DEVELOPMENT... { "data_id": "31903", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3785", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3785", "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: CHEMBL3785 (TID: 100579), and it has 564 rows and 67 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": "unknown", "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 08:48:26", "update_comment": null, "last_update": "2016-07-15 08:48:26", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3463981\/data_53229.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3785", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL3785 (TID: 100579), and it has 564 rows and 67 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": 564, "NumberOfFeatures": 69, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 68, "NumberOfSymbolicFeatures": 1, "Quartile1MutualInformation": null, "PercentageOfBinaryFeatures": 0, "PercentageOfInstancesWithMissingValues": 0, "PercentageOfMissingValues": 0, "PercentageOfNumericFeatures": 98.55072463768117, "PercentageOfSymbolicFeatures": 1.4492753623188406, "Quartile1AttributeEntropy": null, "Quartile1KurtosisOfNumericAtts": -0.39744359155807896, "Quartile1MeansOfNumericAtts": 1.6441117021276592, "StdvNominalAttDistinctValues": null, "Quartile1SkewnessOfNumericAtts": -0.6055167725188357, "Quartile1StdDevOfNumericAtts": 0.6742082570350114, "Quartile2AttributeEntropy": null, "Quartile2KurtosisOfNumericAtts": 0.6453568817552229, "Quartile2MeansOfNumericAtts": 3.4748528368794336, "Quartile2MutualInformation": null, "Quartile2SkewnessOfNumericAtts": 0.14301867799662887, "Quartile2StdDevOfNumericAtts": 1.2130952892167484, "Quartile3AttributeEntropy": null, "Quartile3KurtosisOfNumericAtts": 1.4594902981230673, "Quartile3MeansOfNumericAtts": 6.915339982269504, "Quartile3MutualInformation": null, "Quartile3SkewnessOfNumericAtts": 0.8019477884927466, "Quartile3StdDevOfNumericAtts": 3.5586809762766434, "AutoCorrelation": 0.2338667850799283, "MeanMeansOfNumericAtts": 16.133747079682937, "ClassEntropy": null, "Dimensionality": 0.12234042553191489, "EquivalentNumberOfAtts": null, "MajorityClassPercentage": null, "MajorityClassSize": null, "MaxAttributeEntropy": null, "MaxKurtosisOfNumericAtts": 8.486584329937177, "MaxMeansOfNumericAtts": 130.29179432624113, "MaxMutualInformation": null, "MaxNominalAttDistinctValues": null, "MaxSkewnessOfNumericAtts": 2.2593162241071623, "MaxStdDevOfNumericAtts": 53.80696945312524, "MeanAttributeEntropy": null, "MeanKurtosisOfNumericAtts": 0.9136673928046833, "NumberOfBinaryFeatures": 0, "MeanMutualInformation": null, "MeanNoiseToSignalRatio": null, "MeanNominalAttDistinctValues": null, "MeanSkewnessOfNumericAtts": 0.018988019692803285, "MeanStdDevOfNumericAtts": 6.552326313636583, "MinAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.2529126154852042, "MinMeansOfNumericAtts": 0.06848404255319146, "MinMutualInformation": null, "MinNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -1.8328526643882308, "MinStdDevOfNumericAtts": 0.07932760116243547, "MinorityClassPercentage": null, "MinorityClassSize": null }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "68", "type": "numeric", "distinct": "357", "missing": "0", "target": "1", "min": "4", "max": "9", "mean": "6", "stdev": "1" }, { "name": "IC2", "index": "50", "type": "numeric", "distinct": "348", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "TPSA.Tot.", "index": "35", "type": "numeric", "distinct": "119", "missing": "0", "min": "37", "max": "164", "mean": "88", "stdev": "24" }, { "name": "IC3", "index": "49", "type": "numeric", "distinct": "322", "missing": "0", "min": "3", "max": "6", "mean": "5", "stdev": "0" }, { "name": "Eig03_AEA.dm.", "index": "48", "type": "numeric", "distinct": "343", "missing": "0", "min": "1", "max": "4", "mean": "3", "stdev": "0" }, { "name": "P_VSA_m_3", "index": "47", "type": "numeric", "distinct": "70", "missing": "0", "min": "0", "max": "205", "mean": "86", "stdev": "42" }, { "name": "SM13_AEA.bo.", "index": "46", "type": "numeric", "distinct": "283", "missing": "0", "min": "-1", "max": "3", "mean": "2", "stdev": "1" }, { "name": "Eig05_EA", "index": "45", "type": "numeric", "distinct": "283", "missing": "0", "min": "-1", "max": "3", "mean": "2", "stdev": "1" }, { "name": "Eig05_AEA.ri.", "index": "44", "type": "numeric", "distinct": "403", "missing": "0", "min": "0", "max": "4", "mean": "3", "stdev": "1" }, { "name": "SpMax7_Bh.s.", "index": "43", "type": "numeric", "distinct": "389", "missing": "0", "min": "1", "max": "6", "mean": "4", "stdev": "1" }, { "name": "P_VSA_p_2", "index": "42", "type": "numeric", "distinct": "109", "missing": "0", "min": "68", "max": "259", "mean": "124", "stdev": "39" }, { "name": "nO", "index": "41", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "6", "mean": "3", "stdev": "1" }, { "name": "nHAcc", "index": "40", "type": "numeric", "distinct": "12", "missing": "0", "min": "2", "max": "13", "mean": "6", "stdev": "2" }, { "name": "SAacc", "index": "39", "type": "numeric", "distinct": "145", "missing": "0", "min": "67", "max": "276", "mean": "124", "stdev": "45" }, { "name": "IC4", "index": "38", "type": "numeric", "distinct": "277", "missing": "0", "min": "3", "max": "6", "mean": "5", "stdev": "0" }, { "name": "Eig05_AEA.dm.", "index": "37", "type": "numeric", "distinct": "373", "missing": "0", "min": "0", "max": "3", "mean": "2", "stdev": "1" }, { "name": "Eig06_AEA.ed.", "index": "36", "type": "numeric", "distinct": "280", "missing": "0", "min": "1", "max": "5", "mean": "4", "stdev": "1" }, { "name": "DELS", "index": "34", "type": "numeric", "distinct": "535", "missing": "0", "min": "6", "max": "85", "mean": "29", "stdev": "13" }, { "name": "C.002", "index": "59", "type": "numeric", "distinct": "10", "missing": "0", "min": "0", "max": "10", "mean": "2", "stdev": "2" }, { "name": "P_VSA_v_2", "index": "67", "type": "numeric", "distinct": "150", "missing": "0", "min": "68", "max": "276", "mean": "130", "stdev": "41" }, { "name": "SM10_EA.dm.", "index": "66", "type": "numeric", "distinct": "78", "missing": "0", "min": "0", "max": "14", "mean": "6", "stdev": "3" }, { "name": "SM14_EA.dm.", "index": "65", "type": "numeric", "distinct": "68", "missing": "0", "min": "0", "max": "19", "mean": "8", "stdev": "4" }, { "name": "NssNH", "index": "64", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "1" }, { "name": "SM11_EA.ed.", "index": "63", "type": "numeric", "distinct": "300", "missing": "0", "min": "20", "max": "31", "mean": "26", "stdev": "2" }, { "name": "SM10_EA.ed.", "index": "62", "type": "numeric", "distinct": "312", "missing": "0", "min": "18", "max": "28", "mean": "24", "stdev": "2" }, { "name": "SM07_EA.ed.", "index": "61", "type": "numeric", "distinct": "296", "missing": "0", "min": "13", "max": "20", "mean": "17", "stdev": "1" }, { "name": "SsOH", "index": "60", "type": "numeric", "distinct": "294", "missing": "0", "min": "0", "max": "29", "mean": "7", "stdev": "7" }, { "name": "Eig05_EA.ri.", "index": "51", "type": "numeric", "distinct": "385", "missing": "0", "min": "-1", "max": "2", "mean": "2", "stdev": "1" }, { "name": "ATSC7s", "index": "58", "type": "numeric", "distinct": "530", "missing": "0", "min": "0", "max": "363", "mean": "56", "stdev": "47" }, { "name": "CATS2D_02_DA", "index": "57", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "2", "stdev": "1" }, { "name": "N.072", "index": "56", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "Eig05_AEA.bo.", "index": "55", "type": "numeric", "distinct": "292", "missing": "0", "min": "0", "max": "4", "mean": "3", "stdev": "1" }, { "name": "GGI4", "index": "54", "type": "numeric", "distinct": "236", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "0" }, { "name": "Eig07_EA.ri.", "index": "53", "type": "numeric", "distinct": "374", "missing": "0", "min": "-2", "max": "2", "mean": "1", "stdev": "1" }, { "name": "SssNH", "index": "52", "type": "numeric", "distinct": "260", "missing": "0", "min": "0", "max": "6", "mean": "2", "stdev": "1" }, { "name": "CATS2D_04_DL", "index": "8", "type": "numeric", "distinct": "9", "missing": "0", "min": "0", "max": "8", "mean": "2", "stdev": "2" }, { "name": "CATS2D_06_AA", "index": "16", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "8", "mean": "1", "stdev": "1" }, { "name": "GGI10", "index": "15", "type": "numeric", "distinct": "96", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "P_VSA_LogP_2", "index": "14", "type": "numeric", "distinct": "74", "missing": "0", "min": "0", "max": "64", "mean": "20", "stdev": "15" }, { "name": "SM06_EA.dm.", "index": "13", "type": "numeric", "distinct": "91", "missing": "0", "min": "0", "max": "8", "mean": "4", "stdev": "2" }, { "name": "P_VSA_s_3", "index": "12", "type": "numeric", "distinct": "333", "missing": "0", "min": "4", "max": "79", "mean": "30", "stdev": "14" }, { "name": "ATS6s", "index": "11", "type": "numeric", "distinct": "466", "missing": "0", "min": "0", "max": "7", "mean": "5", "stdev": "1" }, { "name": "SM08_EA.dm.", "index": "10", "type": "numeric", "distinct": "84", "missing": "0", "min": "0", "max": "11", "mean": "5", "stdev": "2" }, { "name": "SpMax3_Bh.s.", "index": "9", "type": "numeric", "distinct": "162", "missing": "0", "min": "4", "max": "8", "mean": "6", "stdev": "1" }, { "name": "C.040", "index": "17", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "2", "stdev": "1" }, { "name": "nR.Ct", "index": "7", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "NdssC", "index": "6", "type": "numeric", "distinct": "8", "missing": "0", "min": "0", "max": "7", "mean": "3", "stdev": "2" }, { "name": "C.017", "index": "5", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "TPSA.NO.", "index": "4", "type": "numeric", "distinct": "105", "missing": "0", "min": "37", "max": "164", "mean": "86", "stdev": "23" }, { "name": "Eig06_AEA.dm.", "index": "3", "type": "numeric", "distinct": "404", "missing": "0", "min": "-1", "max": "3", "mean": "2", "stdev": "1" }, { "name": "SdO", "index": "2", "type": "numeric", "distinct": "453", "missing": "0", "min": "0", "max": "56", "mean": "18", "stdev": "9" }, { "name": "ATSC6s", "index": "1", "type": "numeric", "distinct": "531", "missing": "0", "min": "0", "max": "310", "mean": "81", "stdev": "54" }, { "name": "Eig06_EA.ed.", "index": "25", "type": "numeric", "distinct": "320", "missing": "0", "min": "-3", "max": "7", "mean": "3", "stdev": "2" }, { "name": "SM04_EA.dm.", "index": "33", "type": "numeric", "distinct": "91", "missing": "0", "min": "0", "max": "6", "mean": "3", "stdev": "1" }, { "name": "SM15_EA.dm.", "index": "32", "type": "numeric", "distinct": "43", "missing": "0", "min": "0", "max": "20", "mean": "6", "stdev": "5" }, { "name": "SM13_EA.dm.", "index": "31", "type": "numeric", "distinct": "44", "missing": "0", "min": "0", "max": "18", "mean": "5", "stdev": "4" }, { "name": "SM11_EA.dm.", "index": "30", "type": "numeric", "distinct": "44", "missing": "0", "min": "0", "max": "15", "mean": "4", "stdev": "4" }, { "name": "SM09_EA.dm.", "index": "29", "type": "numeric", "distinct": "46", "missing": "0", "min": "0", "max": "12", "mean": "4", "stdev": "3" }, { "name": "SM07_EA.dm.", "index": "28", "type": "numeric", "distinct": "46", "missing": "0", "min": "0", "max": "9", "mean": "3", "stdev": "2" }, { "name": "SM05_EA.dm.", "index": "27", "type": "numeric", "distinct": "38", "missing": "0", "min": "0", "max": "7", "mean": "2", "stdev": "2" }, { "name": "SM15_AEA.dm.", "index": "26", "type": "numeric", "distinct": "320", "missing": "0", "min": "-3", "max": "7", "mean": "3", "stdev": "2" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "564", "missing": "0", "identifier": "1", "distr": [] }, { "name": "SM03_EA.dm.", "index": "24", "type": "numeric", "distinct": "29", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "ATSC6e", "index": "23", "type": "numeric", "distinct": "408", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "CATS2D_06_DA", "index": "22", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "5", "mean": "1", "stdev": "1" }, { "name": "ATSC4e", "index": "21", "type": "numeric", "distinct": "389", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "ATS4s", "index": "20", "type": "numeric", "distinct": "452", "missing": "0", "min": "4", "max": "7", "mean": "6", "stdev": "0" }, { "name": "SpMax_EA.dm.", "index": "19", "type": "numeric", "distinct": "51", "missing": "0", "min": "0", "max": "4", "mean": "2", "stdev": "1" }, { "name": "Eig01_EA.dm.", "index": "18", "type": "numeric", "distinct": "51", "missing": "0", "min": "0", "max": "4", "mean": "2", "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 }