{ "data_id": "37839", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4641", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4641", "version": 11, "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: CHEMBL4641 (TID: 100100), and it has 259 rows and 62 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 02:02:19", "update_comment": null, "last_update": "2016-07-16 02:02:19", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3622948\/data_52395.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4641", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL4641 (TID: 100100), and it has 259 rows and 62 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": 259, "NumberOfFeatures": 64, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 63, "NumberOfSymbolicFeatures": 1, "Quartile3AttributeEntropy": null, "MaxKurtosisOfNumericAtts": 2.7199368438224187, "MinMeansOfNumericAtts": -4.971891891891892, "PercentageOfInstancesWithMissingValues": 0, "Quartile3KurtosisOfNumericAtts": -0.09103847025077716, "MaxMeansOfNumericAtts": 42.41042084942085, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3MeansOfNumericAtts": 15.156559845559846, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.4375, "Quartile3MutualInformation": null, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -1.077621693888794, "PercentageOfSymbolicFeatures": 1.5625, "Quartile3SkewnessOfNumericAtts": 0.35433292729489824, "MaxSkewnessOfNumericAtts": 1.5151289268304493, "MinStdDevOfNumericAtts": 0.01925912952904144, "Quartile1AttributeEntropy": null, "Quartile3StdDevOfNumericAtts": 2.7259824300393616, "MaxStdDevOfNumericAtts": 9.605084860630372, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": -0.5771123056092522, "StdvNominalAttDistinctValues": null, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 3.7414633204633203, "MeanKurtosisOfNumericAtts": -0.23505895301393234, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 10.831231598945886, "Quartile1SkewnessOfNumericAtts": -0.17470655008549324, "AutoCorrelation": 0.41886821705426375, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.31233467629525485, "ClassEntropy": null, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "Dimensionality": 0.2471042471042471, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": -0.31332389098228175, "EquivalentNumberOfAtts": null, "MeanSkewnessOfNumericAtts": 0.16023682629606334, "Quartile2MeansOfNumericAtts": 9.540540540540539, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 1.8725118168280788, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": 0.1901193489055329, "Quartile2StdDevOfNumericAtts": 0.7824027001579498, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -0.8271797125756906, "PercentageOfBinaryFeatures": 0 }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "63", "type": "numeric", "distinct": "213", "missing": "0", "target": "1", "min": "4", "max": "8", "mean": "6", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "259", "missing": "0", "identifier": "1", "distr": [] }, { "name": "ATSC5p", "index": "1", "type": "numeric", "distinct": "251", "missing": "0", "min": "6", "max": "23", "mean": "14", "stdev": "3" }, { "name": "ATSC5v", "index": "2", "type": "numeric", "distinct": "251", "missing": "0", "min": "9", "max": "32", "mean": "20", "stdev": "5" }, { "name": "ATS5i", "index": "3", "type": "numeric", "distinct": "213", "missing": "0", "min": "5", "max": "6", "mean": "5", "stdev": "0" }, { "name": "ATS5e", "index": "4", "type": "numeric", "distinct": "224", "missing": "0", "min": "5", "max": "6", "mean": "5", "stdev": "0" }, { "name": "ATSC2p", "index": "5", "type": "numeric", "distinct": "186", "missing": "0", "min": "6", "max": "14", "mean": "10", "stdev": "2" }, { "name": "ATSC6p", "index": "6", "type": "numeric", "distinct": "252", "missing": "0", "min": "6", "max": "24", "mean": "14", "stdev": "4" }, { "name": "ATSC3p", "index": "7", "type": "numeric", "distinct": "229", "missing": "0", "min": "8", "max": "19", "mean": "13", "stdev": "2" }, { "name": "ATSC5m", "index": "8", "type": "numeric", "distinct": "253", "missing": "0", "min": "22", "max": "69", "mean": "41", "stdev": "9" }, { "name": "CATS2D_05_LL", "index": "9", "type": "numeric", "distinct": "22", "missing": "0", "min": "0", "max": "21", "mean": "7", "stdev": "5" }, { "name": "CATS2D_03_LL", "index": "10", "type": "numeric", "distinct": "20", "missing": "0", "min": "2", "max": "26", "mean": "10", "stdev": "5" }, { "name": "ATSC4p", "index": "11", "type": "numeric", "distinct": "251", "missing": "0", "min": "7", "max": "21", "mean": "14", "stdev": "3" }, { "name": "CATS2D_04_LL", "index": "12", "type": "numeric", "distinct": "21", "missing": "0", "min": "0", "max": "21", "mean": "6", "stdev": "5" }, { "name": "ATS5p", "index": "13", "type": "numeric", "distinct": "217", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "ATSC6v", "index": "14", "type": "numeric", "distinct": "253", "missing": "0", "min": "8", "max": "34", "mean": "19", "stdev": "6" }, { "name": "ATSC4v", "index": "15", "type": "numeric", "distinct": "251", "missing": "0", "min": "10", "max": "29", "mean": "20", "stdev": "4" }, { "name": "ATS6i", "index": "16", "type": "numeric", "distinct": "215", "missing": "0", "min": "5", "max": "6", "mean": "5", "stdev": "0" }, { "name": "BLTA96", "index": "17", "type": "numeric", "distinct": "136", "missing": "0", "min": "-7", "max": "0", "mean": "-5", "stdev": "1" }, { "name": "MLOGP", "index": "18", "type": "numeric", "distinct": "173", "missing": "0", "min": "1", "max": "6", "mean": "4", "stdev": "1" }, { "name": "MLOGP2", "index": "19", "type": "numeric", "distinct": "173", "missing": "0", "min": "2", "max": "32", "mean": "15", "stdev": "6" }, { "name": "ATSC3v", "index": "20", "type": "numeric", "distinct": "227", "missing": "0", "min": "11", "max": "28", "mean": "18", "stdev": "3" }, { "name": "BLTD48", "index": "21", "type": "numeric", "distinct": "133", "missing": "0", "min": "-7", "max": "0", "mean": "-5", "stdev": "1" }, { "name": "BLTF96", "index": "22", "type": "numeric", "distinct": "133", "missing": "0", "min": "-6", "max": "0", "mean": "-5", "stdev": "1" }, { "name": "ATS4e", "index": "23", "type": "numeric", "distinct": "200", "missing": "0", "min": "5", "max": "6", "mean": "5", "stdev": "0" }, { "name": "ATS4i", "index": "24", "type": "numeric", "distinct": "193", "missing": "0", "min": "5", "max": "6", "mean": "5", "stdev": "0" }, { "name": "Eta_C_A", "index": "25", "type": "numeric", "distinct": "185", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Eta_betaS_A", "index": "26", "type": "numeric", "distinct": "61", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SM08_EA.ed.", "index": "27", "type": "numeric", "distinct": "183", "missing": "0", "min": "17", "max": "22", "mean": "20", "stdev": "1" }, { "name": "SM06_EA.ri.", "index": "28", "type": "numeric", "distinct": "224", "missing": "0", "min": "7", "max": "8", "mean": "8", "stdev": "0" }, { "name": "SM09_EA.ed.", "index": "29", "type": "numeric", "distinct": "180", "missing": "0", "min": "19", "max": "25", "mean": "22", "stdev": "1" }, { "name": "SM04_EA.ed.", "index": "30", "type": "numeric", "distinct": "189", "missing": "0", "min": "10", "max": "12", "mean": "11", "stdev": "0" }, { "name": "DLS_01", "index": "31", "type": "numeric", "distinct": "3", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "ATS4p", "index": "32", "type": "numeric", "distinct": "212", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SpMin1_Bh.m.", "index": "33", "type": "numeric", "distinct": "68", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "ATSC1p", "index": "34", "type": "numeric", "distinct": "182", "missing": "0", "min": "4", "max": "9", "mean": "6", "stdev": "1" }, { "name": "ATSC6i", "index": "35", "type": "numeric", "distinct": "238", "missing": "0", "min": "1", "max": "3", "mean": "2", "stdev": "0" }, { "name": "SpMin2_Bh.e.", "index": "36", "type": "numeric", "distinct": "77", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "ATS6e", "index": "37", "type": "numeric", "distinct": "216", "missing": "0", "min": "4", "max": "6", "mean": "5", "stdev": "0" }, { "name": "SM07_EA.ed.", "index": "38", "type": "numeric", "distinct": "182", "missing": "0", "min": "15", "max": "19", "mean": "17", "stdev": "1" }, { "name": "SM06_EA.ed.", "index": "39", "type": "numeric", "distinct": "190", "missing": "0", "min": "14", "max": "17", "mean": "15", "stdev": "1" }, { "name": "CATS2D_02_LL", "index": "40", "type": "numeric", "distinct": "23", "missing": "0", "min": "4", "max": "29", "mean": "14", "stdev": "5" }, { "name": "SM08_EA.ri.", "index": "41", "type": "numeric", "distinct": "239", "missing": "0", "min": "9", "max": "11", "mean": "10", "stdev": "0" }, { "name": "ATSC5i", "index": "42", "type": "numeric", "distinct": "230", "missing": "0", "min": "1", "max": "3", "mean": "2", "stdev": "0" }, { "name": "DBI", "index": "43", "type": "numeric", "distinct": "39", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "1" }, { "name": "SM07_EA.ri.", "index": "44", "type": "numeric", "distinct": "219", "missing": "0", "min": "7", "max": "9", "mean": "8", "stdev": "0" }, { "name": "ATSC7i", "index": "45", "type": "numeric", "distinct": "237", "missing": "0", "min": "1", "max": "3", "mean": "2", "stdev": "1" }, { "name": "nCt", "index": "46", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "0" }, { "name": "SM08_AEA.ed.", "index": "47", "type": "numeric", "distinct": "193", "missing": "0", "min": "15", "max": "17", "mean": "16", "stdev": "0" }, { "name": "ATSC7p", "index": "48", "type": "numeric", "distinct": "249", "missing": "0", "min": "5", "max": "24", "mean": "13", "stdev": "4" }, { "name": "SpMin2_Bh.m.", "index": "49", "type": "numeric", "distinct": "92", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "Eig01_EA.ed.", "index": "50", "type": "numeric", "distinct": "81", "missing": "0", "min": "8", "max": "16", "mean": "12", "stdev": "2" }, { "name": "SM10_AEA.dm.", "index": "51", "type": "numeric", "distinct": "81", "missing": "0", "min": "8", "max": "16", "mean": "12", "stdev": "2" }, { "name": "SpDiam_EA.ed.", "index": "52", "type": "numeric", "distinct": "95", "missing": "0", "min": "13", "max": "24", "mean": "19", "stdev": "2" }, { "name": "SpMax_EA.ed.", "index": "53", "type": "numeric", "distinct": "81", "missing": "0", "min": "8", "max": "16", "mean": "12", "stdev": "2" }, { "name": "ATSC6m", "index": "54", "type": "numeric", "distinct": "253", "missing": "0", "min": "19", "max": "74", "mean": "40", "stdev": "10" }, { "name": "SM10_EA.ed.", "index": "55", "type": "numeric", "distinct": "177", "missing": "0", "min": "21", "max": "28", "mean": "25", "stdev": "1" }, { "name": "SM05_EA.ed.", "index": "56", "type": "numeric", "distinct": "182", "missing": "0", "min": "11", "max": "14", "mean": "13", "stdev": "1" }, { "name": "SpMin2_Bh.s.", "index": "57", "type": "numeric", "distinct": "110", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "ATSC4i", "index": "58", "type": "numeric", "distinct": "230", "missing": "0", "min": "1", "max": "3", "mean": "2", "stdev": "0" }, { "name": "ATSC4m", "index": "59", "type": "numeric", "distinct": "253", "missing": "0", "min": "23", "max": "63", "mean": "42", "stdev": "7" }, { "name": "SM06_AEA.ed.", "index": "60", "type": "numeric", "distinct": "187", "missing": "0", "min": "12", "max": "13", "mean": "13", "stdev": "0" }, { "name": "SM12_EA.ed.", "index": "61", "type": "numeric", "distinct": "171", "missing": "0", "min": "25", "max": "33", "mean": "29", "stdev": "2" }, { "name": "SM13_EA.ed.", "index": "62", "type": "numeric", "distinct": "168", "missing": "0", "min": "27", "max": "36", "mean": "32", "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 }