numeric", "distinct": "139", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "SM06_EA", "index": "50", "type": "numeric", "distinct": "158", "missing": "0", "min": "4", "max": "9", "mean": "8", "stdev": "1" }, { "name": "MAXDN", "index": "51", "type": "numeric", "distinct": "180", "missing": "0", "min": "0", "max": "6", "mean": "4", "stdev": "1" }, { "name": "SM12_EA", "index": "52", "type": "numeric", "distinct": "160", "missing": "0", "min": "8", "max": "17", "mean": "14", "stdev": "2" }, { "name": "SM14_AEA.ed.", "index": "53", "type": "numeric", "distinct": "156", "missing": "0", "min": "18", "max": "30", "mean": "27", "stdev": "2" }, { "name": "SM15_AEA.ed.", "index": "54", "type": "numeric", "distinct": "149", "missing": "0", "min": "20", "max": "33", "mean": "29", "stdev": "2" }, { "name": "P_VSA_s_1", "index": "55", "type": "numeric", "distinct": "10", "missing": "0", "min": "0", "max": "15", "mean": "5", "stdev": "4" }, { "name": "SM05_EA", "index": "56", "type": "numeric", "distinct": "80", "missing": "0", "min": "0", "max": "8", "mean": "6", "stdev": "1" }, { "name": "SM13_EA.ed.", "index": "57", "type": "numeric", "distinct": "141", "missing": "0", "min": "0", "max": "38", "mean": "31", "stdev": "6" }, { "name": "SM14_EA.ed.", "index": "58", "type": "numeric", "distinct": "148", "missing": "0", "min": "18", "max": "40", "mean": "34", "stdev": "4" }, { "name": "SM15_EA.ed.", "index": "59", "type": "numeric", "distinct": "141", "missing": "0", "min": "0", "max": "43", "mean": "36", "stdev": "7" }, { "name": "X3v", "index": "60", "type": "numeric", "distinct": "194", "missing": "0", "min": "0", "max": "10", "mean": "4", "stdev": "2" }, { "name": "CATS2D_09_PL", "index": "61", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "6", "mean": "0", "stdev": "1" }, { "name": "SpMin3_Bh.i.", "index": "62", "type": "numeric", "distinct": "155", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "ZM2Mad", "index": "63", "type": "numeric", "distinct": "188", "missing": "0", "min": "19", "max": "449", "mean": "170", "stdev": "78" }, { "name": "SM05_EA.ed.", "index": "64", "type": "numeric", "distinct": "148", "missing": "0", "min": "0", "max": "15", "mean": "12", "stdev": "2" }, { "name": "SM06_EA.ed.", "index": "65", "type": "numeric", "distinct": "154", "missing": "0", "min": "8", "max": "18", "mean": "15", "stdev": "2" }, { "name": "SM09_AEA.ed.", "index": "66", "type": "numeric", "distinct": "153", "missing": "0", "min": "12", "max": "20", "mean": "18", "stdev": "1" }, { "name": "SM07_EA.ed.", "index": "67", "type": "numeric", "distinct": "153", "missing": "0", "min": "0", "max": "20", "mean": "17", "stdev": "3" }, { "name": "SM08_EA.ed.", "index": "68", "type": "numeric", "distinct": "157", "missing": "0", "min": "11", "max": "23", "mean": "20", "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 }