{ "data_id": "31122", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3797", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3797", "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: CHEMBL3797 (TID: 20137), and it has 101 rows and 64 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 06:45:31", "update_comment": null, "last_update": "2016-07-15 06:45:31", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3439410\/data_52689.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3797", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL3797 (TID: 20137), and it has 101 rows and 64 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": 101, "NumberOfFeatures": 66, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 65, "NumberOfSymbolicFeatures": 1, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.9881475818744666, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -2.03048486404281, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxKurtosisOfNumericAtts": 46.77151770378384, "MinMeansOfNumericAtts": -0.10363366336633663, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": -0.6623674525521293, "MaxMeansOfNumericAtts": 165.67833663366338, "MinMutualInformation": null, "PercentageOfNumericFeatures": 98.48484848484848, "Quartile3MeansOfNumericAtts": 2.876237623762375, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfSymbolicFeatures": 1.5151515151515151, "Quartile3MutualInformation": null, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -5.635318734056469, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 0.28828728617768906, "MaxSkewnessOfNumericAtts": 2.688880417912812, "MinStdDevOfNumericAtts": 0.028917639962315375, "Quartile1KurtosisOfNumericAtts": -1.702833653179276, "Quartile3StdDevOfNumericAtts": 2.060617545804196, "MaxStdDevOfNumericAtts": 49.62099003109013, "MinorityClassPercentage": null, "Quartile1MeansOfNumericAtts": 0.4801980198019802, "StdvNominalAttDistinctValues": null, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MutualInformation": null, "MeanKurtosisOfNumericAtts": 0.26414250999690686, "NumberOfBinaryFeatures": 0, "Quartile1SkewnessOfNumericAtts": -0.010947317699174217, "MeanMeansOfNumericAtts": 10.769253617669461, "Quartile1StdDevOfNumericAtts": 0.5198974927021731, "AutoCorrelation": 0.45801000000000014, "MeanMutualInformation": null, "Quartile2AttributeEntropy": null, "ClassEntropy": null, "MeanNoiseToSignalRatio": null, "Quartile2KurtosisOfNumericAtts": -1.250985527342572, "Dimensionality": 0.6534653465346535, "MeanNominalAttDistinctValues": null, "Quartile2MeansOfNumericAtts": 0.9801980198019792, "EquivalentNumberOfAtts": null, "MeanSkewnessOfNumericAtts": 0.08603727013357378, "Quartile2MutualInformation": null, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 5.269701267003189, "Quartile2SkewnessOfNumericAtts": 0.1816384307294344, "MajorityClassSize": null, "MinAttributeEntropy": null }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "65", "type": "numeric", "distinct": "26", "missing": "0", "target": "1", "min": "4", "max": "8", "mean": "5", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "101", "missing": "0", "identifier": "1", "distr": [] }, { "name": "CATS2D_07_PL", "index": "1", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "5", "mean": "2", "stdev": "2" }, { "name": "nPyrazines", "index": "2", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "1" }, { "name": "CATS2D_03_DA", "index": "3", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "1" }, { "name": "C.028", "index": "4", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "CATS2D_04_DD", "index": "5", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "1" }, { "name": "CATS2D_07_DL", "index": "6", "type": "numeric", "distinct": "8", "missing": "0", "min": "0", "max": "8", "mean": "3", "stdev": "3" }, { "name": "SssO", "index": "7", "type": "numeric", "distinct": "55", "missing": "0", "min": "0", "max": "21", "mean": "6", "stdev": "7" }, { "name": "CATS2D_04_DP", "index": "8", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "SAdon", "index": "9", "type": "numeric", "distinct": "15", "missing": "0", "min": "0", "max": "94", "mean": "30", "stdev": "28" }, { "name": "CATS2D_08_PL", "index": "10", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "nArCONHR", "index": "11", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "P_VSA_e_3", "index": "12", "type": "numeric", "distinct": "24", "missing": "0", "min": "0", "max": "130", "mean": "51", "stdev": "42" }, { "name": "P_VSA_i_4", "index": "13", "type": "numeric", "distinct": "24", "missing": "0", "min": "0", "max": "117", "mean": "52", "stdev": "41" }, { "name": "NaasC", "index": "14", "type": "numeric", "distinct": "8", "missing": "0", "min": "0", "max": "7", "mean": "4", "stdev": "2" }, { "name": "C.016", "index": "15", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "MATS1p", "index": "16", "type": "numeric", "distinct": "66", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "nR.Cs", "index": "17", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "5", "mean": "1", "stdev": "2" }, { "name": "SdsCH", "index": "18", "type": "numeric", "distinct": "45", "missing": "0", "min": "0", "max": "7", "mean": "1", "stdev": "2" }, { "name": "CATS2D_04_DA", "index": "19", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "CATS2D_02_AL", "index": "20", "type": "numeric", "distinct": "12", "missing": "0", "min": "0", "max": "11", "mean": "5", "stdev": "3" }, { "name": "CATS2D_02_AP", "index": "21", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "CATS2D_03_AP", "index": "22", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "1" }, { "name": "Hy", "index": "23", "type": "numeric", "distinct": "61", "missing": "0", "min": "-1", "max": "5", "mean": "0", "stdev": "1" }, { "name": "C.006", "index": "24", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "8", "mean": "2", "stdev": "2" }, { "name": "CATS2D_06_DL", "index": "25", "type": "numeric", "distinct": "9", "missing": "0", "min": "0", "max": "9", "mean": "3", "stdev": "3" }, { "name": "NdsCH", "index": "26", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "nROR", "index": "27", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "1" }, { "name": "O.059", "index": "28", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "1" }, { "name": "C.020", "index": "29", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "P_VSA_LogP_3", "index": "30", "type": "numeric", "distinct": "31", "missing": "0", "min": "0", "max": "167", "mean": "91", "stdev": "32" }, { "name": "CATS2D_05_PL", "index": "31", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "CATS2D_09_LL", "index": "32", "type": "numeric", "distinct": "10", "missing": "0", "min": "0", "max": "11", "mean": "4", "stdev": "4" }, { "name": "N.068", "index": "33", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "1" }, { "name": "nRNR2", "index": "34", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "1" }, { "name": "MATS3e", "index": "35", "type": "numeric", "distinct": "82", "missing": "0", "min": "-1", "max": "0", "mean": "0", "stdev": "0" }, { "name": "MATS3s", "index": "36", "type": "numeric", "distinct": "83", "missing": "0", "min": "-1", "max": "0", "mean": "0", "stdev": "0" }, { "name": "CATS2D_03_AA", "index": "37", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "H.050", "index": "38", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "5", "mean": "2", "stdev": "2" }, { "name": "nHDon", "index": "39", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "5", "mean": "2", "stdev": "2" }, { "name": "C.029", "index": "40", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "nN", "index": "41", "type": "numeric", "distinct": "8", "missing": "0", "min": "0", "max": "7", "mean": "3", "stdev": "2" }, { "name": "SaaN", "index": "42", "type": "numeric", "distinct": "52", "missing": "0", "min": "0", "max": "14", "mean": "5", "stdev": "5" }, { "name": "P_VSA_MR_6", "index": "43", "type": "numeric", "distinct": "63", "missing": "0", "min": "0", "max": "156", "mean": "102", "stdev": "36" }, { "name": "CATS2D_04_AP", "index": "44", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "SdssC", "index": "45", "type": "numeric", "distinct": "90", "missing": "0", "min": "-3", "max": "1", "mean": "0", "stdev": "1" }, { "name": "MATS1i", "index": "46", "type": "numeric", "distinct": "67", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "MATS1v", "index": "47", "type": "numeric", "distinct": "60", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "NssO", "index": "48", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "Eta_betaP", "index": "49", "type": "numeric", "distinct": "24", "missing": "0", "min": "1", "max": "24", "mean": "17", "stdev": "5" }, { "name": "Eta_F_A", "index": "50", "type": "numeric", "distinct": "89", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "nAB", "index": "51", "type": "numeric", "distinct": "12", "missing": "0", "min": "0", "max": "22", "mean": "13", "stdev": "5" }, { "name": "SsssN", "index": "52", "type": "numeric", "distinct": "50", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "N.075", "index": "53", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "NaaN", "index": "54", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "CATS2D_00_DD", "index": "55", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "1" }, { "name": "CATS2D_00_DP", "index": "56", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "1" }, { "name": "CATS2D_00_PP", "index": "57", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "1" }, { "name": "NsNH2", "index": "58", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "1" }, { "name": "P_VSA_m_2", "index": "59", "type": "numeric", "distinct": "77", "missing": "0", "min": "66", "max": "263", "mean": "166", "stdev": "50" }, { "name": "Eta_L_A", "index": "60", "type": "numeric", "distinct": "56", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SAacc", "index": "61", "type": "numeric", "distinct": "40", "missing": "0", "min": "43", "max": "197", "mean": "105", "stdev": "39" }, { "name": "CATS2D_04_AA", "index": "62", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "8", "mean": "2", "stdev": "1" }, { "name": "Eta_betaP_A", "index": "63", "type": "numeric", "distinct": "56", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "C.027", "index": "64", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "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 }