{ "data_id": "33202", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4336", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4336", "version": 10, "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: CHEMBL4336 (TID: 12507), and it has 314 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": "2016-07-15 12:10:32", "update_comment": null, "last_update": "2016-07-15 12:10:32", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3499530\/data_52446.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4336", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL4336 (TID: 12507), and it has 314 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": 314, "NumberOfFeatures": 64, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 63, "NumberOfSymbolicFeatures": 1, "ClassEntropy": null, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "Dimensionality": 0.20382165605095542, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": -0.7011054809680513, "EquivalentNumberOfAtts": null, "MeanSkewnessOfNumericAtts": 0.07011057843072316, "Quartile2MeansOfNumericAtts": 4.266818471337579, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 5.614899855736824, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": 0.0029148266789805616, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.330474960190738, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.39927418846798607, "MaxKurtosisOfNumericAtts": 3.0956193447109275, "MinMeansOfNumericAtts": -0.06270063694267515, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 627.4419331210191, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": -0.3955362103219602, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.4375, "Quartile3MeansOfNumericAtts": 17.80996178343949, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -0.8471527044291545, "PercentageOfSymbolicFeatures": 1.5625, "Quartile3MutualInformation": null, "MaxSkewnessOfNumericAtts": 1.3244390222470785, "MinStdDevOfNumericAtts": 0.06775081205518099, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 0.3139475577690593, "MaxStdDevOfNumericAtts": 63.55846769485211, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": -0.9075789421577731, "Quartile3StdDevOfNumericAtts": 6.277144712027905, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 1.5159235668789803, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": -0.5231428478115866, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 33.375043473865134, "Quartile1SkewnessOfNumericAtts": -0.21668294566704296, "AutoCorrelation": 0.21257827476038368, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.11730713173988151 }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "63", "type": "numeric", "distinct": "151", "missing": "0", "target": "1", "min": "5", "max": "10", "mean": "7", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "314", "missing": "0", "identifier": "1", "distr": [] }, { "name": "ATS8s", "index": "1", "type": "numeric", "distinct": "250", "missing": "0", "min": "6", "max": "7", "mean": "6", "stdev": "0" }, { "name": "GGI10", "index": "2", "type": "numeric", "distinct": "108", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "ATSC8i", "index": "3", "type": "numeric", "distinct": "263", "missing": "0", "min": "1", "max": "3", "mean": "2", "stdev": "0" }, { "name": "ATSC7i", "index": "4", "type": "numeric", "distinct": "268", "missing": "0", "min": "1", "max": "3", "mean": "2", "stdev": "0" }, { "name": "TIE", "index": "5", "type": "numeric", "distinct": "300", "missing": "0", "min": "44", "max": "160", "mean": "91", "stdev": "23" }, { "name": "ATSC4i", "index": "6", "type": "numeric", "distinct": "257", "missing": "0", "min": "1", "max": "3", "mean": "2", "stdev": "0" }, { "name": "ON0V", "index": "7", "type": "numeric", "distinct": "170", "missing": "0", "min": "7", "max": "15", "mean": "11", "stdev": "2" }, { "name": "Se", "index": "8", "type": "numeric", "distinct": "221", "missing": "0", "min": "42", "max": "76", "mean": "62", "stdev": "7" }, { "name": "Si", "index": "9", "type": "numeric", "distinct": "221", "missing": "0", "min": "46", "max": "85", "mean": "69", "stdev": "8" }, { "name": "GGI9", "index": "10", "type": "numeric", "distinct": "130", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "ATSC5i", "index": "11", "type": "numeric", "distinct": "260", "missing": "0", "min": "1", "max": "3", "mean": "2", "stdev": "0" }, { "name": "ISIZ", "index": "12", "type": "numeric", "distinct": "34", "missing": "0", "min": "220", "max": "475", "mean": "364", "stdev": "52" }, { "name": "nAT", "index": "13", "type": "numeric", "distinct": "34", "missing": "0", "min": "41", "max": "76", "mean": "61", "stdev": "7" }, { "name": "H.046", "index": "14", "type": "numeric", "distinct": "21", "missing": "0", "min": "0", "max": "23", "mean": "6", "stdev": "6" }, { "name": "SpMin4_Bh.m.", "index": "15", "type": "numeric", "distinct": "152", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "P_VSA_MR_1", "index": "16", "type": "numeric", "distinct": "43", "missing": "0", "min": "118", "max": "412", "mean": "282", "stdev": "57" }, { "name": "ATSC6v", "index": "17", "type": "numeric", "distinct": "295", "missing": "0", "min": "8", "max": "27", "mean": "18", "stdev": "4" }, { "name": "CATS2D_02_DA", "index": "18", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "2", "stdev": "1" }, { "name": "CATS2D_07_LL", "index": "19", "type": "numeric", "distinct": "40", "missing": "0", "min": "0", "max": "42", "mean": "17", "stdev": "11" }, { "name": "ATS5p", "index": "20", "type": "numeric", "distinct": "240", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "GGI6", "index": "21", "type": "numeric", "distinct": "132", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "CATS2D_06_LL", "index": "22", "type": "numeric", "distinct": "34", "missing": "0", "min": "3", "max": "36", "mean": "17", "stdev": "9" }, { "name": "ATSC8m", "index": "23", "type": "numeric", "distinct": "296", "missing": "0", "min": "19", "max": "51", "mean": "36", "stdev": "8" }, { "name": "ATS1i", "index": "24", "type": "numeric", "distinct": "173", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "CATS2D_08_LL", "index": "25", "type": "numeric", "distinct": "34", "missing": "0", "min": "0", "max": "36", "mean": "15", "stdev": "8" }, { "name": "ATS6i", "index": "26", "type": "numeric", "distinct": "249", "missing": "0", "min": "5", "max": "6", "mean": "5", "stdev": "0" }, { "name": "SAtot", "index": "27", "type": "numeric", "distinct": "235", "missing": "0", "min": "438", "max": "752", "mean": "627", "stdev": "64" }, { "name": "NssNH", "index": "28", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "DLS_02", "index": "29", "type": "numeric", "distinct": "4", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "MATS4m", "index": "30", "type": "numeric", "distinct": "167", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "MATS4v", "index": "31", "type": "numeric", "distinct": "190", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SpMin4_Bh.p.", "index": "32", "type": "numeric", "distinct": "142", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "ATSC6p", "index": "33", "type": "numeric", "distinct": "293", "missing": "0", "min": "8", "max": "19", "mean": "14", "stdev": "3" }, { "name": "MATS8v", "index": "34", "type": "numeric", "distinct": "187", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "X1Per", "index": "35", "type": "numeric", "distinct": "260", "missing": "0", "min": "6", "max": "11", "mean": "9", "stdev": "1" }, { "name": "Sv", "index": "36", "type": "numeric", "distinct": "222", "missing": "0", "min": "28", "max": "50", "mean": "39", "stdev": "4" }, { "name": "ALOGP", "index": "37", "type": "numeric", "distinct": "246", "missing": "0", "min": "2", "max": "8", "mean": "5", "stdev": "2" }, { "name": "ALOGP2", "index": "38", "type": "numeric", "distinct": "251", "missing": "0", "min": "3", "max": "62", "mean": "28", "stdev": "15" }, { "name": "C.003", "index": "39", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "Uindex", "index": "40", "type": "numeric", "distinct": "181", "missing": "0", "min": "41", "max": "83", "mean": "63", "stdev": "9" }, { "name": "ATS4v", "index": "41", "type": "numeric", "distinct": "230", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "Sp", "index": "42", "type": "numeric", "distinct": "217", "missing": "0", "min": "29", "max": "51", "mean": "41", "stdev": "5" }, { "name": "LLS_02", "index": "43", "type": "numeric", "distinct": "5", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "MATS3i", "index": "44", "type": "numeric", "distinct": "175", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "ATS1e", "index": "45", "type": "numeric", "distinct": "174", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "ATS4e", "index": "46", "type": "numeric", "distinct": "225", "missing": "0", "min": "5", "max": "5", "mean": "5", "stdev": "0" }, { "name": "SpMin7_Bh.m.", "index": "47", "type": "numeric", "distinct": "171", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "SpMax5_Bh.i.", "index": "48", "type": "numeric", "distinct": "142", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "nBT", "index": "49", "type": "numeric", "distinct": "33", "missing": "0", "min": "43", "max": "79", "mean": "63", "stdev": "7" }, { "name": "ATS3i", "index": "50", "type": "numeric", "distinct": "200", "missing": "0", "min": "5", "max": "6", "mean": "5", "stdev": "0" }, { "name": "MATS8p", "index": "51", "type": "numeric", "distinct": "183", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SsCH3", "index": "52", "type": "numeric", "distinct": "195", "missing": "0", "min": "0", "max": "13", "mean": "3", "stdev": "3" }, { "name": "ATS4p", "index": "53", "type": "numeric", "distinct": "226", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "X0v", "index": "54", "type": "numeric", "distinct": "231", "missing": "0", "min": "15", "max": "25", "mean": "19", "stdev": "2" }, { "name": "ATSC3i", "index": "55", "type": "numeric", "distinct": "225", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "SpMax5_Bh.m.", "index": "56", "type": "numeric", "distinct": "144", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "GATS4v", "index": "57", "type": "numeric", "distinct": "170", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "ATS8p", "index": "58", "type": "numeric", "distinct": "242", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "MATS4p", "index": "59", "type": "numeric", "distinct": "166", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "CATS2D_05_LL", "index": "60", "type": "numeric", "distinct": "26", "missing": "0", "min": "1", "max": "26", "mean": "14", "stdev": "6" }, { "name": "BAC", "index": "61", "type": "numeric", "distinct": "52", "missing": "0", "min": "8", "max": "96", "mean": "44", "stdev": "23" }, { "name": "ATS3p", "index": "62", "type": "numeric", "distinct": "206", "missing": "0", "min": "4", "max": "5", "mean": "4", "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 }