{ "data_id": "29122", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3766", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3766", "version": 7, "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: CHEMBL3766 (TID: 10930), and it has 560 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": "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 01:43:24", "update_comment": null, "last_update": "2016-07-15 01:43:24", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3384094\/data_53209.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3766", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL3766 (TID: 10930), and it has 560 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": 560, "NumberOfFeatures": 69, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 68, "NumberOfSymbolicFeatures": 1, "ClassEntropy": null, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "Dimensionality": 0.12321428571428572, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": -0.6065361715455737, "EquivalentNumberOfAtts": null, "MeanSkewnessOfNumericAtts": 0.4706782023991884, "Quartile2MeansOfNumericAtts": 1.1972803571428576, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 5.747307208310731, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": 0.4323430312178471, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.5821215918443405, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.4342340673415676, "MaxKurtosisOfNumericAtts": 11.759296514210826, "MinMeansOfNumericAtts": -0.10874107142857141, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 217.69629107142856, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 0.4150910719128339, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.55072463768117, "Quartile3MeansOfNumericAtts": 5.416882142857142, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -1.3234288648801034, "PercentageOfSymbolicFeatures": 1.4492753623188406, "Quartile3MutualInformation": null, "MaxSkewnessOfNumericAtts": 2.184634477782781, "MinStdDevOfNumericAtts": 0.002732937916418188, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 0.7131663695695818, "MaxStdDevOfNumericAtts": 113.42684223322533, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": -1.1723196252351464, "Quartile3StdDevOfNumericAtts": 1.4837682116490434, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 0.28659776785714286, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": 0.19581138459361339, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 11.806950682773111, "Quartile1SkewnessOfNumericAtts": -0.029154371729960014, "AutoCorrelation": 0.028772808586762386, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.052453278974880384 }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "68", "type": "numeric", "distinct": "273", "missing": "0", "target": "1", "min": "4", "max": "10", "mean": "6", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "560", "missing": "0", "identifier": "1", "distr": [] }, { "name": "D.Dtr07", "index": "1", "type": "numeric", "distinct": "100", "missing": "0", "min": "0", "max": "367", "mean": "28", "stdev": "53" }, { "name": "nR07", "index": "2", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "P_VSA_e_2", "index": "3", "type": "numeric", "distinct": "428", "missing": "0", "min": "71", "max": "285", "mean": "161", "stdev": "47" }, { "name": "Ui", "index": "4", "type": "numeric", "distinct": "31", "missing": "0", "min": "2", "max": "5", "mean": "4", "stdev": "0" }, { "name": "Eta_FL", "index": "5", "type": "numeric", "distinct": "447", "missing": "0", "min": "3", "max": "22", "mean": "8", "stdev": "3" }, { "name": "P_VSA_i_2", "index": "6", "type": "numeric", "distinct": "428", "missing": "0", "min": "71", "max": "285", "mean": "152", "stdev": "41" }, { "name": "Eig03_AEA.bo.", "index": "7", "type": "numeric", "distinct": "173", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SM04_EA.bo.", "index": "8", "type": "numeric", "distinct": "288", "missing": "0", "min": "6", "max": "8", "mean": "7", "stdev": "0" }, { "name": "Eig12_EA.bo.", "index": "9", "type": "numeric", "distinct": "245", "missing": "0", "min": "-1", "max": "3", "mean": "2", "stdev": "1" }, { "name": "SpMax3_Bh.m.", "index": "10", "type": "numeric", "distinct": "176", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "JGI7", "index": "11", "type": "numeric", "distinct": "14", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SRW07", "index": "12", "type": "numeric", "distinct": "24", "missing": "0", "min": "0", "max": "7", "mean": "4", "stdev": "2" }, { "name": "SRW09", "index": "13", "type": "numeric", "distinct": "59", "missing": "0", "min": "0", "max": "9", "mean": "6", "stdev": "3" }, { "name": "MATS4i", "index": "14", "type": "numeric", "distinct": "271", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "C.004", "index": "15", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "nCq", "index": "16", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "nCrq", "index": "17", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "NssssC", "index": "18", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "5", "mean": "1", "stdev": "2" }, { "name": "X3A", "index": "19", "type": "numeric", "distinct": "43", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Eta_beta", "index": "20", "type": "numeric", "distinct": "167", "missing": "0", "min": "20", "max": "108", "mean": "47", "stdev": "14" }, { "name": "X4A", "index": "21", "type": "numeric", "distinct": "33", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "P_VSA_m_2", "index": "22", "type": "numeric", "distinct": "445", "missing": "0", "min": "78", "max": "727", "mean": "218", "stdev": "113" }, { "name": "SpMin3_Bh.s.", "index": "23", "type": "numeric", "distinct": "177", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "X5A", "index": "24", "type": "numeric", "distinct": "29", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "nR09", "index": "25", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "CATS2D_05_AL", "index": "26", "type": "numeric", "distinct": "31", "missing": "0", "min": "2", "max": "32", "mean": "15", "stdev": "8" }, { "name": "BIC5", "index": "27", "type": "numeric", "distinct": "100", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Eig04_EA.ed.", "index": "28", "type": "numeric", "distinct": "268", "missing": "0", "min": "5", "max": "12", "mean": "9", "stdev": "1" }, { "name": "SM13_AEA.dm.", "index": "29", "type": "numeric", "distinct": "268", "missing": "0", "min": "5", "max": "12", "mean": "9", "stdev": "1" }, { "name": "SpMAD_EA.ed.", "index": "30", "type": "numeric", "distinct": "327", "missing": "0", "min": "4", "max": "6", "mean": "5", "stdev": "0" }, { "name": "JGI5", "index": "31", "type": "numeric", "distinct": "26", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SpMAD_EA", "index": "32", "type": "numeric", "distinct": "126", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "JGI3", "index": "33", "type": "numeric", "distinct": "47", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "CATS2D_06_DA", "index": "34", "type": "numeric", "distinct": "14", "missing": "0", "min": "0", "max": "13", "mean": "3", "stdev": "3" }, { "name": "PW3", "index": "35", "type": "numeric", "distinct": "87", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SpMAD_AEA.dm.", "index": "36", "type": "numeric", "distinct": "167", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "SpDiam_AEA.ri.", "index": "37", "type": "numeric", "distinct": "153", "missing": "0", "min": "5", "max": "6", "mean": "6", "stdev": "0" }, { "name": "SssCH2", "index": "38", "type": "numeric", "distinct": "503", "missing": "0", "min": "-3", "max": "19", "mean": "5", "stdev": "3" }, { "name": "SpMAD_AEA.bo.", "index": "39", "type": "numeric", "distinct": "129", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "Eta_sh_x", "index": "40", "type": "numeric", "distinct": "77", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SpMAD_AEA.ri.", "index": "41", "type": "numeric", "distinct": "135", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "JGI2", "index": "42", "type": "numeric", "distinct": "66", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "nSO2N", "index": "43", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "H.053", "index": "44", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "8", "mean": "1", "stdev": "2" }, { "name": "Eta_B_A", "index": "45", "type": "numeric", "distinct": "31", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "GATS6v", "index": "46", "type": "numeric", "distinct": "258", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "nBM", "index": "47", "type": "numeric", "distinct": "28", "missing": "0", "min": "7", "max": "39", "mean": "18", "stdev": "6" }, { "name": "Uc", "index": "48", "type": "numeric", "distinct": "28", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "MATS6p", "index": "49", "type": "numeric", "distinct": "242", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SM07_AEA.bo.", "index": "50", "type": "numeric", "distinct": "335", "missing": "0", "min": "11", "max": "13", "mean": "12", "stdev": "0" }, { "name": "MATS1e", "index": "51", "type": "numeric", "distinct": "211", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "nCt", "index": "52", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "5", "mean": "1", "stdev": "1" }, { "name": "X2A", "index": "53", "type": "numeric", "distinct": "63", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "C.003", "index": "54", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "Eig03_AEA.ri.", "index": "55", "type": "numeric", "distinct": "214", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "JGI8", "index": "56", "type": "numeric", "distinct": "14", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "BIC4", "index": "57", "type": "numeric", "distinct": "98", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "MATS5i", "index": "58", "type": "numeric", "distinct": "240", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "D.Dtr11", "index": "59", "type": "numeric", "distinct": "66", "missing": "0", "min": "0", "max": "275", "mean": "30", "stdev": "66" }, { "name": "nR11", "index": "60", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "nCrt", "index": "61", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "5", "mean": "1", "stdev": "1" }, { "name": "ARR", "index": "62", "type": "numeric", "distinct": "144", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "DLS_04", "index": "63", "type": "numeric", "distinct": "8", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "C.001", "index": "64", "type": "numeric", "distinct": "8", "missing": "0", "min": "0", "max": "7", "mean": "1", "stdev": "1" }, { "name": "nCrs", "index": "65", "type": "numeric", "distinct": "15", "missing": "0", "min": "0", "max": "14", "mean": "6", "stdev": "4" }, { "name": "nArCONHR", "index": "66", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "GGI3", "index": "67", "type": "numeric", "distinct": "170", "missing": "0", "min": "1", "max": "7", "mean": "4", "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 }