{ "data_id": "35557", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL2721", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL2721", "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: CHEMBL2721 (TID: 11538), and it has 84 rows and 63 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 18:22:15", "update_comment": null, "last_update": "2016-07-15 18:22:15", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3561916\/data_52563.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-CHEMBL2721", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL2721 (TID: 11538), and it has 84 rows and 63 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": 84, "NumberOfFeatures": 65, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 64, "NumberOfSymbolicFeatures": 1, "MaxSkewnessOfNumericAtts": 1.9831593816282695, "MinStdDevOfNumericAtts": 0.005529493756648911, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 1.6938128343682708, "MaxStdDevOfNumericAtts": 47.742003228152754, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": -0.6085792974970891, "Quartile3StdDevOfNumericAtts": 1.3600110410735284, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 0.17857142857142852, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": 0.6948868628389727, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 8.957176339285715, "Quartile1SkewnessOfNumericAtts": -0.2251562726550435, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.4168553482599103, "AutoCorrelation": 0.35437349397590373, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "ClassEntropy": null, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": 0.4104216548515105, "Dimensionality": 0.7738095238095238, "MeanSkewnessOfNumericAtts": 0.5503603297247786, "Quartile2MeansOfNumericAtts": 1.0476190476190477, "EquivalentNumberOfAtts": null, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 3.8212296791907345, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": 0.27423535041269154, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -2.049382716049383, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.7952714601362436, "MaxKurtosisOfNumericAtts": 9.254776039215411, "MinMeansOfNumericAtts": -1.60075, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 125.02554761904761, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 0.9749731384026614, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.46153846153847, "Quartile3MeansOfNumericAtts": 2.672107142857143, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -1.179022886299801, "PercentageOfSymbolicFeatures": 1.5384615384615385, "Quartile3MutualInformation": null }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "64", "type": "numeric", "distinct": "49", "missing": "0", "target": "1", "min": "3", "max": "7", "mean": "5", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "84", "missing": "0", "identifier": "1", "distr": [] }, { "name": "MAXDN", "index": "1", "type": "numeric", "distinct": "74", "missing": "0", "min": "2", "max": "6", "mean": "3", "stdev": "1" }, { "name": "CATS2D_04_AN", "index": "2", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "1" }, { "name": "JGI9", "index": "3", "type": "numeric", "distinct": "15", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "CATS2D_05_AA", "index": "4", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "1" }, { "name": "CATS2D_04_AL", "index": "5", "type": "numeric", "distinct": "12", "missing": "0", "min": "0", "max": "15", "mean": "4", "stdev": "3" }, { "name": "CATS2D_05_AL", "index": "6", "type": "numeric", "distinct": "14", "missing": "0", "min": "0", "max": "15", "mean": "4", "stdev": "3" }, { "name": "SM03_EA.dm.", "index": "7", "type": "numeric", "distinct": "14", "missing": "0", "min": "0", "max": "4", "mean": "3", "stdev": "1" }, { "name": "GATS7p", "index": "8", "type": "numeric", "distinct": "70", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SdssC", "index": "9", "type": "numeric", "distinct": "76", "missing": "0", "min": "-4", "max": "2", "mean": "-2", "stdev": "1" }, { "name": "MATS6s", "index": "10", "type": "numeric", "distinct": "71", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "ATSC3s", "index": "11", "type": "numeric", "distinct": "76", "missing": "0", "min": "40", "max": "366", "mean": "108", "stdev": "48" }, { "name": "CATS2D_06_AL", "index": "12", "type": "numeric", "distinct": "14", "missing": "0", "min": "0", "max": "16", "mean": "3", "stdev": "4" }, { "name": "PW5", "index": "13", "type": "numeric", "distinct": "44", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "CATS2D_06_DA", "index": "14", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "CATS2D_04_DD", "index": "15", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "1" }, { "name": "CATS2D_04_DP", "index": "16", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "1" }, { "name": "Eig15_EA", "index": "17", "type": "numeric", "distinct": "43", "missing": "0", "min": "-2", "max": "1", "mean": "-1", "stdev": "1" }, { "name": "Eig15_EA.ri.", "index": "18", "type": "numeric", "distinct": "46", "missing": "0", "min": "-2", "max": "1", "mean": "-1", "stdev": "1" }, { "name": "SM09_AEA.dm.", "index": "19", "type": "numeric", "distinct": "43", "missing": "0", "min": "-2", "max": "1", "mean": "-1", "stdev": "1" }, { "name": "C.017", "index": "20", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "C.019", "index": "21", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "C.020", "index": "22", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "CATS2D_01_AN", "index": "23", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "CATS2D_01_DN", "index": "24", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "CATS2D_03_DA", "index": "25", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "CATS2D_04_AA", "index": "26", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "CATS2D_04_DN", "index": "27", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "CATS2D_05_DD", "index": "28", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "GATS1s", "index": "29", "type": "numeric", "distinct": "68", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "JGI1", "index": "30", "type": "numeric", "distinct": "44", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "MATS1e", "index": "31", "type": "numeric", "distinct": "55", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "N.074", "index": "32", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "nCconj", "index": "33", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "nCIC", "index": "34", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "5", "mean": "2", "stdev": "2" }, { "name": "nCsp", "index": "35", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "NdssC", "index": "36", "type": "numeric", "distinct": "5", "missing": "0", "min": "1", "max": "6", "mean": "3", "stdev": "1" }, { "name": "nRCN", "index": "37", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "nRCOOH", "index": "38", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "nR.Cs", "index": "39", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "nR.Ct", "index": "40", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "nROH", "index": "41", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "NRS", "index": "42", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "NsOH", "index": "43", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "nTB", "index": "44", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "NtN", "index": "45", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "NtsC", "index": "46", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "O.057", "index": "47", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "P_VSA_e_5", "index": "48", "type": "numeric", "distinct": "16", "missing": "0", "min": "36", "max": "203", "mean": "114", "stdev": "44" }, { "name": "P_VSA_m_3", "index": "49", "type": "numeric", "distinct": "25", "missing": "0", "min": "36", "max": "217", "mean": "122", "stdev": "45" }, { "name": "P_VSA_MR_2", "index": "50", "type": "numeric", "distinct": "24", "missing": "0", "min": "25", "max": "227", "mean": "125", "stdev": "47" }, { "name": "SM05_EA.dm.", "index": "51", "type": "numeric", "distinct": "18", "missing": "0", "min": "0", "max": "7", "mean": "4", "stdev": "1" }, { "name": "SM07_EA.dm.", "index": "52", "type": "numeric", "distinct": "18", "missing": "0", "min": "0", "max": "9", "mean": "6", "stdev": "2" }, { "name": "SM09_EA.dm.", "index": "53", "type": "numeric", "distinct": "20", "missing": "0", "min": "0", "max": "12", "mean": "8", "stdev": "2" }, { "name": "SM11_EA.dm.", "index": "54", "type": "numeric", "distinct": "20", "missing": "0", "min": "0", "max": "15", "mean": "10", "stdev": "2" }, { "name": "SM13_EA.dm.", "index": "55", "type": "numeric", "distinct": "20", "missing": "0", "min": "0", "max": "17", "mean": "12", "stdev": "3" }, { "name": "SM15_EA.dm.", "index": "56", "type": "numeric", "distinct": "21", "missing": "0", "min": "0", "max": "20", "mean": "14", "stdev": "3" }, { "name": "StN", "index": "57", "type": "numeric", "distinct": "16", "missing": "0", "min": "0", "max": "10", "mean": "2", "stdev": "4" }, { "name": "StsC", "index": "58", "type": "numeric", "distinct": "16", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "X4v", "index": "59", "type": "numeric", "distinct": "75", "missing": "0", "min": "0", "max": "5", "mean": "2", "stdev": "1" }, { "name": "GATS7s", "index": "60", "type": "numeric", "distinct": "75", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "0" }, { "name": "CATS2D_05_DA", "index": "61", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "Eig15_EA.bo.", "index": "62", "type": "numeric", "distinct": "45", "missing": "0", "min": "-2", "max": "1", "mean": "-1", "stdev": "1" }, { "name": "CATS2D_07_NL", "index": "63", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "6", "mean": "1", "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 }